{"gene":"EIF2A","run_date":"2026-06-09T23:54:42","timeline":{"discoveries":[{"year":2002,"finding":"Mammalian eIF2A is a 585 amino acid, single-chain protein encoded by a gene on chromosome 3. The yeast homolog (YGR054W) localizes on both 40S and 80S ribosomes. A double knockout of yeast eIF2A and eIF5B yields a synthetically sick slow-growth phenotype, suggesting eIF2A participates in translation initiation. eIF2A does not appear to participate in re-initiation, as the ΔeIF2A strain shows the same level of GCN4 induction with amino acid starvation as wild-type yeast.","method":"Peptide sequencing of rabbit reticulocyte eIF2A, cDNA/EST cloning, HA-tagging and ribosome fractionation in yeast, genetic double-knockout analysis, GCN4-lacZ reporter assay","journal":"The Journal of biological chemistry","confidence":"High","confidence_rationale":"Tier 2 / Strong — multiple orthogonal methods (biochemical fractionation, genetics, reporter assay) in a single focused characterization study","pmids":["12133843"],"is_preprint":false},{"year":2009,"finding":"In yeast, eIF2A acts as a negative regulator of IRES-mediated (cap-independent) translation under normal cellular conditions. eIF2A-mediated repression is not specific to the URE2 IRES; GIC1 and PAB1 IRES elements are also repressed by eIF2A. The stability of secondary structure within the URE2 IRES is not required for eIF2A-dependent repression.","method":"Monocistronic reporter assays in ΔeIF2A yeast strains, mutational analysis of URE2 IRES stem-loop structures","journal":"RNA (New York, N.Y.)","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — genetic deletion combined with reporter assays, single lab, multiple IRES elements tested","pmids":["19861427"],"is_preprint":false},{"year":2011,"finding":"In yeast, eIF2A abundance is reduced at both mRNA and protein levels during ethanol stress or heat shock; eIF2A protein is also post-translationally modified during ethanol stress. eIF2A interacts with eEF1A (identified by immunoprecipitation-mass spectrometry), and this interaction increases during ethanol stress, correlating with increased IRES-mediated translation from the URE2 IRES.","method":"Western blot and qRT-PCR for eIF2A levels under stress; immunoprecipitation-mass spectrometry to identify eEF1A as binding partner; IRES reporter assays in ΔeIF2A yeast","journal":"PloS one","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — Co-IP/MS identification of eEF1A interaction, correlated with functional IRES reporter data, single lab","pmids":["21915340"],"is_preprint":false},{"year":2011,"finding":"eIF2A mediates translation of HCV mRNA under stress conditions when eIF2α is phosphorylated. eIF2A directly interacts with the IIId domain of the HCV IRES, and this direct interaction is required for eIF2A-dependent translation. eIF2A acts as an alternative initiator tRNA-binding protein that recruits Met-tRNAi to the P site of the 40S ribosomal subunit in an eIF2-independent manner. eIF2A also promotes eIF2α phosphorylation by activating the eIF2α kinase PKR during HCV infection.","method":"siRNA knockdown of eIF2A in HCV-infected cells, in vitro binding assays between eIF2A and HCV IRES domains, toeprinting assays, polysome profiling, PKR activation assays","journal":"The EMBO journal","confidence":"High","confidence_rationale":"Tier 2 / Strong — multiple orthogonal methods (knockdown, direct binding assay, toeprinting, PKR activation) in a single focused study with strong controls","pmids":["21556050"],"is_preprint":false},{"year":2016,"finding":"eIF2A is responsible for stress-resistant translation of c-Src mRNA via its IRES element. eIF2A facilitates tRNAi loading onto the 40S ribosomal subunit in a c-Src mRNA-dependent manner. A direct interaction between eIF2A and a stem-loop structure (SL I) in the c-Src IRES is required for IRES-dependent translation under stress conditions but not under normal conditions. eIF2A-dependent translation of c-Src mRNA promotes cell proliferation under stress.","method":"siRNA knockdown of eIF2A, in vitro binding assays between eIF2A and c-Src IRES SL I, toeprinting assays, bicistronic reporter assays under stress conditions, cell proliferation assays","journal":"Nucleic acids research","confidence":"High","confidence_rationale":"Tier 2 / Strong — direct binding assay, toeprinting, reporter assays, and functional cell proliferation data, multiple orthogonal methods in one study","pmids":["27899592"],"is_preprint":false},{"year":2016,"finding":"In an eIF2A knockout mouse strain (gene trap between exons 1 and 2), mice are viable with no apparent gross phenotype, suggesting eIF2A is not essential for viability in mammals under standard conditions.","method":"Gene-trap knockout mouse generation, viability and phenotypic assessment","journal":"Cell cycle (Georgetown, Tex.)","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — direct genetic KO in mammals with phenotypic assessment, single lab","pmids":["27686860"],"is_preprint":false},{"year":2017,"finding":"Translation of Sindbis virus subgenomic mRNA is independent of eIF2A and eIF2D. HAP1 cells knocked-out for eIF2A, eIF2D, or both via CRISPR/Cas9 showed comparable Sindbis virus infection and viral protein synthesis to wild-type cells, even when eIF2α was phosphorylated. This is a negative finding: eIF2A and eIF2D are not required for sgmRNA translation when eIF2α is phosphorylated.","method":"CRISPR/Cas9 knockout of eIF2A and eIF2D in HAP1 cells, Sindbis virus infection, siRNA silencing, measurement of viral protein synthesis by Western blot","journal":"Scientific reports","confidence":"High","confidence_rationale":"Tier 2 / Strong — clean CRISPR KO cells with multiple viral conditions and siRNA confirmation, rigorous negative result","pmids":["28240315"],"is_preprint":false},{"year":2018,"finding":"Neither eIF2A nor eIF2D participates in HCV IRES-driven translation in human cells. Human HAP1 cells depleted for eIF2A, eIF2D, or both were able to synthesize luciferase from an HCV IRES-bearing mRNA even when eIF2α was phosphorylated. This is a negative finding contradicting earlier reports that eIF2A mediates HCV IRES translation under stress.","method":"HAP1 cells depleted for eIF2A and/or eIF2D via CRISPR/Cas9, HCV IRES luciferase reporter assays under multiple stress conditions (arsenite, thapsigargin, tunicamycin, salubrinal)","journal":"Frontiers in microbiology","confidence":"High","confidence_rationale":"Tier 2 / Strong — CRISPR KO cells, multiple stress inducers, luciferase reporter assays; directly contradicts PMID:21556050","pmids":["29487587"],"is_preprint":false},{"year":2021,"finding":"eIF2A knockout mice exhibit decreased life span, metabolic syndrome features (impaired lipid homeostasis, glucose tolerance defects, insulin resistance), and reduced B lymphocytes and dendritic cells in thymic medulla. Effects differ between male and female mice. Pharmacological ER stress induction with tunicamycin did not reveal substantial differences between KO and wild-type mice in ER stress response.","method":"eIF2A KO mouse model, metabolic phenotyping (glucose tolerance test, insulin resistance assays), lifespan analysis, flow cytometry of thymic cell populations, tunicamycin treatment","journal":"FASEB journal","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — direct KO mouse model with multiple phenotypic assays, single lab","pmids":["34665898"],"is_preprint":false},{"year":2021,"finding":"Overexpression of eIF2A increases RAN (repeat-associated non-AUG) translation of both LPAC (from CCUG repeats) and QAGR (from CAGG repeats) proteins in DM2 myotonic dystrophy. The effect of eIF2A on QAGR (CAGG transcripts lacking efficient close-cognate codons) is novel and dependent on phosphorylated eIF2α, whereas eIF2A effects on LPAC are partially independent of p-eIF2α.","method":"CRISPR/Cas9-edited HEK293T cell lines (PKR-/-, PERK-/-, eIF2α-S51A), eIF2A overexpression, RAN protein measurement by Western blot and immunofluorescence","journal":"Human molecular genetics","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — multiple CRISPR-edited cell lines, overexpression, two different repeat substrates tested, single lab","pmids":["33856033"],"is_preprint":false},{"year":2021,"finding":"Drosophila EIF2A (encoded by CG7414) is essential for spermatogenesis. Loss of function (Mi{Mic} null allele) causes male sterility due to failure of sperm individualization, defects in F-actin cones, and failure to form and maintain cystic bulges. The Mi{Mic} null allele is homozygous lethal, while a hypomorphic allele causes male sterility and female fertility. The gene undergoes sex-specific splicing regulating male-specific expression.","method":"Transposon insertion mutant alleles in Drosophila (null Mi{Mic} and hypomorphic PBac), fertility assays, immunofluorescence of F-actin cones, genetic analysis","journal":"Developmental dynamics","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — multiple alleles in Drosophila ortholog, direct cellular phenotyping, single lab","pmids":["34278643"],"is_preprint":false},{"year":2023,"finding":"Increased levels of recombinant human eIF2A inhibit translation of multiple reporter mRNAs in a mammalian in vitro translation system, including those translated by cognate and near-cognate start codons, and inhibit all four types of cap-independent viral IRES-driven translation including the CrPV IGR IRES (which requires no initiation factors or initiator tRNA). Supplementation with additional 40S subunits rescues eIF2A-mediated inhibition. Pull-down assays demonstrate direct binding between recombinant eIF2A and purified 40S subunits, supporting a model that excess eIF2A sequesters 40S ribosomal subunits.","method":"Purification of recombinant human eIF2A from E. coli and insect cells, mammalian in vitro translation assays with multiple reporter mRNAs and IRES types, 40S subunit supplementation rescue experiment, pull-down assays with purified 40S subunits","journal":"Nucleic acids research","confidence":"High","confidence_rationale":"Tier 1 / Strong — in vitro reconstitution with purified recombinant protein, direct binding assay, multiple IRES types tested, rescue experiment with 40S subunits, multiple orthogonal methods","pmids":["37602404"],"is_preprint":false},{"year":2023,"finding":"eIF2A specifically and directly enhances SARS-CoV-2 programmed -1 ribosomal frameshifting (-1 PRF), independently of changes in translation initiation. Loss of eIF2A reduces SARS-CoV-2 replication in cells. Transcriptome-wide analysis shows eIF2A preferentially binds CG-rich RNA motifs, including a region within 18S rRNA near the contacts between the SARS-CoV-2 frameshift-stimulatory element (FSE) and the ribosome.","method":"Genome-wide CRISPR-Cas9 knockout screen for -1 PRF regulators, eIF2A KO cell validation of frameshifting, SARS-CoV-2 replication assays in KO cells, transcriptome-wide RNA binding analysis (CLIP-seq or equivalent)","journal":"Cell reports","confidence":"High","confidence_rationale":"Tier 2 / Strong — genome-wide screen followed by targeted KO validation, viral replication assays, and transcriptome-wide binding data, multiple orthogonal methods","pmids":["37581984"],"is_preprint":false},{"year":2023,"finding":"eIF2A and eIF2D are required for IRES-independent translation of enteroviral genomes. In cells with complete inactivation of IRES-mediated translation, sufficient translation of the nonstructural region still occurs to support recombination, and this IRES-independent translation depends on eIF2A and eIF2D.","method":"IRES-inactivating mutations in enteroviral genome, siRNA knockdown of eIF2A and eIF2D, viral replication and recombination assays","journal":"PLoS biology","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — siRNA knockdown combined with IRES-mutant viral genome, single lab, specific functional readout","pmids":["36689548"],"is_preprint":false},{"year":2024,"finding":"Yeast eIF2A has a minimal role in translation initiation in vivo. Ribosome profiling of ΔeIF2A yeast showed no significant translational efficiency reductions for any mRNAs in non-starved cells, and only minor reductions in starved cells with phosphorylated eIF2α. No evidence was found that eIF2A altered IRES-mediated translation or translation of mRNAs with uORFs initiated by AUG or near-cognate codons. Very few mRNAs (possibly only one) appear to employ eIF2A for Met-tRNAi recruitment in yeast.","method":"Ribosome profiling (genome-wide) of ΔeIF2A yeast under normal and amino acid starvation conditions, bioinformatic analysis of translational efficiencies","journal":"eLife","confidence":"High","confidence_rationale":"Tier 1 / Strong — genome-wide ribosome profiling in clean KO, multiple conditions tested, rigorous negative result at transcriptome scale","pmids":["38266075"],"is_preprint":false},{"year":2025,"finding":"Human eIF2A has a minimal role in translation initiation and uORF-mediated translational control in HeLa cells. Ribosome profiling and luciferase reporter assays in eIF2A-depleted HeLa cells, including conditions of integrated stress response activation, detected no role for eIF2A in translation initiation.","method":"Ribosome profiling in eIF2A-depleted HeLa cells, luciferase reporter assays for uORF-containing and IRES-containing mRNAs, ISR activation with chemical inducers","journal":"eLife","confidence":"High","confidence_rationale":"Tier 1 / Strong — genome-wide ribosome profiling plus reporter assays in human cells, multiple stress conditions, rigorous negative result","pmids":["40600802"],"is_preprint":false},{"year":2025,"finding":"eIF2A regulates cell migration in a translation-independent manner. Interactome studies (proximity labeling) identified centrosomal proteins as major binding partners of eIF2A. eIF2A colocalizes with the centrosome, enhances centrosome composition, and promotes centrosome orientation during cell migration. This function requires the C-terminal disordered region of eIF2A involved in mRNA binding, but does not require ongoing translation.","method":"TurboID proximity labeling interactome, co-localization imaging (eIF2A with centrosomal markers), eIF2A depletion with migration assays, domain deletion mutants, translation inhibition controls","journal":"Science advances","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — proximity labeling combined with imaging and functional migration assays and domain mapping, single lab","pmids":["40749049"],"is_preprint":false},{"year":2025,"finding":"eIF2A has a novel function in ribosome-associated quality control (RQC). Using TurboID proximity labeling combined with polysome gradients and mass spectrometry, eIF2A's binding site was mapped close to the mRNA entry channel of the 40S ribosomal subunit. eIF2A strongly interacts with G3BP1-USP10 complexes and ribosomal proteins RPS2 and RPS3. In the absence of eIF2A, RPS2 and RPS3 ubiquitination is diminished specifically upon ribosome stalling. eIF2A antagonizes USP10-dependent rescue of 40S ribosomes, resulting in altered turnover of 40S subunits upon cellular stress.","method":"TurboID proximity labeling + mass spectrometry, polysome gradient fractionation, dynamic SILAC mass spectrometry, eIF2A knockout cells, ribosome stalling assays, ubiquitination measurements","journal":"bioRxiv","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — multiple orthogonal methods (proximity labeling, SILAC, polysome gradients, KO cells), preprint not yet peer-reviewed","pmids":["bio_10.1101_2025.05.22.655611"],"is_preprint":true},{"year":1980,"finding":"Co-eIF-2A (an activity later attributed to a component of what became eIF2A) is absolutely required for protein synthesis in reticulocyte lysates; antibody inhibition of Co-eIF-2A cannot be reversed by eIF-2, establishing a non-redundant requirement. Co-eIF-2A stimulates eIF-2-dependent ternary complex formation and protects ternary complexes from dissociation by aurintricarboxylic acid. Co-eIF-2A does not interact with free eIF-2 but specifically with the preformed ternary complex.","method":"Antibody inhibition of reticulocyte lysate protein synthesis, reversal experiments with purified factors, fluorescence polarization with dansyl-labeled Co-eIF-2A","journal":"The Journal of biological chemistry","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — antibody inhibition and fluorescence polarization assays with purified components, older biochemical studies with limited molecular identity of the factor","pmids":["7356618","7372648"],"is_preprint":false},{"year":1981,"finding":"Co-eIF-2A reverses mRNA inhibition of ternary complex formation by eIF-2. At low mRNA concentrations, mRNAs strongly inhibit ternary complex (Met-tRNAf·eIF-2·GTP) formation and dissociate preformed ternary complexes; excess Co-eIF-2A renders Met-tRNAf binding to eIF-2 fully resistant to this mRNA inhibition. Other cofactors (Co-eIF-2B and Co-eIF-2C) did not reverse mRNA inhibition.","method":"In vitro ternary complex formation assays with purified Co-eIF-2A, mRNA titration, filter-binding assays","journal":"The Journal of biological chemistry","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — in vitro reconstitution with purified components testing specific factor function, single lab, older biochemical study","pmids":["6153053"],"is_preprint":false},{"year":1985,"finding":"An 80 kDa polypeptide (Co-eIF-2A80) was purified to homogeneity from rabbit reticulocytes and shown to stimulate Met-tRNAf binding to eIF-2 in a manner resistant to aurintricarboxylic acid. Antibodies against Co-eIF-2A80 strongly inhibited protein synthesis in reticulocyte lysates and blocked eIF-2 and Co-eIF-2-promoted Met-tRNAf binding to 40S ribosomes. Limited proteolysis mapped the protein to the 80 kDa band within the Co-eIF-2 complex.","method":"Protein purification to homogeneity, in vitro translation assays, antibody inhibition, limited V8 protease mapping","journal":"The Journal of biological chemistry","confidence":"Medium","confidence_rationale":"Tier 1 / Moderate — in vitro reconstitution with purified protein, antibody inhibition, single lab","pmids":["3888988"],"is_preprint":false},{"year":2015,"finding":"EIF2A phosphorylation is induced in leukemia cells by FK866 (NAMPT inhibitor) via the LKB1-AMPK-EIF2A axis and is responsible for translational arrest and cell survival. Expression of a non-phosphorylatable EIF2A mutant in Jurkat cells enhanced sensitivity to FK866, confirming that EIF2A phosphorylation mediates protein synthesis arrest as a survival mechanism.","method":"FK866 treatment of leukemia cell lines, ectopic expression of non-phosphorylatable EIF2A mutant, AMPK/LKB1 silencing, polysome profiling","journal":"BMC cancer","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — phosphomutant rescue experiment combined with knockdown, single lab, single study","pmids":["26542945"],"is_preprint":false},{"year":2019,"finding":"EIF2A is essential for cancer cell survival after paclitaxel-mediated integrated stress response both in vitro and in vivo. Paclitaxel activates the EIF2AK3/EIF2AK4-pEIF2S1-ATF4 axis, and EIF2A is required for maintenance of redox homeostasis by supporting expression of antioxidant enzymes (HMOX1, SHMT2, SLC7A11) in this context.","method":"siRNA knockdown and overexpression of EIF2A in breast cancer cells, xenograft mouse models, ROS scavenger rescue experiment (Trolox), Western blot for ISR markers","journal":"Journal of cellular and molecular medicine","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — KD/OE with in vivo xenograft validation and mechanistic rescue experiment, single lab","pmids":["31211507"],"is_preprint":false}],"current_model":"EIF2A is a single-chain 65 kDa protein that directly binds the 40S ribosomal subunit near the mRNA entry channel and, at elevated levels, sequesters 40S subunits to inhibit translation broadly; it plays a minor, context-specific role in alternative translation initiation (including at near-cognate/non-AUG codons, certain viral IRES elements, and RAN translation under stress when eIF2 is inactivated), directly enhances SARS-CoV-2 programmed −1 ribosomal frameshifting, participates in ribosome-associated quality control by antagonizing USP10-dependent 40S rescue during ribosome stalling, and has a translation-independent role in centrosome orientation during cell migration; genome-wide ribosome profiling in both yeast and human cells indicates that EIF2A has minimal impact on global or uORF-mediated translation initiation even during integrated stress response activation, with only a small number of mRNAs demonstrably dependent on it."},"narrative":{"mechanistic_narrative":"EIF2A is a single-chain ribosome-associated protein that binds the 40S ribosomal subunit near the mRNA entry channel and modulates translation in a narrow, context-specific manner rather than acting as a core initiation factor [PMID:12133843, PMID:37602404, PMID:bio_10.1101_2025.05.22.655611]. It can function as an eIF2-independent initiator-tRNA carrier, recruiting Met-tRNAi to the 40S P site to support cap-independent translation of specific IRES-bearing mRNAs under conditions of eIF2α phosphorylation, including the HCV IRES and the c-Src IRES, through direct binding to defined IRES stem-loop structures [PMID:21556050, PMID:27899592]. At elevated abundance, recombinant EIF2A binds purified 40S subunits and broadly inhibits both cap-dependent and IRES-driven translation, an effect reversed by supplementing additional 40S subunits, indicating a 40S-sequestration mechanism [PMID:37602404]. Consistent with a limited physiological role in initiation, genome-wide ribosome profiling in both yeast and human cells found essentially no requirement for EIF2A in global or uORF-mediated translation, even during integrated stress response activation [PMID:38266075, PMID:40600802]. Beyond initiation, EIF2A directly enhances SARS-CoV-2 programmed −1 ribosomal frameshifting independently of initiation and preferentially binds CG-rich RNA, with a binding site near the frameshift element contacts on 18S rRNA [PMID:37581984], antagonizes USP10-dependent rescue of 40S ribosomes during ribosome stalling in ribosome-associated quality control [PMID:bio_10.1101_2025.05.22.655611], and supports a translation-independent role in centrosome orientation during cell migration via its C-terminal disordered region [PMID:40749049]. EIF2A is dispensable for mammalian viability, but knockout mice develop metabolic syndrome features and altered immune cell populations [PMID:27686860, PMID:34665898]. The mammalian factor traces to the historically defined Co-eIF-2A activity, which stimulated and protected eIF-2 ternary complexes and Met-tRNAf binding to 40S ribosomes in reticulocyte lysates [PMID:7356618, PMID:7372648, PMID:3888988].","teleology":[{"year":1981,"claim":"Before the gene was molecularly defined, biochemistry asked whether a cofactor regulated eIF-2 ternary complex behavior; Co-eIF-2A was shown to stimulate and stabilize Met-tRNAf binding and to render it resistant to mRNA-mediated inhibition, establishing an early activity later attributed to EIF2A.","evidence":"antibody inhibition and in vitro ternary complex / Met-tRNAf binding assays with purified Co-eIF-2A from rabbit reticulocytes","pmids":["7356618","7372648","6153053","3888988"],"confidence":"Medium","gaps":["Molecular identity of the purified factor (reported as ~80 kDa) not definitively tied to the cloned EIF2A gene","Mechanism inferred from lysate activity, not reconstitution with defined recombinant protein"]},{"year":2002,"claim":"Whether mammalian eIF2A corresponded to a defined gene and participated in initiation was unresolved; cloning and yeast genetics defined the 585-residue single-chain protein, placed it on 40S/80S ribosomes, and showed a synthetic-sick interaction with eIF5B implicating it in initiation but not in GCN4 reinitiation.","evidence":"peptide sequencing, cDNA cloning, ribosome fractionation, and double-knockout/GCN4 reporter genetics in yeast","pmids":["12133843"],"confidence":"High","gaps":["Specific mRNA clients not identified","Molecular basis of the eIF5B synthetic interaction unknown"]},{"year":2011,"claim":"It was unknown how eIF2A supported translation when eIF2 is inactivated; HCV studies showed eIF2A binds the HCV IRES IIId domain directly and recruits Met-tRNAi to the 40S P site in an eIF2-independent manner, defining an alternative initiator-tRNA carrier activity.","evidence":"siRNA knockdown in HCV-infected cells, direct IRES-domain binding and toeprinting assays, polysome profiling","pmids":["21556050"],"confidence":"High","gaps":["Later contradicted in CRISPR-knockout HAP1 cells","PKR-activation role not mechanistically resolved"]},{"year":2016,"claim":"To test whether eIF2A-driven IRES translation extends to cellular mRNAs, c-Src work showed direct binding to its IRES stem-loop SL I and stress-specific Met-tRNAi loading that promotes proliferation, generalizing the alternative-initiation model to a host transcript.","evidence":"siRNA knockdown, in vitro IRES binding and toeprinting, bicistronic reporters and proliferation assays under stress","pmids":["27899592"],"confidence":"High","gaps":["Number of physiological cellular IRES clients unclear","Stress-specificity mechanism not defined"]},{"year":2016,"claim":"Whether eIF2A is essential in mammals was tested by gene-trap knockout, which yielded viable mice without gross phenotype, indicating it is not required for viability under standard conditions.","evidence":"gene-trap knockout mouse generation and phenotypic assessment","pmids":["27686860"],"confidence":"Medium","gaps":["Subtle or stress-conditional phenotypes not examined in this study","Molecular cause of dispensability unaddressed"]},{"year":2018,"claim":"The proposed eIF2A role in viral IRES translation was directly challenged; clean CRISPR knockouts of eIF2A (and eIF2D) in HAP1 cells supported HCV IRES and Sindbis sgmRNA translation even with phosphorylated eIF2α, contradicting the knockdown-based alternative-initiation reports.","evidence":"CRISPR/Cas9 single and double knockouts in HAP1 cells, IRES luciferase reporters under multiple stress inducers, viral protein synthesis assays","pmids":["28240315","29487587"],"confidence":"High","gaps":["Discrepancy with knockdown studies unresolved","Does not exclude a minor or transcript-restricted role"]},{"year":2021,"claim":"Whether eIF2A drives non-canonical translation of repeat expansions was tested in myotonic dystrophy models, where eIF2A overexpression increased RAN translation of CCUG- and CAGG-derived products, partly dependent on phospho-eIF2α.","evidence":"CRISPR-edited HEK293T lines (PKR-/-, PERK-/-, eIF2α-S51A), eIF2A overexpression, RAN protein detection","pmids":["33856033"],"confidence":"Medium","gaps":["Effect shown by overexpression, not endogenous requirement","Direct mechanism of RAN initiation enhancement unmapped"]},{"year":2021,"claim":"The organismal consequences of eIF2A loss were extended; knockout mice showed reduced lifespan, metabolic syndrome features, and altered thymic immune populations, with sex-specific effects, indicating physiological importance despite viability.","evidence":"eIF2A KO mouse metabolic phenotyping, lifespan analysis, flow cytometry, tunicamycin challenge","pmids":["34665898"],"confidence":"Medium","gaps":["Molecular link between eIF2A loss and metabolic phenotype unknown","No ER-stress-response difference observed, leaving mechanism unclear"]},{"year":2021,"claim":"A conserved developmental requirement was uncovered in Drosophila, where the EIF2A ortholog is essential for spermatogenesis through sperm individualization and F-actin cone formation, with sex-specific splicing.","evidence":"null and hypomorphic transposon alleles, fertility assays, F-actin immunofluorescence in Drosophila","pmids":["34278643"],"confidence":"Medium","gaps":["Whether this reflects a translational or non-translational role unknown","Relevance to mammalian function not established"]},{"year":2023,"claim":"The basis of eIF2A's broad inhibitory effect was defined by reconstitution: excess recombinant eIF2A binds purified 40S subunits and inhibits cap-dependent and all classes of IRES translation, with rescue by added 40S, establishing a 40S-sequestration mechanism.","evidence":"recombinant eIF2A purification, mammalian in vitro translation with multiple reporters/IRES types, 40S pull-down and supplementation rescue","pmids":["37602404"],"confidence":"High","gaps":["Physiological relevance of sequestration at endogenous levels unclear","Binding interface on 40S not structurally defined"]},{"year":2023,"claim":"Translation-independent and quality-control-adjacent activities emerged: eIF2A directly enhances SARS-CoV-2 −1 frameshifting, binds CG-rich RNA near the FSE-ribosome contacts on 18S rRNA, and supports viral replication, separating a frameshifting role from initiation.","evidence":"genome-wide CRISPR screen, eIF2A KO frameshifting validation, viral replication assays, transcriptome-wide RNA-binding analysis","pmids":["37581984"],"confidence":"High","gaps":["Whether eIF2A acts at endogenous host frameshift sites unclear","Structural basis of frameshift enhancement undefined"]},{"year":2023,"claim":"eIF2A (with eIF2D) was shown to be required for IRES-independent translation of enteroviral genomes, supporting recombination when canonical IRES translation is disabled.","evidence":"IRES-inactivating viral mutants, siRNA knockdown of eIF2A and eIF2D, viral replication/recombination assays","pmids":["36689548"],"confidence":"Medium","gaps":["Direct molecular role versus indirect effect not distinguished","Knockdown-based, no reconstitution"]},{"year":2024,"claim":"Whether eIF2A is a meaningful initiation factor in vivo was resolved at transcriptome scale; yeast ribosome profiling found no significant translational-efficiency dependence on eIF2A, even during eIF2α phosphorylation, narrowing its initiation role to possibly a single mRNA.","evidence":"genome-wide ribosome profiling of ΔeIF2A yeast under normal and starvation conditions","pmids":["38266075"],"confidence":"High","gaps":["Does not address non-initiation functions (frameshifting, RQC, centrosome)","Species-specific differences from mammals not excluded"]},{"year":2025,"claim":"The human ribosome-profiling counterpart confirmed minimal involvement of eIF2A in initiation and uORF control, including under ISR activation, consolidating the conclusion that eIF2A is not a general initiation factor.","evidence":"ribosome profiling and uORF/IRES luciferase reporters in eIF2A-depleted HeLa cells under ISR induction","pmids":["40600802"],"confidence":"High","gaps":["Specialized clients still possible but unidentified","Mechanism of the rare dependent mRNAs not defined"]},{"year":2025,"claim":"A translation-independent function was established: proximity labeling identified centrosomal proteins as major eIF2A partners, and eIF2A promotes centrosome composition and orientation during migration via its C-terminal disordered (mRNA-binding) region without requiring ongoing translation.","evidence":"TurboID interactome, co-localization imaging, depletion/migration assays, domain-deletion mutants, translation-inhibition controls","pmids":["40749049"],"confidence":"Medium","gaps":["Mechanism of centrosome recruitment unknown","How the disordered region acts at the centrosome unclear"]},{"year":2025,"claim":"A role in ribosome-associated quality control was proposed: eIF2A binds near the 40S mRNA entry channel, interacts with G3BP1-USP10 and RPS2/RPS3, and antagonizes USP10-dependent 40S rescue, shaping 40S turnover upon stalling.","evidence":"TurboID + mass spectrometry, polysome gradients, dynamic SILAC, eIF2A KO cells, stalling and ubiquitination assays (preprint)","pmids":["bio_10.1101_2025.05.22.655611"],"confidence":"Medium","gaps":["Preprint, not yet peer-reviewed","Direct versus indirect antagonism of USP10 not resolved","Structural detail of the 40S contact not defined"]},{"year":null,"claim":"Despite agreement that eIF2A is not a core initiation factor, the unifying molecular activity linking its 40S-binding, frameshift-enhancing, RQC, and centrosomal functions remains undefined.","evidence":"","pmids":[],"confidence":"Medium","gaps":["No structure of eIF2A on the 40S ribosome","The identity and number of genuine endogenous mRNA clients unknown","Whether RNA-binding underlies the centrosomal role is untested"]}],"mechanism_profile":{"molecular_activity":[{"term_id":"GO:0003723","term_label":"RNA binding","supporting_discovery_ids":[3,4,12,16]},{"term_id":"GO:0140110","term_label":"transcription regulator activity","supporting_discovery_ids":[11]},{"term_id":"GO:0140104","term_label":"molecular carrier activity","supporting_discovery_ids":[3,4,18]}],"localization":[{"term_id":"GO:0005840","term_label":"ribosome","supporting_discovery_ids":[0,11,17]},{"term_id":"GO:0005815","term_label":"microtubule organizing center","supporting_discovery_ids":[16]}],"pathway":[{"term_id":"R-HSA-8953854","term_label":"Metabolism of RNA","supporting_discovery_ids":[14,15,17]}],"complexes":[],"partners":["EEF1A1","USP10","G3BP1","RPS2","RPS3","EIF2D"],"other_free_text":[]}},"prefetch_data":{"uniprot":{"accession":"P05198","full_name":"Eukaryotic translation initiation factor 2 subunit 1","aliases":["Eukaryotic translation initiation factor 2 subunit alpha","eIF-2-alpha","eIF-2A","eIF-2alpha","eIF2-alpha"],"length_aa":315,"mass_kda":36.1,"function":"Member of the eIF2 complex that functions in the early steps of protein synthesis by forming a ternary complex with GTP and initiator tRNA (PubMed:16289705, PubMed:38340717). This complex binds to a 40S ribosomal subunit, followed by mRNA binding to form a 43S pre-initiation complex (43S PIC) (PubMed:16289705). Junction of the 60S ribosomal subunit to form the 80S initiation complex is preceded by hydrolysis of the GTP bound to eIF2 and release of an eIF2-GDP binary complex (PubMed:16289705). In order for eIF2 to recycle and catalyze another round of initiation, the GDP bound to eIF2 must exchange with GTP by way of a reaction catalyzed by eIF2B (PubMed:16289705). EIF2S1/eIF2-alpha is a key component of the integrated stress response (ISR), required for adaptation to various stress: phosphorylation by metabolic-stress sensing protein kinases (EIF2AK1/HRI, EIF2AK2/PKR, EIF2AK3/PERK and EIF2AK4/GCN2) in response to stress converts EIF2S1/eIF2-alpha in a global protein synthesis inhibitor, leading to an attenuation of cap-dependent translation, while concomitantly initiating the preferential translation of ISR-specific mRNAs, such as the transcriptional activators ATF4 and QRICH1, and hence allowing ATF4- and QRICH1-mediated reprogramming (PubMed:19131336, PubMed:33384352, PubMed:38340717). EIF2S1/eIF2-alpha also acts as an activator of mitophagy in response to mitochondrial damage: phosphorylation by EIF2AK1/HRI promotes relocalization to the mitochondrial surface, thereby triggering PRKN-independent mitophagy (PubMed:38340717)","subcellular_location":"Cytoplasm, Stress granule; Cytoplasm, cytosol; Mitochondrion","url":"https://www.uniprot.org/uniprotkb/P05198/entry"},"depmap":{"release":"DepMap","has_data":true,"is_common_essential":false,"resolved_as":"","url":"https://depmap.org/portal/gene/EIF2A","classification":"Not Classified","n_dependent_lines":7,"n_total_lines":1208,"dependency_fraction":0.005794701986754967},"opencell":{"profiled":false,"resolved_as":"","ensg_id":"","cell_line_id":"","localizations":[],"interactors":[],"url":"https://opencell.sf.czbiohub.org/search/EIF2A","total_profiled":1310},"omim":[{"mim_id":"619687","title":"DYSTONIA 33; DYT33","url":"https://www.omim.org/entry/619687"},{"mim_id":"618515","title":"TRANSMEMBRANE PROTEIN 33; TMEM33","url":"https://www.omim.org/entry/618515"},{"mim_id":"617458","title":"PRKR-INTERACTING PROTEIN 1, IL11-INDUCIBLE; PRKRIP1","url":"https://www.omim.org/entry/617458"},{"mim_id":"615857","title":"2-OXOGLUTARATE- AND IRON-DEPENDENT OXYGENASE DOMAIN-CONTAINING PROTEIN 1; OGFOD1","url":"https://www.omim.org/entry/615857"},{"mim_id":"613257","title":"PROTEIN PHOSPHATASE 1, REGULATORY SUBUNIT 15B; PPP1R15B","url":"https://www.omim.org/entry/613257"}],"hpa":{"profiled":true,"resolved_as":"","reliability":"Approved","locations":[{"location":"Cytosol","reliability":"Approved"}],"tissue_specificity":"Low tissue specificity","tissue_distribution":"Detected in all","driving_tissues":[],"url":"https://www.proteinatlas.org/search/EIF2A"},"hgnc":{"alias_symbol":["EIF-2A"],"prev_symbol":[]},"alphafold":{"accession":"P05198","domains":[{"cath_id":"2.40.50.140","chopping":"17-89","consensus_level":"high","plddt":82.7147,"start":17,"end":89},{"cath_id":"1.10.150.190","chopping":"94-183","consensus_level":"high","plddt":76.4101,"start":94,"end":183},{"cath_id":"3.30.70.1130","chopping":"188-296","consensus_level":"high","plddt":80.5791,"start":188,"end":296}],"viewer_url":"https://alphafold.ebi.ac.uk/entry/P05198","model_url":"https://alphafold.ebi.ac.uk/files/AF-P05198-F1-model_v6.cif","pae_url":"https://alphafold.ebi.ac.uk/files/AF-P05198-F1-predicted_aligned_error_v6.png","plddt_mean":77.81},"mouse_models":{"mgi_url":"https://www.informatics.jax.org/marker/summary?nomen=EIF2A","jax_strain_url":"https://www.jax.org/strain/search?query=EIF2A"},"sequence":{"accession":"P05198","fasta_url":"https://rest.uniprot.org/uniprotkb/P05198.fasta","uniprot_url":"https://www.uniprot.org/uniprotkb/P05198/entry","alphafold_viewer_url":"https://alphafold.ebi.ac.uk/entry/P05198"}},"corpus_meta":[{"pmid":"21556050","id":"PMC_21556050","title":"eIF2A mediates translation of hepatitis C viral mRNA under stress conditions.","date":"2011","source":"The EMBO journal","url":"https://pubmed.ncbi.nlm.nih.gov/21556050","citation_count":102,"is_preprint":false},{"pmid":"18305250","id":"PMC_18305250","title":"Eif-2a protects brainstem motoneurons in a murine model of sleep apnea.","date":"2008","source":"The Journal of neuroscience : the official journal of the Society for Neuroscience","url":"https://pubmed.ncbi.nlm.nih.gov/18305250","citation_count":72,"is_preprint":false},{"pmid":"26986695","id":"PMC_26986695","title":"Activation of the EIF2AK4-EIF2A/eIF2α-ATF4 pathway triggers autophagy response to Crohn disease-associated adherent-invasive Escherichia coli infection.","date":"2016","source":"Autophagy","url":"https://pubmed.ncbi.nlm.nih.gov/26986695","citation_count":64,"is_preprint":false},{"pmid":"12133843","id":"PMC_12133843","title":"Characterization of mammalian eIF2A and identification of the yeast homolog.","date":"2002","source":"The Journal of biological chemistry","url":"https://pubmed.ncbi.nlm.nih.gov/12133843","citation_count":60,"is_preprint":false},{"pmid":"32192132","id":"PMC_32192132","title":"A Retrospective on eIF2A-and Not the Alpha Subunit of eIF2.","date":"2020","source":"International journal of molecular sciences","url":"https://pubmed.ncbi.nlm.nih.gov/32192132","citation_count":52,"is_preprint":false},{"pmid":"31211507","id":"PMC_31211507","title":"EIF2A promotes cell survival during paclitaxel treatment in vitro and in vivo.","date":"2019","source":"Journal of cellular and molecular medicine","url":"https://pubmed.ncbi.nlm.nih.gov/31211507","citation_count":48,"is_preprint":false},{"pmid":"29065505","id":"PMC_29065505","title":"Kinases of eIF2a Switch Translation of mRNA Subset during Neuronal Plasticity.","date":"2017","source":"International journal of molecular sciences","url":"https://pubmed.ncbi.nlm.nih.gov/29065505","citation_count":41,"is_preprint":false},{"pmid":"3233204","id":"PMC_3233204","title":"Natural mRNA is required for directing Met-tRNA(f) binding to 40S ribosomal subunits in animal cells: involvement of Co-eIF-2A in natural mRNA-directed initiation complex formation.","date":"1988","source":"Biochemistry","url":"https://pubmed.ncbi.nlm.nih.gov/3233204","citation_count":34,"is_preprint":false},{"pmid":"27899592","id":"PMC_27899592","title":"An mRNA-specific tRNAi carrier eIF2A plays a pivotal role in cell proliferation under stress conditions: stress-resistant translation of c-Src mRNA is mediated by eIF2A.","date":"2016","source":"Nucleic acids research","url":"https://pubmed.ncbi.nlm.nih.gov/27899592","citation_count":30,"is_preprint":false},{"pmid":"28240315","id":"PMC_28240315","title":"Translation of Sindbis Subgenomic mRNA is Independent of eIF2, eIF2A and eIF2D.","date":"2017","source":"Scientific reports","url":"https://pubmed.ncbi.nlm.nih.gov/28240315","citation_count":28,"is_preprint":false},{"pmid":"27686860","id":"PMC_27686860","title":"The eIF2A knockout mouse.","date":"2016","source":"Cell cycle (Georgetown, Tex.)","url":"https://pubmed.ncbi.nlm.nih.gov/27686860","citation_count":27,"is_preprint":false},{"pmid":"21915340","id":"PMC_21915340","title":"Insights into the role of yeast eIF2A in IRES-mediated translation.","date":"2011","source":"PloS one","url":"https://pubmed.ncbi.nlm.nih.gov/21915340","citation_count":27,"is_preprint":false},{"pmid":"29487587","id":"PMC_29487587","title":"The Initiation Factors eIF2, eIF2A, eIF2D, eIF4A, and eIF4G Are Not Involved in Translation Driven by Hepatitis C Virus IRES in Human Cells.","date":"2018","source":"Frontiers in microbiology","url":"https://pubmed.ncbi.nlm.nih.gov/29487587","citation_count":27,"is_preprint":false},{"pmid":"26142622","id":"PMC_26142622","title":"Polypeptide from Chlamys farreri suppresses ultraviolet-B irradiation-induced apoptosis through restoring ER redox homeostasis, scavenging ROS generation, and suppressing the PERK-eIF2a-CHOP pathway in HaCaT cells.","date":"2015","source":"Journal of photochemistry and photobiology. B, Biology","url":"https://pubmed.ncbi.nlm.nih.gov/26142622","citation_count":26,"is_preprint":false},{"pmid":"31894250","id":"PMC_31894250","title":"miR‑195 promotes LPS‑mediated intestinal epithelial cell apoptosis via targeting SIRT1/eIF2a.","date":"2019","source":"International journal of molecular medicine","url":"https://pubmed.ncbi.nlm.nih.gov/31894250","citation_count":25,"is_preprint":false},{"pmid":"19861427","id":"PMC_19861427","title":"Characterization of the functional role of nucleotides within the URE2 IRES element and the requirements for eIF2A-mediated repression.","date":"2009","source":"RNA (New York, N.Y.)","url":"https://pubmed.ncbi.nlm.nih.gov/19861427","citation_count":24,"is_preprint":false},{"pmid":"34665898","id":"PMC_34665898","title":"eIF2A-knockout mice reveal decreased life span and metabolic syndrome.","date":"2021","source":"FASEB journal : official publication of the Federation of American Societies for Experimental Biology","url":"https://pubmed.ncbi.nlm.nih.gov/34665898","citation_count":22,"is_preprint":false},{"pmid":"33856033","id":"PMC_33856033","title":"The alternative initiation factor eIF2A plays key role in RAN translation of myotonic dystrophy type 2 CCUG•CAGG repeats.","date":"2021","source":"Human molecular genetics","url":"https://pubmed.ncbi.nlm.nih.gov/33856033","citation_count":21,"is_preprint":false},{"pmid":"3888988","id":"PMC_3888988","title":"Protein synthesis in rabbit reticulocytes. Purification and properties of an Mr 80,000 polypeptide (Co-eIF-2A80) with Co-eIF-2A activity.","date":"1985","source":"The Journal of biological chemistry","url":"https://pubmed.ncbi.nlm.nih.gov/3888988","citation_count":21,"is_preprint":false},{"pmid":"3888989","id":"PMC_3888989","title":"Purification and properties of eukaryotic initiation factor 2 and its ancillary protein factor (Co-eIF-2A) from yeast Saccharomyces cerevisiae.","date":"1985","source":"The Journal of biological chemistry","url":"https://pubmed.ncbi.nlm.nih.gov/3888989","citation_count":21,"is_preprint":false},{"pmid":"7356618","id":"PMC_7356618","title":"Protein synthesis in rabbit reticulocytes. Demonstration of the requirements for eIF-2 and Co-eIF-2A for peptide chain initiation using immune sera.","date":"1980","source":"The Journal of biological chemistry","url":"https://pubmed.ncbi.nlm.nih.gov/7356618","citation_count":21,"is_preprint":false},{"pmid":"22053000","id":"PMC_22053000","title":"Endoplasmic reticulum stress decreases intracellular thyroid hormone activation via an eIF2a-mediated decrease in type 2 deiodinase synthesis.","date":"2011","source":"Molecular endocrinology (Baltimore, Md.)","url":"https://pubmed.ncbi.nlm.nih.gov/22053000","citation_count":19,"is_preprint":false},{"pmid":"6153053","id":"PMC_6153053","title":"Protein synthesis in rabbit reticulocytes. Co-eIF-2A reverses mRNA inhibition of ternary complex (Met-tRNAf.eIF-2.GTP) formation by eIF-2.","date":"1981","source":"The Journal of biological chemistry","url":"https://pubmed.ncbi.nlm.nih.gov/6153053","citation_count":17,"is_preprint":false},{"pmid":"26542945","id":"PMC_26542945","title":"EIF2A-dependent translational arrest protects leukemia cells from the energetic stress induced by NAMPT inhibition.","date":"2015","source":"BMC cancer","url":"https://pubmed.ncbi.nlm.nih.gov/26542945","citation_count":13,"is_preprint":false},{"pmid":"29848262","id":"PMC_29848262","title":"The Effect of Culture Temperature on the Aggregation of Recombinant TNFR-Fc is Regulated by the PERK-eIF2a Pathway in CHO Cells.","date":"2018","source":"Protein and peptide letters","url":"https://pubmed.ncbi.nlm.nih.gov/29848262","citation_count":12,"is_preprint":false},{"pmid":"37581984","id":"PMC_37581984","title":"Genome-wide CRISPR screens identify noncanonical translation factor eIF2A as an enhancer of SARS-CoV-2 programmed -1 ribosomal frameshifting.","date":"2023","source":"Cell reports","url":"https://pubmed.ncbi.nlm.nih.gov/37581984","citation_count":11,"is_preprint":false},{"pmid":"7372648","id":"PMC_7372648","title":"Protein synthesis in rabbit reticulocytes. A study of the mechanism of interreaction of fluorescently labeled co-eIF-2A with eIF-2 using fluorescence polarization.","date":"1980","source":"The Journal of biological chemistry","url":"https://pubmed.ncbi.nlm.nih.gov/7372648","citation_count":11,"is_preprint":false},{"pmid":"37602404","id":"PMC_37602404","title":"Increased levels of eIF2A inhibit translation by sequestering 40S ribosomal subunits.","date":"2023","source":"Nucleic acids research","url":"https://pubmed.ncbi.nlm.nih.gov/37602404","citation_count":10,"is_preprint":false},{"pmid":"38433101","id":"PMC_38433101","title":"To initiate or not to initiate: A critical assessment of eIF2A, eIF2D, and MCT-1·DENR to deliver initiator tRNA to ribosomes.","date":"2024","source":"Wiley interdisciplinary reviews. RNA","url":"https://pubmed.ncbi.nlm.nih.gov/38433101","citation_count":10,"is_preprint":false},{"pmid":"36689548","id":"PMC_36689548","title":"The enterovirus genome can be translated in an IRES-independent manner that requires the initiation factors eIF2A/eIF2D.","date":"2023","source":"PLoS biology","url":"https://pubmed.ncbi.nlm.nih.gov/36689548","citation_count":10,"is_preprint":false},{"pmid":"39380677","id":"PMC_39380677","title":"African swine fever virus RNA polymerase subunits C315R and H359L inhibition host translation by activating the PKR-eIF2a pathway and suppression inflammatory responses.","date":"2024","source":"Frontiers in microbiology","url":"https://pubmed.ncbi.nlm.nih.gov/39380677","citation_count":8,"is_preprint":false},{"pmid":"38266075","id":"PMC_38266075","title":"Yeast eIF2A has a minimal role in translation initiation and uORF-mediated translational control in vivo.","date":"2024","source":"eLife","url":"https://pubmed.ncbi.nlm.nih.gov/38266075","citation_count":8,"is_preprint":false},{"pmid":"34278643","id":"PMC_34278643","title":"Unconventional translation initiation factor EIF2A is required for Drosophila spermatogenesis.","date":"2021","source":"Developmental dynamics : an official publication of the American Association of Anatomists","url":"https://pubmed.ncbi.nlm.nih.gov/34278643","citation_count":7,"is_preprint":false},{"pmid":"36555509","id":"PMC_36555509","title":"PKR-Mediated Phosphorylation of eIF2a and CHK1 Is Associated with Doxorubicin-Mediated Apoptosis in HCC1143 Triple-Negative Breast Cancer Cells.","date":"2022","source":"International journal of molecular sciences","url":"https://pubmed.ncbi.nlm.nih.gov/36555509","citation_count":7,"is_preprint":false},{"pmid":"33391409","id":"PMC_33391409","title":"U three protein 14a (UTP14A) promotes tumour proliferation and metastasis via the PERK/eIF2a/GRP78 signalling pathway in oesophageal squamous cell carcinoma.","date":"2021","source":"Journal of Cancer","url":"https://pubmed.ncbi.nlm.nih.gov/33391409","citation_count":7,"is_preprint":false},{"pmid":"33935494","id":"PMC_33935494","title":"Alendronate Alleviated Femoral Head Necrosis and Upregulated BMP2/EIF2AK3/EIF2A/ATF4 Pathway in Liquid Nitrogen Treated Rats.","date":"2021","source":"Drug design, development and therapy","url":"https://pubmed.ncbi.nlm.nih.gov/33935494","citation_count":5,"is_preprint":false},{"pmid":"40600802","id":"PMC_40600802","title":"Human eIF2A has a minimal role in translation initiation and in uORF-mediated translational control in HeLa cells.","date":"2025","source":"eLife","url":"https://pubmed.ncbi.nlm.nih.gov/40600802","citation_count":4,"is_preprint":false},{"pmid":"30133715","id":"PMC_30133715","title":"PERK, mTORC1 and eEF2 interplay during long term potentiation: An Editorial for 'Genetic removal of eIF2a kinase PERK in mice enables hippocampal L-LTP independent of mTORC1 activity' on page 133.","date":"2018","source":"Journal of neurochemistry","url":"https://pubmed.ncbi.nlm.nih.gov/30133715","citation_count":3,"is_preprint":false},{"pmid":"37294427","id":"PMC_37294427","title":"Integrating network pharmacology and experimental models to examine the mechanisms of corosolic acid in preventing hepatocellular carcinoma progression through activation PERK-eIF2a-ATF4 signaling.","date":"2023","source":"Naunyn-Schmiedeberg's archives of pharmacology","url":"https://pubmed.ncbi.nlm.nih.gov/37294427","citation_count":3,"is_preprint":false},{"pmid":"17407708","id":"PMC_17407708","title":"[Genetic polymorphisms of MxA protein and eIF-2a-reg2 and their responses to interferon treatment in patients with chronic hepatitis B].","date":"2007","source":"Zhonghua gan zang bing za zhi = Zhonghua ganzangbing zazhi = Chinese journal of hepatology","url":"https://pubmed.ncbi.nlm.nih.gov/17407708","citation_count":3,"is_preprint":false},{"pmid":"40749049","id":"PMC_40749049","title":"eIF2A regulates cell migration in a translation-independent manner.","date":"2025","source":"Science advances","url":"https://pubmed.ncbi.nlm.nih.gov/40749049","citation_count":2,"is_preprint":false},{"pmid":"21059295","id":"PMC_21059295","title":"[Role of PERK/eIF2a signaling pathway in hepatocyte apoptosis of alcoholic liver injury rats].","date":"2010","source":"Zhonghua gan zang bing za zhi = Zhonghua ganzangbing zazhi = Chinese journal of hepatology","url":"https://pubmed.ncbi.nlm.nih.gov/21059295","citation_count":2,"is_preprint":false},{"pmid":"26019549","id":"PMC_26019549","title":"Gene cloning of an important eukaryotic translation initiation factor family, eIF2A gene in halophytic Leymus chinensis (Trin.).","date":"2014","source":"Biotechnology, biotechnological equipment","url":"https://pubmed.ncbi.nlm.nih.gov/26019549","citation_count":1,"is_preprint":false},{"pmid":"39562297","id":"PMC_39562297","title":"Adjuvant alum regulates the eIF2a-GATA3 axis in CD4+ T cells to influence allergen immunotherapy.","date":"2024","source":"Scandinavian journal of immunology","url":"https://pubmed.ncbi.nlm.nih.gov/39562297","citation_count":1,"is_preprint":false},{"pmid":"3096729","id":"PMC_3096729","title":"Protein synthesis in yeast Saccharomyces cerevisiae. Purification of Co-eIF-2A and 'mRNA-binding factor(s)' and studies of their roles in Met-tRNAf.40S.mRNA complex formation.","date":"1986","source":"European journal of biochemistry","url":"https://pubmed.ncbi.nlm.nih.gov/3096729","citation_count":1,"is_preprint":false},{"pmid":"40639044","id":"PMC_40639044","title":"Super-enhancer PPP1R15B/EIF2A axis characterizes aggressive drug-tolerant persister cells in Glioblastoma.","date":"2025","source":"Biomedicine & pharmacotherapy = Biomedecine & pharmacotherapie","url":"https://pubmed.ncbi.nlm.nih.gov/40639044","citation_count":0,"is_preprint":false},{"pmid":"37986989","id":"PMC_37986989","title":"Yeast eIF2A has a minimal role in translation initiation and uORF-mediated translational control in vivo.","date":"2023","source":"bioRxiv : the preprint server for biology","url":"https://pubmed.ncbi.nlm.nih.gov/37986989","citation_count":0,"is_preprint":false},{"pmid":"40979716","id":"PMC_40979716","title":"Correction: PERK/eIF2a pathway affected the thyroid hormone synthetic in hypertensive disorders of pregnancy rats.","date":"2025","source":"Frontiers in endocrinology","url":"https://pubmed.ncbi.nlm.nih.gov/40979716","citation_count":0,"is_preprint":false},{"pmid":null,"id":"bio_10.1101_2025.05.22.655611","title":"The alternative initiation factor eIF2A regulates 40S subunit turnover in ribosome-associated quality control","date":"2025-05-24","source":"bioRxiv","url":"https://doi.org/10.1101/2025.05.22.655611","citation_count":0,"is_preprint":true},{"pmid":null,"id":"bio_10.1101_2025.03.12.642754","title":"WEE1 inhibitors trigger GCN2-mediated activation of the integrated stress response","date":"2025-03-14","source":"bioRxiv","url":"https://doi.org/10.1101/2025.03.12.642754","citation_count":0,"is_preprint":true},{"pmid":null,"id":"bio_10.1101_2024.09.25.614975","title":"Betacoronaviruses Differentially Activate the Integrated Stress Response to Optimize Viral Replication in Lung Derived Cell Lines","date":"2024-09-26","source":"bioRxiv","url":"https://doi.org/10.1101/2024.09.25.614975","citation_count":0,"is_preprint":true}],"cost":{"stage1":{"model":"claude-sonnet-4-6","input_tokens":28200,"output_tokens":6633,"usd":0.092048,"stage1_stop_reason":"end_turn"},"stage2":{"model":"claude-opus-4-8","input_tokens":15491,"output_tokens":5345,"usd":0.10554,"stage2_stop_reason":"end_turn"},"total_usd":0.197588,"stage1_batch_id":"msgbatch_01AsR7g8dGTEiEw9U83bJeWn","stage2_batch_id":"msgbatch_01YV5ZyxtFNUZEjxRcpd9jzb","note":"batch pricing = 50% of standard"},"stage1_raw":"```json\n{\n  \"discoveries\": [\n    {\n      \"year\": 2002,\n      \"finding\": \"Mammalian eIF2A is a 585 amino acid, single-chain protein encoded by a gene on chromosome 3. The yeast homolog (YGR054W) localizes on both 40S and 80S ribosomes. A double knockout of yeast eIF2A and eIF5B yields a synthetically sick slow-growth phenotype, suggesting eIF2A participates in translation initiation. eIF2A does not appear to participate in re-initiation, as the ΔeIF2A strain shows the same level of GCN4 induction with amino acid starvation as wild-type yeast.\",\n      \"method\": \"Peptide sequencing of rabbit reticulocyte eIF2A, cDNA/EST cloning, HA-tagging and ribosome fractionation in yeast, genetic double-knockout analysis, GCN4-lacZ reporter assay\",\n      \"journal\": \"The Journal of biological chemistry\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 / Strong — multiple orthogonal methods (biochemical fractionation, genetics, reporter assay) in a single focused characterization study\",\n      \"pmids\": [\"12133843\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2009,\n      \"finding\": \"In yeast, eIF2A acts as a negative regulator of IRES-mediated (cap-independent) translation under normal cellular conditions. eIF2A-mediated repression is not specific to the URE2 IRES; GIC1 and PAB1 IRES elements are also repressed by eIF2A. The stability of secondary structure within the URE2 IRES is not required for eIF2A-dependent repression.\",\n      \"method\": \"Monocistronic reporter assays in ΔeIF2A yeast strains, mutational analysis of URE2 IRES stem-loop structures\",\n      \"journal\": \"RNA (New York, N.Y.)\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — genetic deletion combined with reporter assays, single lab, multiple IRES elements tested\",\n      \"pmids\": [\"19861427\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2011,\n      \"finding\": \"In yeast, eIF2A abundance is reduced at both mRNA and protein levels during ethanol stress or heat shock; eIF2A protein is also post-translationally modified during ethanol stress. eIF2A interacts with eEF1A (identified by immunoprecipitation-mass spectrometry), and this interaction increases during ethanol stress, correlating with increased IRES-mediated translation from the URE2 IRES.\",\n      \"method\": \"Western blot and qRT-PCR for eIF2A levels under stress; immunoprecipitation-mass spectrometry to identify eEF1A as binding partner; IRES reporter assays in ΔeIF2A yeast\",\n      \"journal\": \"PloS one\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — Co-IP/MS identification of eEF1A interaction, correlated with functional IRES reporter data, single lab\",\n      \"pmids\": [\"21915340\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2011,\n      \"finding\": \"eIF2A mediates translation of HCV mRNA under stress conditions when eIF2α is phosphorylated. eIF2A directly interacts with the IIId domain of the HCV IRES, and this direct interaction is required for eIF2A-dependent translation. eIF2A acts as an alternative initiator tRNA-binding protein that recruits Met-tRNAi to the P site of the 40S ribosomal subunit in an eIF2-independent manner. eIF2A also promotes eIF2α phosphorylation by activating the eIF2α kinase PKR during HCV infection.\",\n      \"method\": \"siRNA knockdown of eIF2A in HCV-infected cells, in vitro binding assays between eIF2A and HCV IRES domains, toeprinting assays, polysome profiling, PKR activation assays\",\n      \"journal\": \"The EMBO journal\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 / Strong — multiple orthogonal methods (knockdown, direct binding assay, toeprinting, PKR activation) in a single focused study with strong controls\",\n      \"pmids\": [\"21556050\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2016,\n      \"finding\": \"eIF2A is responsible for stress-resistant translation of c-Src mRNA via its IRES element. eIF2A facilitates tRNAi loading onto the 40S ribosomal subunit in a c-Src mRNA-dependent manner. A direct interaction between eIF2A and a stem-loop structure (SL I) in the c-Src IRES is required for IRES-dependent translation under stress conditions but not under normal conditions. eIF2A-dependent translation of c-Src mRNA promotes cell proliferation under stress.\",\n      \"method\": \"siRNA knockdown of eIF2A, in vitro binding assays between eIF2A and c-Src IRES SL I, toeprinting assays, bicistronic reporter assays under stress conditions, cell proliferation assays\",\n      \"journal\": \"Nucleic acids research\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 / Strong — direct binding assay, toeprinting, reporter assays, and functional cell proliferation data, multiple orthogonal methods in one study\",\n      \"pmids\": [\"27899592\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2016,\n      \"finding\": \"In an eIF2A knockout mouse strain (gene trap between exons 1 and 2), mice are viable with no apparent gross phenotype, suggesting eIF2A is not essential for viability in mammals under standard conditions.\",\n      \"method\": \"Gene-trap knockout mouse generation, viability and phenotypic assessment\",\n      \"journal\": \"Cell cycle (Georgetown, Tex.)\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — direct genetic KO in mammals with phenotypic assessment, single lab\",\n      \"pmids\": [\"27686860\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2017,\n      \"finding\": \"Translation of Sindbis virus subgenomic mRNA is independent of eIF2A and eIF2D. HAP1 cells knocked-out for eIF2A, eIF2D, or both via CRISPR/Cas9 showed comparable Sindbis virus infection and viral protein synthesis to wild-type cells, even when eIF2α was phosphorylated. This is a negative finding: eIF2A and eIF2D are not required for sgmRNA translation when eIF2α is phosphorylated.\",\n      \"method\": \"CRISPR/Cas9 knockout of eIF2A and eIF2D in HAP1 cells, Sindbis virus infection, siRNA silencing, measurement of viral protein synthesis by Western blot\",\n      \"journal\": \"Scientific reports\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 / Strong — clean CRISPR KO cells with multiple viral conditions and siRNA confirmation, rigorous negative result\",\n      \"pmids\": [\"28240315\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2018,\n      \"finding\": \"Neither eIF2A nor eIF2D participates in HCV IRES-driven translation in human cells. Human HAP1 cells depleted for eIF2A, eIF2D, or both were able to synthesize luciferase from an HCV IRES-bearing mRNA even when eIF2α was phosphorylated. This is a negative finding contradicting earlier reports that eIF2A mediates HCV IRES translation under stress.\",\n      \"method\": \"HAP1 cells depleted for eIF2A and/or eIF2D via CRISPR/Cas9, HCV IRES luciferase reporter assays under multiple stress conditions (arsenite, thapsigargin, tunicamycin, salubrinal)\",\n      \"journal\": \"Frontiers in microbiology\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 / Strong — CRISPR KO cells, multiple stress inducers, luciferase reporter assays; directly contradicts PMID:21556050\",\n      \"pmids\": [\"29487587\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2021,\n      \"finding\": \"eIF2A knockout mice exhibit decreased life span, metabolic syndrome features (impaired lipid homeostasis, glucose tolerance defects, insulin resistance), and reduced B lymphocytes and dendritic cells in thymic medulla. Effects differ between male and female mice. Pharmacological ER stress induction with tunicamycin did not reveal substantial differences between KO and wild-type mice in ER stress response.\",\n      \"method\": \"eIF2A KO mouse model, metabolic phenotyping (glucose tolerance test, insulin resistance assays), lifespan analysis, flow cytometry of thymic cell populations, tunicamycin treatment\",\n      \"journal\": \"FASEB journal\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — direct KO mouse model with multiple phenotypic assays, single lab\",\n      \"pmids\": [\"34665898\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2021,\n      \"finding\": \"Overexpression of eIF2A increases RAN (repeat-associated non-AUG) translation of both LPAC (from CCUG repeats) and QAGR (from CAGG repeats) proteins in DM2 myotonic dystrophy. The effect of eIF2A on QAGR (CAGG transcripts lacking efficient close-cognate codons) is novel and dependent on phosphorylated eIF2α, whereas eIF2A effects on LPAC are partially independent of p-eIF2α.\",\n      \"method\": \"CRISPR/Cas9-edited HEK293T cell lines (PKR-/-, PERK-/-, eIF2α-S51A), eIF2A overexpression, RAN protein measurement by Western blot and immunofluorescence\",\n      \"journal\": \"Human molecular genetics\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — multiple CRISPR-edited cell lines, overexpression, two different repeat substrates tested, single lab\",\n      \"pmids\": [\"33856033\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2021,\n      \"finding\": \"Drosophila EIF2A (encoded by CG7414) is essential for spermatogenesis. Loss of function (Mi{Mic} null allele) causes male sterility due to failure of sperm individualization, defects in F-actin cones, and failure to form and maintain cystic bulges. The Mi{Mic} null allele is homozygous lethal, while a hypomorphic allele causes male sterility and female fertility. The gene undergoes sex-specific splicing regulating male-specific expression.\",\n      \"method\": \"Transposon insertion mutant alleles in Drosophila (null Mi{Mic} and hypomorphic PBac), fertility assays, immunofluorescence of F-actin cones, genetic analysis\",\n      \"journal\": \"Developmental dynamics\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — multiple alleles in Drosophila ortholog, direct cellular phenotyping, single lab\",\n      \"pmids\": [\"34278643\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2023,\n      \"finding\": \"Increased levels of recombinant human eIF2A inhibit translation of multiple reporter mRNAs in a mammalian in vitro translation system, including those translated by cognate and near-cognate start codons, and inhibit all four types of cap-independent viral IRES-driven translation including the CrPV IGR IRES (which requires no initiation factors or initiator tRNA). Supplementation with additional 40S subunits rescues eIF2A-mediated inhibition. Pull-down assays demonstrate direct binding between recombinant eIF2A and purified 40S subunits, supporting a model that excess eIF2A sequesters 40S ribosomal subunits.\",\n      \"method\": \"Purification of recombinant human eIF2A from E. coli and insect cells, mammalian in vitro translation assays with multiple reporter mRNAs and IRES types, 40S subunit supplementation rescue experiment, pull-down assays with purified 40S subunits\",\n      \"journal\": \"Nucleic acids research\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 1 / Strong — in vitro reconstitution with purified recombinant protein, direct binding assay, multiple IRES types tested, rescue experiment with 40S subunits, multiple orthogonal methods\",\n      \"pmids\": [\"37602404\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2023,\n      \"finding\": \"eIF2A specifically and directly enhances SARS-CoV-2 programmed -1 ribosomal frameshifting (-1 PRF), independently of changes in translation initiation. Loss of eIF2A reduces SARS-CoV-2 replication in cells. Transcriptome-wide analysis shows eIF2A preferentially binds CG-rich RNA motifs, including a region within 18S rRNA near the contacts between the SARS-CoV-2 frameshift-stimulatory element (FSE) and the ribosome.\",\n      \"method\": \"Genome-wide CRISPR-Cas9 knockout screen for -1 PRF regulators, eIF2A KO cell validation of frameshifting, SARS-CoV-2 replication assays in KO cells, transcriptome-wide RNA binding analysis (CLIP-seq or equivalent)\",\n      \"journal\": \"Cell reports\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 / Strong — genome-wide screen followed by targeted KO validation, viral replication assays, and transcriptome-wide binding data, multiple orthogonal methods\",\n      \"pmids\": [\"37581984\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2023,\n      \"finding\": \"eIF2A and eIF2D are required for IRES-independent translation of enteroviral genomes. In cells with complete inactivation of IRES-mediated translation, sufficient translation of the nonstructural region still occurs to support recombination, and this IRES-independent translation depends on eIF2A and eIF2D.\",\n      \"method\": \"IRES-inactivating mutations in enteroviral genome, siRNA knockdown of eIF2A and eIF2D, viral replication and recombination assays\",\n      \"journal\": \"PLoS biology\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — siRNA knockdown combined with IRES-mutant viral genome, single lab, specific functional readout\",\n      \"pmids\": [\"36689548\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2024,\n      \"finding\": \"Yeast eIF2A has a minimal role in translation initiation in vivo. Ribosome profiling of ΔeIF2A yeast showed no significant translational efficiency reductions for any mRNAs in non-starved cells, and only minor reductions in starved cells with phosphorylated eIF2α. No evidence was found that eIF2A altered IRES-mediated translation or translation of mRNAs with uORFs initiated by AUG or near-cognate codons. Very few mRNAs (possibly only one) appear to employ eIF2A for Met-tRNAi recruitment in yeast.\",\n      \"method\": \"Ribosome profiling (genome-wide) of ΔeIF2A yeast under normal and amino acid starvation conditions, bioinformatic analysis of translational efficiencies\",\n      \"journal\": \"eLife\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 1 / Strong — genome-wide ribosome profiling in clean KO, multiple conditions tested, rigorous negative result at transcriptome scale\",\n      \"pmids\": [\"38266075\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2025,\n      \"finding\": \"Human eIF2A has a minimal role in translation initiation and uORF-mediated translational control in HeLa cells. Ribosome profiling and luciferase reporter assays in eIF2A-depleted HeLa cells, including conditions of integrated stress response activation, detected no role for eIF2A in translation initiation.\",\n      \"method\": \"Ribosome profiling in eIF2A-depleted HeLa cells, luciferase reporter assays for uORF-containing and IRES-containing mRNAs, ISR activation with chemical inducers\",\n      \"journal\": \"eLife\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 1 / Strong — genome-wide ribosome profiling plus reporter assays in human cells, multiple stress conditions, rigorous negative result\",\n      \"pmids\": [\"40600802\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2025,\n      \"finding\": \"eIF2A regulates cell migration in a translation-independent manner. Interactome studies (proximity labeling) identified centrosomal proteins as major binding partners of eIF2A. eIF2A colocalizes with the centrosome, enhances centrosome composition, and promotes centrosome orientation during cell migration. This function requires the C-terminal disordered region of eIF2A involved in mRNA binding, but does not require ongoing translation.\",\n      \"method\": \"TurboID proximity labeling interactome, co-localization imaging (eIF2A with centrosomal markers), eIF2A depletion with migration assays, domain deletion mutants, translation inhibition controls\",\n      \"journal\": \"Science advances\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — proximity labeling combined with imaging and functional migration assays and domain mapping, single lab\",\n      \"pmids\": [\"40749049\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2025,\n      \"finding\": \"eIF2A has a novel function in ribosome-associated quality control (RQC). Using TurboID proximity labeling combined with polysome gradients and mass spectrometry, eIF2A's binding site was mapped close to the mRNA entry channel of the 40S ribosomal subunit. eIF2A strongly interacts with G3BP1-USP10 complexes and ribosomal proteins RPS2 and RPS3. In the absence of eIF2A, RPS2 and RPS3 ubiquitination is diminished specifically upon ribosome stalling. eIF2A antagonizes USP10-dependent rescue of 40S ribosomes, resulting in altered turnover of 40S subunits upon cellular stress.\",\n      \"method\": \"TurboID proximity labeling + mass spectrometry, polysome gradient fractionation, dynamic SILAC mass spectrometry, eIF2A knockout cells, ribosome stalling assays, ubiquitination measurements\",\n      \"journal\": \"bioRxiv\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — multiple orthogonal methods (proximity labeling, SILAC, polysome gradients, KO cells), preprint not yet peer-reviewed\",\n      \"pmids\": [\"bio_10.1101_2025.05.22.655611\"],\n      \"is_preprint\": true\n    },\n    {\n      \"year\": 1980,\n      \"finding\": \"Co-eIF-2A (an activity later attributed to a component of what became eIF2A) is absolutely required for protein synthesis in reticulocyte lysates; antibody inhibition of Co-eIF-2A cannot be reversed by eIF-2, establishing a non-redundant requirement. Co-eIF-2A stimulates eIF-2-dependent ternary complex formation and protects ternary complexes from dissociation by aurintricarboxylic acid. Co-eIF-2A does not interact with free eIF-2 but specifically with the preformed ternary complex.\",\n      \"method\": \"Antibody inhibition of reticulocyte lysate protein synthesis, reversal experiments with purified factors, fluorescence polarization with dansyl-labeled Co-eIF-2A\",\n      \"journal\": \"The Journal of biological chemistry\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — antibody inhibition and fluorescence polarization assays with purified components, older biochemical studies with limited molecular identity of the factor\",\n      \"pmids\": [\"7356618\", \"7372648\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 1981,\n      \"finding\": \"Co-eIF-2A reverses mRNA inhibition of ternary complex formation by eIF-2. At low mRNA concentrations, mRNAs strongly inhibit ternary complex (Met-tRNAf·eIF-2·GTP) formation and dissociate preformed ternary complexes; excess Co-eIF-2A renders Met-tRNAf binding to eIF-2 fully resistant to this mRNA inhibition. Other cofactors (Co-eIF-2B and Co-eIF-2C) did not reverse mRNA inhibition.\",\n      \"method\": \"In vitro ternary complex formation assays with purified Co-eIF-2A, mRNA titration, filter-binding assays\",\n      \"journal\": \"The Journal of biological chemistry\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — in vitro reconstitution with purified components testing specific factor function, single lab, older biochemical study\",\n      \"pmids\": [\"6153053\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 1985,\n      \"finding\": \"An 80 kDa polypeptide (Co-eIF-2A80) was purified to homogeneity from rabbit reticulocytes and shown to stimulate Met-tRNAf binding to eIF-2 in a manner resistant to aurintricarboxylic acid. Antibodies against Co-eIF-2A80 strongly inhibited protein synthesis in reticulocyte lysates and blocked eIF-2 and Co-eIF-2-promoted Met-tRNAf binding to 40S ribosomes. Limited proteolysis mapped the protein to the 80 kDa band within the Co-eIF-2 complex.\",\n      \"method\": \"Protein purification to homogeneity, in vitro translation assays, antibody inhibition, limited V8 protease mapping\",\n      \"journal\": \"The Journal of biological chemistry\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 1 / Moderate — in vitro reconstitution with purified protein, antibody inhibition, single lab\",\n      \"pmids\": [\"3888988\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2015,\n      \"finding\": \"EIF2A phosphorylation is induced in leukemia cells by FK866 (NAMPT inhibitor) via the LKB1-AMPK-EIF2A axis and is responsible for translational arrest and cell survival. Expression of a non-phosphorylatable EIF2A mutant in Jurkat cells enhanced sensitivity to FK866, confirming that EIF2A phosphorylation mediates protein synthesis arrest as a survival mechanism.\",\n      \"method\": \"FK866 treatment of leukemia cell lines, ectopic expression of non-phosphorylatable EIF2A mutant, AMPK/LKB1 silencing, polysome profiling\",\n      \"journal\": \"BMC cancer\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — phosphomutant rescue experiment combined with knockdown, single lab, single study\",\n      \"pmids\": [\"26542945\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2019,\n      \"finding\": \"EIF2A is essential for cancer cell survival after paclitaxel-mediated integrated stress response both in vitro and in vivo. Paclitaxel activates the EIF2AK3/EIF2AK4-pEIF2S1-ATF4 axis, and EIF2A is required for maintenance of redox homeostasis by supporting expression of antioxidant enzymes (HMOX1, SHMT2, SLC7A11) in this context.\",\n      \"method\": \"siRNA knockdown and overexpression of EIF2A in breast cancer cells, xenograft mouse models, ROS scavenger rescue experiment (Trolox), Western blot for ISR markers\",\n      \"journal\": \"Journal of cellular and molecular medicine\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — KD/OE with in vivo xenograft validation and mechanistic rescue experiment, single lab\",\n      \"pmids\": [\"31211507\"],\n      \"is_preprint\": false\n    }\n  ],\n  \"current_model\": \"EIF2A is a single-chain 65 kDa protein that directly binds the 40S ribosomal subunit near the mRNA entry channel and, at elevated levels, sequesters 40S subunits to inhibit translation broadly; it plays a minor, context-specific role in alternative translation initiation (including at near-cognate/non-AUG codons, certain viral IRES elements, and RAN translation under stress when eIF2 is inactivated), directly enhances SARS-CoV-2 programmed −1 ribosomal frameshifting, participates in ribosome-associated quality control by antagonizing USP10-dependent 40S rescue during ribosome stalling, and has a translation-independent role in centrosome orientation during cell migration; genome-wide ribosome profiling in both yeast and human cells indicates that EIF2A has minimal impact on global or uORF-mediated translation initiation even during integrated stress response activation, with only a small number of mRNAs demonstrably dependent on it.\"\n}\n```","stage2_raw":"{\n  \"mechanistic_narrative\": \"EIF2A is a single-chain ribosome-associated protein that binds the 40S ribosomal subunit near the mRNA entry channel and modulates translation in a narrow, context-specific manner rather than acting as a core initiation factor [#0, #11, #17]. It can function as an eIF2-independent initiator-tRNA carrier, recruiting Met-tRNAi to the 40S P site to support cap-independent translation of specific IRES-bearing mRNAs under conditions of eIF2\\u03b1 phosphorylation, including the HCV IRES and the c-Src IRES, through direct binding to defined IRES stem-loop structures [#3, #4]. At elevated abundance, recombinant EIF2A binds purified 40S subunits and broadly inhibits both cap-dependent and IRES-driven translation, an effect reversed by supplementing additional 40S subunits, indicating a 40S-sequestration mechanism [#11]. Consistent with a limited physiological role in initiation, genome-wide ribosome profiling in both yeast and human cells found essentially no requirement for EIF2A in global or uORF-mediated translation, even during integrated stress response activation [#14, #15]. Beyond initiation, EIF2A directly enhances SARS-CoV-2 programmed \\u22121 ribosomal frameshifting independently of initiation and preferentially binds CG-rich RNA, with a binding site near the frameshift element contacts on 18S rRNA [#12], antagonizes USP10-dependent rescue of 40S ribosomes during ribosome stalling in ribosome-associated quality control [#17], and supports a translation-independent role in centrosome orientation during cell migration via its C-terminal disordered region [#16]. EIF2A is dispensable for mammalian viability, but knockout mice develop metabolic syndrome features and altered immune cell populations [#5, #8]. The mammalian factor traces to the historically defined Co-eIF-2A activity, which stimulated and protected eIF-2 ternary complexes and Met-tRNAf binding to 40S ribosomes in reticulocyte lysates [#18, #20].\",\n  \"teleology\": [\n    {\n      \"year\": 1981,\n      \"claim\": \"Before the gene was molecularly defined, biochemistry asked whether a cofactor regulated eIF-2 ternary complex behavior; Co-eIF-2A was shown to stimulate and stabilize Met-tRNAf binding and to render it resistant to mRNA-mediated inhibition, establishing an early activity later attributed to EIF2A.\",\n      \"evidence\": \"antibody inhibition and in vitro ternary complex / Met-tRNAf binding assays with purified Co-eIF-2A from rabbit reticulocytes\",\n      \"pmids\": [\"7356618\", \"7372648\", \"6153053\", \"3888988\"],\n      \"confidence\": \"Medium\",\n      \"gaps\": [\"Molecular identity of the purified factor (reported as ~80 kDa) not definitively tied to the cloned EIF2A gene\", \"Mechanism inferred from lysate activity, not reconstitution with defined recombinant protein\"]\n    },\n    {\n      \"year\": 2002,\n      \"claim\": \"Whether mammalian eIF2A corresponded to a defined gene and participated in initiation was unresolved; cloning and yeast genetics defined the 585-residue single-chain protein, placed it on 40S/80S ribosomes, and showed a synthetic-sick interaction with eIF5B implicating it in initiation but not in GCN4 reinitiation.\",\n      \"evidence\": \"peptide sequencing, cDNA cloning, ribosome fractionation, and double-knockout/GCN4 reporter genetics in yeast\",\n      \"pmids\": [\"12133843\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Specific mRNA clients not identified\", \"Molecular basis of the eIF5B synthetic interaction unknown\"]\n    },\n    {\n      \"year\": 2011,\n      \"claim\": \"It was unknown how eIF2A supported translation when eIF2 is inactivated; HCV studies showed eIF2A binds the HCV IRES IIId domain directly and recruits Met-tRNAi to the 40S P site in an eIF2-independent manner, defining an alternative initiator-tRNA carrier activity.\",\n      \"evidence\": \"siRNA knockdown in HCV-infected cells, direct IRES-domain binding and toeprinting assays, polysome profiling\",\n      \"pmids\": [\"21556050\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Later contradicted in CRISPR-knockout HAP1 cells\", \"PKR-activation role not mechanistically resolved\"]\n    },\n    {\n      \"year\": 2016,\n      \"claim\": \"To test whether eIF2A-driven IRES translation extends to cellular mRNAs, c-Src work showed direct binding to its IRES stem-loop SL I and stress-specific Met-tRNAi loading that promotes proliferation, generalizing the alternative-initiation model to a host transcript.\",\n      \"evidence\": \"siRNA knockdown, in vitro IRES binding and toeprinting, bicistronic reporters and proliferation assays under stress\",\n      \"pmids\": [\"27899592\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Number of physiological cellular IRES clients unclear\", \"Stress-specificity mechanism not defined\"]\n    },\n    {\n      \"year\": 2016,\n      \"claim\": \"Whether eIF2A is essential in mammals was tested by gene-trap knockout, which yielded viable mice without gross phenotype, indicating it is not required for viability under standard conditions.\",\n      \"evidence\": \"gene-trap knockout mouse generation and phenotypic assessment\",\n      \"pmids\": [\"27686860\"],\n      \"confidence\": \"Medium\",\n      \"gaps\": [\"Subtle or stress-conditional phenotypes not examined in this study\", \"Molecular cause of dispensability unaddressed\"]\n    },\n    {\n      \"year\": 2018,\n      \"claim\": \"The proposed eIF2A role in viral IRES translation was directly challenged; clean CRISPR knockouts of eIF2A (and eIF2D) in HAP1 cells supported HCV IRES and Sindbis sgmRNA translation even with phosphorylated eIF2\\u03b1, contradicting the knockdown-based alternative-initiation reports.\",\n      \"evidence\": \"CRISPR/Cas9 single and double knockouts in HAP1 cells, IRES luciferase reporters under multiple stress inducers, viral protein synthesis assays\",\n      \"pmids\": [\"28240315\", \"29487587\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Discrepancy with knockdown studies unresolved\", \"Does not exclude a minor or transcript-restricted role\"]\n    },\n    {\n      \"year\": 2021,\n      \"claim\": \"Whether eIF2A drives non-canonical translation of repeat expansions was tested in myotonic dystrophy models, where eIF2A overexpression increased RAN translation of CCUG- and CAGG-derived products, partly dependent on phospho-eIF2\\u03b1.\",\n      \"evidence\": \"CRISPR-edited HEK293T lines (PKR-/-, PERK-/-, eIF2\\u03b1-S51A), eIF2A overexpression, RAN protein detection\",\n      \"pmids\": [\"33856033\"],\n      \"confidence\": \"Medium\",\n      \"gaps\": [\"Effect shown by overexpression, not endogenous requirement\", \"Direct mechanism of RAN initiation enhancement unmapped\"]\n    },\n    {\n      \"year\": 2021,\n      \"claim\": \"The organismal consequences of eIF2A loss were extended; knockout mice showed reduced lifespan, metabolic syndrome features, and altered thymic immune populations, with sex-specific effects, indicating physiological importance despite viability.\",\n      \"evidence\": \"eIF2A KO mouse metabolic phenotyping, lifespan analysis, flow cytometry, tunicamycin challenge\",\n      \"pmids\": [\"34665898\"],\n      \"confidence\": \"Medium\",\n      \"gaps\": [\"Molecular link between eIF2A loss and metabolic phenotype unknown\", \"No ER-stress-response difference observed, leaving mechanism unclear\"]\n    },\n    {\n      \"year\": 2021,\n      \"claim\": \"A conserved developmental requirement was uncovered in Drosophila, where the EIF2A ortholog is essential for spermatogenesis through sperm individualization and F-actin cone formation, with sex-specific splicing.\",\n      \"evidence\": \"null and hypomorphic transposon alleles, fertility assays, F-actin immunofluorescence in Drosophila\",\n      \"pmids\": [\"34278643\"],\n      \"confidence\": \"Medium\",\n      \"gaps\": [\"Whether this reflects a translational or non-translational role unknown\", \"Relevance to mammalian function not established\"]\n    },\n    {\n      \"year\": 2023,\n      \"claim\": \"The basis of eIF2A's broad inhibitory effect was defined by reconstitution: excess recombinant eIF2A binds purified 40S subunits and inhibits cap-dependent and all classes of IRES translation, with rescue by added 40S, establishing a 40S-sequestration mechanism.\",\n      \"evidence\": \"recombinant eIF2A purification, mammalian in vitro translation with multiple reporters/IRES types, 40S pull-down and supplementation rescue\",\n      \"pmids\": [\"37602404\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Physiological relevance of sequestration at endogenous levels unclear\", \"Binding interface on 40S not structurally defined\"]\n    },\n    {\n      \"year\": 2023,\n      \"claim\": \"Translation-independent and quality-control-adjacent activities emerged: eIF2A directly enhances SARS-CoV-2 \\u22121 frameshifting, binds CG-rich RNA near the FSE-ribosome contacts on 18S rRNA, and supports viral replication, separating a frameshifting role from initiation.\",\n      \"evidence\": \"genome-wide CRISPR screen, eIF2A KO frameshifting validation, viral replication assays, transcriptome-wide RNA-binding analysis\",\n      \"pmids\": [\"37581984\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Whether eIF2A acts at endogenous host frameshift sites unclear\", \"Structural basis of frameshift enhancement undefined\"]\n    },\n    {\n      \"year\": 2023,\n      \"claim\": \"eIF2A (with eIF2D) was shown to be required for IRES-independent translation of enteroviral genomes, supporting recombination when canonical IRES translation is disabled.\",\n      \"evidence\": \"IRES-inactivating viral mutants, siRNA knockdown of eIF2A and eIF2D, viral replication/recombination assays\",\n      \"pmids\": [\"36689548\"],\n      \"confidence\": \"Medium\",\n      \"gaps\": [\"Direct molecular role versus indirect effect not distinguished\", \"Knockdown-based, no reconstitution\"]\n    },\n    {\n      \"year\": 2024,\n      \"claim\": \"Whether eIF2A is a meaningful initiation factor in vivo was resolved at transcriptome scale; yeast ribosome profiling found no significant translational-efficiency dependence on eIF2A, even during eIF2\\u03b1 phosphorylation, narrowing its initiation role to possibly a single mRNA.\",\n      \"evidence\": \"genome-wide ribosome profiling of \\u0394eIF2A yeast under normal and starvation conditions\",\n      \"pmids\": [\"38266075\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Does not address non-initiation functions (frameshifting, RQC, centrosome)\", \"Species-specific differences from mammals not excluded\"]\n    },\n    {\n      \"year\": 2025,\n      \"claim\": \"The human ribosome-profiling counterpart confirmed minimal involvement of eIF2A in initiation and uORF control, including under ISR activation, consolidating the conclusion that eIF2A is not a general initiation factor.\",\n      \"evidence\": \"ribosome profiling and uORF/IRES luciferase reporters in eIF2A-depleted HeLa cells under ISR induction\",\n      \"pmids\": [\"40600802\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Specialized clients still possible but unidentified\", \"Mechanism of the rare dependent mRNAs not defined\"]\n    },\n    {\n      \"year\": 2025,\n      \"claim\": \"A translation-independent function was established: proximity labeling identified centrosomal proteins as major eIF2A partners, and eIF2A promotes centrosome composition and orientation during migration via its C-terminal disordered (mRNA-binding) region without requiring ongoing translation.\",\n      \"evidence\": \"TurboID interactome, co-localization imaging, depletion/migration assays, domain-deletion mutants, translation-inhibition controls\",\n      \"pmids\": [\"40749049\"],\n      \"confidence\": \"Medium\",\n      \"gaps\": [\"Mechanism of centrosome recruitment unknown\", \"How the disordered region acts at the centrosome unclear\"]\n    },\n    {\n      \"year\": 2025,\n      \"claim\": \"A role in ribosome-associated quality control was proposed: eIF2A binds near the 40S mRNA entry channel, interacts with G3BP1-USP10 and RPS2/RPS3, and antagonizes USP10-dependent 40S rescue, shaping 40S turnover upon stalling.\",\n      \"evidence\": \"TurboID + mass spectrometry, polysome gradients, dynamic SILAC, eIF2A KO cells, stalling and ubiquitination assays (preprint)\",\n      \"pmids\": [\"bio_10.1101_2025.05.22.655611\"],\n      \"confidence\": \"Medium\",\n      \"gaps\": [\"Preprint, not yet peer-reviewed\", \"Direct versus indirect antagonism of USP10 not resolved\", \"Structural detail of the 40S contact not defined\"]\n    },\n    {\n      \"year\": null,\n      \"claim\": \"Despite agreement that eIF2A is not a core initiation factor, the unifying molecular activity linking its 40S-binding, frameshift-enhancing, RQC, and centrosomal functions remains undefined.\",\n      \"evidence\": \"\",\n      \"pmids\": [],\n      \"confidence\": \"Medium\",\n      \"gaps\": [\"No structure of eIF2A on the 40S ribosome\", \"The identity and number of genuine endogenous mRNA clients unknown\", \"Whether RNA-binding underlies the centrosomal role is untested\"]\n    }\n  ],\n  \"mechanism_profile\": {\n    \"molecular_activity\": [\n      {\"term_id\": \"GO:0003723\", \"supporting_discovery_ids\": [3, 4, 12, 16]},\n      {\"term_id\": \"GO:0140110\", \"supporting_discovery_ids\": [11]},\n      {\"term_id\": \"GO:0140104\", \"supporting_discovery_ids\": [3, 4, 18]}\n    ],\n    \"localization\": [\n      {\"term_id\": \"GO:0005840\", \"supporting_discovery_ids\": [0, 11, 17]},\n      {\"term_id\": \"GO:0005815\", \"supporting_discovery_ids\": [16]}\n    ],\n    \"pathway\": [\n      {\"term_id\": \"R-HSA-72766\", \"supporting_discovery_ids\": [3, 4, 11]},\n      {\"term_id\": \"R-HSA-8953854\", \"supporting_discovery_ids\": [14, 15, 17]}\n    ],\n    \"complexes\": [],\n    \"partners\": [\"EEF1A1\", \"USP10\", \"G3BP1\", \"RPS2\", \"RPS3\", \"EIF2D\"],\n    \"other_free_text\": []\n  }\n}","audit_flag":null,"evaluation":{"pairwise":"loss","faith_supported":7,"faith_total":7,"faith_pct":100.0}}