{"gene":"HLA-E","run_date":"2026-04-28T18:06:53","timeline":{"discoveries":[{"year":1998,"finding":"HLA-E is the major ligand for the inhibitory NK cell receptor CD94/NKG2A. Surface stabilization of HLA-E with appropriate peptides confers protection from NK cell lysis mediated specifically through CD94/NKG2A, not through Ig-SF killer cell inhibitory receptors or ILT2/LIR1.","method":"NK cell cytotoxicity assays with HLA-E transfectants (.221 cells), antibody blocking of HLA-E, CD94, or CD94/NKG2A, cold-loading of peptides onto target cells","journal":"Proceedings of the National Academy of Sciences of the United States of America","confidence":"High","confidence_rationale":"Tier 2 — reciprocal blocking antibody experiments with multiple HLA class I allotype transfectants, replicated across labs subsequently","pmids":["9560253"],"is_preprint":false},{"year":1998,"finding":"HLA-E crystal structure reveals that it binds a tightly defined set of nearly identical hydrophobic nonameric peptides derived from MHC class I leader sequences (prototypic: VMAPRTVLL), with novel structural features that enforce peptide-binding specificity and function as a checkpoint reporting on antigen processing pathway integrity to CD94/NKG2 receptors.","method":"X-ray crystallography of HLA-E/β2m/peptide complex at 2.85 Å resolution","journal":"Molecular cell","confidence":"High","confidence_rationale":"Tier 1 — crystal structure determination with functional interpretation","pmids":["9660937"],"is_preprint":false},{"year":1998,"finding":"HLA-E interacts with TAP in the endoplasmic reticulum for peptide loading, and this interaction can be prolonged by proteasome inhibition. HLA-E can bind peptides ranging from 7 to 16 amino acids, and the exact N-terminal positioning is critical for binding.","method":"Peptide binding assays measuring surface HLA-E expression, thermostability assays of soluble HLA-E/β2m dimers, TAP interaction studies with proteasome inhibitor N-acetyl-L-leucyl-L-leucyl-L-norleucinal","journal":"Journal of immunology","confidence":"High","confidence_rationale":"Tier 1 — in vitro biochemical assays with multiple orthogonal methods (surface stabilization, thermostability, TAP co-immunoprecipitation)","pmids":["9574542"],"is_preprint":false},{"year":2000,"finding":"Human cytomegalovirus glycoprotein UL40 (gpUL40) contains a leader sequence peptide identical to HLA class I signal sequences; this peptide loads HLA-E independently of TAP, upregulating HLA-E surface expression and protecting infected cells from NK cell lysis while classical MHC class I molecules are downregulated by HCMV.","method":"HCMV infection of cells, TAP-independent peptide loading demonstrated in TAP-deficient cell lines, NK cell cytotoxicity assays","journal":"Science","confidence":"High","confidence_rationale":"Tier 2 — TAP-deficient cell line experiments with NK cytotoxicity readout, mechanistically definitive","pmids":["10669413"],"is_preprint":false},{"year":2000,"finding":"HLA-E is expressed on trophoblast cell surfaces and interacts with CD94/NKG2 receptors on decidual NK cells, with the overall functional consequence being inhibition of decidual NK cell cytotoxicity.","method":"HLA-E tetrameric complex binding to decidual NK cells, anti-CD94 antibody blocking, cytotoxicity assays with polyclonal decidual NK cells","journal":"European journal of immunology","confidence":"High","confidence_rationale":"Tier 2 — HLA-E tetramers with blocking antibody and functional cytotoxicity readout","pmids":["10898498"],"is_preprint":false},{"year":2001,"finding":"MHC class I signal peptides are processed by signal peptide peptidase in the hydrophobic membrane-spanning region after cleavage from the pre-protein; this intramembrane proteolysis is essential for release of the HLA-E epitope-containing fragment from the lipid bilayer and its subsequent TAP-dependent transport into the ER lumen.","method":"Signal peptide peptidase inhibition experiments, biochemical fractionation, demonstration of TAP-dependent transport of the processed fragment","journal":"Journal of immunology","confidence":"High","confidence_rationale":"Tier 1 — mechanistic enzymatic study with inhibitors identifying the specific protease step required for HLA-E peptide generation","pmids":["11714810"],"is_preprint":false},{"year":2002,"finding":"HLA-E alleles (E*0101 with Arg107 vs. E*0103 with Gly107) differ in peptide affinity and thermal stability, which correlates with differential cell surface expression levels, but the crystal structures of HLA-E(G) with two peptides show no significant structural differences induced by peptide binding or allelic substitution at position 107.","method":"X-ray crystallography of HLA-E(G) allele with two peptides, thermal stability assays, cell surface expression analysis","journal":"The Journal of biological chemistry","confidence":"High","confidence_rationale":"Tier 1 — crystal structures combined with biochemical thermal stability and surface expression assays","pmids":["12411439"],"is_preprint":false},{"year":2002,"finding":"HLA-E presents a peptide derived from the leader sequence of heat shock protein 60 (hsp60), which gains access to HLA-E intracellularly during cellular stress. HLA-E/hsp60 signal peptide complexes are not recognized by CD94/NKG2A inhibitory receptors, thereby reducing NK cell inhibition and providing a mechanism for NK cells to detect stressed cells.","method":"HLA-E/hsp60 peptide complex characterization, CD94/NKG2A binding assays, NK cell functional assays with stressed cells","journal":"The Journal of experimental medicine","confidence":"High","confidence_rationale":"Tier 2 — peptide-specific functional experiments with NK cell receptor blocking, mechanistic pathway established","pmids":["12461076"],"is_preprint":false},{"year":2003,"finding":"HLA-E cell surface expression in tumor cells requires availability of free β2-microglobulin; tumors with imbalanced HLA class Ia heavy chain/β2m expression show increased HLA-E surface detection, while total loss of HLA class Ia expression abolishes HLA-E surface expression.","method":"FACS analysis with anti-HLA-E mAb (3D12) on tumor cell lines, exogenous β2m addition experiments, analysis of cell lines with defined HLA class I genetic alterations","journal":"Immunogenetics","confidence":"Medium","confidence_rationale":"Tier 2 — multiple cell line analyses with genetic characterization but single lab","pmids":["12618909"],"is_preprint":false},{"year":2005,"finding":"An HLA-E single-chain trimer (SCT) consisting of linked HLA-B leader peptide, β2m, and HLA-E heavy chain confers surface expression on porcine cells and protects them from NK cell lysis via CD94/NKG2A interaction; an SCT bearing the hsp60-derived peptide is expressed but does not inhibit NK lysis, demonstrating peptide-dependent functional specificity.","method":"HLA-E SCT transfection of LLC-PK1 porcine cells, NK cell cytotoxicity assays with NKL and NK-92 cell lines, IFN-γ secretion assays","journal":"Molecular immunology","confidence":"High","confidence_rationale":"Tier 2 — engineered SCT with peptide specificity controls and functional NK assays","pmids":["15829309"],"is_preprint":false},{"year":2007,"finding":"Gliadin peptides (alpha and omega fractions) stabilize HLA-E molecules on dendritic cells, protecting immature DCs from NK cell lysis and modulating NK-DC crosstalk; a peptide derived from gliadin alpha increases HLA-E levels on RMA-S/HLA-E-transfected cells.","method":"HLA-E surface expression analysis, NK cell cytotoxicity assays with gliadin-treated DCs, RMA-S/HLA-E transfectant loading assays, immunohistochemistry of intestinal mucosa from celiac patients","journal":"Journal of immunology","confidence":"Medium","confidence_rationale":"Tier 2 — in vitro functional assays with transfectant cell lines and primary cells, confirmed in tissue sections","pmids":["17579058"],"is_preprint":false},{"year":2008,"finding":"Crystal structure of CD94-NKG2A in complex with HLA-E bound to HLA-G leader peptide reveals that CD94 dominates the interaction with HLA-E while NKG2A is more peripheral; the invariant CD94 subunit dominates peptide-mediated contacts; there are few conformational changes upon ligation ('lock and key' interaction). Mutagenesis at the CD94-NKG2A-HLA-E interface confirmed the structural contacts.","method":"X-ray crystallography of CD94-NKG2A/HLA-E complex at 3.5 Å, site-directed mutagenesis","journal":"The Journal of experimental medicine","confidence":"High","confidence_rationale":"Tier 1 — crystal structure with mutagenesis validation","pmids":["18332182"],"is_preprint":false},{"year":2008,"finding":"Crystal structure of NKG2A/CD94/HLA-E complex at 4.4 Å reveals that the C-terminal region of the peptide (most variable among class I leader sequences) interacts entirely with CD94, and residues 167-170 of NKG2A account for the ~6-fold higher affinity of NKG2A/CD94 versus NKG2C/CD94 through their role in the heterodimer interface with CD94 rather than direct HLA-E contact.","method":"X-ray crystallography, affinity measurements, binding assays with UL18","journal":"Proceedings of the National Academy of Sciences of the United States of America","confidence":"High","confidence_rationale":"Tier 1 — crystal structure with functional affinity and binding data","pmids":["18448674"],"is_preprint":false},{"year":2008,"finding":"Crystal structures of HLA-E with two leader peptides (HLA-Cw*07: VMAPRALLL, poorly recognized; HLA-G*01: VMAPRTLFL, high-affinity) at 2.5 Å show that allotypic variations do not alter HLA-E heavy chain conformation, but subtle changes in peptide conformation within the binding groove profoundly affect CD94-NKG2 receptor recognition.","method":"X-ray crystallography at 2.5 Å resolution for both complexes","journal":"Journal of molecular biology","confidence":"High","confidence_rationale":"Tier 1 — two crystal structures compared with functional correlation","pmids":["18339401"],"is_preprint":false},{"year":2009,"finding":"HLA-E surface expression on transgenic pig cells expressing HLA-E and human β2-microglobulin inhibits human NK cell-mediated cytotoxicity in a CD94/NKG2A-dependent manner and also inhibits IFN-γ secretion by co-cultured human NK cells.","method":"HLA-E/hβ2m transgenic pig generation, NK cell cytotoxicity assays, IFN-γ ELISA, FACS","journal":"Transplantation","confidence":"High","confidence_rationale":"Tier 2 — transgenic animal model with in vitro functional NK assays and CD94/NKG2A expression correlation","pmids":["19136889"],"is_preprint":false},{"year":2003,"finding":"HLA-E-mediated inhibition of NK cell lysis requires peptide loading and is TAP-independent when specific signal sequence peptides are available: HCMV gpUS6, which blocks TAP by 95%, does not affect HLA-E surface expression or its ability to inhibit NK cell lysis via CD94/NKG2A, and HLA-E is functional on TAP-deficient RMA-S transfectants.","method":"gpUS6-expressing transfectants, TAP inhibition assays, NK cell cytotoxicity assays, HLA-E surface expression by FACS","journal":"Human immunology","confidence":"High","confidence_rationale":"Tier 2 — TAP-deficient cell line experiments with gpUS6 providing mechanistic clarity on TAP independence","pmids":["12559625"],"is_preprint":false},{"year":2013,"finding":"Polymorphisms in the HCMV UL40 leader sequence mimic region modulate the affinity of UL40-derived peptide/HLA-E complexes for CD94-NKG2 receptors; some UL40 peptide variants can inhibit NK lysis via CD94-NKG2A but have little capacity to activate NK cells through CD94-NKG2C, suggesting UL40 polymorphisms facilitate viral immune evasion by differential receptor engagement.","method":"UL40 sequencing from HSCT recipients, HLA-E/peptide binding affinity assays, NK cell clone cytotoxicity assays (NKG2A+ or NKG2C+ clones)","journal":"The Journal of biological chemistry","confidence":"High","confidence_rationale":"Tier 2 — affinity measurements combined with NK clone functional assays showing differential receptor activation","pmids":["23335510"],"is_preprint":false},{"year":2015,"finding":"HLA-E*01:01 and HLA-E*01:03 alleles present distinct and non-overlapping peptide repertoires (9-17 amino acids); differences in peptide stabilization capacity caused by the Arg107Gly substitution affect cell surface HLA-E density and half-life, which in turn impact NK cell inhibition as measured by cytotoxicity assays.","method":"Soluble HLA technology with mass spectrometric peptide sequencing (HLA-E*01:03 ligandome), artificial APCs expressing peptide-stabilized HLA-E, NK cell cytotoxicity assays","journal":"Immunogenetics","confidence":"High","confidence_rationale":"Tier 1–2 — mass spectrometry ligandome combined with functional NK assays","pmids":["26552660"],"is_preprint":false},{"year":2016,"finding":"HLA-E presents a conserved peptide from HIV-1 capsid (AISPRTLNA) that is not recognized by NKG2A/CD94, causing HIV-infected T cells to be susceptible to killing by NKG2A/CD94+ NK cells despite high HLA-E surface expression; NKG2A/CD94+ NK cells generate the most efficient responses against HIV-infected T cells.","method":"In vitro cytolytic assays with autologous primary NK cells and HIV-infected primary T cells, HLA-E peptide loading with HIV capsid peptide, NKG2A/CD94 blocking","journal":"PLoS pathogens","confidence":"High","confidence_rationale":"Tier 2 — primary cell system with specific peptide identification and receptor blocking","pmids":["26828202"],"is_preprint":false},{"year":2018,"finding":"HLA-E presents diverse pathogen-derived peptides (HIV and Mtb) with conformational flexibility: pathogen-derived peptides adopt alternative conformations within the HLA-E binding groove, and mutagenesis reveals greater tolerance for hydrophobic and polar residues in primary anchor pockets than previously appreciated.","method":"X-ray crystallography of HLA-E with HIV- and Mtb-derived peptides, mutagenesis, biochemical peptide binding studies","journal":"Nature communications","confidence":"High","confidence_rationale":"Tier 1 — crystal structures with mutagenesis validation","pmids":["30087334"],"is_preprint":false},{"year":2018,"finding":"Adaptive NK cells discriminate between different HLA-E peptide complexes with exquisite specificity via CD94/NKG2C; prolonged exposure to HLA-E/VMAPRTLFL (HLA-G leader peptide) enriches adaptive NK cells with altered signaling molecule expression and elevated antibody-dependent cellular cytotoxicity and IFN-γ responses.","method":"Flow cytometry, ADCC assays, IFN-γ ELISA, comparison of NK cell function with different HLA-E peptide complexes","journal":"Cell reports","confidence":"High","confidence_rationale":"Tier 2 — multiple orthogonal functional assays showing peptide-specific adaptive NK cell modulation","pmids":["30134159"],"is_preprint":false},{"year":2019,"finding":"Senescent dermal fibroblasts upregulate HLA-E expression via senescence-associated secretory phenotype (SASP)-related pro-inflammatory cytokines through p38 MAP kinase signaling; HLA-E on senescent cells interacts with NKG2A on NK and highly differentiated CD8+ T cells to inhibit immune responses, contributing to senescent cell accumulation.","method":"Flow cytometry of senescent fibroblasts, p38 inhibitor experiments, in vitro NK and CD8+ T cell cytotoxicity assays with NKG2A blocking antibody, immunohistochemistry of human skin sections","journal":"Nature communications","confidence":"High","confidence_rationale":"Tier 2 — multiple orthogonal methods including inhibitor studies, blocking antibodies, and in vivo tissue sections","pmids":["31160572"],"is_preprint":false},{"year":2019,"finding":"HIV-1 Nef protein downregulates HLA-E surface levels by targeting the cytoplasmic tail of HLA-E; cytoplasmic tail swap experiments showed that the HLA-A2 cytoplasmic tail grafted onto HLA-E abolished Nef-mediated downmodulation, demonstrating that Nef acts on the HLA-E cytoplasmic tail specifically.","method":"Primary HIV-1 strain infection of CD4+ T cells, single Nef/Vpu protein expression in T cell lines, cytoplasmic tail swap experiments, FACS for surface HLA-E","journal":"Journal of virology","confidence":"High","confidence_rationale":"Tier 2 — cytoplasmic tail swap experiments with primary cell validation mechanistically defining Nef target","pmids":["31375574"],"is_preprint":false},{"year":2022,"finding":"SARS-CoV-2 non-structural protein 13 (Nsp13) encodes a peptide presented by HLA-E that, unlike self-peptides, prevents binding of HLA-E to the inhibitory receptor NKG2A, rendering infected target cells susceptible to NKG2A-expressing NK cell killing; NKG2A+ NK cells are particularly activated in COVID-19 patients and can limit SARS-CoV-2 replication in infected lung epithelial cells.","method":"HLA-E peptide loading and NKG2A binding assays, NK cell activation assays, in vitro SARS-CoV-2 replication suppression assays, flow cytometry of NK cells from COVID-19 patients","journal":"Cell reports","confidence":"High","confidence_rationale":"Tier 2 — mechanistic peptide-receptor binding combined with functional viral replication assay","pmids":["35235832"],"is_preprint":false},{"year":2022,"finding":"Crystal structures and SAXS analysis show that HLA-E-VL9 (canonical leader peptide) complexes are more stable and compact, while HLA-E bound to pathogen-derived non-VL9 peptides adopts larger, more extended conformations in solution with reconfiguration of a key TCR-interacting α2 region; three HLA-E-exclusive residues position VL9 close to the α2 helix and allow non-VL9 peptide binding with an alternative binding motif.","method":"X-ray crystallography, small-angle X-ray scattering (SAXS), excess peptide experiments","journal":"Cell reports","confidence":"High","confidence_rationale":"Tier 1 — multiple structural methods (crystallography + SAXS) with functional interpretations","pmids":["35705051"],"is_preprint":false},{"year":2023,"finding":"HLA-E is largely retained in the ER after synthesis due to limited supply of high-affinity peptides, with its cytoplasmic tail contributing to ER retention; once at the cell surface, HLA-E is unstable and rapidly internalized; the cytoplasmic tail facilitates internalization and enrichment in late and recycling endosomes.","method":"Live cell imaging, FRAP, subcellular fractionation, cytoplasmic tail mutant constructs, pulse-chase experiments","journal":"The Journal of experimental medicine","confidence":"High","confidence_rationale":"Tier 2 — multiple direct localization and trafficking experiments with mutant constructs defining functional role of cytoplasmic tail","pmids":["37140910"],"is_preprint":false},{"year":2023,"finding":"Platelet-derived RGS18 promotes HLA-E expression on circulating tumor cells through AKT-GSK3β-CREB signaling; this HLA-E upregulation enables CTCs to evade NK cell surveillance via the HLA-E:CD94-NKG2A checkpoint axis, facilitating metastasis.","method":"Mechanistic studies including RGS18 knockdown/overexpression, AKT-GSK3β-CREB pathway inhibitors, in vitro NK cell killing assays, in vivo mouse metastasis models","journal":"Cancer cell","confidence":"High","confidence_rationale":"Tier 2 — pathway dissection with inhibitors, knockdown, overexpression, and in vivo validation","pmids":["36706761"],"is_preprint":false},{"year":2023,"finding":"Among 16 common HLA class I signal peptide variants, only 6 ('functional SPs') are efficiently processed to generate epitopes enabling CD94/NKG2 engagement; the single functional HLA-B SP (HLA-B/-21M) induces high HLA-E expression but confers the lowest receptor recognition, and it competes with other SPs to reduce overall CD94/NKG2A recognition of target cells.","method":"Systematic quantitative HLA-E surface expression assays, CD94/NKG2A binding assays, NK cell functional assays, genetic population analysis","journal":"Nature immunology","confidence":"High","confidence_rationale":"Tier 2 — systematic quantitative approach with multiple SP variants and NK functional readouts","pmids":["37264229"],"is_preprint":false},{"year":2023,"finding":"A yeast-displayed peptide library screen identified 500 unique peptides that bind both HLA-E and CD94/NKG2A or CD94/NKG2C; some peptides selectively activate NKG2C+ NK cells; human and CMV proteome-derived HLA-E-presented peptides capable of signaling through both receptors were identified using trained prediction algorithms.","method":"Yeast-display peptide library screening, CD94/NKG2A and CD94/NKG2C binding selection, NK cell activation assays","journal":"Nature communications","confidence":"High","confidence_rationale":"Tier 2 — high-throughput library screen with functional NK cell validation","pmids":["37558657"],"is_preprint":false},{"year":2015,"finding":"NKG2A+ NK cell degranulation is inhibited by HLA-E loaded with almost all tested peptides (CMV, Hsp60, HLA class I-derived), whereas NKG2C+ NK cell activation is selectively enhanced only by a restricted set of HLA-E peptide complexes, particularly HLA-E/HLA-G peptide, which also triggers NKG2C receptor internalization.","method":"NK cell degranulation (CD107a) assays with HLA-E peptide-loaded target cells, flow cytometry, Bafilomycin experiments for receptor internalization","journal":"Human immunology","confidence":"High","confidence_rationale":"Tier 2 — multiple peptide panels tested with NKG2A+ and NKG2C+ NK cell subsets, receptor internalization mechanistically defined","pmids":["26382247"],"is_preprint":false},{"year":2015,"finding":"HLA-E expression on myeloma cells is substantially upregulated in the bone marrow microenvironment in vivo (compared to in vitro), abrogating degranulation of NKG2A+ NK cell subsets; NKG2A-negative, KIR-ligand-mismatched NK cells show the highest anti-myeloma reactivity.","method":"In vivo xenograft mouse model (RAG-2-/- γc-/- mice), ex vivo HLA-E expression analysis, NK cell degranulation assays under hypoxic conditions (0.6% O2)","journal":"Cancer immunology, immunotherapy","confidence":"High","confidence_rationale":"Tier 2 — in vivo model combined with mechanistic in vitro functional assays under physiologically relevant conditions","pmids":["25920521"],"is_preprint":false},{"year":2018,"finding":"HLA-E presents ER-stress-generated signal peptides; bortezomib-induced ER stress in multiple myeloma cells specifically reduces cell surface HLA-E expression (without affecting classical HLA class I), selectively sensitizing myeloma cells to killing by NKG2A single-positive NK cells through loss of NKG2A/HLA-E inhibitory signaling.","method":"Bortezomib treatment of MM cells, FACS for surface HLA-E and HLA class I, NK cell subpopulation cytotoxicity assays with NKG2A single-positive NK cells","journal":"Oncoimmunology","confidence":"High","confidence_rationale":"Tier 2 — mechanistic dissection of ER-stress pathway with specific NK subset functional readout","pmids":["30713790"],"is_preprint":false},{"year":2017,"finding":"HLA-E presents a glycopeptide from the M. tuberculosis protein MPT32 to CD8+ T cells; recognition requires N-terminal O-linked mannosylation of the peptide by a mannosyltransferase encoded by Mtb gene Rv1002c, representing the first post-translationally modified bacterial antigen presented by HLA-E.","method":"HLA-E-restricted CD8+ T cell clone identification, MPT32 antigen characterization, Rv1002c mannosyltransferase knockout experiments, T cell recognition assays","journal":"Scientific reports","confidence":"High","confidence_rationale":"Tier 2 — T cell clone experiments with specific gene knockout defining the modification requirement","pmids":["28676677"],"is_preprint":false},{"year":2021,"finding":"HLA-E-restricted CD8+ T cells bearing high-affinity TCRs for HLA-E are regulated by inhibitory NK receptors KIR2DL1 and KIR2DL2/L3, while lower-affinity TCR-bearing T cells express activating NKG2C; KIR2D/HLA-C interaction regulates T cells with high self-reactive TCR affinities, providing self/non-self discrimination for HLA-E-restricted responses.","method":"RNA sequencing, flow cytometry, TCR affinity measurements, KIR blocking experiments, cytokine response assays","journal":"Science immunology","confidence":"High","confidence_rationale":"Tier 2 — mechanistic epistasis established by RNA-seq, flow cytometry, and functional blocking experiments","pmids":["33893172"],"is_preprint":false},{"year":2015,"finding":"Regulation of monocyte-to-macrophage differentiation causes HLA-E upregulation; in differentiated macrophages, the primary intracellular destination of newly synthesized HLA-E is the autophagy-lysosomal network (colocalizing with LC3 and LAMP1) rather than the cell surface, unlike classical HLA class I molecules.","method":"Immunofluorescence confocal microscopy, colocalization with LC3/LAMP1, NK cell cytotoxicity assays with anti-NKG2A blocking, subcellular fractionation in U937, THP1, and PBMC-derived macrophages","journal":"Journal of leukocyte biology","confidence":"High","confidence_rationale":"Tier 2 — direct subcellular localization with functional consequence demonstrated in multiple cell systems","pmids":["26310830"],"is_preprint":false},{"year":2023,"finding":"Antigen-specific NK cell memory against HIV-1 and influenza develops via a conserved, epitope-specific mechanism largely dependent on the activating CD94/NKG2C receptor and its ligand HLA-E; individual memory NK cells validated by single-cell cloning show permanent antigen specificity, and KLRG1, α4β7, and NKG2C mark antigen-specific memory NK cells.","method":"Single-cell cloning, complex immunophenotyping, HLA-E-restricted peptide identification, in vitro NK cell memory assays","journal":"Science immunology","confidence":"High","confidence_rationale":"Tier 2 — single-cell cloning with blocking experiments establishing HLA-E/NKG2C-dependent mechanism","pmids":["38064568"],"is_preprint":false},{"year":2019,"finding":"HLA-E surface expression is regulated by XPO1 (exportin-1); XPO1 inhibition with selinexor significantly reduces HLA-E surface expression on lymphoma cells and primary CLL cells, selectively increasing activation of NKG2A+ NK cells and enhancing NK cell-mediated cytotoxicity against these target cells.","method":"Selinexor treatment of lymphoma cell lines and primary CLL cells, FACS for surface HLA-E, NK cell activation assays (CD107a, IFNγ), ADCC assays","journal":"Frontiers in oncology","confidence":"High","confidence_rationale":"Tier 2 — direct mechanistic link between XPO1 inhibition and HLA-E reduction with NKG2A+ NK functional readout","pmids":["34926302"],"is_preprint":false}],"current_model":"HLA-E is a non-classical MHC class I molecule that assembles in the ER with β2-microglobulin and peptides derived from MHC class I signal sequences (generated by signal peptide peptidase and transported by TAP), is largely ER-retained due to limited high-affinity peptide supply with its cytoplasmic tail regulating intracellular trafficking and rapid endocytosis at the cell surface; when stably expressed on the cell surface, HLA-E serves as the principal ligand for the CD94/NKG2A inhibitory receptor on NK cells and CD8+ T cells (inhibiting their cytotoxicity) and for the CD94/NKG2C activating receptor, with the identity of the bound peptide determining whether NK/T cell inhibition or activation ensues, and the entire axis is exploited by pathogens (HCMV UL40, HIV Nef, SARS-CoV-2 Nsp13) and by cellular stress states (senescence, ER stress) to modulate immune surveillance."},"narrative":{"teleology":[{"year":1998,"claim":"Identification of HLA-E as the principal ligand for CD94/NKG2A established the functional role of this non-classical MHC molecule as an NK cell inhibitory checkpoint, resolving the question of which molecule presented self-information to CD94-bearing receptors.","evidence":"NK cytotoxicity assays with HLA-E transfectants and blocking antibodies against CD94/NKG2A; crystal structure of HLA-E/β2m/peptide complex at 2.85 Å revealing constrained peptide specificity for MHC class I leader sequences; TAP interaction and peptide binding biochemistry","pmids":["9560253","9660937","9574542"],"confidence":"High","gaps":["Mechanism of HLA-E trafficking from ER to surface was not yet defined","Whether HLA-E engages CD94/NKG2C with distinct functional consequences was unresolved","In vivo physiological relevance beyond cell line assays not established"]},{"year":2000,"claim":"Discovery that HCMV UL40 provides a TAP-independent peptide to stabilize HLA-E and that HLA-E functions on trophoblasts revealed pathogen exploitation and physiological immune tolerance roles for the HLA-E/NKG2A axis.","evidence":"HCMV infection with TAP-deficient cell lines showing TAP-independent HLA-E loading by UL40 leader peptide; HLA-E tetramer binding and cytotoxicity assays with decidual NK cells","pmids":["10669413","10898498"],"confidence":"High","gaps":["Structural basis for UL40 peptide mimicry of host leader sequences not yet determined","Whether other viruses employ similar evasion strategies was unknown","Trophoblast HLA-E peptide repertoire not defined"]},{"year":2001,"claim":"Identification of signal peptide peptidase as the protease generating HLA-E epitopes from MHC class I signal sequences resolved how the immune system couples classical MHC class I biosynthesis to non-classical HLA-E-mediated NK surveillance.","evidence":"Signal peptide peptidase inhibition blocking release of epitope-containing fragment from the lipid bilayer, with demonstration of subsequent TAP-dependent ER transport","pmids":["11714810"],"confidence":"High","gaps":["Whether signal peptide peptidase activity is rate-limiting for HLA-E surface expression was unclear","Contribution of other ER-resident proteases not excluded"]},{"year":2002,"claim":"Discovery that HLA-E presents an hsp60-derived signal peptide unrecognized by CD94/NKG2A demonstrated that HLA-E acts as a stress sensor, not merely a reporter of MHC class I biosynthesis, fundamentally broadening its immunological role.","evidence":"HLA-E/hsp60 peptide complex characterization with CD94/NKG2A binding and NK functional assays on stressed cells; allelic comparison crystal structures showing that peptide identity rather than heavy chain conformation determines receptor engagement","pmids":["12461076","12411439"],"confidence":"High","gaps":["Range of stress-induced peptides binding HLA-E was not systematically catalogued","Whether hsp60 peptide engages NKG2C was unknown"]},{"year":2008,"claim":"Crystal structures of the CD94/NKG2A–HLA-E complex revealed that CD94 dominates the interaction interface and peptide contacts, while NKG2A residues 167–170 account for the higher affinity over NKG2C, explaining the molecular basis for differential inhibitory vs. activating receptor engagement.","evidence":"X-ray crystallography of CD94-NKG2A/HLA-E at 3.5 Å and 4.4 Å with mutagenesis validation and affinity measurements; parallel structures of HLA-E with peptides showing that subtle peptide conformational differences dictate receptor recognition","pmids":["18332182","18448674","18339401"],"confidence":"High","gaps":["Full structure of CD94/NKG2C–HLA-E complex not yet solved","How peptide conformational differences translate to signaling outcomes remained unclear"]},{"year":2015,"claim":"Systematic analyses of HLA-E allelic peptide repertoires and NK cell subset responses demonstrated that NKG2A inhibition is broadly permissive for diverse peptides while NKG2C activation is selectively triggered by restricted peptide identities, establishing the asymmetric peptide-selectivity principle governing the HLA-E checkpoint.","evidence":"Mass spectrometric HLA-E ligandome for E*01:01 vs. E*01:03; degranulation assays with NKG2A+ and NKG2C+ NK subsets across panels of HLA-E–peptide complexes; in vivo myeloma xenograft showing microenvironment-driven HLA-E upregulation inhibiting NKG2A+ NK cells","pmids":["26552660","26382247","25920521"],"confidence":"High","gaps":["Structural explanation for NKG2C peptide selectivity lacking","How HLA-E allelic differences affect disease outcomes not established in patient cohorts"]},{"year":2016,"claim":"Demonstration that HLA-E presents an HIV capsid peptide not recognized by NKG2A revealed that pathogen-derived peptides can convert HLA-E from an inhibitory to a permissive ligand, directly licensing NK killing of HIV-infected cells.","evidence":"Cytolytic assays with autologous primary NK cells against HIV-infected T cells with HLA-E peptide loading and NKG2A blocking","pmids":["26828202"],"confidence":"High","gaps":["Breadth of HIV-derived HLA-E epitopes unknown","Whether HIV-specific NK responses are durable in vivo was unresolved"]},{"year":2017,"claim":"Discovery that HLA-E presents a mannosylated M. tuberculosis glycopeptide to CD8+ T cells expanded the antigen repertoire to post-translationally modified bacterial antigens and established HLA-E-restricted T cell immunity as a component of anti-mycobacterial defense.","evidence":"CD8+ T cell clone characterization with mannosyltransferase (Rv1002c) knockout confirming glycosylation requirement for HLA-E presentation","pmids":["28676677"],"confidence":"High","gaps":["Prevalence of HLA-E-restricted T cell responses in TB patients not quantified","Whether glycopeptide presentation follows the same loading pathway as signal peptides was unknown"]},{"year":2018,"claim":"Crystal structures of HLA-E with pathogen-derived peptides revealed conformational flexibility in the binding groove and broader anchor residue tolerance than anticipated, providing the structural explanation for how HLA-E accommodates both self-leader and diverse non-self peptides.","evidence":"X-ray crystallography of HLA-E with HIV and Mtb peptides with mutagenesis validation","pmids":["30087334"],"confidence":"High","gaps":["Peptide exchange dynamics at the cell surface not characterized","How groove flexibility affects receptor engagement kinetics unknown"]},{"year":2019,"claim":"Multiple studies converged to show that HLA-E upregulation serves as an immune evasion strategy in senescence and viral infection: senescent cells upregulate HLA-E via p38/SASP signaling to inhibit NKG2A+ effectors, while HIV Nef targets the HLA-E cytoplasmic tail for downregulation, revealing the cytoplasmic tail as a key regulatory element.","evidence":"p38 inhibitor and NKG2A blocking antibody experiments in senescent fibroblasts; cytoplasmic tail swap experiments in HIV Nef-expressing cells","pmids":["31160572","31375574"],"confidence":"High","gaps":["Specific motifs in the cytoplasmic tail required for Nef interaction not mapped","Whether senescence-induced HLA-E peptide repertoire differs from homeostatic repertoire was unclear"]},{"year":2022,"claim":"SARS-CoV-2 Nsp13 peptide was shown to abrogate HLA-E/NKG2A inhibitory signaling, licensing NK killing of infected cells, while structural studies revealed that non-VL9 peptides induce extended HLA-E conformations that disfavor NKG2A recognition, providing a unified structural-functional framework for peptide-dependent checkpoint control.","evidence":"HLA-E/Nsp13 peptide loading with NKG2A binding assays and viral replication suppression assays; crystallography and SAXS showing compact VL9-bound vs. extended non-VL9-bound HLA-E conformations","pmids":["35235832","35705051"],"confidence":"High","gaps":["Whether conformational differences affect NKG2C engagement was not addressed","In vivo relevance of Nsp13 peptide presentation during COVID-19 not confirmed"]},{"year":2023,"claim":"Multiple advances defined the complete HLA-E trafficking cycle, the quantitative rules governing signal peptide competition, the breadth of the HLA-E peptidome, and the role of HLA-E/NKG2C in antigen-specific NK cell memory, collectively reframing HLA-E as a versatile immune surveillance hub beyond simple inhibitory checkpointing.","evidence":"Live-cell imaging and cytoplasmic tail mutants defining ER retention and rapid endocytic cycling; systematic SP variant analysis showing only 6 of 16 common SPs are functional; yeast-display library identifying 500 binding peptides; single-cell cloning of epitope-specific memory NK cells dependent on HLA-E/NKG2C; RGS18-AKT-CREB pathway driving tumor HLA-E upregulation for metastatic immune evasion","pmids":["37140910","37264229","37558657","38064568","36706761"],"confidence":"High","gaps":["Full in vivo trafficking itinerary of HLA-E in different tissues not mapped","How memory NK cell TCR-like specificity for HLA-E–peptide is encoded at the molecular level remains unknown","Competition dynamics among signal peptides in physiological multi-allele settings not modeled"]},{"year":null,"claim":"Key unresolved questions include the complete structural basis of CD94/NKG2C engagement with HLA-E, the in vivo peptide repertoire of HLA-E across tissues and disease states, the molecular mechanism of XPO1-dependent HLA-E surface regulation, and whether HLA-E-restricted adaptive NK memory can be therapeutically harnessed.","evidence":"","pmids":[],"confidence":"High","gaps":["No crystal structure of CD94/NKG2C–HLA-E complex published","In vivo HLA-E peptidome from primary tissues not comprehensively determined","Mechanism linking XPO1 to HLA-E surface expression is correlative","Therapeutic exploitation of HLA-E/NKG2C memory axis untested in clinical settings"]}],"mechanism_profile":{"molecular_activity":[{"term_id":"GO:0048018","term_label":"receptor ligand activity","supporting_discovery_ids":[0,4,11,12]},{"term_id":"GO:0098772","term_label":"molecular function regulator activity","supporting_discovery_ids":[0,7,21,29]}],"localization":[{"term_id":"GO:0005886","term_label":"plasma membrane","supporting_discovery_ids":[0,4,8,25]},{"term_id":"GO:0005783","term_label":"endoplasmic reticulum","supporting_discovery_ids":[2,25]},{"term_id":"GO:0005768","term_label":"endosome","supporting_discovery_ids":[25]},{"term_id":"GO:0005764","term_label":"lysosome","supporting_discovery_ids":[34]}],"pathway":[{"term_id":"R-HSA-168256","term_label":"Immune System","supporting_discovery_ids":[0,7,11,18,21,23,35]},{"term_id":"R-HSA-392499","term_label":"Metabolism of proteins","supporting_discovery_ids":[1,2,5,17]},{"term_id":"R-HSA-1643685","term_label":"Disease","supporting_discovery_ids":[3,16,22,26,30]}],"complexes":["HLA-E/β2-microglobulin/peptide","CD94/NKG2A/HLA-E","CD94/NKG2C/HLA-E"],"partners":["B2M","KLRD1","KLRC1","KLRC2","TAP1","SPPL3","XPO1"],"other_free_text":[]},"mechanistic_narrative":"HLA-E is a non-classical MHC class I molecule that functions as a sentinel of antigen-processing pathway integrity and cellular stress by presenting a restricted repertoire of peptides—primarily nonameric sequences derived from MHC class I signal peptides—to the inhibitory receptor CD94/NKG2A and the activating receptor CD94/NKG2C on NK cells and CD8+ T cells [PMID:9560253, PMID:9660937, PMID:11714810]. HLA-E assembles with β2-microglobulin and peptide in the ER via TAP-dependent loading of signal peptide fragments generated by signal peptide peptidase; it is largely ER-retained due to limited high-affinity peptide supply, and its cytoplasmic tail drives rapid endocytosis when the molecule reaches the cell surface [PMID:9574542, PMID:37140910]. The identity of the bound peptide determines functional outcome: canonical MHC class I leader peptides engage CD94/NKG2A to inhibit NK cell cytotoxicity, whereas pathogen-derived peptides (from HIV capsid, SARS-CoV-2 Nsp13, or M. tuberculosis) or stress-induced peptides (hsp60 signal peptide) adopt alternative conformations that fail to engage the inhibitory receptor, thereby licensing NK cell killing of infected or stressed targets [PMID:12461076, PMID:26828202, PMID:35705051, PMID:35235832]. This peptide-dependent checkpoint is exploited by HCMV UL40, which supplies an HLA-E-binding peptide independently of TAP to maintain inhibitory signaling during viral immune evasion, and by tumors and senescent cells that upregulate HLA-E to escape NKG2A+ effector responses [PMID:10669413, PMID:31160572, PMID:36706761]."},"prefetch_data":{"uniprot":{"accession":"P13747","full_name":"HLA class I histocompatibility antigen, alpha chain E","aliases":["MHC class I antigen E"],"length_aa":358,"mass_kda":40.1,"function":"Non-classical major histocompatibility class Ib molecule involved in immune self-nonself discrimination. In complex with B2M/beta-2-microglobulin binds nonamer self-peptides derived from the signal sequence of classical MHC class Ia molecules (VL9 peptides - VMAPRT[V/L][L/V/I/F]L) (PubMed:18083576, PubMed:18339401, PubMed:35705051, PubMed:37264229, PubMed:9754572). Peptide-bound HLA-E-B2M heterotrimeric complex primarily functions as a ligand for natural killer (NK) cell inhibitory receptor KLRD1-KLRC1, enabling NK cells to monitor the expression of other MHC class I molecules in healthy cells and to tolerate self (PubMed:17179229, PubMed:18083576, PubMed:37264229, PubMed:9486650, PubMed:9754572). Upon cellular stress, preferentially binds signal sequence-derived peptides from stress-induced chaperones and is no longer recognized by NK cell inhibitory receptor KLRD1-KLRC1, resulting in impaired protection from NK cells (PubMed:12461076). Binds signal sequence-derived peptides from non-classical MHC class Ib HLA-G molecules and acts as a ligand for NK cell activating receptor KLRD1-KLRC2, likely playing a role in the generation and effector functions of adaptive NK cells and in maternal-fetal tolerance during pregnancy (PubMed:30134159, PubMed:37264229, PubMed:9754572). Besides self-peptides, can also bind and present pathogen-derived peptides conformationally similar to VL9 peptides to alpha-beta T cell receptor (TCR) on unconventional CD8-positive cytotoxic T cells, ultimately triggering antimicrobial immune response (PubMed:16474394, PubMed:20195504, PubMed:30087334, PubMed:34228645). Presents HIV gag peptides (immunodominant KAFSPEVIPMF and subdominant KALGPAATL epitopes) predominantly to CD8-positive T cell clones expressing a TRAV17-containing TCR, triggering HLA-E-restricted T cell responses (PubMed:34228645). Presents mycobacterial peptides to HLA-E-restricted CD8-positive T cells eliciting both cytotoxic and immunoregulatory functions (PubMed:20195504, PubMed:35705051) (Microbial infection) Viruses like human cytomegalovirus have evolved an escape mechanism whereby virus-induced down-regulation of host MHC class I molecules is coupled to the binding of viral peptides to HLA-E, restoring HLA-E expression and inducing HLA-E-dependent NK cell immune tolerance to infected cells (Microbial infection) May bind HIV-1 gag/Capsid protein p24-derived peptide (AISPRTLNA) on infected cells and may inhibit NK cell cytotoxicity, a mechanism that allows HIV-1 to escape immune recognition (Microbial infection) Upon SARS-CoV-2 infection, may contribute to functional exhaustion of cytotoxic NK cells and CD8-positive T cells (PubMed:32859121). Binds SARS-CoV-2 S/Spike protein S1-derived peptide (LQPRTFLL) expressed on the surface of lung epithelial cells, inducing NK cell exhaustion and dampening of antiviral immune surveillance (PubMed:32859121)","subcellular_location":"Secreted","url":"https://www.uniprot.org/uniprotkb/P13747/entry"},"depmap":{"release":"DepMap","has_data":true,"is_common_essential":false,"resolved_as":"","url":"https://depmap.org/portal/gene/HLA-E","classification":"Not Classified","n_dependent_lines":12,"n_total_lines":1208,"dependency_fraction":0.009933774834437087},"opencell":{"profiled":false,"resolved_as":"","ensg_id":"","cell_line_id":"","localizations":[],"interactors":[],"url":"https://opencell.sf.czbiohub.org/search/HLA-E","total_profiled":1310},"omim":[{"mim_id":"613609","title":"HOMEOSTATIC IRON REGULATOR; HFE","url":"https://www.omim.org/entry/613609"},{"mim_id":"609423","title":"HUMAN IMMUNODEFICIENCY VIRUS TYPE 1, SUSCEPTIBILITY TO","url":"https://www.omim.org/entry/609423"},{"mim_id":"603771","title":"PROTEIN PHOSPHATASE 1, REGULATORY SUBUNIT 10; PPP1R10","url":"https://www.omim.org/entry/603771"},{"mim_id":"602894","title":"KILLER CELL LECTIN-LIKE RECEPTOR, SUBFAMILY D, MEMBER 1; KLRD1","url":"https://www.omim.org/entry/602894"},{"mim_id":"602891","title":"KILLER CELL LECTIN-LIKE RECEPTOR, SUBFAMILY C, MEMBER 2; KLRC2","url":"https://www.omim.org/entry/602891"}],"hpa":{"profiled":true,"resolved_as":"","reliability":"Supported","locations":[{"location":"Vesicles","reliability":"Supported"},{"location":"Plasma membrane","reliability":"Supported"}],"tissue_specificity":"Low tissue specificity","tissue_distribution":"Detected in many","driving_tissues":[],"url":"https://www.proteinatlas.org/search/HLA-E"},"hgnc":{"alias_symbol":[],"prev_symbol":[]},"alphafold":{"accession":"P13747","domains":[{"cath_id":"3.30.500.10","chopping":"22-200","consensus_level":"high","plddt":96.2909,"start":22,"end":200},{"cath_id":"2.60.40.10","chopping":"206-293","consensus_level":"high","plddt":95.4244,"start":206,"end":293}],"viewer_url":"https://alphafold.ebi.ac.uk/entry/P13747","model_url":"https://alphafold.ebi.ac.uk/files/AF-P13747-F1-model_v6.cif","pae_url":"https://alphafold.ebi.ac.uk/files/AF-P13747-F1-predicted_aligned_error_v6.png","plddt_mean":87.0},"mouse_models":{"mgi_url":"https://www.informatics.jax.org/marker/summary?nomen=HLA-E","jax_strain_url":"https://www.jax.org/strain/search?query=HLA-E"},"sequence":{"accession":"P13747","fasta_url":"https://rest.uniprot.org/uniprotkb/P13747.fasta","uniprot_url":"https://www.uniprot.org/uniprotkb/P13747/entry","alphafold_viewer_url":"https://alphafold.ebi.ac.uk/entry/P13747"}},"corpus_meta":[{"pmid":"9560253","id":"PMC_9560253","title":"HLA-E is a major ligand for the natural killer inhibitory receptor CD94/NKG2A.","date":"1998","source":"Proceedings of the National Academy of Sciences of the United States of America","url":"https://pubmed.ncbi.nlm.nih.gov/9560253","citation_count":837,"is_preprint":false},{"pmid":"10669413","id":"PMC_10669413","title":"Surface expression of HLA-E, an inhibitor of natural killer cells, enhanced by human cytomegalovirus gpUL40.","date":"2000","source":"Science (New York, N.Y.)","url":"https://pubmed.ncbi.nlm.nih.gov/10669413","citation_count":499,"is_preprint":false},{"pmid":"28504668","id":"PMC_28504668","title":"HLA-E-expressing pluripotent stem cells escape allogeneic responses and lysis by NK cells.","date":"2017","source":"Nature biotechnology","url":"https://pubmed.ncbi.nlm.nih.gov/28504668","citation_count":486,"is_preprint":false},{"pmid":"31160572","id":"PMC_31160572","title":"Senescent cells evade immune clearance via HLA-E-mediated NK and CD8+ T cell inhibition.","date":"2019","source":"Nature communications","url":"https://pubmed.ncbi.nlm.nih.gov/31160572","citation_count":415,"is_preprint":false},{"pmid":"10898498","id":"PMC_10898498","title":"HLA-E is expressed on trophoblast and interacts with CD94/NKG2 receptors on decidual NK cells.","date":"2000","source":"European journal of immunology","url":"https://pubmed.ncbi.nlm.nih.gov/10898498","citation_count":290,"is_preprint":false},{"pmid":"12411439","id":"PMC_12411439","title":"HLA-E allelic variants. Correlating differential expression, peptide affinities, crystal structures, and thermal stabilities.","date":"2002","source":"The Journal of biological chemistry","url":"https://pubmed.ncbi.nlm.nih.gov/12411439","citation_count":265,"is_preprint":false},{"pmid":"36706761","id":"PMC_36706761","title":"Immune checkpoint HLA-E:CD94-NKG2A mediates evasion of circulating tumor cells from NK cell surveillance.","date":"2023","source":"Cancer cell","url":"https://pubmed.ncbi.nlm.nih.gov/36706761","citation_count":258,"is_preprint":false},{"pmid":"12461076","id":"PMC_12461076","title":"A signal peptide derived from hsp60 binds HLA-E and interferes with CD94/NKG2A recognition.","date":"2002","source":"The Journal of experimental medicine","url":"https://pubmed.ncbi.nlm.nih.gov/12461076","citation_count":203,"is_preprint":false},{"pmid":"18332182","id":"PMC_18332182","title":"CD94-NKG2A recognition of human leukocyte antigen (HLA)-E bound to an HLA class I leader sequence.","date":"2008","source":"The Journal of experimental medicine","url":"https://pubmed.ncbi.nlm.nih.gov/18332182","citation_count":190,"is_preprint":false},{"pmid":"10784586","id":"PMC_10784586","title":"Selective expansion of intraepithelial lymphocytes expressing the HLA-E-specific natural killer receptor CD94 in celiac disease.","date":"2000","source":"Gastroenterology","url":"https://pubmed.ncbi.nlm.nih.gov/10784586","citation_count":185,"is_preprint":false},{"pmid":"32409305","id":"PMC_32409305","title":"The NKG2A-HLA-E Axis as a Novel Checkpoint in the Tumor Microenvironment.","date":"2020","source":"Clinical cancer research : an official journal of the American Association for Cancer Research","url":"https://pubmed.ncbi.nlm.nih.gov/32409305","citation_count":178,"is_preprint":false},{"pmid":"18448674","id":"PMC_18448674","title":"Structural basis for NKG2A/CD94 recognition of HLA-E.","date":"2008","source":"Proceedings of the National Academy of Sciences of the United States of America","url":"https://pubmed.ncbi.nlm.nih.gov/18448674","citation_count":176,"is_preprint":false},{"pmid":"9660937","id":"PMC_9660937","title":"Structural features impose tight peptide binding specificity in the nonclassical MHC molecule HLA-E.","date":"1998","source":"Molecular cell","url":"https://pubmed.ncbi.nlm.nih.gov/9660937","citation_count":172,"is_preprint":false},{"pmid":"11714810","id":"PMC_11714810","title":"Intramembrane proteolysis of signal peptides: an essential step in the generation of HLA-E epitopes.","date":"2001","source":"Journal of immunology (Baltimore, Md. : 1950)","url":"https://pubmed.ncbi.nlm.nih.gov/11714810","citation_count":158,"is_preprint":false},{"pmid":"15494539","id":"PMC_15494539","title":"Identification of a human HLA-E-restricted CD8+ T cell subset in volunteers immunized with Salmonella enterica serovar Typhi strain Ty21a typhoid vaccine.","date":"2004","source":"Journal of immunology (Baltimore, Md. : 1950)","url":"https://pubmed.ncbi.nlm.nih.gov/15494539","citation_count":144,"is_preprint":false},{"pmid":"20195504","id":"PMC_20195504","title":"Mycobacterium tuberculosis peptides presented by HLA-E molecules are targets for human CD8 T-cells with cytotoxic as well as regulatory activity.","date":"2010","source":"PLoS pathogens","url":"https://pubmed.ncbi.nlm.nih.gov/20195504","citation_count":143,"is_preprint":false},{"pmid":"15751767","id":"PMC_15751767","title":"HIV-1 infection leads to increased HLA-E expression resulting in impaired function of natural killer cells.","date":"2005","source":"Antiviral therapy","url":"https://pubmed.ncbi.nlm.nih.gov/15751767","citation_count":137,"is_preprint":false},{"pmid":"12618909","id":"PMC_12618909","title":"Analysis of HLA-E expression in human tumors.","date":"2003","source":"Immunogenetics","url":"https://pubmed.ncbi.nlm.nih.gov/12618909","citation_count":135,"is_preprint":false},{"pmid":"19136889","id":"PMC_19136889","title":"HLA-E/human beta2-microglobulin transgenic pigs: protection against xenogeneic human anti-pig natural killer cell cytotoxicity.","date":"2009","source":"Transplantation","url":"https://pubmed.ncbi.nlm.nih.gov/19136889","citation_count":120,"is_preprint":false},{"pmid":"9021407","id":"PMC_9021407","title":"Population genetic studies of HLA-E: evidence for selection.","date":"1997","source":"Human immunology","url":"https://pubmed.ncbi.nlm.nih.gov/9021407","citation_count":117,"is_preprint":false},{"pmid":"18946929","id":"PMC_18946929","title":"The major histocompatibility complex class Ib molecule HLA-E at the interface between innate and adaptive immunity.","date":"2008","source":"Tissue antigens","url":"https://pubmed.ncbi.nlm.nih.gov/18946929","citation_count":106,"is_preprint":false},{"pmid":"23335510","id":"PMC_23335510","title":"Polymorphism in human cytomegalovirus UL40 impacts on recognition of human leukocyte antigen-E (HLA-E) by natural killer cells.","date":"2013","source":"The Journal of biological chemistry","url":"https://pubmed.ncbi.nlm.nih.gov/23335510","citation_count":101,"is_preprint":false},{"pmid":"36099881","id":"PMC_36099881","title":"NKG2A and HLA-E define an alternative immune checkpoint axis in bladder cancer.","date":"2022","source":"Cancer cell","url":"https://pubmed.ncbi.nlm.nih.gov/36099881","citation_count":98,"is_preprint":false},{"pmid":"21953582","id":"PMC_21953582","title":"HLA-E/β2 microglobulin overexpression in colorectal cancer is associated with recruitment of inhibitory immune cells and tumor progression.","date":"2012","source":"International journal of cancer","url":"https://pubmed.ncbi.nlm.nih.gov/21953582","citation_count":96,"is_preprint":false},{"pmid":"20877010","id":"PMC_20877010","title":"HLA-E-restricted regulatory CD8(+) T cells are involved in development and control of human autoimmune type 1 diabetes.","date":"2010","source":"The Journal of clinical investigation","url":"https://pubmed.ncbi.nlm.nih.gov/20877010","citation_count":91,"is_preprint":false},{"pmid":"18339401","id":"PMC_18339401","title":"Subtle changes in peptide conformation profoundly affect recognition of the non-classical MHC class I molecule HLA-E by the CD94-NKG2 natural killer cell receptors.","date":"2008","source":"Journal of molecular biology","url":"https://pubmed.ncbi.nlm.nih.gov/18339401","citation_count":88,"is_preprint":false},{"pmid":"20634877","id":"PMC_20634877","title":"The emerging role of HLA-E-restricted CD8+ T lymphocytes in the adaptive immune response to pathogens and tumors.","date":"2010","source":"Journal of biomedicine & biotechnology","url":"https://pubmed.ncbi.nlm.nih.gov/20634877","citation_count":81,"is_preprint":false},{"pmid":"12445303","id":"PMC_12445303","title":"Definitive high resolution typing of HLA-E allelic polymorphisms: Identifying potential errors in existing allele data.","date":"2002","source":"Tissue antigens","url":"https://pubmed.ncbi.nlm.nih.gov/12445303","citation_count":81,"is_preprint":false},{"pmid":"21800130","id":"PMC_21800130","title":"Clinical significance of the HLA-E and CD94/NKG2 interaction.","date":"2011","source":"Archivum immunologiae et therapiae experimentalis","url":"https://pubmed.ncbi.nlm.nih.gov/21800130","citation_count":80,"is_preprint":false},{"pmid":"9574542","id":"PMC_9574542","title":"Interaction of HLA-E with peptides and the peptide transporter in vitro: implications for its function in antigen presentation.","date":"1998","source":"Journal of immunology (Baltimore, Md. : 1950)","url":"https://pubmed.ncbi.nlm.nih.gov/9574542","citation_count":80,"is_preprint":false},{"pmid":"31213473","id":"PMC_31213473","title":"Enriched HLA-E and CD94/NKG2A Interaction Limits Antitumor CD8+ Tumor-Infiltrating T Lymphocyte Responses.","date":"2019","source":"Cancer immunology research","url":"https://pubmed.ncbi.nlm.nih.gov/31213473","citation_count":77,"is_preprint":false},{"pmid":"30134159","id":"PMC_30134159","title":"Distinct HLA-E Peptide Complexes Modify Antibody-Driven Effector Functions of Adaptive NK Cells.","date":"2018","source":"Cell reports","url":"https://pubmed.ncbi.nlm.nih.gov/30134159","citation_count":75,"is_preprint":false},{"pmid":"26828202","id":"PMC_26828202","title":"A Conserved HIV-1-Derived Peptide Presented by HLA-E Renders Infected T-cells Highly Susceptible to Attack by NKG2A/CD94-Bearing Natural Killer Cells.","date":"2016","source":"PLoS pathogens","url":"https://pubmed.ncbi.nlm.nih.gov/26828202","citation_count":72,"is_preprint":false},{"pmid":"16487601","id":"PMC_16487601","title":"The involvement of HLA-E and -F in pregnancy.","date":"2006","source":"Journal of reproductive immunology","url":"https://pubmed.ncbi.nlm.nih.gov/16487601","citation_count":71,"is_preprint":false},{"pmid":"30087334","id":"PMC_30087334","title":"Pathogen-derived HLA-E bound epitopes reveal broad primary anchor pocket tolerability and conformationally malleable peptide binding.","date":"2018","source":"Nature communications","url":"https://pubmed.ncbi.nlm.nih.gov/30087334","citation_count":69,"is_preprint":false},{"pmid":"25631937","id":"PMC_25631937","title":"Human CD8 T lymphocytes recognize Mycobacterium tuberculosis antigens presented by HLA-E during active tuberculosis and express type 2 cytokines.","date":"2015","source":"European journal of immunology","url":"https://pubmed.ncbi.nlm.nih.gov/25631937","citation_count":63,"is_preprint":false},{"pmid":"25413103","id":"PMC_25413103","title":"Clinical and immunological significance of HLA-E in stem cell transplantation and cancer.","date":"2014","source":"Tissue antigens","url":"https://pubmed.ncbi.nlm.nih.gov/25413103","citation_count":58,"is_preprint":false},{"pmid":"26552660","id":"PMC_26552660","title":"The diversity of the HLA-E-restricted peptide repertoire explains the immunological impact of the Arg107Gly mismatch.","date":"2015","source":"Immunogenetics","url":"https://pubmed.ncbi.nlm.nih.gov/26552660","citation_count":56,"is_preprint":false},{"pmid":"26382247","id":"PMC_26382247","title":"HLA-E regulates NKG2C+ natural killer cell function through presentation of a restricted peptide repertoire.","date":"2015","source":"Human immunology","url":"https://pubmed.ncbi.nlm.nih.gov/26382247","citation_count":53,"is_preprint":false},{"pmid":"17675252","id":"PMC_17675252","title":"Elevated HLA-E levels in human glioblastomas but not in grade I to III astrocytomas correlate with infiltrating CD8+ cells.","date":"2007","source":"Journal of neuroimmunology","url":"https://pubmed.ncbi.nlm.nih.gov/17675252","citation_count":53,"is_preprint":false},{"pmid":"36560403","id":"PMC_36560403","title":"Disruption of the NKG2A:HLA-E Immune Checkpoint Axis to Enhance NK Cell Activation against Cancer.","date":"2022","source":"Vaccines","url":"https://pubmed.ncbi.nlm.nih.gov/36560403","citation_count":52,"is_preprint":false},{"pmid":"35235832","id":"PMC_35235832","title":"SARS-CoV-2 Nsp13 encodes for an HLA-E-stabilizing peptide that abrogates inhibition of NKG2A-expressing NK cells.","date":"2022","source":"Cell reports","url":"https://pubmed.ncbi.nlm.nih.gov/35235832","citation_count":51,"is_preprint":false},{"pmid":"19318419","id":"PMC_19318419","title":"Cetuximab-mediated cellular cytotoxicity is inhibited by HLA-E membrane expression in colon cancer cells.","date":"2009","source":"Innate immunity","url":"https://pubmed.ncbi.nlm.nih.gov/19318419","citation_count":51,"is_preprint":false},{"pmid":"38064568","id":"PMC_38064568","title":"Antigen-specific memory NK cell responses against HIV and influenza use the NKG2/HLA-E axis.","date":"2023","source":"Science immunology","url":"https://pubmed.ncbi.nlm.nih.gov/38064568","citation_count":49,"is_preprint":false},{"pmid":"37264229","id":"PMC_37264229","title":"HLA class I signal peptide polymorphism determines the level of CD94/NKG2-HLA-E-mediated regulation of effector cell responses.","date":"2023","source":"Nature immunology","url":"https://pubmed.ncbi.nlm.nih.gov/37264229","citation_count":49,"is_preprint":false},{"pmid":"25920521","id":"PMC_25920521","title":"Optimal selection of natural killer cells to kill myeloma: the role of HLA-E and NKG2A.","date":"2015","source":"Cancer immunology, immunotherapy : CII","url":"https://pubmed.ncbi.nlm.nih.gov/25920521","citation_count":49,"is_preprint":false},{"pmid":"21712991","id":"PMC_21712991","title":"Serum soluble HLA-E in melanoma: a new potential immune-related marker in cancer.","date":"2011","source":"PloS one","url":"https://pubmed.ncbi.nlm.nih.gov/21712991","citation_count":49,"is_preprint":false},{"pmid":"32113130","id":"PMC_32113130","title":"The unconventional role of HLA-E: The road less traveled.","date":"2020","source":"Molecular immunology","url":"https://pubmed.ncbi.nlm.nih.gov/32113130","citation_count":48,"is_preprint":false},{"pmid":"31690066","id":"PMC_31690066","title":"Dimorphism of HLA-E and its Disease Association.","date":"2019","source":"International journal of molecular sciences","url":"https://pubmed.ncbi.nlm.nih.gov/31690066","citation_count":47,"is_preprint":false},{"pmid":"16573557","id":"PMC_16573557","title":"HLA-E and immunobiology of pregnancy.","date":"2006","source":"Tissue antigens","url":"https://pubmed.ncbi.nlm.nih.gov/16573557","citation_count":47,"is_preprint":false},{"pmid":"19696636","id":"PMC_19696636","title":"Clinical significance of HLA-E*0103 homozygosity on survival after allogeneic hematopoietic stem-cell transplantation.","date":"2009","source":"Transplantation","url":"https://pubmed.ncbi.nlm.nih.gov/19696636","citation_count":45,"is_preprint":false},{"pmid":"17579058","id":"PMC_17579058","title":"Gliadin regulates the NK-dendritic cell cross-talk by HLA-E surface stabilization.","date":"2007","source":"Journal of immunology (Baltimore, Md. : 1950)","url":"https://pubmed.ncbi.nlm.nih.gov/17579058","citation_count":45,"is_preprint":false},{"pmid":"15829309","id":"PMC_15829309","title":"An HLA-E single chain trimer inhibits human NK cell reactivity towards porcine cells.","date":"2005","source":"Molecular immunology","url":"https://pubmed.ncbi.nlm.nih.gov/15829309","citation_count":43,"is_preprint":false},{"pmid":"19860683","id":"PMC_19860683","title":"HLA-E and HLA-E-bound peptides: recognition by subsets of NK and T cells.","date":"2009","source":"Current pharmaceutical design","url":"https://pubmed.ncbi.nlm.nih.gov/19860683","citation_count":42,"is_preprint":false},{"pmid":"29176828","id":"PMC_29176828","title":"T cell recognition of Mycobacterium tuberculosis peptides presented by HLA-E derived from infected human cells.","date":"2017","source":"PloS one","url":"https://pubmed.ncbi.nlm.nih.gov/29176828","citation_count":41,"is_preprint":false},{"pmid":"30713790","id":"PMC_30713790","title":"Bortezomib sensitizes multiple myeloma to NK cells via ER-stress-induced suppression of HLA-E and upregulation of DR5.","date":"2018","source":"Oncoimmunology","url":"https://pubmed.ncbi.nlm.nih.gov/30713790","citation_count":41,"is_preprint":false},{"pmid":"10689118","id":"PMC_10689118","title":"The HLA-E locus is associated with age at onset and susceptibility to type 1 diabetes mellitus.","date":"2000","source":"Human immunology","url":"https://pubmed.ncbi.nlm.nih.gov/10689118","citation_count":39,"is_preprint":false},{"pmid":"18759005","id":"PMC_18759005","title":"Influence of Hsp70 and HLA-E on the killing of leukemic blasts by cytokine/Hsp70 peptide-activated human natural killer (NK) cells.","date":"2008","source":"Cell stress & chaperones","url":"https://pubmed.ncbi.nlm.nih.gov/18759005","citation_count":38,"is_preprint":false},{"pmid":"23049954","id":"PMC_23049954","title":"Epstein-Barr virus peptide presented by HLA-E is predominantly recognized by CD8(bright) cells in multiple sclerosis patients.","date":"2012","source":"PloS one","url":"https://pubmed.ncbi.nlm.nih.gov/23049954","citation_count":38,"is_preprint":false},{"pmid":"30386347","id":"PMC_30386347","title":"HLA-E Peptide Repertoire and Dimorphism-Centerpieces in the Adaptive NK Cell Puzzle?","date":"2018","source":"Frontiers in immunology","url":"https://pubmed.ncbi.nlm.nih.gov/30386347","citation_count":37,"is_preprint":false},{"pmid":"28676677","id":"PMC_28676677","title":"HLA-E Presents Glycopeptides from the Mycobacterium tuberculosis Protein MPT32 to Human CD8+ T cells.","date":"2017","source":"Scientific reports","url":"https://pubmed.ncbi.nlm.nih.gov/28676677","citation_count":36,"is_preprint":false},{"pmid":"37140910","id":"PMC_37140910","title":"Intracellular trafficking of HLA-E and its regulation.","date":"2023","source":"The Journal of experimental medicine","url":"https://pubmed.ncbi.nlm.nih.gov/37140910","citation_count":35,"is_preprint":false},{"pmid":"30968409","id":"PMC_30968409","title":"HLA-E: exploiting pathogen-host interactions for vaccine development.","date":"2019","source":"Clinical and experimental immunology","url":"https://pubmed.ncbi.nlm.nih.gov/30968409","citation_count":34,"is_preprint":false},{"pmid":"31375574","id":"PMC_31375574","title":"Primary HIV-1 Strains Use Nef To Downmodulate HLA-E Surface Expression.","date":"2019","source":"Journal of virology","url":"https://pubmed.ncbi.nlm.nih.gov/31375574","citation_count":33,"is_preprint":false},{"pmid":"25401109","id":"PMC_25401109","title":"HLA-E: a novel player for histocompatibility.","date":"2014","source":"Journal of immunology research","url":"https://pubmed.ncbi.nlm.nih.gov/25401109","citation_count":33,"is_preprint":false},{"pmid":"32716529","id":"PMC_32716529","title":"Detailed and atypical HLA-E peptide binding motifs revealed by a novel peptide exchange binding assay.","date":"2020","source":"European journal of immunology","url":"https://pubmed.ncbi.nlm.nih.gov/32716529","citation_count":32,"is_preprint":false},{"pmid":"17961774","id":"PMC_17961774","title":"HLA-E*0101 allele in homozygous state favors severe bacterial infections in sickle cell anemia.","date":"2007","source":"Human immunology","url":"https://pubmed.ncbi.nlm.nih.gov/17961774","citation_count":32,"is_preprint":false},{"pmid":"37675109","id":"PMC_37675109","title":"KLRC1 knockout overcomes HLA-E-mediated inhibition and improves NK cell antitumor activity against solid tumors.","date":"2023","source":"Frontiers in immunology","url":"https://pubmed.ncbi.nlm.nih.gov/37675109","citation_count":32,"is_preprint":false},{"pmid":"30172717","id":"PMC_30172717","title":"Identification of novel HIV-1-derived HLA-E-binding peptides.","date":"2018","source":"Immunology letters","url":"https://pubmed.ncbi.nlm.nih.gov/30172717","citation_count":31,"is_preprint":false},{"pmid":"36477802","id":"PMC_36477802","title":"HLA-E-restricted immune responses are crucial for the control of EBV infections and the prevention of PTLD.","date":"2023","source":"Blood","url":"https://pubmed.ncbi.nlm.nih.gov/36477802","citation_count":30,"is_preprint":false},{"pmid":"39486805","id":"PMC_39486805","title":"Unlocking the therapeutic potential of the NKG2A-HLA-E immune checkpoint pathway in T cells and NK cells for cancer immunotherapy.","date":"2024","source":"Journal for immunotherapy of cancer","url":"https://pubmed.ncbi.nlm.nih.gov/39486805","citation_count":30,"is_preprint":false},{"pmid":"26310830","id":"PMC_26310830","title":"Regulation and trafficking of the HLA-E molecules during monocyte-macrophage differentiation.","date":"2015","source":"Journal of leukocyte biology","url":"https://pubmed.ncbi.nlm.nih.gov/26310830","citation_count":29,"is_preprint":false},{"pmid":"35596615","id":"PMC_35596615","title":"NKG2A-checkpoint inhibition and its blockade critically depends on peptides presented by its ligand HLA-E.","date":"2022","source":"Immunology","url":"https://pubmed.ncbi.nlm.nih.gov/35596615","citation_count":29,"is_preprint":false},{"pmid":"16542007","id":"PMC_16542007","title":"The orthology of HLA-E and H2-Qa1 is hidden by their concerted evolution with other MHC class I molecules.","date":"2006","source":"Biology direct","url":"https://pubmed.ncbi.nlm.nih.gov/16542007","citation_count":29,"is_preprint":false},{"pmid":"9605335","id":"PMC_9605335","title":"Production, crystallization, and preliminary X-ray analysis of the human MHC class Ib molecule HLA-E.","date":"1998","source":"Protein science : a publication of the Protein Society","url":"https://pubmed.ncbi.nlm.nih.gov/9605335","citation_count":28,"is_preprint":false},{"pmid":"37558657","id":"PMC_37558657","title":"High-throughput characterization of HLA-E-presented CD94/NKG2x ligands reveals peptides which modulate NK cell activation.","date":"2023","source":"Nature communications","url":"https://pubmed.ncbi.nlm.nih.gov/37558657","citation_count":27,"is_preprint":false},{"pmid":"28127896","id":"PMC_28127896","title":"New insights in HLA-E polymorphism by refined analysis of the full-length gene.","date":"2017","source":"HLA","url":"https://pubmed.ncbi.nlm.nih.gov/28127896","citation_count":27,"is_preprint":false},{"pmid":"26187162","id":"PMC_26187162","title":"HLA-E coding and 3' untranslated region variability determined by next-generation sequencing in two West-African population samples.","date":"2015","source":"Human immunology","url":"https://pubmed.ncbi.nlm.nih.gov/26187162","citation_count":27,"is_preprint":false},{"pmid":"23395341","id":"PMC_23395341","title":"The impact of HLA-E polymorphisms on relapse following allogeneic hematopoietic stem cell transplantation.","date":"2013","source":"Leukemia research","url":"https://pubmed.ncbi.nlm.nih.gov/23395341","citation_count":27,"is_preprint":false},{"pmid":"31009335","id":"PMC_31009335","title":"Enhancing Natural Killer and CD8+ T Cell-Mediated Anticancer Cytotoxicity and Proliferation of CD8+ T Cells with HLA-E Monospecific Monoclonal Antibodies.","date":"2019","source":"Monoclonal antibodies in immunodiagnosis and immunotherapy","url":"https://pubmed.ncbi.nlm.nih.gov/31009335","citation_count":26,"is_preprint":false},{"pmid":"17767552","id":"PMC_17767552","title":"Association of CD94/NKG2A, CD94/NKG2C, and its ligand HLA-E polymorphisms with Behcet's disease.","date":"2007","source":"Tissue antigens","url":"https://pubmed.ncbi.nlm.nih.gov/17767552","citation_count":25,"is_preprint":false},{"pmid":"34228645","id":"PMC_34228645","title":"HLA-E-restricted HIV-1-specific CD8+ T cell responses in natural infection.","date":"2021","source":"The Journal of clinical investigation","url":"https://pubmed.ncbi.nlm.nih.gov/34228645","citation_count":24,"is_preprint":false},{"pmid":"22256791","id":"PMC_22256791","title":"HLA-E polymorphisms in hematopoietic stem cell transplantation.","date":"2012","source":"Tissue antigens","url":"https://pubmed.ncbi.nlm.nih.gov/22256791","citation_count":23,"is_preprint":false},{"pmid":"26302084","id":"PMC_26302084","title":"The Presence of HLA-E-Restricted, CMV-Specific CD8+ T Cells in the Blood of Lung Transplant Recipients Correlates with Chronic Allograft Rejection.","date":"2015","source":"PloS one","url":"https://pubmed.ncbi.nlm.nih.gov/26302084","citation_count":23,"is_preprint":false},{"pmid":"32066399","id":"PMC_32066399","title":"HLA-E expression in diffuse glioma: relationship with clinicopathological features and patient survival.","date":"2020","source":"BMC neurology","url":"https://pubmed.ncbi.nlm.nih.gov/32066399","citation_count":23,"is_preprint":false},{"pmid":"23039207","id":"PMC_23039207","title":"Increased HLA-E expression in white matter lesions in multiple sclerosis.","date":"2012","source":"Immunology","url":"https://pubmed.ncbi.nlm.nih.gov/23039207","citation_count":22,"is_preprint":false},{"pmid":"34926302","id":"PMC_34926302","title":"Selinexor Enhances NK Cell Activation Against Malignant B Cells via Downregulation of HLA-E.","date":"2021","source":"Frontiers in oncology","url":"https://pubmed.ncbi.nlm.nih.gov/34926302","citation_count":22,"is_preprint":false},{"pmid":"22050290","id":"PMC_22050290","title":"Non-classical HLA-E gene variability in Brazilians: a nearly invariable locus surrounded by the most variable genes in the human genome.","date":"2011","source":"Tissue antigens","url":"https://pubmed.ncbi.nlm.nih.gov/22050290","citation_count":22,"is_preprint":false},{"pmid":"33893172","id":"PMC_33893172","title":"Natural killer cell receptors regulate responses of HLA-E-restricted T cells.","date":"2021","source":"Science immunology","url":"https://pubmed.ncbi.nlm.nih.gov/33893172","citation_count":21,"is_preprint":false},{"pmid":"22177730","id":"PMC_22177730","title":"Multifunctional immune-modulatory protein HLA-E identified in classical Hodgkin lymphoma: possible implications.","date":"2011","source":"Pathology, research and practice","url":"https://pubmed.ncbi.nlm.nih.gov/22177730","citation_count":21,"is_preprint":false},{"pmid":"33727352","id":"PMC_33727352","title":"Extent of Cytomegalovirus Replication in the Human Host Depends on Variations of the HLA-E/UL40 Axis.","date":"2021","source":"mBio","url":"https://pubmed.ncbi.nlm.nih.gov/33727352","citation_count":21,"is_preprint":false},{"pmid":"35181585","id":"PMC_35181585","title":"HLA-E and HLA-F Are Overexpressed in Glioblastoma and HLA-E Increased After Exposure to Ionizing Radiation.","date":"2022","source":"Cancer genomics & proteomics","url":"https://pubmed.ncbi.nlm.nih.gov/35181585","citation_count":21,"is_preprint":false},{"pmid":"35705051","id":"PMC_35705051","title":"Primary and secondary functions of HLA-E are determined by stability and conformation of the peptide-bound complexes.","date":"2022","source":"Cell reports","url":"https://pubmed.ncbi.nlm.nih.gov/35705051","citation_count":21,"is_preprint":false},{"pmid":"37528310","id":"PMC_37528310","title":"XPO1 inhibition sensitises CLL cells to NK cell mediated cytotoxicity and overcomes HLA-E expression.","date":"2023","source":"Leukemia","url":"https://pubmed.ncbi.nlm.nih.gov/37528310","citation_count":20,"is_preprint":false},{"pmid":"18822330","id":"PMC_18822330","title":"Qa-1/HLA-E-restricted regulatory CD8+ T cells and self-nonself discrimination: an essay on peripheral T-cell regulation.","date":"2008","source":"Human immunology","url":"https://pubmed.ncbi.nlm.nih.gov/18822330","citation_count":20,"is_preprint":false},{"pmid":"12559625","id":"PMC_12559625","title":"HCMV glycoprotein US6 mediated inhibition of TAP does not affect HLA-E dependent protection of K-562 cells from NK cell lysis.","date":"2003","source":"Human immunology","url":"https://pubmed.ncbi.nlm.nih.gov/12559625","citation_count":20,"is_preprint":false},{"pmid":"24105714","id":"PMC_24105714","title":"Gastric cancer progression may involve a shift in HLA-E profile from an intact heterodimer to β2-microglobulin-free monomer.","date":"2013","source":"International journal of cancer","url":"https://pubmed.ncbi.nlm.nih.gov/24105714","citation_count":20,"is_preprint":false},{"pmid":"37390223","id":"PMC_37390223","title":"HLA-E-restricted SARS-CoV-2-specific T cells from convalescent COVID-19 patients suppress virus replication despite HLA class Ia down-regulation.","date":"2023","source":"Science immunology","url":"https://pubmed.ncbi.nlm.nih.gov/37390223","citation_count":19,"is_preprint":false},{"pmid":"31697586","id":"PMC_31697586","title":"HLA-E-restricted CD8+ T Lymphocytes Efficiently Control Mycobacterium tuberculosis and HIV-1 Coinfection.","date":"2020","source":"American journal of respiratory cell and molecular biology","url":"https://pubmed.ncbi.nlm.nih.gov/31697586","citation_count":19,"is_preprint":false},{"pmid":"31445404","id":"PMC_31445404","title":"Capturing the antigen landscape: HLA-E, CD1 and MR1.","date":"2019","source":"Current opinion in immunology","url":"https://pubmed.ncbi.nlm.nih.gov/31445404","citation_count":18,"is_preprint":false}],"cost":{"stage1":{"model":"claude-sonnet-4-6","input_tokens":47544,"output_tokens":8783,"usd":0.137188},"stage2":{"model":"claude-opus-4-6","input_tokens":12670,"output_tokens":3895,"usd":0.241088},"total_usd":0.378276,"stage1_batch_id":"msgbatch_01DzrsgVgYngY1hvM3DU1yF2","stage2_batch_id":"msgbatch_01KA9b7iRzKFdhoBUT7vCvSe","note":"batch pricing = 50% of standard"},"stage1_raw":"```json\n{\n  \"discoveries\": [\n    {\n      \"year\": 1998,\n      \"finding\": \"HLA-E is the major ligand for the inhibitory NK cell receptor CD94/NKG2A. Surface stabilization of HLA-E with appropriate peptides confers protection from NK cell lysis mediated specifically through CD94/NKG2A, not through Ig-SF killer cell inhibitory receptors or ILT2/LIR1.\",\n      \"method\": \"NK cell cytotoxicity assays with HLA-E transfectants (.221 cells), antibody blocking of HLA-E, CD94, or CD94/NKG2A, cold-loading of peptides onto target cells\",\n      \"journal\": \"Proceedings of the National Academy of Sciences of the United States of America\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 — reciprocal blocking antibody experiments with multiple HLA class I allotype transfectants, replicated across labs subsequently\",\n      \"pmids\": [\"9560253\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 1998,\n      \"finding\": \"HLA-E crystal structure reveals that it binds a tightly defined set of nearly identical hydrophobic nonameric peptides derived from MHC class I leader sequences (prototypic: VMAPRTVLL), with novel structural features that enforce peptide-binding specificity and function as a checkpoint reporting on antigen processing pathway integrity to CD94/NKG2 receptors.\",\n      \"method\": \"X-ray crystallography of HLA-E/β2m/peptide complex at 2.85 Å resolution\",\n      \"journal\": \"Molecular cell\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 1 — crystal structure determination with functional interpretation\",\n      \"pmids\": [\"9660937\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 1998,\n      \"finding\": \"HLA-E interacts with TAP in the endoplasmic reticulum for peptide loading, and this interaction can be prolonged by proteasome inhibition. HLA-E can bind peptides ranging from 7 to 16 amino acids, and the exact N-terminal positioning is critical for binding.\",\n      \"method\": \"Peptide binding assays measuring surface HLA-E expression, thermostability assays of soluble HLA-E/β2m dimers, TAP interaction studies with proteasome inhibitor N-acetyl-L-leucyl-L-leucyl-L-norleucinal\",\n      \"journal\": \"Journal of immunology\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 1 — in vitro biochemical assays with multiple orthogonal methods (surface stabilization, thermostability, TAP co-immunoprecipitation)\",\n      \"pmids\": [\"9574542\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2000,\n      \"finding\": \"Human cytomegalovirus glycoprotein UL40 (gpUL40) contains a leader sequence peptide identical to HLA class I signal sequences; this peptide loads HLA-E independently of TAP, upregulating HLA-E surface expression and protecting infected cells from NK cell lysis while classical MHC class I molecules are downregulated by HCMV.\",\n      \"method\": \"HCMV infection of cells, TAP-independent peptide loading demonstrated in TAP-deficient cell lines, NK cell cytotoxicity assays\",\n      \"journal\": \"Science\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 — TAP-deficient cell line experiments with NK cytotoxicity readout, mechanistically definitive\",\n      \"pmids\": [\"10669413\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2000,\n      \"finding\": \"HLA-E is expressed on trophoblast cell surfaces and interacts with CD94/NKG2 receptors on decidual NK cells, with the overall functional consequence being inhibition of decidual NK cell cytotoxicity.\",\n      \"method\": \"HLA-E tetrameric complex binding to decidual NK cells, anti-CD94 antibody blocking, cytotoxicity assays with polyclonal decidual NK cells\",\n      \"journal\": \"European journal of immunology\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 — HLA-E tetramers with blocking antibody and functional cytotoxicity readout\",\n      \"pmids\": [\"10898498\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2001,\n      \"finding\": \"MHC class I signal peptides are processed by signal peptide peptidase in the hydrophobic membrane-spanning region after cleavage from the pre-protein; this intramembrane proteolysis is essential for release of the HLA-E epitope-containing fragment from the lipid bilayer and its subsequent TAP-dependent transport into the ER lumen.\",\n      \"method\": \"Signal peptide peptidase inhibition experiments, biochemical fractionation, demonstration of TAP-dependent transport of the processed fragment\",\n      \"journal\": \"Journal of immunology\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 1 — mechanistic enzymatic study with inhibitors identifying the specific protease step required for HLA-E peptide generation\",\n      \"pmids\": [\"11714810\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2002,\n      \"finding\": \"HLA-E alleles (E*0101 with Arg107 vs. E*0103 with Gly107) differ in peptide affinity and thermal stability, which correlates with differential cell surface expression levels, but the crystal structures of HLA-E(G) with two peptides show no significant structural differences induced by peptide binding or allelic substitution at position 107.\",\n      \"method\": \"X-ray crystallography of HLA-E(G) allele with two peptides, thermal stability assays, cell surface expression analysis\",\n      \"journal\": \"The Journal of biological chemistry\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 1 — crystal structures combined with biochemical thermal stability and surface expression assays\",\n      \"pmids\": [\"12411439\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2002,\n      \"finding\": \"HLA-E presents a peptide derived from the leader sequence of heat shock protein 60 (hsp60), which gains access to HLA-E intracellularly during cellular stress. HLA-E/hsp60 signal peptide complexes are not recognized by CD94/NKG2A inhibitory receptors, thereby reducing NK cell inhibition and providing a mechanism for NK cells to detect stressed cells.\",\n      \"method\": \"HLA-E/hsp60 peptide complex characterization, CD94/NKG2A binding assays, NK cell functional assays with stressed cells\",\n      \"journal\": \"The Journal of experimental medicine\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 — peptide-specific functional experiments with NK cell receptor blocking, mechanistic pathway established\",\n      \"pmids\": [\"12461076\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2003,\n      \"finding\": \"HLA-E cell surface expression in tumor cells requires availability of free β2-microglobulin; tumors with imbalanced HLA class Ia heavy chain/β2m expression show increased HLA-E surface detection, while total loss of HLA class Ia expression abolishes HLA-E surface expression.\",\n      \"method\": \"FACS analysis with anti-HLA-E mAb (3D12) on tumor cell lines, exogenous β2m addition experiments, analysis of cell lines with defined HLA class I genetic alterations\",\n      \"journal\": \"Immunogenetics\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 — multiple cell line analyses with genetic characterization but single lab\",\n      \"pmids\": [\"12618909\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2005,\n      \"finding\": \"An HLA-E single-chain trimer (SCT) consisting of linked HLA-B leader peptide, β2m, and HLA-E heavy chain confers surface expression on porcine cells and protects them from NK cell lysis via CD94/NKG2A interaction; an SCT bearing the hsp60-derived peptide is expressed but does not inhibit NK lysis, demonstrating peptide-dependent functional specificity.\",\n      \"method\": \"HLA-E SCT transfection of LLC-PK1 porcine cells, NK cell cytotoxicity assays with NKL and NK-92 cell lines, IFN-γ secretion assays\",\n      \"journal\": \"Molecular immunology\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 — engineered SCT with peptide specificity controls and functional NK assays\",\n      \"pmids\": [\"15829309\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2007,\n      \"finding\": \"Gliadin peptides (alpha and omega fractions) stabilize HLA-E molecules on dendritic cells, protecting immature DCs from NK cell lysis and modulating NK-DC crosstalk; a peptide derived from gliadin alpha increases HLA-E levels on RMA-S/HLA-E-transfected cells.\",\n      \"method\": \"HLA-E surface expression analysis, NK cell cytotoxicity assays with gliadin-treated DCs, RMA-S/HLA-E transfectant loading assays, immunohistochemistry of intestinal mucosa from celiac patients\",\n      \"journal\": \"Journal of immunology\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 — in vitro functional assays with transfectant cell lines and primary cells, confirmed in tissue sections\",\n      \"pmids\": [\"17579058\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2008,\n      \"finding\": \"Crystal structure of CD94-NKG2A in complex with HLA-E bound to HLA-G leader peptide reveals that CD94 dominates the interaction with HLA-E while NKG2A is more peripheral; the invariant CD94 subunit dominates peptide-mediated contacts; there are few conformational changes upon ligation ('lock and key' interaction). Mutagenesis at the CD94-NKG2A-HLA-E interface confirmed the structural contacts.\",\n      \"method\": \"X-ray crystallography of CD94-NKG2A/HLA-E complex at 3.5 Å, site-directed mutagenesis\",\n      \"journal\": \"The Journal of experimental medicine\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 1 — crystal structure with mutagenesis validation\",\n      \"pmids\": [\"18332182\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2008,\n      \"finding\": \"Crystal structure of NKG2A/CD94/HLA-E complex at 4.4 Å reveals that the C-terminal region of the peptide (most variable among class I leader sequences) interacts entirely with CD94, and residues 167-170 of NKG2A account for the ~6-fold higher affinity of NKG2A/CD94 versus NKG2C/CD94 through their role in the heterodimer interface with CD94 rather than direct HLA-E contact.\",\n      \"method\": \"X-ray crystallography, affinity measurements, binding assays with UL18\",\n      \"journal\": \"Proceedings of the National Academy of Sciences of the United States of America\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 1 — crystal structure with functional affinity and binding data\",\n      \"pmids\": [\"18448674\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2008,\n      \"finding\": \"Crystal structures of HLA-E with two leader peptides (HLA-Cw*07: VMAPRALLL, poorly recognized; HLA-G*01: VMAPRTLFL, high-affinity) at 2.5 Å show that allotypic variations do not alter HLA-E heavy chain conformation, but subtle changes in peptide conformation within the binding groove profoundly affect CD94-NKG2 receptor recognition.\",\n      \"method\": \"X-ray crystallography at 2.5 Å resolution for both complexes\",\n      \"journal\": \"Journal of molecular biology\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 1 — two crystal structures compared with functional correlation\",\n      \"pmids\": [\"18339401\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2009,\n      \"finding\": \"HLA-E surface expression on transgenic pig cells expressing HLA-E and human β2-microglobulin inhibits human NK cell-mediated cytotoxicity in a CD94/NKG2A-dependent manner and also inhibits IFN-γ secretion by co-cultured human NK cells.\",\n      \"method\": \"HLA-E/hβ2m transgenic pig generation, NK cell cytotoxicity assays, IFN-γ ELISA, FACS\",\n      \"journal\": \"Transplantation\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 — transgenic animal model with in vitro functional NK assays and CD94/NKG2A expression correlation\",\n      \"pmids\": [\"19136889\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2003,\n      \"finding\": \"HLA-E-mediated inhibition of NK cell lysis requires peptide loading and is TAP-independent when specific signal sequence peptides are available: HCMV gpUS6, which blocks TAP by 95%, does not affect HLA-E surface expression or its ability to inhibit NK cell lysis via CD94/NKG2A, and HLA-E is functional on TAP-deficient RMA-S transfectants.\",\n      \"method\": \"gpUS6-expressing transfectants, TAP inhibition assays, NK cell cytotoxicity assays, HLA-E surface expression by FACS\",\n      \"journal\": \"Human immunology\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 — TAP-deficient cell line experiments with gpUS6 providing mechanistic clarity on TAP independence\",\n      \"pmids\": [\"12559625\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2013,\n      \"finding\": \"Polymorphisms in the HCMV UL40 leader sequence mimic region modulate the affinity of UL40-derived peptide/HLA-E complexes for CD94-NKG2 receptors; some UL40 peptide variants can inhibit NK lysis via CD94-NKG2A but have little capacity to activate NK cells through CD94-NKG2C, suggesting UL40 polymorphisms facilitate viral immune evasion by differential receptor engagement.\",\n      \"method\": \"UL40 sequencing from HSCT recipients, HLA-E/peptide binding affinity assays, NK cell clone cytotoxicity assays (NKG2A+ or NKG2C+ clones)\",\n      \"journal\": \"The Journal of biological chemistry\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 — affinity measurements combined with NK clone functional assays showing differential receptor activation\",\n      \"pmids\": [\"23335510\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2015,\n      \"finding\": \"HLA-E*01:01 and HLA-E*01:03 alleles present distinct and non-overlapping peptide repertoires (9-17 amino acids); differences in peptide stabilization capacity caused by the Arg107Gly substitution affect cell surface HLA-E density and half-life, which in turn impact NK cell inhibition as measured by cytotoxicity assays.\",\n      \"method\": \"Soluble HLA technology with mass spectrometric peptide sequencing (HLA-E*01:03 ligandome), artificial APCs expressing peptide-stabilized HLA-E, NK cell cytotoxicity assays\",\n      \"journal\": \"Immunogenetics\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 1–2 — mass spectrometry ligandome combined with functional NK assays\",\n      \"pmids\": [\"26552660\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2016,\n      \"finding\": \"HLA-E presents a conserved peptide from HIV-1 capsid (AISPRTLNA) that is not recognized by NKG2A/CD94, causing HIV-infected T cells to be susceptible to killing by NKG2A/CD94+ NK cells despite high HLA-E surface expression; NKG2A/CD94+ NK cells generate the most efficient responses against HIV-infected T cells.\",\n      \"method\": \"In vitro cytolytic assays with autologous primary NK cells and HIV-infected primary T cells, HLA-E peptide loading with HIV capsid peptide, NKG2A/CD94 blocking\",\n      \"journal\": \"PLoS pathogens\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 — primary cell system with specific peptide identification and receptor blocking\",\n      \"pmids\": [\"26828202\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2018,\n      \"finding\": \"HLA-E presents diverse pathogen-derived peptides (HIV and Mtb) with conformational flexibility: pathogen-derived peptides adopt alternative conformations within the HLA-E binding groove, and mutagenesis reveals greater tolerance for hydrophobic and polar residues in primary anchor pockets than previously appreciated.\",\n      \"method\": \"X-ray crystallography of HLA-E with HIV- and Mtb-derived peptides, mutagenesis, biochemical peptide binding studies\",\n      \"journal\": \"Nature communications\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 1 — crystal structures with mutagenesis validation\",\n      \"pmids\": [\"30087334\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2018,\n      \"finding\": \"Adaptive NK cells discriminate between different HLA-E peptide complexes with exquisite specificity via CD94/NKG2C; prolonged exposure to HLA-E/VMAPRTLFL (HLA-G leader peptide) enriches adaptive NK cells with altered signaling molecule expression and elevated antibody-dependent cellular cytotoxicity and IFN-γ responses.\",\n      \"method\": \"Flow cytometry, ADCC assays, IFN-γ ELISA, comparison of NK cell function with different HLA-E peptide complexes\",\n      \"journal\": \"Cell reports\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 — multiple orthogonal functional assays showing peptide-specific adaptive NK cell modulation\",\n      \"pmids\": [\"30134159\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2019,\n      \"finding\": \"Senescent dermal fibroblasts upregulate HLA-E expression via senescence-associated secretory phenotype (SASP)-related pro-inflammatory cytokines through p38 MAP kinase signaling; HLA-E on senescent cells interacts with NKG2A on NK and highly differentiated CD8+ T cells to inhibit immune responses, contributing to senescent cell accumulation.\",\n      \"method\": \"Flow cytometry of senescent fibroblasts, p38 inhibitor experiments, in vitro NK and CD8+ T cell cytotoxicity assays with NKG2A blocking antibody, immunohistochemistry of human skin sections\",\n      \"journal\": \"Nature communications\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 — multiple orthogonal methods including inhibitor studies, blocking antibodies, and in vivo tissue sections\",\n      \"pmids\": [\"31160572\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2019,\n      \"finding\": \"HIV-1 Nef protein downregulates HLA-E surface levels by targeting the cytoplasmic tail of HLA-E; cytoplasmic tail swap experiments showed that the HLA-A2 cytoplasmic tail grafted onto HLA-E abolished Nef-mediated downmodulation, demonstrating that Nef acts on the HLA-E cytoplasmic tail specifically.\",\n      \"method\": \"Primary HIV-1 strain infection of CD4+ T cells, single Nef/Vpu protein expression in T cell lines, cytoplasmic tail swap experiments, FACS for surface HLA-E\",\n      \"journal\": \"Journal of virology\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 — cytoplasmic tail swap experiments with primary cell validation mechanistically defining Nef target\",\n      \"pmids\": [\"31375574\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2022,\n      \"finding\": \"SARS-CoV-2 non-structural protein 13 (Nsp13) encodes a peptide presented by HLA-E that, unlike self-peptides, prevents binding of HLA-E to the inhibitory receptor NKG2A, rendering infected target cells susceptible to NKG2A-expressing NK cell killing; NKG2A+ NK cells are particularly activated in COVID-19 patients and can limit SARS-CoV-2 replication in infected lung epithelial cells.\",\n      \"method\": \"HLA-E peptide loading and NKG2A binding assays, NK cell activation assays, in vitro SARS-CoV-2 replication suppression assays, flow cytometry of NK cells from COVID-19 patients\",\n      \"journal\": \"Cell reports\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 — mechanistic peptide-receptor binding combined with functional viral replication assay\",\n      \"pmids\": [\"35235832\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2022,\n      \"finding\": \"Crystal structures and SAXS analysis show that HLA-E-VL9 (canonical leader peptide) complexes are more stable and compact, while HLA-E bound to pathogen-derived non-VL9 peptides adopts larger, more extended conformations in solution with reconfiguration of a key TCR-interacting α2 region; three HLA-E-exclusive residues position VL9 close to the α2 helix and allow non-VL9 peptide binding with an alternative binding motif.\",\n      \"method\": \"X-ray crystallography, small-angle X-ray scattering (SAXS), excess peptide experiments\",\n      \"journal\": \"Cell reports\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 1 — multiple structural methods (crystallography + SAXS) with functional interpretations\",\n      \"pmids\": [\"35705051\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2023,\n      \"finding\": \"HLA-E is largely retained in the ER after synthesis due to limited supply of high-affinity peptides, with its cytoplasmic tail contributing to ER retention; once at the cell surface, HLA-E is unstable and rapidly internalized; the cytoplasmic tail facilitates internalization and enrichment in late and recycling endosomes.\",\n      \"method\": \"Live cell imaging, FRAP, subcellular fractionation, cytoplasmic tail mutant constructs, pulse-chase experiments\",\n      \"journal\": \"The Journal of experimental medicine\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 — multiple direct localization and trafficking experiments with mutant constructs defining functional role of cytoplasmic tail\",\n      \"pmids\": [\"37140910\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2023,\n      \"finding\": \"Platelet-derived RGS18 promotes HLA-E expression on circulating tumor cells through AKT-GSK3β-CREB signaling; this HLA-E upregulation enables CTCs to evade NK cell surveillance via the HLA-E:CD94-NKG2A checkpoint axis, facilitating metastasis.\",\n      \"method\": \"Mechanistic studies including RGS18 knockdown/overexpression, AKT-GSK3β-CREB pathway inhibitors, in vitro NK cell killing assays, in vivo mouse metastasis models\",\n      \"journal\": \"Cancer cell\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 — pathway dissection with inhibitors, knockdown, overexpression, and in vivo validation\",\n      \"pmids\": [\"36706761\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2023,\n      \"finding\": \"Among 16 common HLA class I signal peptide variants, only 6 ('functional SPs') are efficiently processed to generate epitopes enabling CD94/NKG2 engagement; the single functional HLA-B SP (HLA-B/-21M) induces high HLA-E expression but confers the lowest receptor recognition, and it competes with other SPs to reduce overall CD94/NKG2A recognition of target cells.\",\n      \"method\": \"Systematic quantitative HLA-E surface expression assays, CD94/NKG2A binding assays, NK cell functional assays, genetic population analysis\",\n      \"journal\": \"Nature immunology\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 — systematic quantitative approach with multiple SP variants and NK functional readouts\",\n      \"pmids\": [\"37264229\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2023,\n      \"finding\": \"A yeast-displayed peptide library screen identified 500 unique peptides that bind both HLA-E and CD94/NKG2A or CD94/NKG2C; some peptides selectively activate NKG2C+ NK cells; human and CMV proteome-derived HLA-E-presented peptides capable of signaling through both receptors were identified using trained prediction algorithms.\",\n      \"method\": \"Yeast-display peptide library screening, CD94/NKG2A and CD94/NKG2C binding selection, NK cell activation assays\",\n      \"journal\": \"Nature communications\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 — high-throughput library screen with functional NK cell validation\",\n      \"pmids\": [\"37558657\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2015,\n      \"finding\": \"NKG2A+ NK cell degranulation is inhibited by HLA-E loaded with almost all tested peptides (CMV, Hsp60, HLA class I-derived), whereas NKG2C+ NK cell activation is selectively enhanced only by a restricted set of HLA-E peptide complexes, particularly HLA-E/HLA-G peptide, which also triggers NKG2C receptor internalization.\",\n      \"method\": \"NK cell degranulation (CD107a) assays with HLA-E peptide-loaded target cells, flow cytometry, Bafilomycin experiments for receptor internalization\",\n      \"journal\": \"Human immunology\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 — multiple peptide panels tested with NKG2A+ and NKG2C+ NK cell subsets, receptor internalization mechanistically defined\",\n      \"pmids\": [\"26382247\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2015,\n      \"finding\": \"HLA-E expression on myeloma cells is substantially upregulated in the bone marrow microenvironment in vivo (compared to in vitro), abrogating degranulation of NKG2A+ NK cell subsets; NKG2A-negative, KIR-ligand-mismatched NK cells show the highest anti-myeloma reactivity.\",\n      \"method\": \"In vivo xenograft mouse model (RAG-2-/- γc-/- mice), ex vivo HLA-E expression analysis, NK cell degranulation assays under hypoxic conditions (0.6% O2)\",\n      \"journal\": \"Cancer immunology, immunotherapy\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 — in vivo model combined with mechanistic in vitro functional assays under physiologically relevant conditions\",\n      \"pmids\": [\"25920521\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2018,\n      \"finding\": \"HLA-E presents ER-stress-generated signal peptides; bortezomib-induced ER stress in multiple myeloma cells specifically reduces cell surface HLA-E expression (without affecting classical HLA class I), selectively sensitizing myeloma cells to killing by NKG2A single-positive NK cells through loss of NKG2A/HLA-E inhibitory signaling.\",\n      \"method\": \"Bortezomib treatment of MM cells, FACS for surface HLA-E and HLA class I, NK cell subpopulation cytotoxicity assays with NKG2A single-positive NK cells\",\n      \"journal\": \"Oncoimmunology\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 — mechanistic dissection of ER-stress pathway with specific NK subset functional readout\",\n      \"pmids\": [\"30713790\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2017,\n      \"finding\": \"HLA-E presents a glycopeptide from the M. tuberculosis protein MPT32 to CD8+ T cells; recognition requires N-terminal O-linked mannosylation of the peptide by a mannosyltransferase encoded by Mtb gene Rv1002c, representing the first post-translationally modified bacterial antigen presented by HLA-E.\",\n      \"method\": \"HLA-E-restricted CD8+ T cell clone identification, MPT32 antigen characterization, Rv1002c mannosyltransferase knockout experiments, T cell recognition assays\",\n      \"journal\": \"Scientific reports\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 — T cell clone experiments with specific gene knockout defining the modification requirement\",\n      \"pmids\": [\"28676677\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2021,\n      \"finding\": \"HLA-E-restricted CD8+ T cells bearing high-affinity TCRs for HLA-E are regulated by inhibitory NK receptors KIR2DL1 and KIR2DL2/L3, while lower-affinity TCR-bearing T cells express activating NKG2C; KIR2D/HLA-C interaction regulates T cells with high self-reactive TCR affinities, providing self/non-self discrimination for HLA-E-restricted responses.\",\n      \"method\": \"RNA sequencing, flow cytometry, TCR affinity measurements, KIR blocking experiments, cytokine response assays\",\n      \"journal\": \"Science immunology\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 — mechanistic epistasis established by RNA-seq, flow cytometry, and functional blocking experiments\",\n      \"pmids\": [\"33893172\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2015,\n      \"finding\": \"Regulation of monocyte-to-macrophage differentiation causes HLA-E upregulation; in differentiated macrophages, the primary intracellular destination of newly synthesized HLA-E is the autophagy-lysosomal network (colocalizing with LC3 and LAMP1) rather than the cell surface, unlike classical HLA class I molecules.\",\n      \"method\": \"Immunofluorescence confocal microscopy, colocalization with LC3/LAMP1, NK cell cytotoxicity assays with anti-NKG2A blocking, subcellular fractionation in U937, THP1, and PBMC-derived macrophages\",\n      \"journal\": \"Journal of leukocyte biology\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 — direct subcellular localization with functional consequence demonstrated in multiple cell systems\",\n      \"pmids\": [\"26310830\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2023,\n      \"finding\": \"Antigen-specific NK cell memory against HIV-1 and influenza develops via a conserved, epitope-specific mechanism largely dependent on the activating CD94/NKG2C receptor and its ligand HLA-E; individual memory NK cells validated by single-cell cloning show permanent antigen specificity, and KLRG1, α4β7, and NKG2C mark antigen-specific memory NK cells.\",\n      \"method\": \"Single-cell cloning, complex immunophenotyping, HLA-E-restricted peptide identification, in vitro NK cell memory assays\",\n      \"journal\": \"Science immunology\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 — single-cell cloning with blocking experiments establishing HLA-E/NKG2C-dependent mechanism\",\n      \"pmids\": [\"38064568\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2019,\n      \"finding\": \"HLA-E surface expression is regulated by XPO1 (exportin-1); XPO1 inhibition with selinexor significantly reduces HLA-E surface expression on lymphoma cells and primary CLL cells, selectively increasing activation of NKG2A+ NK cells and enhancing NK cell-mediated cytotoxicity against these target cells.\",\n      \"method\": \"Selinexor treatment of lymphoma cell lines and primary CLL cells, FACS for surface HLA-E, NK cell activation assays (CD107a, IFNγ), ADCC assays\",\n      \"journal\": \"Frontiers in oncology\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 — direct mechanistic link between XPO1 inhibition and HLA-E reduction with NKG2A+ NK functional readout\",\n      \"pmids\": [\"34926302\"],\n      \"is_preprint\": false\n    }\n  ],\n  \"current_model\": \"HLA-E is a non-classical MHC class I molecule that assembles in the ER with β2-microglobulin and peptides derived from MHC class I signal sequences (generated by signal peptide peptidase and transported by TAP), is largely ER-retained due to limited high-affinity peptide supply with its cytoplasmic tail regulating intracellular trafficking and rapid endocytosis at the cell surface; when stably expressed on the cell surface, HLA-E serves as the principal ligand for the CD94/NKG2A inhibitory receptor on NK cells and CD8+ T cells (inhibiting their cytotoxicity) and for the CD94/NKG2C activating receptor, with the identity of the bound peptide determining whether NK/T cell inhibition or activation ensues, and the entire axis is exploited by pathogens (HCMV UL40, HIV Nef, SARS-CoV-2 Nsp13) and by cellular stress states (senescence, ER stress) to modulate immune surveillance.\"\n}\n```","stage2_raw":"```json\n{\n  \"mechanistic_narrative\": \"HLA-E is a non-classical MHC class I molecule that functions as a sentinel of antigen-processing pathway integrity and cellular stress by presenting a restricted repertoire of peptides—primarily nonameric sequences derived from MHC class I signal peptides—to the inhibitory receptor CD94/NKG2A and the activating receptor CD94/NKG2C on NK cells and CD8+ T cells [PMID:9560253, PMID:9660937, PMID:11714810]. HLA-E assembles with β2-microglobulin and peptide in the ER via TAP-dependent loading of signal peptide fragments generated by signal peptide peptidase; it is largely ER-retained due to limited high-affinity peptide supply, and its cytoplasmic tail drives rapid endocytosis when the molecule reaches the cell surface [PMID:9574542, PMID:37140910]. The identity of the bound peptide determines functional outcome: canonical MHC class I leader peptides engage CD94/NKG2A to inhibit NK cell cytotoxicity, whereas pathogen-derived peptides (from HIV capsid, SARS-CoV-2 Nsp13, or M. tuberculosis) or stress-induced peptides (hsp60 signal peptide) adopt alternative conformations that fail to engage the inhibitory receptor, thereby licensing NK cell killing of infected or stressed targets [PMID:12461076, PMID:26828202, PMID:35705051, PMID:35235832]. This peptide-dependent checkpoint is exploited by HCMV UL40, which supplies an HLA-E-binding peptide independently of TAP to maintain inhibitory signaling during viral immune evasion, and by tumors and senescent cells that upregulate HLA-E to escape NKG2A+ effector responses [PMID:10669413, PMID:31160572, PMID:36706761].\",\n  \"teleology\": [\n    {\n      \"year\": 1998,\n      \"claim\": \"Identification of HLA-E as the principal ligand for CD94/NKG2A established the functional role of this non-classical MHC molecule as an NK cell inhibitory checkpoint, resolving the question of which molecule presented self-information to CD94-bearing receptors.\",\n      \"evidence\": \"NK cytotoxicity assays with HLA-E transfectants and blocking antibodies against CD94/NKG2A; crystal structure of HLA-E/β2m/peptide complex at 2.85 Å revealing constrained peptide specificity for MHC class I leader sequences; TAP interaction and peptide binding biochemistry\",\n      \"pmids\": [\"9560253\", \"9660937\", \"9574542\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Mechanism of HLA-E trafficking from ER to surface was not yet defined\", \"Whether HLA-E engages CD94/NKG2C with distinct functional consequences was unresolved\", \"In vivo physiological relevance beyond cell line assays not established\"]\n    },\n    {\n      \"year\": 2000,\n      \"claim\": \"Discovery that HCMV UL40 provides a TAP-independent peptide to stabilize HLA-E and that HLA-E functions on trophoblasts revealed pathogen exploitation and physiological immune tolerance roles for the HLA-E/NKG2A axis.\",\n      \"evidence\": \"HCMV infection with TAP-deficient cell lines showing TAP-independent HLA-E loading by UL40 leader peptide; HLA-E tetramer binding and cytotoxicity assays with decidual NK cells\",\n      \"pmids\": [\"10669413\", \"10898498\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Structural basis for UL40 peptide mimicry of host leader sequences not yet determined\", \"Whether other viruses employ similar evasion strategies was unknown\", \"Trophoblast HLA-E peptide repertoire not defined\"]\n    },\n    {\n      \"year\": 2001,\n      \"claim\": \"Identification of signal peptide peptidase as the protease generating HLA-E epitopes from MHC class I signal sequences resolved how the immune system couples classical MHC class I biosynthesis to non-classical HLA-E-mediated NK surveillance.\",\n      \"evidence\": \"Signal peptide peptidase inhibition blocking release of epitope-containing fragment from the lipid bilayer, with demonstration of subsequent TAP-dependent ER transport\",\n      \"pmids\": [\"11714810\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Whether signal peptide peptidase activity is rate-limiting for HLA-E surface expression was unclear\", \"Contribution of other ER-resident proteases not excluded\"]\n    },\n    {\n      \"year\": 2002,\n      \"claim\": \"Discovery that HLA-E presents an hsp60-derived signal peptide unrecognized by CD94/NKG2A demonstrated that HLA-E acts as a stress sensor, not merely a reporter of MHC class I biosynthesis, fundamentally broadening its immunological role.\",\n      \"evidence\": \"HLA-E/hsp60 peptide complex characterization with CD94/NKG2A binding and NK functional assays on stressed cells; allelic comparison crystal structures showing that peptide identity rather than heavy chain conformation determines receptor engagement\",\n      \"pmids\": [\"12461076\", \"12411439\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Range of stress-induced peptides binding HLA-E was not systematically catalogued\", \"Whether hsp60 peptide engages NKG2C was unknown\"]\n    },\n    {\n      \"year\": 2008,\n      \"claim\": \"Crystal structures of the CD94/NKG2A–HLA-E complex revealed that CD94 dominates the interaction interface and peptide contacts, while NKG2A residues 167–170 account for the higher affinity over NKG2C, explaining the molecular basis for differential inhibitory vs. activating receptor engagement.\",\n      \"evidence\": \"X-ray crystallography of CD94-NKG2A/HLA-E at 3.5 Å and 4.4 Å with mutagenesis validation and affinity measurements; parallel structures of HLA-E with peptides showing that subtle peptide conformational differences dictate receptor recognition\",\n      \"pmids\": [\"18332182\", \"18448674\", \"18339401\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Full structure of CD94/NKG2C–HLA-E complex not yet solved\", \"How peptide conformational differences translate to signaling outcomes remained unclear\"]\n    },\n    {\n      \"year\": 2015,\n      \"claim\": \"Systematic analyses of HLA-E allelic peptide repertoires and NK cell subset responses demonstrated that NKG2A inhibition is broadly permissive for diverse peptides while NKG2C activation is selectively triggered by restricted peptide identities, establishing the asymmetric peptide-selectivity principle governing the HLA-E checkpoint.\",\n      \"evidence\": \"Mass spectrometric HLA-E ligandome for E*01:01 vs. E*01:03; degranulation assays with NKG2A+ and NKG2C+ NK subsets across panels of HLA-E–peptide complexes; in vivo myeloma xenograft showing microenvironment-driven HLA-E upregulation inhibiting NKG2A+ NK cells\",\n      \"pmids\": [\"26552660\", \"26382247\", \"25920521\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Structural explanation for NKG2C peptide selectivity lacking\", \"How HLA-E allelic differences affect disease outcomes not established in patient cohorts\"]\n    },\n    {\n      \"year\": 2016,\n      \"claim\": \"Demonstration that HLA-E presents an HIV capsid peptide not recognized by NKG2A revealed that pathogen-derived peptides can convert HLA-E from an inhibitory to a permissive ligand, directly licensing NK killing of HIV-infected cells.\",\n      \"evidence\": \"Cytolytic assays with autologous primary NK cells against HIV-infected T cells with HLA-E peptide loading and NKG2A blocking\",\n      \"pmids\": [\"26828202\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Breadth of HIV-derived HLA-E epitopes unknown\", \"Whether HIV-specific NK responses are durable in vivo was unresolved\"]\n    },\n    {\n      \"year\": 2017,\n      \"claim\": \"Discovery that HLA-E presents a mannosylated M. tuberculosis glycopeptide to CD8+ T cells expanded the antigen repertoire to post-translationally modified bacterial antigens and established HLA-E-restricted T cell immunity as a component of anti-mycobacterial defense.\",\n      \"evidence\": \"CD8+ T cell clone characterization with mannosyltransferase (Rv1002c) knockout confirming glycosylation requirement for HLA-E presentation\",\n      \"pmids\": [\"28676677\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Prevalence of HLA-E-restricted T cell responses in TB patients not quantified\", \"Whether glycopeptide presentation follows the same loading pathway as signal peptides was unknown\"]\n    },\n    {\n      \"year\": 2018,\n      \"claim\": \"Crystal structures of HLA-E with pathogen-derived peptides revealed conformational flexibility in the binding groove and broader anchor residue tolerance than anticipated, providing the structural explanation for how HLA-E accommodates both self-leader and diverse non-self peptides.\",\n      \"evidence\": \"X-ray crystallography of HLA-E with HIV and Mtb peptides with mutagenesis validation\",\n      \"pmids\": [\"30087334\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Peptide exchange dynamics at the cell surface not characterized\", \"How groove flexibility affects receptor engagement kinetics unknown\"]\n    },\n    {\n      \"year\": 2019,\n      \"claim\": \"Multiple studies converged to show that HLA-E upregulation serves as an immune evasion strategy in senescence and viral infection: senescent cells upregulate HLA-E via p38/SASP signaling to inhibit NKG2A+ effectors, while HIV Nef targets the HLA-E cytoplasmic tail for downregulation, revealing the cytoplasmic tail as a key regulatory element.\",\n      \"evidence\": \"p38 inhibitor and NKG2A blocking antibody experiments in senescent fibroblasts; cytoplasmic tail swap experiments in HIV Nef-expressing cells\",\n      \"pmids\": [\"31160572\", \"31375574\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Specific motifs in the cytoplasmic tail required for Nef interaction not mapped\", \"Whether senescence-induced HLA-E peptide repertoire differs from homeostatic repertoire was unclear\"]\n    },\n    {\n      \"year\": 2022,\n      \"claim\": \"SARS-CoV-2 Nsp13 peptide was shown to abrogate HLA-E/NKG2A inhibitory signaling, licensing NK killing of infected cells, while structural studies revealed that non-VL9 peptides induce extended HLA-E conformations that disfavor NKG2A recognition, providing a unified structural-functional framework for peptide-dependent checkpoint control.\",\n      \"evidence\": \"HLA-E/Nsp13 peptide loading with NKG2A binding assays and viral replication suppression assays; crystallography and SAXS showing compact VL9-bound vs. extended non-VL9-bound HLA-E conformations\",\n      \"pmids\": [\"35235832\", \"35705051\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Whether conformational differences affect NKG2C engagement was not addressed\", \"In vivo relevance of Nsp13 peptide presentation during COVID-19 not confirmed\"]\n    },\n    {\n      \"year\": 2023,\n      \"claim\": \"Multiple advances defined the complete HLA-E trafficking cycle, the quantitative rules governing signal peptide competition, the breadth of the HLA-E peptidome, and the role of HLA-E/NKG2C in antigen-specific NK cell memory, collectively reframing HLA-E as a versatile immune surveillance hub beyond simple inhibitory checkpointing.\",\n      \"evidence\": \"Live-cell imaging and cytoplasmic tail mutants defining ER retention and rapid endocytic cycling; systematic SP variant analysis showing only 6 of 16 common SPs are functional; yeast-display library identifying 500 binding peptides; single-cell cloning of epitope-specific memory NK cells dependent on HLA-E/NKG2C; RGS18-AKT-CREB pathway driving tumor HLA-E upregulation for metastatic immune evasion\",\n      \"pmids\": [\"37140910\", \"37264229\", \"37558657\", \"38064568\", \"36706761\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Full in vivo trafficking itinerary of HLA-E in different tissues not mapped\", \"How memory NK cell TCR-like specificity for HLA-E–peptide is encoded at the molecular level remains unknown\", \"Competition dynamics among signal peptides in physiological multi-allele settings not modeled\"]\n    },\n    {\n      \"year\": null,\n      \"claim\": \"Key unresolved questions include the complete structural basis of CD94/NKG2C engagement with HLA-E, the in vivo peptide repertoire of HLA-E across tissues and disease states, the molecular mechanism of XPO1-dependent HLA-E surface regulation, and whether HLA-E-restricted adaptive NK memory can be therapeutically harnessed.\",\n      \"evidence\": \"\",\n      \"pmids\": [],\n      \"confidence\": \"High\",\n      \"gaps\": [\"No crystal structure of CD94/NKG2C–HLA-E complex published\", \"In vivo HLA-E peptidome from primary tissues not comprehensively determined\", \"Mechanism linking XPO1 to HLA-E surface expression is correlative\", \"Therapeutic exploitation of HLA-E/NKG2C memory axis untested in clinical settings\"]\n    }\n  ],\n  \"mechanism_profile\": {\n    \"molecular_activity\": [\n      {\"term_id\": \"GO:0048018\", \"supporting_discovery_ids\": [0, 4, 11, 12]},\n      {\"term_id\": \"GO:0098772\", \"supporting_discovery_ids\": [0, 7, 21, 29]}\n    ],\n    \"localization\": [\n      {\"term_id\": \"GO:0005886\", \"supporting_discovery_ids\": [0, 4, 8, 25]},\n      {\"term_id\": \"GO:0005783\", \"supporting_discovery_ids\": [2, 25]},\n      {\"term_id\": \"GO:0005768\", \"supporting_discovery_ids\": [25]},\n      {\"term_id\": \"GO:0005764\", \"supporting_discovery_ids\": [34]}\n    ],\n    \"pathway\": [\n      {\"term_id\": \"R-HSA-168256\", \"supporting_discovery_ids\": [0, 7, 11, 18, 21, 23, 35]},\n      {\"term_id\": \"R-HSA-392499\", \"supporting_discovery_ids\": [1, 2, 5, 17]},\n      {\"term_id\": \"R-HSA-1643685\", \"supporting_discovery_ids\": [3, 16, 22, 26, 30]}\n    ],\n    \"complexes\": [\n      \"HLA-E/β2-microglobulin/peptide\",\n      \"CD94/NKG2A/HLA-E\",\n      \"CD94/NKG2C/HLA-E\"\n    ],\n    \"partners\": [\n      \"B2M\",\n      \"KLRD1\",\n      \"KLRC1\",\n      \"KLRC2\",\n      \"TAP1\",\n      \"SPPL3\",\n      \"XPO1\"\n    ],\n    \"other_free_text\": []\n  }\n}\n```"}