{"gene":"CALM2","run_date":"2026-04-28T17:28:52","timeline":{"discoveries":[{"year":2013,"finding":"De novo heterozygous missense mutations in CALM1 and CALM2 (encoding calmodulin) reduce calcium binding affinity of the recombinant protein by several-fold. A CALM2 mutation (N97S in CALM2 context) also showed aberrant interaction with the RYR2 calmodulin-binding-domain peptide at low calcium concentrations, establishing that calmodulin mutations disrupt Ca2+ binding and alter RyR2 interactions, causing life-threatening ventricular arrhythmias in infants.","method":"Exome sequencing of parent-child trios; recombinant mutant calmodulin calcium binding affinity assays; calmodulin-binding-domain peptide interaction assays","journal":"Circulation","confidence":"High","confidence_rationale":"Tier 1–2 — in vitro calcium binding assays plus peptide interaction assays on recombinant protein; replicated across multiple mutation carriers","pmids":["23388215"],"is_preprint":false},{"year":2012,"finding":"Heterozygous missense mutations in CALM1 (encoding calmodulin) causing catecholaminergic polymorphic ventricular tachycardia demonstrate compromised calcium binding and aberrant interaction with the RYR2 calmodulin-binding-domain peptide at low calcium concentrations, establishing calmodulin genes (including CALM2 as a candidate) as genetic determinants of severe cardiac arrhythmia.","method":"Genome-wide linkage analysis; Sanger sequencing; recombinant calmodulin calcium binding assays; RYR2 calmodulin-binding-domain peptide interaction assays","journal":"American journal of human genetics","confidence":"High","confidence_rationale":"Tier 1–2 — biochemical assays on recombinant protein combined with genetic linkage; foundational mechanistic paper","pmids":["23040497"],"is_preprint":false},{"year":2016,"finding":"A novel CALM2 variant E141G reduces Ca2+ binding affinity of calmodulin by 11-fold and causes a dominant loss of inactivation of the cardiac L-type calcium channel (CaV1.2), mild accentuation of NaV1.5 late current, but no effect on intracellular RyR2-mediated calcium release, establishing channel-specific functional consequences of this CALM2 variant.","method":"Whole-exome sequencing; recombinant protein Ca2+ binding affinity assays; patch-clamp electrophysiology of CaV1.2, NaV1.5, and RyR2","journal":"Circulation. Cardiovascular genetics","confidence":"High","confidence_rationale":"Tier 1–2 — reconstituted biochemical assays plus multi-channel electrophysiology with orthogonal methods","pmids":["26969752"],"is_preprint":false},{"year":2017,"finding":"The CALM2-N98S mutation in hiPSC-derived cardiomyocytes causes significantly lower beating rates, prolonged action potential durations, and impaired inactivation of L-type Ca2+ channel (LTCC) currents compared with control cells. Allele-specific CRISPR-Cas9 knockout of the mutant allele rescued these electrophysiological abnormalities, demonstrating that the CALM2-N98S mutant allele acts in a dominant-negative manner to suppress LTCC inactivation and thereby prolong action potential duration.","method":"hiPSC differentiation into cardiomyocytes; patch-clamp electrophysiology (action potential recordings, LTCC current measurements); CRISPR-Cas9 allele-specific knockout","journal":"Human molecular genetics","confidence":"High","confidence_rationale":"Tier 1–2 — disease model with patch-clamp electrophysiology and genetic rescue (CRISPR), multiple orthogonal methods in human cardiomyocytes","pmids":["28335032"],"is_preprint":false},{"year":1997,"finding":"Calmodulin (encoded by CALM genes) wraps around the calmodulin-binding peptide M13 upon Ca2+ binding, increasing fluorescence resonance energy transfer (FRET) between flanking GFP variants. This conformational change was harnessed to create genetically encoded Ca2+ indicators ('cameleons') enabling real-time visualization of Ca2+ dynamics in specific subcellular compartments including cytosol, nucleus, and endoplasmic reticulum.","method":"Recombinant fusion protein construction; FRET measurements; transfection in HeLa cells; live-cell fluorescence microscopy; calmodulin mutagenesis to tune Ca2+ affinity","journal":"Nature","confidence":"High","confidence_rationale":"Tier 1 — reconstitution with mutagenesis and live-cell imaging; highly replicated foundational paper","pmids":["9278050"],"is_preprint":false},{"year":1998,"finding":"The CALM2 gene spans approximately 16 kb with intron interruptions at identical positions to CALM1 and CALM3. Its 5' flanking region contains a TATA-like sequence 27 nucleotides upstream of the transcriptional start site. In proliferating human teratoma cells, CALM3 is at least 5-fold more actively transcribed than CALM1 or CALM2, and the 5' untranslated regions are required for full promoter activation in luciferase reporter assays.","method":"Genomic library screening; genomic PCR; nuclear run-on transcription assays; luciferase reporter transfection assays; mRNA quantification","journal":"Cell calcium","confidence":"Medium","confidence_rationale":"Tier 2 — direct transcriptional activity measurements with nuclear run-on and reporter assays in a single cell line","pmids":["9681195"],"is_preprint":false},{"year":2024,"finding":"A suppression-and-replacement (SupRep) gene therapy construct simultaneously knocks down endogenous CALM1, CALM2, and CALM3 using gene-specific shRNAs (71% knockdown for CALM2) while delivering a shRNA-immune CALM1 replacement. In CALM2-D130G hiPSC-derived cardiomyocytes with pathologically prolonged APD90 (647±9 ms vs. 359±12 ms in WT), CALM-SupRep transfection shortened APD90 to 457±19 ms (66% attenuation), demonstrating proof-of-principle for gene therapy targeting CALM2-mediated long-QT syndrome.","method":"shRNA knockdown efficiency testing by RT-qPCR; voltage-sensing dye action potential measurements in hiPSC-derived cardiomyocytes; CALM2-D130G patient-derived iPSC lines","journal":"Circulation. Arrhythmia and electrophysiology","confidence":"Medium","confidence_rationale":"Tier 2 — functional electrophysiology rescue in patient-derived cardiomyocytes with quantitative APD measurements; single study","pmids":["39069900"],"is_preprint":false},{"year":2022,"finding":"Knockdown of CALM2 in HER2-amplified gastric cancer cells inhibits Akt signaling, which derepresses the FoxO3a/Puma axis, promoting mitochondrial apoptosis in a caspase-dependent manner and sensitizing cells to afatinib. Inhibition of either FoxO3a or Puma abrogated the pro-apoptotic effects of CALM2 knockdown, placing CALM2 upstream of the Akt–FoxO3a–Puma signaling cascade.","method":"siRNA knockdown of CALM2; Western blot for Akt phosphorylation, FoxO3a, Puma; caspase activity assays; flow cytometry for apoptosis; pharmacological inhibition of FoxO3a and Puma","journal":"Toxicology in vitro","confidence":"Medium","confidence_rationale":"Tier 2–3 — knockdown with pathway epistasis via pharmacological inhibitors; single lab study","pmids":["36460225"],"is_preprint":false},{"year":2021,"finding":"Knockdown of CALM2 in hepatocellular carcinoma (HCC) cells inhibits proliferation, colony formation, migration, and invasion, and reduces tumor formation in vivo. At the molecular level, CALM2-specific knockdown leads to downregulation of E2F transcription factor 5 (E2F5), which is functionally associated with migration, invasion, and proliferation, placing CALM2 upstream of E2F5-mediated cell cycle progression in HCC.","method":"siRNA knockdown of CALM2; transcriptomic profiling of dysregulated genes; cell proliferation and colony formation assays; migration/invasion assays; in vivo tumor formation; HCC clinical sample validation","journal":"Anticancer research","confidence":"Medium","confidence_rationale":"Tier 2–3 — loss-of-function with defined molecular pathway (E2F5 downregulation) and in vivo validation; single lab","pmids":["33788723"],"is_preprint":false},{"year":2021,"finding":"In cardiac myocytes subjected to oxygen-glucose deprivation (OGD), circ_0010729 acts as a sponge for miR-338-3p, which directly targets CALM2 mRNA. Knockdown of circ_0010729 increases miR-338-3p availability, reducing CALM2 expression and attenuating OGD-induced apoptosis and autophagy in AC16 cells, establishing CALM2 as a downstream effector in this non-coding RNA regulatory axis during cardiac ischemic injury.","method":"RT-qPCR and Western blot for CALM2 expression; dual-luciferase reporter assay validating miR-338-3p targeting of CALM2; siRNA knockdown; flow cytometry for apoptosis; cell viability assays","journal":"Journal of cardiovascular pharmacology","confidence":"Low","confidence_rationale":"Tier 3 — luciferase reporter validation of miRNA-target relationship; functional readouts limited to cell viability/apoptosis; single lab","pmids":["33951696"],"is_preprint":false},{"year":2019,"finding":"In post-myocardial infarction myocardial cells, GAS5 lncRNA acts as a sponge for miR-525-5p, which targets CALM2 mRNA. Overexpression of CALM2 promotes apoptosis and inhibits proliferation of myocardial cells, while miR-525-5p can reverse CALM2-induced MI effects. Dual luciferase reporter and RIP assays confirmed the targeting relationships among GAS5, miR-525-5p, and CALM2.","method":"RT-qPCR; Western blot; flow cytometry; MTT assay; dual luciferase reporter assay; RNA-binding protein immunoprecipitation (RIP); knockdown experiments","journal":"Journal of cellular biochemistry","confidence":"Low","confidence_rationale":"Tier 3 — luciferase and RIP validation of miRNA-target relationship; functional phenotype (apoptosis/proliferation) without deep pathway mechanistic follow-up; single lab","pmids":["31429119"],"is_preprint":false},{"year":2026,"finding":"RNA sequencing and ribosome profiling of left ventricular tissue show that CALM2 contributes approximately 44% of total calmodulin-coding mRNA (versus 37% for CALM1 and 21% for CALM3) and approximately 44% of calmodulin protein translation, making CALM1 and CALM2 the dominant sources of calmodulin in the human heart. This greater contribution of CALM2 relative to CALM3 explains why CALM3 missense variants are under less negative selection and cause less severe cardiac phenotypes.","method":"GTEx RNA sequencing data analysis; ribosome profiling of left ventricle; Genome Aggregation Database (gnomAD) observed-to-expected variant ratio analysis; International Calmodulinopathy Registry clinical outcomes","journal":"Europace","confidence":"Medium","confidence_rationale":"Tier 2 — quantitative transcriptomic and ribosome profiling data from large public datasets with population genetics validation; single analysis but uses multiple independent data sources","pmids":["41846582"],"is_preprint":false},{"year":2025,"finding":"LncRNA ABHD11-AS1 acts as a sponge for miR-876-5p, which targets CALM2 mRNA, in thyroid cancer cells. ABHD11-AS1 knockdown reduces CALM2 expression and inhibits migration, invasion, and EMT of thyroid cancer cells; these effects are counteracted by miR-876-5p inhibition or CALM2 overexpression, placing CALM2 downstream in the ABHD11-AS1/miR-876-5p/CALM2 regulatory axis promoting thyroid cancer metastasis.","method":"Scratch assay; transwell invasion assay; RT-qPCR; Western blot; dual-luciferase reporter assay; siRNA and overexpression approaches","journal":"Biochemical genetics","confidence":"Low","confidence_rationale":"Tier 3 — luciferase reporter validation of miRNA-target relationships; functional migration/invasion assays without deep mechanistic pathway characterization; single lab","pmids":["40117023"],"is_preprint":false}],"current_model":"CALM2 encodes one of three genes producing the identical calmodulin protein, contributing ~44% of cardiac calmodulin mRNA and protein; pathogenic CALM2 missense variants reduce Ca2+ binding affinity of calmodulin, impair inactivation of the cardiac L-type Ca2+ channel (CaV1.2) in a dominant-negative manner, and alter RyR2 interactions, causing long-QT syndrome and catecholaminergic polymorphic ventricular tachycardia, while in cancer contexts CALM2 acts upstream of Akt–FoxO3a–Puma and E2F5 pathways to regulate apoptosis and cell cycle progression."},"narrative":{"teleology":[{"year":1997,"claim":"The demonstration that calmodulin undergoes a large Ca²⁺-dependent conformational change around target peptides — sufficient to drive FRET between flanking fluorophores — established calmodulin as a bona fide intramolecular Ca²⁺ switch and enabled genetically encoded Ca²⁺ indicators for live-cell imaging.","evidence":"Recombinant calmodulin-M13 fusion protein with GFP variants; FRET measurements in HeLa cells","pmids":["9278050"],"confidence":"High","gaps":["This study used calmodulin generically without distinguishing contributions of CALM1, CALM2, or CALM3","Conformational dynamics on full-length channel targets were not assessed"]},{"year":1998,"claim":"Genomic characterization of CALM2 defined its gene structure, promoter elements, and relative transcriptional activity compared with CALM1 and CALM3, showing CALM2 was moderately transcribed in proliferating cells.","evidence":"Genomic library screening, nuclear run-on assays, and luciferase reporter assays in human teratoma cells","pmids":["9681195"],"confidence":"Medium","gaps":["Transcriptional analysis limited to a single teratoma cell line; tissue-specific regulation uncharacterized","Post-transcriptional control of CALM2 mRNA not addressed"]},{"year":2012,"claim":"Genetic linkage of calmodulin missense mutations to catecholaminergic polymorphic ventricular tachycardia, combined with biochemical evidence of reduced Ca²⁺ binding and aberrant RyR2 interaction, established calmodulin genes as direct genetic determinants of lethal cardiac arrhythmia.","evidence":"Genome-wide linkage in affected families; recombinant calmodulin Ca²⁺ binding and RYR2 peptide interaction assays","pmids":["23040497"],"confidence":"High","gaps":["Initial study focused on CALM1; CALM2 variants were identified shortly after but not in this cohort","Full-length RyR2 channel interaction not tested"]},{"year":2013,"claim":"De novo CALM2 missense mutations were directly shown to reduce Ca²⁺ binding affinity of recombinant calmodulin and alter RyR2 calmodulin-binding-domain interaction at low Ca²⁺, establishing CALM2-specific pathogenicity in infant arrhythmias.","evidence":"Exome sequencing of parent–child trios; recombinant protein Ca²⁺ affinity assays and RYR2 peptide binding","pmids":["23388215"],"confidence":"High","gaps":["Effects on L-type Ca²⁺ channel inactivation not yet tested for these specific CALM2 variants","Dominant-negative mechanism versus haploinsufficiency not resolved"]},{"year":2016,"claim":"The CALM2-E141G variant was shown to cause an 11-fold reduction in Ca²⁺ affinity and channel-specific consequences — dominant loss of CaV1.2 inactivation and mild NaV1.5 late current enhancement without RyR2 effects — revealing that individual CALM2 mutations differentially affect distinct ion channel targets.","evidence":"Recombinant protein Ca²⁺ binding assays; patch-clamp electrophysiology on CaV1.2, NaV1.5, and RyR2 in heterologous expression systems","pmids":["26969752"],"confidence":"High","gaps":["Mechanism by which the same Ca²⁺-binding deficit selectively affects CaV1.2 but not RyR2 is unknown","No structural data explaining variant-specific channel selectivity"]},{"year":2017,"claim":"CRISPR-Cas9 allele-specific knockout of the CALM2-N98S mutant allele in patient iPSC-derived cardiomyocytes rescued prolonged action potential duration and impaired L-type Ca²⁺ channel inactivation, definitively proving a dominant-negative mechanism for CALM2-linked long-QT syndrome.","evidence":"hiPSC-derived cardiomyocytes; patch-clamp action potential and LTCC current recordings; allele-specific CRISPR-Cas9 knockout","pmids":["28335032"],"confidence":"High","gaps":["Whether the dominant-negative mechanism generalizes to all CALM2 arrhythmia variants is untested","Stoichiometric threshold of mutant versus wild-type calmodulin required to produce pathology is unknown"]},{"year":2021,"claim":"CALM2 knockdown in hepatocellular carcinoma cells suppressed proliferation, migration, and in vivo tumor growth through downregulation of E2F5, positioning CALM2 as an upstream regulator of E2F5-dependent cell cycle progression in a cancer context.","evidence":"siRNA knockdown; transcriptomic profiling; proliferation and invasion assays; xenograft tumor formation","pmids":["33788723"],"confidence":"Medium","gaps":["Mechanistic link between calmodulin and E2F5 transcription not characterized","Whether calmodulin's Ca²⁺-sensing activity is required for E2F5 regulation is unknown"]},{"year":2022,"claim":"In HER2-amplified gastric cancer cells, CALM2 knockdown inhibited Akt phosphorylation, derepressing the FoxO3a–Puma apoptotic axis in a caspase-dependent manner, establishing CALM2 as an upstream activator of Akt-mediated survival signaling.","evidence":"siRNA knockdown; Western blot for phospho-Akt, FoxO3a, Puma; caspase assays; pharmacological epistasis experiments","pmids":["36460225"],"confidence":"Medium","gaps":["Whether calmodulin directly activates Akt or acts through CaMKK/CaMKII intermediaries is not resolved","Findings limited to a single cancer cell type"]},{"year":2024,"claim":"A suppression-and-replacement gene therapy strategy simultaneously knocking down all three CALM genes and replacing with shRNA-immune wild-type calmodulin partially rescued prolonged action potential duration in CALM2-D130G patient cardiomyocytes, providing proof-of-principle for therapeutic intervention in calmodulinopathy.","evidence":"shRNA knockdown with RT-qPCR validation; voltage-sensing dye APD measurements in CALM2-D130G hiPSC-derived cardiomyocytes","pmids":["39069900"],"confidence":"Medium","gaps":["Rescue was partial (66% attenuation); full APD normalization not achieved","In vivo efficacy and delivery to cardiomyocytes not tested","Long-term effects on total calmodulin protein levels not assessed"]},{"year":2025,"claim":"Ribosome profiling confirmed that CALM2 contributes ~44% of cardiac calmodulin protein translation, explaining why CALM2 variants cause more severe arrhythmia phenotypes than CALM3 variants and providing a quantitative basis for the genotype–phenotype relationship.","evidence":"GTEx RNA-seq; ribosome profiling of human left ventricle; gnomAD variant constraint analysis; International Calmodulinopathy Registry outcomes","pmids":["41846582"],"confidence":"Medium","gaps":["Whether translational contribution varies across cardiac chambers or developmental stages is unknown","Protein-level quantification of CALM2-derived calmodulin (indistinguishable from other CALM gene products) relies on ribosome profiling as a proxy"]},{"year":null,"claim":"Structural and biophysical understanding of how individual CALM2 missense variants differentially disrupt specific ion channel targets (CaV1.2 versus RyR2 versus NaV1.5) remains incomplete, and the stoichiometric threshold of mutant calmodulin required for dominant-negative pathology has not been determined.","evidence":"","pmids":[],"confidence":"High","gaps":["No high-resolution structure of mutant calmodulin bound to full-length CaV1.2 or RyR2","Quantitative dose-response for mutant-to-wild-type calmodulin ratio and electrophysiological phenotype not established","In vivo gene therapy efficacy for CALM2-linked arrhythmias untested"]}],"mechanism_profile":{"molecular_activity":[{"term_id":"GO:0098772","term_label":"molecular function regulator activity","supporting_discovery_ids":[0,1,2,3,4]},{"term_id":"GO:0140299","term_label":"molecular sensor activity","supporting_discovery_ids":[0,2,4]}],"localization":[{"term_id":"GO:0005829","term_label":"cytosol","supporting_discovery_ids":[4]}],"pathway":[{"term_id":"R-HSA-162582","term_label":"Signal Transduction","supporting_discovery_ids":[2,3,7]},{"term_id":"R-HSA-5357801","term_label":"Programmed Cell Death","supporting_discovery_ids":[7,8]},{"term_id":"R-HSA-1643685","term_label":"Disease","supporting_discovery_ids":[0,2,3,6]}],"complexes":[],"partners":["CACNA1C","RYR2","SCN5A","AKT1","E2F5"],"other_free_text":[]},"mechanistic_narrative":"CALM2 is one of three human genes (CALM1, CALM2, CALM3) encoding the identical calmodulin protein, a ubiquitous Ca²⁺ sensor that undergoes a conformational change upon Ca²⁺ binding to regulate diverse downstream targets including ion channels and kinases [PMID:9278050]. In the human heart, CALM2 contributes approximately 44% of total calmodulin mRNA and translated protein, making it a dominant source of cardiac calmodulin [PMID:41846582]. Heterozygous missense variants in CALM2 reduce Ca²⁺ binding affinity and impair Ca²⁺-dependent inactivation of the L-type Ca²⁺ channel (CaV1.2) in a dominant-negative manner, prolonging action potential duration and causing long-QT syndrome and catecholaminergic polymorphic ventricular tachycardia, with allele-specific CRISPR knockout rescuing the electrophysiological phenotype in patient-derived cardiomyocytes [PMID:23388215, PMID:26969752, PMID:28335032]. In cancer cell contexts, CALM2 knockdown inhibits Akt signaling to derepress the FoxO3a–Puma apoptotic axis and downregulates E2F5-mediated cell cycle progression [PMID:36460225, PMID:33788723]."},"prefetch_data":{"uniprot":{"accession":"P0DP24","full_name":"Calmodulin-2","aliases":[],"length_aa":149,"mass_kda":16.8,"function":"Calmodulin acts as part of a calcium signal transduction pathway by mediating the control of a large number of enzymes, ion channels, aquaporins and other proteins through calcium-binding (PubMed:16760425, PubMed:26969752, PubMed:27165696). Calcium-binding is required for the activation of calmodulin (PubMed:16760425, PubMed:26969752, PubMed:27165696, PubMed:35568036). Among the enzymes to be stimulated by the calmodulin-calcium complex are a number of protein kinases, such as myosin light-chain kinases and calmodulin-dependent protein kinase type II (CaMK2), and phosphatases (PubMed:16760425, PubMed:26969752, PubMed:27165696, PubMed:35568036). Together with CCP110 and centrin, is involved in a genetic pathway that regulates the centrosome cycle and progression through cytokinesis (PubMed:16760425). Mediates calcium-dependent inactivation of CACNA1C (PubMed:26969752). Positively regulates calcium-activated potassium channel activity of KCNN2 (PubMed:27165696) (Microbial infection) Required for C.violaceum CopC and S.flexneri OspC3 arginine ADP-riboxanase activity","subcellular_location":"Cytoplasm, cytoskeleton, spindle; Cytoplasm, cytoskeleton, spindle pole; Cytoplasm, cytoskeleton, microtubule organizing center, centrosome","url":"https://www.uniprot.org/uniprotkb/P0DP24/entry"},"depmap":{"release":"DepMap","has_data":true,"is_common_essential":false,"resolved_as":"","url":"https://depmap.org/portal/gene/CALM2","classification":"Not Classified","n_dependent_lines":37,"n_total_lines":1208,"dependency_fraction":0.030629139072847682},"opencell":{"profiled":true,"resolved_as":"","ensg_id":"ENSG00000143933","cell_line_id":"CID000512","localizations":[{"compartment":"centrosome","grade":3},{"compartment":"membrane","grade":3},{"compartment":"cytoplasmic","grade":2},{"compartment":"nucleoplasm","grade":2},{"compartment":"cell_contact","grade":1}],"interactors":[{"gene":"CALM2;CALM3;CALM1","stoichiometry":10.0},{"gene":"MYL6","stoichiometry":10.0},{"gene":"SCO1","stoichiometry":0.2},{"gene":"KIF1B","stoichiometry":0.2},{"gene":"TOM1","stoichiometry":0.2},{"gene":"PCNT","stoichiometry":0.2},{"gene":"MYO9B","stoichiometry":0.2},{"gene":"MYO1D","stoichiometry":0.2},{"gene":"CCP110","stoichiometry":0.2},{"gene":"ZNF536","stoichiometry":0.2}],"url":"https://opencell.sf.czbiohub.org/target/CID000512","total_profiled":1310},"omim":[{"mim_id":"618782","title":"LONG QT SYNDROME 16; LQT16","url":"https://www.omim.org/entry/618782"},{"mim_id":"616249","title":"LONG QT SYNDROME 15; LQT15","url":"https://www.omim.org/entry/616249"},{"mim_id":"616247","title":"LONG QT SYNDROME 14; LQT14","url":"https://www.omim.org/entry/616247"},{"mim_id":"302020","title":"S100 CALCIUM-BINDING PROTEIN G; S100G","url":"https://www.omim.org/entry/302020"},{"mim_id":"300798","title":"PHOSPHORYLASE KINASE, LIVER, ALPHA-2 SUBUNIT; PHKA2","url":"https://www.omim.org/entry/300798"}],"hpa":{"profiled":true,"resolved_as":"","reliability":"","locations":[],"tissue_specificity":"Low tissue specificity","tissue_distribution":"Detected in all","driving_tissues":[],"url":"https://www.proteinatlas.org/search/CALM2"},"hgnc":{"alias_symbol":["PHKD","PHKD2","CAMII"],"prev_symbol":[]},"alphafold":{"accession":"P0DP24","domains":[{"cath_id":"1.10.238.10","chopping":"1-78","consensus_level":"high","plddt":84.5077,"start":1,"end":78},{"cath_id":"1.10.238.10","chopping":"94-146","consensus_level":"high","plddt":91.3345,"start":94,"end":146}],"viewer_url":"https://alphafold.ebi.ac.uk/entry/P0DP24","model_url":"https://alphafold.ebi.ac.uk/files/AF-P0DP24-F1-model_v6.cif","pae_url":"https://alphafold.ebi.ac.uk/files/AF-P0DP24-F1-predicted_aligned_error_v6.png","plddt_mean":85.81},"mouse_models":{"mgi_url":"https://www.informatics.jax.org/marker/summary?nomen=CALM2","jax_strain_url":"https://www.jax.org/strain/search?query=CALM2"},"sequence":{"accession":"P0DP24","fasta_url":"https://rest.uniprot.org/uniprotkb/P0DP24.fasta","uniprot_url":"https://www.uniprot.org/uniprotkb/P0DP24/entry","alphafold_viewer_url":"https://alphafold.ebi.ac.uk/entry/P0DP24"}},"corpus_meta":[{"pmid":"26969752","id":"PMC_26969752","title":"Spectrum and Prevalence of CALM1-, CALM2-, and CALM3-Encoded Calmodulin Variants in Long QT Syndrome and Functional Characterization of a Novel Long QT Syndrome-Associated Calmodulin Missense Variant, E141G.","date":"2016","source":"Circulation. Cardiovascular genetics","url":"https://pubmed.ncbi.nlm.nih.gov/26969752","citation_count":109,"is_preprint":false,"source_track":"pubmed_title"},{"pmid":"8314583","id":"PMC_8314583","title":"Localization of the human bona fide calmodulin genes CALM1, CALM2, and CALM3 to chromosomes 14q24-q31, 2p21.1-p21.3, and 19q13.2-q13.3.","date":"1993","source":"Genomics","url":"https://pubmed.ncbi.nlm.nih.gov/8314583","citation_count":80,"is_preprint":false,"source_track":"pubmed_title"},{"pmid":"28335032","id":"PMC_28335032","title":"Allele-specific ablation rescues electrophysiological abnormalities in a human iPS cell model of long-QT syndrome with a CALM2 mutation.","date":"2017","source":"Human molecular genetics","url":"https://pubmed.ncbi.nlm.nih.gov/28335032","citation_count":72,"is_preprint":false,"source_track":"pubmed_title"},{"pmid":"9681195","id":"PMC_9681195","title":"Characterization of the human CALM2 calmodulin gene and comparison of the transcriptional activity of CALM1, CALM2 and CALM3.","date":"1998","source":"Cell calcium","url":"https://pubmed.ncbi.nlm.nih.gov/9681195","citation_count":61,"is_preprint":false,"source_track":"pubmed_title"},{"pmid":"31429119","id":"PMC_31429119","title":"lncRNA GAS5 regulates myocardial infarction by targeting the miR-525-5p/CALM2 axis.","date":"2019","source":"Journal of cellular biochemistry","url":"https://pubmed.ncbi.nlm.nih.gov/31429119","citation_count":37,"is_preprint":false,"source_track":"pubmed_title"},{"pmid":"16351635","id":"PMC_16351635","title":"High expression of calcium-binding proteins, S100A10, S100A11 and CALM2 in anaplastic large cell lymphoma.","date":"2005","source":"British journal of haematology","url":"https://pubmed.ncbi.nlm.nih.gov/16351635","citation_count":36,"is_preprint":false,"source_track":"pubmed_title"},{"pmid":"30317608","id":"PMC_30317608","title":"Identification of TAF1, HNF4A, and CALM2 as potential therapeutic target genes for liver fibrosis.","date":"2018","source":"Journal of cellular physiology","url":"https://pubmed.ncbi.nlm.nih.gov/30317608","citation_count":28,"is_preprint":false,"source_track":"pubmed_title"},{"pmid":"1999288","id":"PMC_1999288","title":"Characterization of two novel human retropseudogenes related to the calmodulin-encoding gene, CaMII.","date":"1991","source":"Gene","url":"https://pubmed.ncbi.nlm.nih.gov/1999288","citation_count":23,"is_preprint":false,"source_track":"pubmed_title"},{"pmid":"20198394","id":"PMC_20198394","title":"Identification of sequence polymorphisms in CALM2 and analysis of association with hip osteoarthritis in a Japanese population.","date":"2010","source":"Journal of bone and mineral metabolism","url":"https://pubmed.ncbi.nlm.nih.gov/20198394","citation_count":14,"is_preprint":false,"source_track":"pubmed_title"},{"pmid":"25009623","id":"PMC_25009623","title":"Investigation into the promoter DNA methylation of three genes (CAMK1D, CRY2 and CALM2) in the peripheral blood of patients with type 2 diabetes.","date":"2014","source":"Experimental and therapeutic medicine","url":"https://pubmed.ncbi.nlm.nih.gov/25009623","citation_count":13,"is_preprint":false,"source_track":"pubmed_title"},{"pmid":"31283864","id":"PMC_31283864","title":"Long QT syndrome with a de novo CALM2 mutation in a 4-year-old boy.","date":"2019","source":"Pediatrics international : official journal of the Japan Pediatric Society","url":"https://pubmed.ncbi.nlm.nih.gov/31283864","citation_count":13,"is_preprint":false,"source_track":"pubmed_title"},{"pmid":"36460225","id":"PMC_36460225","title":"Knockdown of CALM2 increases the sensitivity to afatinib in HER2-amplified gastric cancer cells by regulating the Akt/FoxO3a/Puma axis.","date":"2022","source":"Toxicology in vitro : an international journal published in association with BIBRA","url":"https://pubmed.ncbi.nlm.nih.gov/36460225","citation_count":12,"is_preprint":false,"source_track":"pubmed_title"},{"pmid":"39069900","id":"PMC_39069900","title":"Single Construct Suppression and Replacement Gene Therapy for the Treatment of All CALM1-, CALM2-, and CALM3-Mediated Arrhythmia Disorders.","date":"2024","source":"Circulation. Arrhythmia and electrophysiology","url":"https://pubmed.ncbi.nlm.nih.gov/39069900","citation_count":11,"is_preprint":false,"source_track":"pubmed_title"},{"pmid":"33788723","id":"PMC_33788723","title":"Targeting CALM2 Inhibits Hepatocellular Carcinoma Growth and Metastasis by Suppressing E2F5-mediated Cell Cycle Progression.","date":"2021","source":"Anticancer research","url":"https://pubmed.ncbi.nlm.nih.gov/33788723","citation_count":10,"is_preprint":false,"source_track":"pubmed_title"},{"pmid":"33951696","id":"PMC_33951696","title":"Circular RNA circ_0010729 Knockdown Attenuates Oxygen-Glucose Deprivation-Induced Human Cardiac Myocytes Injury by miR-338-3p/CALM2 Axis.","date":"2021","source":"Journal of cardiovascular pharmacology","url":"https://pubmed.ncbi.nlm.nih.gov/33951696","citation_count":6,"is_preprint":false,"source_track":"pubmed_title"},{"pmid":"39104518","id":"PMC_39104518","title":"A rare case report of catecholaminergic polymorphic ventricular tachycardia with an uncommon CALM2 mutation.","date":"2024","source":"European heart journal. Case reports","url":"https://pubmed.ncbi.nlm.nih.gov/39104518","citation_count":2,"is_preprint":false,"source_track":"pubmed_title"},{"pmid":"36507129","id":"PMC_36507129","title":"Case report: Prenatal diagnosis of fetal non-compaction cardiomyopathy with bradycardia accompanied by de novo CALM2 mutation.","date":"2022","source":"Frontiers in pediatrics","url":"https://pubmed.ncbi.nlm.nih.gov/36507129","citation_count":1,"is_preprint":false,"source_track":"pubmed_title"},{"pmid":"39137556","id":"PMC_39137556","title":"Generation of a human induced pluripotent stem cell line ZZUNEUi030-A from a female patient carrying a heterozygous CALM2 (c.395 A > T) mutation.","date":"2024","source":"Stem cell research","url":"https://pubmed.ncbi.nlm.nih.gov/39137556","citation_count":0,"is_preprint":false,"source_track":"pubmed_title"},{"pmid":"40117023","id":"PMC_40117023","title":"LncRNA ABHD11-AS1 Elevates CALM2 to Promote Metastasis of Thyroid Cancer Through Sponging miR-876-5p.","date":"2025","source":"Biochemical genetics","url":"https://pubmed.ncbi.nlm.nih.gov/40117023","citation_count":0,"is_preprint":false,"source_track":"pubmed_title"},{"pmid":"41846582","id":"PMC_41846582","title":"CALM1, CALM2, and CALM3 expression and translation efficiency provide insight into the severity of calmodulinopathy.","date":"2026","source":"Europace : European pacing, arrhythmias, and cardiac electrophysiology : journal of the working groups on cardiac pacing, arrhythmias, and cardiac cellular electrophysiology of the European Society of Cardiology","url":"https://pubmed.ncbi.nlm.nih.gov/41846582","citation_count":0,"is_preprint":false,"source_track":"pubmed_title"},{"pmid":"41665141","id":"PMC_41665141","title":"The first case of a Caucasian child with calmodulinopathy related to CALM2 N98S mutation.","date":"2026","source":"Cardiology in the young","url":"https://pubmed.ncbi.nlm.nih.gov/41665141","citation_count":0,"is_preprint":false,"source_track":"pubmed_title"},{"pmid":"41550621","id":"PMC_41550621","title":"Long-term follow-up of patients with catecholaminergic polymorphic ventricular tachycardia related to a novel CALM2 variant.","date":"2025","source":"Journal of cardiology cases","url":"https://pubmed.ncbi.nlm.nih.gov/41550621","citation_count":0,"is_preprint":false,"source_track":"pubmed_title"},{"pmid":null,"id":"bio_10.1101_2025.05.15.25327594","title":"<i>CALM1, CALM2,</i>and<i>CALM3</i>expression and translation efficiency provide insight into the severity of calmodulinopathy","date":"2025-05-15","source":"bioRxiv","url":"https://doi.org/10.1101/2025.05.15.25327594","citation_count":0,"is_preprint":true,"source_track":"pubmed_title"},{"pmid":null,"id":"bio_10.1101_2025.07.10.663151","title":"Early-life stress as a potential resilience factor in king penguins","date":"2025-07-11","source":"bioRxiv","url":"https://doi.org/10.1101/2025.07.10.663151","citation_count":0,"is_preprint":true,"source_track":"pubmed_title"},{"pmid":"9278050","id":"PMC_9278050","title":"Fluorescent indicators for Ca2+ based on green fluorescent proteins and calmodulin.","date":"1997","source":"Nature","url":"https://pubmed.ncbi.nlm.nih.gov/9278050","citation_count":2324,"is_preprint":false,"source_track":"gene2pubmed"},{"pmid":"16189514","id":"PMC_16189514","title":"Towards a proteome-scale map of the human protein-protein interaction network.","date":"2005","source":"Nature","url":"https://pubmed.ncbi.nlm.nih.gov/16189514","citation_count":2090,"is_preprint":false,"source_track":"gene2pubmed"},{"pmid":"16169070","id":"PMC_16169070","title":"A human protein-protein interaction network: a resource for annotating the proteome.","date":"2005","source":"Cell","url":"https://pubmed.ncbi.nlm.nih.gov/16169070","citation_count":1704,"is_preprint":false,"source_track":"gene2pubmed"},{"pmid":"12477932","id":"PMC_12477932","title":"Generation and initial analysis of more than 15,000 full-length human and mouse cDNA sequences.","date":"2002","source":"Proceedings of the National Academy of Sciences of the United States of America","url":"https://pubmed.ncbi.nlm.nih.gov/12477932","citation_count":1479,"is_preprint":false,"source_track":"gene2pubmed"},{"pmid":"25416956","id":"PMC_25416956","title":"A proteome-scale map of the human interactome network.","date":"2014","source":"Cell","url":"https://pubmed.ncbi.nlm.nih.gov/25416956","citation_count":977,"is_preprint":false,"source_track":"gene2pubmed"},{"pmid":"32296183","id":"PMC_32296183","title":"A reference map of the human binary protein interactome.","date":"2020","source":"Nature","url":"https://pubmed.ncbi.nlm.nih.gov/32296183","citation_count":849,"is_preprint":false,"source_track":"gene2pubmed"},{"pmid":"14743216","id":"PMC_14743216","title":"A physical and functional map of the human TNF-alpha/NF-kappa B signal transduction pathway.","date":"2004","source":"Nature cell biology","url":"https://pubmed.ncbi.nlm.nih.gov/14743216","citation_count":841,"is_preprint":false,"source_track":"gene2pubmed"},{"pmid":"14702039","id":"PMC_14702039","title":"Complete sequencing and characterization of 21,243 full-length human cDNAs.","date":"2003","source":"Nature genetics","url":"https://pubmed.ncbi.nlm.nih.gov/14702039","citation_count":754,"is_preprint":false,"source_track":"gene2pubmed"},{"pmid":"17353931","id":"PMC_17353931","title":"Large-scale mapping of human protein-protein interactions by mass spectrometry.","date":"2007","source":"Molecular systems biology","url":"https://pubmed.ncbi.nlm.nih.gov/17353931","citation_count":733,"is_preprint":false,"source_track":"gene2pubmed"},{"pmid":"22939629","id":"PMC_22939629","title":"A census of human soluble protein complexes.","date":"2012","source":"Cell","url":"https://pubmed.ncbi.nlm.nih.gov/22939629","citation_count":689,"is_preprint":false,"source_track":"gene2pubmed"},{"pmid":"21873635","id":"PMC_21873635","title":"Phylogenetic-based propagation of functional annotations within the Gene Ontology consortium.","date":"2011","source":"Briefings in bioinformatics","url":"https://pubmed.ncbi.nlm.nih.gov/21873635","citation_count":656,"is_preprint":false,"source_track":"gene2pubmed"},{"pmid":"21565611","id":"PMC_21565611","title":"Mapping the NPHP-JBTS-MKS protein network reveals ciliopathy disease genes and pathways.","date":"2011","source":"Cell","url":"https://pubmed.ncbi.nlm.nih.gov/21565611","citation_count":507,"is_preprint":false,"source_track":"gene2pubmed"},{"pmid":"26638075","id":"PMC_26638075","title":"A Dynamic Protein Interaction Landscape of the Human Centrosome-Cilium Interface.","date":"2015","source":"Cell","url":"https://pubmed.ncbi.nlm.nih.gov/26638075","citation_count":433,"is_preprint":false,"source_track":"gene2pubmed"},{"pmid":"35271311","id":"PMC_35271311","title":"OpenCell: Endogenous tagging for the cartography of human cellular organization.","date":"2022","source":"Science (New York, N.Y.)","url":"https://pubmed.ncbi.nlm.nih.gov/35271311","citation_count":432,"is_preprint":false,"source_track":"gene2pubmed"},{"pmid":"11980920","id":"PMC_11980920","title":"DAP kinase and DRP-1 mediate membrane blebbing and the formation of autophagic vesicles during programmed cell death.","date":"2002","source":"The Journal of cell biology","url":"https://pubmed.ncbi.nlm.nih.gov/11980920","citation_count":408,"is_preprint":false,"source_track":"gene2pubmed"},{"pmid":"17719545","id":"PMC_17719545","title":"Cep97 and CP110 suppress a cilia assembly program.","date":"2007","source":"Cell","url":"https://pubmed.ncbi.nlm.nih.gov/17719545","citation_count":386,"is_preprint":false,"source_track":"gene2pubmed"},{"pmid":"17620599","id":"PMC_17620599","title":"Functional specialization of beta-arrestin interactions revealed by proteomic analysis.","date":"2007","source":"Proceedings of the National Academy of Sciences of the United States of America","url":"https://pubmed.ncbi.nlm.nih.gov/17620599","citation_count":360,"is_preprint":false,"source_track":"gene2pubmed"},{"pmid":"21726808","id":"PMC_21726808","title":"Acetylation regulates gluconeogenesis by promoting PEPCK1 degradation via recruiting the UBR5 ubiquitin ligase.","date":"2011","source":"Molecular cell","url":"https://pubmed.ncbi.nlm.nih.gov/21726808","citation_count":337,"is_preprint":false,"source_track":"gene2pubmed"},{"pmid":"17582331","id":"PMC_17582331","title":"The ankyrin repeats of TRPV1 bind multiple ligands and modulate channel sensitivity.","date":"2007","source":"Neuron","url":"https://pubmed.ncbi.nlm.nih.gov/17582331","citation_count":334,"is_preprint":false,"source_track":"gene2pubmed"},{"pmid":"11807546","id":"PMC_11807546","title":"Structural basis for the activation of anthrax adenylyl cyclase exotoxin by calmodulin.","date":"2002","source":"Nature","url":"https://pubmed.ncbi.nlm.nih.gov/11807546","citation_count":323,"is_preprint":false,"source_track":"gene2pubmed"},{"pmid":"21145461","id":"PMC_21145461","title":"Dynamics of cullin-RING ubiquitin ligase network revealed by systematic quantitative proteomics.","date":"2010","source":"Cell","url":"https://pubmed.ncbi.nlm.nih.gov/21145461","citation_count":318,"is_preprint":false,"source_track":"gene2pubmed"},{"pmid":"15723066","id":"PMC_15723066","title":"Nephrocystin-5, a ciliary IQ domain protein, is mutated in Senior-Loken syndrome and interacts with RPGR and calmodulin.","date":"2005","source":"Nature genetics","url":"https://pubmed.ncbi.nlm.nih.gov/15723066","citation_count":311,"is_preprint":false,"source_track":"gene2pubmed"},{"pmid":"23388215","id":"PMC_23388215","title":"Calmodulin mutations associated with recurrent cardiac arrest in infants.","date":"2013","source":"Circulation","url":"https://pubmed.ncbi.nlm.nih.gov/23388215","citation_count":308,"is_preprint":false,"source_track":"gene2pubmed"},{"pmid":"23040497","id":"PMC_23040497","title":"Mutations in calmodulin cause ventricular tachycardia and sudden cardiac death.","date":"2012","source":"American journal of human genetics","url":"https://pubmed.ncbi.nlm.nih.gov/23040497","citation_count":296,"is_preprint":false,"source_track":"gene2pubmed"},{"pmid":"17640527","id":"PMC_17640527","title":"AKAP79/150 anchoring of calcineurin controls neuronal L-type Ca2+ channel activity and nuclear signaling.","date":"2007","source":"Neuron","url":"https://pubmed.ncbi.nlm.nih.gov/17640527","citation_count":284,"is_preprint":false,"source_track":"gene2pubmed"},{"pmid":"19190083","id":"PMC_19190083","title":"Characterization of exosome-like vesicles released from human tracheobronchial ciliated epithelium: a possible role in innate defense.","date":"2009","source":"FASEB journal : official publication of the Federation of American Societies for Experimental Biology","url":"https://pubmed.ncbi.nlm.nih.gov/19190083","citation_count":284,"is_preprint":false,"source_track":"gene2pubmed"},{"pmid":"30110629","id":"PMC_30110629","title":"Enhancer Activity Requires CBP/P300 Bromodomain-Dependent Histone H3K27 Acetylation.","date":"2018","source":"Cell reports","url":"https://pubmed.ncbi.nlm.nih.gov/30110629","citation_count":274,"is_preprint":false,"source_track":"gene2pubmed"},{"pmid":"8631904","id":"PMC_8631904","title":"Calcineurin binds the transcription factor NFAT1 and reversibly regulates its activity.","date":"1996","source":"The Journal of biological chemistry","url":"https://pubmed.ncbi.nlm.nih.gov/8631904","citation_count":253,"is_preprint":false,"source_track":"gene2pubmed"},{"pmid":"20458337","id":"PMC_20458337","title":"MHC class II-associated proteins in B-cell exosomes and potential functional implications for exosome biogenesis.","date":"2010","source":"Immunology and cell biology","url":"https://pubmed.ncbi.nlm.nih.gov/20458337","citation_count":221,"is_preprint":false,"source_track":"gene2pubmed"},{"pmid":"18694559","id":"PMC_18694559","title":"CP110 suppresses primary cilia formation through its interaction with CEP290, a protein deficient in human ciliary disease.","date":"2008","source":"Developmental cell","url":"https://pubmed.ncbi.nlm.nih.gov/18694559","citation_count":220,"is_preprint":false,"source_track":"gene2pubmed"}],"cost":{"stage1":{"model":"claude-sonnet-4-6","input_tokens":13305,"output_tokens":1803,"usd":0.03348},"stage2":{"model":"claude-opus-4-6","input_tokens":5055,"output_tokens":2066,"usd":0.115388},"total_usd":0.514416,"stage1_batch_id":"msgbatch_011kfMfE81o6CTcyhVUqumuW","stage2_batch_id":"msgbatch_01DTputS6WNkH745x1nVSoBo","note":"batch pricing = 50% of standard","round2_stage1":{"model":"claude-sonnet-4-6","input_tokens":25499,"output_tokens":5590,"usd":0.080173},"round2_rules_fired":"R3","round2_stage2":{"model":"claude-opus-4-6","input_tokens":7465,"output_tokens":6117,"usd":0.285375}},"stage1_raw":"```json\n{\n  \"discoveries\": [\n    {\n      \"year\": 2016,\n      \"finding\": \"The CALM2-encoded calmodulin variant E141G reduces Ca2+ binding affinity by 11-fold and causes loss of inactivation of the cardiac L-type calcium channel (CaV1.2) in a functionally dominant manner, with mild accentuation of NaV1.5 late current but no effect on RyR2-mediated intracellular calcium release.\",\n      \"method\": \"Patch-clamp electrophysiology, Ca2+-binding affinity assays, functional characterization in heterologous expression systems\",\n      \"journal\": \"Circulation. Cardiovascular genetics\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 1-2 — multiple orthogonal functional assays (Ca2+ binding, CaV1.2 inactivation, NaV1.5, RyR2) in a single rigorous study\",\n      \"pmids\": [\"26969752\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2017,\n      \"finding\": \"The CALM2-N98S mutation causes dominant-negative suppression of L-type Ca2+ channel (LTCC) inactivation in human cardiomyocytes, resulting in prolonged action potential duration; allele-specific CRISPR-Cas9 knockout of the mutant allele rescued electrophysiological abnormalities.\",\n      \"method\": \"hiPSC-derived cardiomyocytes, patch-clamp electrophysiology, CRISPR-Cas9 allele-specific knockout\",\n      \"journal\": \"Human molecular genetics\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 — clean genetic rescue (allele-specific KO) with electrophysiological phenotypic readout in human cardiomyocytes, multiple orthogonal methods\",\n      \"pmids\": [\"28335032\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2022,\n      \"finding\": \"CALM2 knockdown in HER2-amplified gastric cancer cells promotes mitochondrial apoptosis in a caspase-dependent manner by inhibiting Akt signaling, which de-represses the FoxO3a/Puma axis; inhibition of either FoxO3a or Puma abrogates the apoptotic effect of CALM2 knockdown.\",\n      \"method\": \"siRNA knockdown, Western blot, epistasis via FoxO3a/Puma inhibition, apoptosis assays\",\n      \"journal\": \"Toxicology in vitro\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2-3 — genetic epistasis with two pathway components and caspase-dependence assay in a single lab study\",\n      \"pmids\": [\"36460225\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2021,\n      \"finding\": \"CALM2 knockdown in hepatocellular carcinoma cells suppresses E2F5 transcription factor expression, reduces cell migration, invasion, and proliferation, and abrogates tumor formation in vivo, placing CALM2 upstream of an E2F5-mediated cell cycle/metastasis program.\",\n      \"method\": \"siRNA knockdown, transcriptomic profiling, in vitro migration/invasion assays, in vivo tumor formation assay\",\n      \"journal\": \"Anticancer research\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2-3 — loss-of-function with defined downstream target (E2F5) and in vivo validation, single lab\",\n      \"pmids\": [\"33788723\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2024,\n      \"finding\": \"A suppression-and-replacement gene therapy (CALM-SupRep) using CALM2-targeting shRNA (71% knockdown) combined with a shRNA-immune CALM1 cDNA replacement significantly shortened pathologically prolonged action potential duration (APD90) in CALM2-D130G patient-derived hiPSC-cardiomyocytes, demonstrating that selective suppression of mutant CALM2 and replacement with wild-type calmodulin rescues the electrophysiological defect.\",\n      \"method\": \"shRNA knockdown, hiPSC-derived cardiomyocytes, voltage-sensing dye action potential measurements\",\n      \"journal\": \"Circulation. Arrhythmia and electrophysiology\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 — functional rescue in patient-derived human cardiomyocytes with quantitative APD readout, single lab\",\n      \"pmids\": [\"39069900\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 1998,\n      \"finding\": \"CALM2 gene structure was resolved: intron interruptions occur at identical positions as in CALM1 and CALM3, CALM2 spans ~16 kb (nearly twice the size of CALM1/CALM3), contains a TATA-like sequence 27 nt upstream of the transcription start site, and CALM3 is at least 5-fold more actively transcribed than CALM1 or CALM2 in proliferating teratoma cells; the 5' UTR is required for full promoter activation.\",\n      \"method\": \"Genomic library screening, genomic PCR, luciferase reporter assays, transcriptional activity measurements\",\n      \"journal\": \"Cell calcium\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 — direct transcriptional assays with reporter constructs and endogenous mRNA quantification\",\n      \"pmids\": [\"9681195\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2021,\n      \"finding\": \"circ_0010729 acts as a sponge for miR-338-3p, which directly targets CALM2; circ_0010729 knockdown reduces CALM2 expression via miR-338-3p de-repression and attenuates OGD-induced apoptosis and autophagy in cardiac myocytes.\",\n      \"method\": \"Dual-luciferase reporter assay, siRNA knockdown, flow cytometry apoptosis assay, Western blot\",\n      \"journal\": \"Journal of cardiovascular pharmacology\",\n      \"confidence\": \"Low\",\n      \"confidence_rationale\": \"Tier 3 — single lab, luciferase reporter + knockdown, no direct mechanistic dissection of CALM2 function\",\n      \"pmids\": [\"33951696\"],\n      \"is_preprint\": false\n    }\n  ],\n  \"current_model\": \"CALM2-encoded calmodulin functions as a Ca2+ sensor whose pathogenic missense variants (e.g., N98S, E141G, D130G) reduce Ca2+ binding affinity and dominantly suppress L-type Ca2+ channel (CaV1.2) inactivation in cardiomyocytes, prolonging action potential duration and causing arrhythmia (LQT15/CPVT); in cancer cells, CALM2 promotes survival by sustaining Akt signaling to suppress the FoxO3a/Puma apoptotic axis and by maintaining E2F5-driven cell cycle progression.\"\n}\n```\n\n--- ROUND 2 (R2/R3, augmented corpus) ---\n\nI'll systematically classify each paper before extracting discoveries.\n\n**Classification:**\n\n**Retrieved Papers:**\n1. PMID:26969752 - CALM2 variants in LQTS, functional characterization of E141G — KEEP\n2. PMID:8314583 - Chromosomal localization of CALM1/2/3 — KEEP (genomic, minimal mechanism)\n3. PMID:28335032 - CALM2-N98S hiPSC model, allele-specific ablation — KEEP\n4. PMID:9681195 - CALM2 gene characterization, transcriptional activity — KEEP\n5. PMID:31429119 - lncRNA GAS5/miR-525-5p/CALM2 axis in MI — KEEP (involves CALM2 protein)\n6. PMID:16351635 - CALM2 expression in ALCL — EXCLUDE (expression only, no mechanism)\n7. PMID:30317608 - CALM2 as therapeutic target for liver fibrosis — EXCLUDE (expression/bioinformatics only)\n8. PMID:1999288 - Calmodulin retropseudogenes — EXCLUDE (pseudogenes, not CALM2 protein)\n9. PMID:20198394 - CALM2 SNPs and hip OA — EXCLUDE (association study)\n10. PMID:25009623 - Promoter methylation of CALM2 in T2D — EXCLUDE (epigenetic association)\n11. PMID:31283864 - CALM2 p.N98S case report — KEEP (clinical/mechanistic context)\n12. PMID:36460225 - CALM2 knockdown, Akt/FoxO3a/Puma axis in GC — KEEP\n13. PMID:33788723 - CALM2 knockdown, E2F5, HCC — KEEP\n14. PMID:39069900 - SupRep gene therapy for CALM-mediated LQTS — KEEP\n15. PMID:33951696 - circ_0010729/miR-338-3p/CALM2 in OGD — KEEP\n16. PMID:39104518 - CPVT case with CALM2 variant — KEEP (limited mechanism)\n17. PMID:36507129 - CALM2 D130G in fetal non-compaction cardiomyopathy — KEEP\n18. PMID:39137556 - hiPSC line from CALM2 mutation — EXCLUDE (resource paper, no mechanism)\n19. PMID:40117023 - ABHD11-AS1/miR-876-5p/CALM2 in thyroid cancer — KEEP\n20. PMID:41846582 - CALM1/2/3 expression and translation efficiency — KEEP\n21. PMID:41665141 - CALM2 N98S case report — EXCLUDE (clinical, no new mechanism)\n22. PMID:41550621 - CALM2 T63K CPVT case — EXCLUDE (clinical case, no mechanism)\n23. bio_10.1101_2025.05.15.25327594 - PREPRINT same as PMID:41846582 — EXCLUDE (duplicate of peer-reviewed)\n24. bio_10.1101_2025.07.10.663151 - King penguins, mentions CALM2 in DEGs — EXCLUDE (non-ortholog context, penguin transcriptomics)\n\n**Gene2pubmed Additional Papers:**\n- PMID:9278050 - Cameleon Ca2+ indicators using calmodulin — KEEP (uses calmodulin/M13 mechanism)\n- PMID:16189514, 16169070, 12477932, 25416956, 32296183, 14743216, 14702039, 17353931, 22939629, 21873635, 21565611, 26638075, 35271311, 11980920, 17719545, 17620599, 21726808, 17582331, 11807546, 21145461, 15723066, 23388215, 23040497, 17640527, 19190083, 30110629, 8631904, 20458337, 18694559 — Most are large interactome screens, cilia biology, or calmodulin-general papers not specifically about CALM2. I need to check:\n  - PMID:23388215 - Calmodulin mutations in CALM1/CALM2 causing cardiac arrest — KEEP\n  - PMID:23040497 - CALM1 mutations (CPVT), mentions calmodulin genes broadly — KEEP (foundational, includes CALM2 context)\n  - PMID:11807546 - Oedema factor + calmodulin structure — KEEP (calmodulin mechanism, but uses generic calmodulin not specifically CALM2)\n  - PMID:15723066 - Nephrocystin-5 interacts with calmodulin — EXCLUDE (about NPHP5/IQCB1, calmodulin is general)\n  - PMID:17582331 - TRPV1 ARD binds calmodulin — EXCLUDE (about TRPV1, calmodulin is general binding partner)\n  - PMID:17640527 - AKAP79/150 anchoring calcineurin — EXCLUDE (about AKAP/CaV1.2/calcineurin)\n  - PMID:11980920 - DAPk/DRP-1, Ca2+/calmodulin-regulated kinases — EXCLUDE (about DAPk family)\n  - PMID:8631904 - Calcineurin/NFAT1 — EXCLUDE (about calcineurin/NFAT)\n  - All large interactome maps (PMID:16189514, 16169070, 25416956, 32296183, 14743216, 17353931, 22939629, 17620599, 21145461, 26638075, 35271311, 19190083, 20458337, 21565611, 18694559, 17719545) — EXCLUDE (CALM2 appears incidentally in large proteomics datasets, not mechanistic findings about CALM2 specifically)\n  - PMID:12477932, 14702039 — cDNA sequencing projects — EXCLUDE\n  - PMID:21873635 — GO annotation — EXCLUDE\n  - PMID:30110629 — CBP/P300, H3K27Ac — EXCLUDE\n  - PMID:21726808 — PEPCK1 acetylation — EXCLUDE\n  - PMID:9278050 — Cameleon indicators using calmodulin + M13 — this uses calmodulin (encoded by CALM genes) as the Ca2+ sensor. The paper describes calmodulin wrapping around M13 upon Ca2+ binding. This is about calmodulin's general mechanism, relevant to CALM2 as one of the three genes encoding calmodulin. KEEP.\n\n```json\n{\n  \"discoveries\": [\n    {\n      \"year\": 2013,\n      \"finding\": \"De novo heterozygous missense mutations in CALM1 and CALM2 (encoding calmodulin) reduce calcium binding affinity of the recombinant protein by several-fold. A CALM2 mutation (N97S in CALM2 context) also showed aberrant interaction with the RYR2 calmodulin-binding-domain peptide at low calcium concentrations, establishing that calmodulin mutations disrupt Ca2+ binding and alter RyR2 interactions, causing life-threatening ventricular arrhythmias in infants.\",\n      \"method\": \"Exome sequencing of parent-child trios; recombinant mutant calmodulin calcium binding affinity assays; calmodulin-binding-domain peptide interaction assays\",\n      \"journal\": \"Circulation\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 1–2 — in vitro calcium binding assays plus peptide interaction assays on recombinant protein; replicated across multiple mutation carriers\",\n      \"pmids\": [\"23388215\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2012,\n      \"finding\": \"Heterozygous missense mutations in CALM1 (encoding calmodulin) causing catecholaminergic polymorphic ventricular tachycardia demonstrate compromised calcium binding and aberrant interaction with the RYR2 calmodulin-binding-domain peptide at low calcium concentrations, establishing calmodulin genes (including CALM2 as a candidate) as genetic determinants of severe cardiac arrhythmia.\",\n      \"method\": \"Genome-wide linkage analysis; Sanger sequencing; recombinant calmodulin calcium binding assays; RYR2 calmodulin-binding-domain peptide interaction assays\",\n      \"journal\": \"American journal of human genetics\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 1–2 — biochemical assays on recombinant protein combined with genetic linkage; foundational mechanistic paper\",\n      \"pmids\": [\"23040497\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2016,\n      \"finding\": \"A novel CALM2 variant E141G reduces Ca2+ binding affinity of calmodulin by 11-fold and causes a dominant loss of inactivation of the cardiac L-type calcium channel (CaV1.2), mild accentuation of NaV1.5 late current, but no effect on intracellular RyR2-mediated calcium release, establishing channel-specific functional consequences of this CALM2 variant.\",\n      \"method\": \"Whole-exome sequencing; recombinant protein Ca2+ binding affinity assays; patch-clamp electrophysiology of CaV1.2, NaV1.5, and RyR2\",\n      \"journal\": \"Circulation. Cardiovascular genetics\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 1–2 — reconstituted biochemical assays plus multi-channel electrophysiology with orthogonal methods\",\n      \"pmids\": [\"26969752\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2017,\n      \"finding\": \"The CALM2-N98S mutation in hiPSC-derived cardiomyocytes causes significantly lower beating rates, prolonged action potential durations, and impaired inactivation of L-type Ca2+ channel (LTCC) currents compared with control cells. Allele-specific CRISPR-Cas9 knockout of the mutant allele rescued these electrophysiological abnormalities, demonstrating that the CALM2-N98S mutant allele acts in a dominant-negative manner to suppress LTCC inactivation and thereby prolong action potential duration.\",\n      \"method\": \"hiPSC differentiation into cardiomyocytes; patch-clamp electrophysiology (action potential recordings, LTCC current measurements); CRISPR-Cas9 allele-specific knockout\",\n      \"journal\": \"Human molecular genetics\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 1–2 — disease model with patch-clamp electrophysiology and genetic rescue (CRISPR), multiple orthogonal methods in human cardiomyocytes\",\n      \"pmids\": [\"28335032\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 1997,\n      \"finding\": \"Calmodulin (encoded by CALM genes) wraps around the calmodulin-binding peptide M13 upon Ca2+ binding, increasing fluorescence resonance energy transfer (FRET) between flanking GFP variants. This conformational change was harnessed to create genetically encoded Ca2+ indicators ('cameleons') enabling real-time visualization of Ca2+ dynamics in specific subcellular compartments including cytosol, nucleus, and endoplasmic reticulum.\",\n      \"method\": \"Recombinant fusion protein construction; FRET measurements; transfection in HeLa cells; live-cell fluorescence microscopy; calmodulin mutagenesis to tune Ca2+ affinity\",\n      \"journal\": \"Nature\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 1 — reconstitution with mutagenesis and live-cell imaging; highly replicated foundational paper\",\n      \"pmids\": [\"9278050\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 1998,\n      \"finding\": \"The CALM2 gene spans approximately 16 kb with intron interruptions at identical positions to CALM1 and CALM3. Its 5' flanking region contains a TATA-like sequence 27 nucleotides upstream of the transcriptional start site. In proliferating human teratoma cells, CALM3 is at least 5-fold more actively transcribed than CALM1 or CALM2, and the 5' untranslated regions are required for full promoter activation in luciferase reporter assays.\",\n      \"method\": \"Genomic library screening; genomic PCR; nuclear run-on transcription assays; luciferase reporter transfection assays; mRNA quantification\",\n      \"journal\": \"Cell calcium\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 — direct transcriptional activity measurements with nuclear run-on and reporter assays in a single cell line\",\n      \"pmids\": [\"9681195\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2024,\n      \"finding\": \"A suppression-and-replacement (SupRep) gene therapy construct simultaneously knocks down endogenous CALM1, CALM2, and CALM3 using gene-specific shRNAs (71% knockdown for CALM2) while delivering a shRNA-immune CALM1 replacement. In CALM2-D130G hiPSC-derived cardiomyocytes with pathologically prolonged APD90 (647±9 ms vs. 359±12 ms in WT), CALM-SupRep transfection shortened APD90 to 457±19 ms (66% attenuation), demonstrating proof-of-principle for gene therapy targeting CALM2-mediated long-QT syndrome.\",\n      \"method\": \"shRNA knockdown efficiency testing by RT-qPCR; voltage-sensing dye action potential measurements in hiPSC-derived cardiomyocytes; CALM2-D130G patient-derived iPSC lines\",\n      \"journal\": \"Circulation. Arrhythmia and electrophysiology\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 — functional electrophysiology rescue in patient-derived cardiomyocytes with quantitative APD measurements; single study\",\n      \"pmids\": [\"39069900\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2022,\n      \"finding\": \"Knockdown of CALM2 in HER2-amplified gastric cancer cells inhibits Akt signaling, which derepresses the FoxO3a/Puma axis, promoting mitochondrial apoptosis in a caspase-dependent manner and sensitizing cells to afatinib. Inhibition of either FoxO3a or Puma abrogated the pro-apoptotic effects of CALM2 knockdown, placing CALM2 upstream of the Akt–FoxO3a–Puma signaling cascade.\",\n      \"method\": \"siRNA knockdown of CALM2; Western blot for Akt phosphorylation, FoxO3a, Puma; caspase activity assays; flow cytometry for apoptosis; pharmacological inhibition of FoxO3a and Puma\",\n      \"journal\": \"Toxicology in vitro\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2–3 — knockdown with pathway epistasis via pharmacological inhibitors; single lab study\",\n      \"pmids\": [\"36460225\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2021,\n      \"finding\": \"Knockdown of CALM2 in hepatocellular carcinoma (HCC) cells inhibits proliferation, colony formation, migration, and invasion, and reduces tumor formation in vivo. At the molecular level, CALM2-specific knockdown leads to downregulation of E2F transcription factor 5 (E2F5), which is functionally associated with migration, invasion, and proliferation, placing CALM2 upstream of E2F5-mediated cell cycle progression in HCC.\",\n      \"method\": \"siRNA knockdown of CALM2; transcriptomic profiling of dysregulated genes; cell proliferation and colony formation assays; migration/invasion assays; in vivo tumor formation; HCC clinical sample validation\",\n      \"journal\": \"Anticancer research\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2–3 — loss-of-function with defined molecular pathway (E2F5 downregulation) and in vivo validation; single lab\",\n      \"pmids\": [\"33788723\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2021,\n      \"finding\": \"In cardiac myocytes subjected to oxygen-glucose deprivation (OGD), circ_0010729 acts as a sponge for miR-338-3p, which directly targets CALM2 mRNA. Knockdown of circ_0010729 increases miR-338-3p availability, reducing CALM2 expression and attenuating OGD-induced apoptosis and autophagy in AC16 cells, establishing CALM2 as a downstream effector in this non-coding RNA regulatory axis during cardiac ischemic injury.\",\n      \"method\": \"RT-qPCR and Western blot for CALM2 expression; dual-luciferase reporter assay validating miR-338-3p targeting of CALM2; siRNA knockdown; flow cytometry for apoptosis; cell viability assays\",\n      \"journal\": \"Journal of cardiovascular pharmacology\",\n      \"confidence\": \"Low\",\n      \"confidence_rationale\": \"Tier 3 — luciferase reporter validation of miRNA-target relationship; functional readouts limited to cell viability/apoptosis; single lab\",\n      \"pmids\": [\"33951696\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2019,\n      \"finding\": \"In post-myocardial infarction myocardial cells, GAS5 lncRNA acts as a sponge for miR-525-5p, which targets CALM2 mRNA. Overexpression of CALM2 promotes apoptosis and inhibits proliferation of myocardial cells, while miR-525-5p can reverse CALM2-induced MI effects. Dual luciferase reporter and RIP assays confirmed the targeting relationships among GAS5, miR-525-5p, and CALM2.\",\n      \"method\": \"RT-qPCR; Western blot; flow cytometry; MTT assay; dual luciferase reporter assay; RNA-binding protein immunoprecipitation (RIP); knockdown experiments\",\n      \"journal\": \"Journal of cellular biochemistry\",\n      \"confidence\": \"Low\",\n      \"confidence_rationale\": \"Tier 3 — luciferase and RIP validation of miRNA-target relationship; functional phenotype (apoptosis/proliferation) without deep pathway mechanistic follow-up; single lab\",\n      \"pmids\": [\"31429119\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2026,\n      \"finding\": \"RNA sequencing and ribosome profiling of left ventricular tissue show that CALM2 contributes approximately 44% of total calmodulin-coding mRNA (versus 37% for CALM1 and 21% for CALM3) and approximately 44% of calmodulin protein translation, making CALM1 and CALM2 the dominant sources of calmodulin in the human heart. This greater contribution of CALM2 relative to CALM3 explains why CALM3 missense variants are under less negative selection and cause less severe cardiac phenotypes.\",\n      \"method\": \"GTEx RNA sequencing data analysis; ribosome profiling of left ventricle; Genome Aggregation Database (gnomAD) observed-to-expected variant ratio analysis; International Calmodulinopathy Registry clinical outcomes\",\n      \"journal\": \"Europace\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 — quantitative transcriptomic and ribosome profiling data from large public datasets with population genetics validation; single analysis but uses multiple independent data sources\",\n      \"pmids\": [\"41846582\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2025,\n      \"finding\": \"LncRNA ABHD11-AS1 acts as a sponge for miR-876-5p, which targets CALM2 mRNA, in thyroid cancer cells. ABHD11-AS1 knockdown reduces CALM2 expression and inhibits migration, invasion, and EMT of thyroid cancer cells; these effects are counteracted by miR-876-5p inhibition or CALM2 overexpression, placing CALM2 downstream in the ABHD11-AS1/miR-876-5p/CALM2 regulatory axis promoting thyroid cancer metastasis.\",\n      \"method\": \"Scratch assay; transwell invasion assay; RT-qPCR; Western blot; dual-luciferase reporter assay; siRNA and overexpression approaches\",\n      \"journal\": \"Biochemical genetics\",\n      \"confidence\": \"Low\",\n      \"confidence_rationale\": \"Tier 3 — luciferase reporter validation of miRNA-target relationships; functional migration/invasion assays without deep mechanistic pathway characterization; single lab\",\n      \"pmids\": [\"40117023\"],\n      \"is_preprint\": false\n    }\n  ],\n  \"current_model\": \"CALM2 encodes one of three genes producing the identical calmodulin protein, contributing ~44% of cardiac calmodulin mRNA and protein; pathogenic CALM2 missense variants reduce Ca2+ binding affinity of calmodulin, impair inactivation of the cardiac L-type Ca2+ channel (CaV1.2) in a dominant-negative manner, and alter RyR2 interactions, causing long-QT syndrome and catecholaminergic polymorphic ventricular tachycardia, while in cancer contexts CALM2 acts upstream of Akt–FoxO3a–Puma and E2F5 pathways to regulate apoptosis and cell cycle progression.\"\n}\n```","stage2_raw":"```json\n{\n  \"mechanistic_narrative\": \"CALM2 encodes one of three genes producing identical calmodulin protein, a ubiquitous Ca²⁺ sensor that regulates cardiac ion channel function and cell survival signaling. Pathogenic missense variants in CALM2 (e.g., N98S, E141G, D130G) reduce Ca²⁺ binding affinity and dominantly suppress Ca²⁺-dependent inactivation of the L-type Ca²⁺ channel CaV1.2 in cardiomyocytes, prolonging action potential duration and causing long-QT syndrome (LQT15); allele-specific CRISPR knockout of the mutant allele or suppression-and-replacement gene therapy rescues the electrophysiological defect [PMID:26969752, PMID:28335032, PMID:39069900]. In cancer cells, CALM2 sustains Akt signaling to suppress FoxO3a/Puma-mediated mitochondrial apoptosis and maintains E2F5-driven proliferation and migration programs [PMID:36460225, PMID:33788723].\",\n  \"teleology\": [\n    {\n      \"year\": 1998,\n      \"claim\": \"Resolving the genomic organization of the three calmodulin genes revealed that CALM2, despite sharing identical coding-region intron positions with CALM1 and CALM3, spans a larger genomic locus (~16 kb) and is transcribed at lower levels than CALM3, establishing that distinct promoter architectures control expression of otherwise identical proteins.\",\n      \"evidence\": \"Genomic library screening, PCR mapping, and luciferase reporter assays in teratoma cells\",\n      \"pmids\": [\"9681195\"],\n      \"confidence\": \"Medium\",\n      \"gaps\": [\n        \"Tissue- and developmental-stage-specific transcriptional regulation of CALM2 versus CALM1/CALM3 remains unresolved\",\n        \"No protein-level quantification of each calmodulin gene's contribution to total cellular calmodulin\"\n      ]\n    },\n    {\n      \"year\": 2016,\n      \"claim\": \"Demonstrating that the CALM2-E141G variant reduces Ca²⁺ affinity 11-fold and dominantly abolishes CaV1.2 Ca²⁺-dependent inactivation established the first ion-channel-specific pathomechanism for a CALM2 arrhythmia mutation, showing that even a minority of mutant calmodulin can override wild-type function at CaV1.2.\",\n      \"evidence\": \"Patch-clamp electrophysiology and Ca²⁺-binding assays in heterologous expression systems\",\n      \"pmids\": [\"26969752\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\n        \"Structural basis for dominant-negative action at CaV1.2 not resolved\",\n        \"Effect in native human cardiomyocytes not yet tested\"\n      ]\n    },\n    {\n      \"year\": 2017,\n      \"claim\": \"Using patient-derived hiPSC-cardiomyocytes, allele-specific CRISPR knockout of CALM2-N98S rescued prolonged action potential duration, confirming the dominant-negative mechanism in a human cardiac context and validating that removing the mutant allele is sufficient for electrophysiological correction.\",\n      \"evidence\": \"hiPSC-derived cardiomyocytes with CRISPR-Cas9 allele-specific knockout and patch-clamp electrophysiology\",\n      \"pmids\": [\"28335032\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\n        \"In vivo cardiac phenotype correction not demonstrated\",\n        \"Whether all CALM2 arrhythmia variants share the same CaV1.2-centric mechanism is unresolved\"\n      ]\n    },\n    {\n      \"year\": 2021,\n      \"claim\": \"Identifying E2F5 as a downstream effector of CALM2 in hepatocellular carcinoma broadened CALM2's functional scope beyond ion-channel regulation to include cell cycle and metastasis control, showing that CALM2 loss suppresses proliferation, migration, and in vivo tumor growth.\",\n      \"evidence\": \"siRNA knockdown, transcriptomic profiling, migration/invasion assays, and xenograft tumor formation\",\n      \"pmids\": [\"33788723\"],\n      \"confidence\": \"Medium\",\n      \"gaps\": [\n        \"Direct binding between calmodulin and the E2F5 regulatory pathway not demonstrated\",\n        \"Unclear whether this is a CALM2-specific or general calmodulin effect\",\n        \"Single-lab finding without independent replication\"\n      ]\n    },\n    {\n      \"year\": 2022,\n      \"claim\": \"Epistatic experiments placed CALM2 upstream of the Akt→FoxO3a→Puma apoptotic axis in HER2-amplified gastric cancer, showing that CALM2 depletion triggers caspase-dependent mitochondrial apoptosis by de-repressing this pathway.\",\n      \"evidence\": \"siRNA knockdown with FoxO3a/Puma epistasis analysis and caspase-dependence assays in gastric cancer cells\",\n      \"pmids\": [\"36460225\"],\n      \"confidence\": \"Medium\",\n      \"gaps\": [\n        \"Whether calmodulin directly activates Akt or acts via an intermediate kinase (e.g., CaMKII) is not resolved\",\n        \"Applicability beyond HER2-amplified gastric cancer not tested\"\n      ]\n    },\n    {\n      \"year\": 2024,\n      \"claim\": \"A suppression-and-replacement gene therapy (shRNA against CALM2 plus shRNA-immune CALM1 cDNA) rescued prolonged APD in CALM2-D130G patient cardiomyocytes, providing preclinical proof-of-concept that a single therapeutic vector can correct the dominant-negative calmodulinopathy mechanism.\",\n      \"evidence\": \"shRNA knockdown combined with immune-cDNA replacement in hiPSC-cardiomyocytes, voltage-sensing dye APD measurements\",\n      \"pmids\": [\"39069900\"],\n      \"confidence\": \"Medium\",\n      \"gaps\": [\n        \"In vivo efficacy and cardiac-specific delivery not demonstrated\",\n        \"Long-term effects of CALM2 suppression on non-cardiac calmodulin-dependent processes unknown\",\n        \"Single-lab study without independent replication\"\n      ]\n    },\n    {\n      \"year\": null,\n      \"claim\": \"The structural basis for dominant-negative poisoning of CaV1.2 by substoichiometric mutant calmodulin, and whether CALM2 has non-redundant gene-specific functions distinct from CALM1/CALM3 beyond promoter-level regulation, remain unresolved.\",\n      \"evidence\": \"\",\n      \"pmids\": [],\n      \"confidence\": \"High\",\n      \"gaps\": [\n        \"No atomic-resolution structure of mutant calmodulin bound to CaV1.2 IQ domain\",\n        \"Gene-specific versus protein-level redundancy among CALM1/2/3 not systematically dissected in vivo\",\n        \"Relative contribution of each CALM gene to total calmodulin pool in human cardiomyocytes unknown\"\n      ]\n    }\n  ],\n  \"mechanism_profile\": {\n    \"molecular_activity\": [\n      {\"term_id\": \"GO:0098772\", \"supporting_discovery_ids\": [0, 1, 4]},\n      {\"term_id\": \"GO:0140299\", \"supporting_discovery_ids\": [0, 1]}\n    ],\n    \"localization\": [\n      {\"term_id\": \"GO:0005829\", \"supporting_discovery_ids\": [0, 1, 2]}\n    ],\n    \"pathway\": [\n      {\"term_id\": \"R-HSA-162582\", \"supporting_discovery_ids\": [2, 3]},\n      {\"term_id\": \"R-HSA-5357801\", \"supporting_discovery_ids\": [2]},\n      {\"term_id\": \"R-HSA-1643685\", \"supporting_discovery_ids\": [0, 1, 4]}\n    ],\n    \"complexes\": [],\n    \"partners\": [\n      \"CACNA1C\",\n      \"AKT1\",\n      \"E2F5\",\n      \"FOXO3\",\n      \"BBC3\"\n    ],\n    \"other_free_text\": []\n  }\n}\n```\n\n--- ROUND 2 (R2/R3, augmented corpus) ---\n\n```json\n{\n  \"mechanistic_narrative\": \"CALM2 is one of three human genes (CALM1, CALM2, CALM3) encoding the identical calmodulin protein, a ubiquitous Ca²⁺ sensor that undergoes a conformational change upon Ca²⁺ binding to regulate diverse downstream targets including ion channels and kinases [PMID:9278050]. In the human heart, CALM2 contributes approximately 44% of total calmodulin mRNA and translated protein, making it a dominant source of cardiac calmodulin [PMID:41846582]. Heterozygous missense variants in CALM2 reduce Ca²⁺ binding affinity and impair Ca²⁺-dependent inactivation of the L-type Ca²⁺ channel (CaV1.2) in a dominant-negative manner, prolonging action potential duration and causing long-QT syndrome and catecholaminergic polymorphic ventricular tachycardia, with allele-specific CRISPR knockout rescuing the electrophysiological phenotype in patient-derived cardiomyocytes [PMID:23388215, PMID:26969752, PMID:28335032]. In cancer cell contexts, CALM2 knockdown inhibits Akt signaling to derepress the FoxO3a–Puma apoptotic axis and downregulates E2F5-mediated cell cycle progression [PMID:36460225, PMID:33788723].\",\n  \"teleology\": [\n    {\n      \"year\": 1997,\n      \"claim\": \"The demonstration that calmodulin undergoes a large Ca²⁺-dependent conformational change around target peptides — sufficient to drive FRET between flanking fluorophores — established calmodulin as a bona fide intramolecular Ca²⁺ switch and enabled genetically encoded Ca²⁺ indicators for live-cell imaging.\",\n      \"evidence\": \"Recombinant calmodulin-M13 fusion protein with GFP variants; FRET measurements in HeLa cells\",\n      \"pmids\": [\"9278050\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\n        \"This study used calmodulin generically without distinguishing contributions of CALM1, CALM2, or CALM3\",\n        \"Conformational dynamics on full-length channel targets were not assessed\"\n      ]\n    },\n    {\n      \"year\": 1998,\n      \"claim\": \"Genomic characterization of CALM2 defined its gene structure, promoter elements, and relative transcriptional activity compared with CALM1 and CALM3, showing CALM2 was moderately transcribed in proliferating cells.\",\n      \"evidence\": \"Genomic library screening, nuclear run-on assays, and luciferase reporter assays in human teratoma cells\",\n      \"pmids\": [\"9681195\"],\n      \"confidence\": \"Medium\",\n      \"gaps\": [\n        \"Transcriptional analysis limited to a single teratoma cell line; tissue-specific regulation uncharacterized\",\n        \"Post-transcriptional control of CALM2 mRNA not addressed\"\n      ]\n    },\n    {\n      \"year\": 2012,\n      \"claim\": \"Genetic linkage of calmodulin missense mutations to catecholaminergic polymorphic ventricular tachycardia, combined with biochemical evidence of reduced Ca²⁺ binding and aberrant RyR2 interaction, established calmodulin genes as direct genetic determinants of lethal cardiac arrhythmia.\",\n      \"evidence\": \"Genome-wide linkage in affected families; recombinant calmodulin Ca²⁺ binding and RYR2 peptide interaction assays\",\n      \"pmids\": [\"23040497\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\n        \"Initial study focused on CALM1; CALM2 variants were identified shortly after but not in this cohort\",\n        \"Full-length RyR2 channel interaction not tested\"\n      ]\n    },\n    {\n      \"year\": 2013,\n      \"claim\": \"De novo CALM2 missense mutations were directly shown to reduce Ca²⁺ binding affinity of recombinant calmodulin and alter RyR2 calmodulin-binding-domain interaction at low Ca²⁺, establishing CALM2-specific pathogenicity in infant arrhythmias.\",\n      \"evidence\": \"Exome sequencing of parent–child trios; recombinant protein Ca²⁺ affinity assays and RYR2 peptide binding\",\n      \"pmids\": [\"23388215\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\n        \"Effects on L-type Ca²⁺ channel inactivation not yet tested for these specific CALM2 variants\",\n        \"Dominant-negative mechanism versus haploinsufficiency not resolved\"\n      ]\n    },\n    {\n      \"year\": 2016,\n      \"claim\": \"The CALM2-E141G variant was shown to cause an 11-fold reduction in Ca²⁺ affinity and channel-specific consequences — dominant loss of CaV1.2 inactivation and mild NaV1.5 late current enhancement without RyR2 effects — revealing that individual CALM2 mutations differentially affect distinct ion channel targets.\",\n      \"evidence\": \"Recombinant protein Ca²⁺ binding assays; patch-clamp electrophysiology on CaV1.2, NaV1.5, and RyR2 in heterologous expression systems\",\n      \"pmids\": [\"26969752\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\n        \"Mechanism by which the same Ca²⁺-binding deficit selectively affects CaV1.2 but not RyR2 is unknown\",\n        \"No structural data explaining variant-specific channel selectivity\"\n      ]\n    },\n    {\n      \"year\": 2017,\n      \"claim\": \"CRISPR-Cas9 allele-specific knockout of the CALM2-N98S mutant allele in patient iPSC-derived cardiomyocytes rescued prolonged action potential duration and impaired L-type Ca²⁺ channel inactivation, definitively proving a dominant-negative mechanism for CALM2-linked long-QT syndrome.\",\n      \"evidence\": \"hiPSC-derived cardiomyocytes; patch-clamp action potential and LTCC current recordings; allele-specific CRISPR-Cas9 knockout\",\n      \"pmids\": [\"28335032\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\n        \"Whether the dominant-negative mechanism generalizes to all CALM2 arrhythmia variants is untested\",\n        \"Stoichiometric threshold of mutant versus wild-type calmodulin required to produce pathology is unknown\"\n      ]\n    },\n    {\n      \"year\": 2021,\n      \"claim\": \"CALM2 knockdown in hepatocellular carcinoma cells suppressed proliferation, migration, and in vivo tumor growth through downregulation of E2F5, positioning CALM2 as an upstream regulator of E2F5-dependent cell cycle progression in a cancer context.\",\n      \"evidence\": \"siRNA knockdown; transcriptomic profiling; proliferation and invasion assays; xenograft tumor formation\",\n      \"pmids\": [\"33788723\"],\n      \"confidence\": \"Medium\",\n      \"gaps\": [\n        \"Mechanistic link between calmodulin and E2F5 transcription not characterized\",\n        \"Whether calmodulin's Ca²⁺-sensing activity is required for E2F5 regulation is unknown\"\n      ]\n    },\n    {\n      \"year\": 2022,\n      \"claim\": \"In HER2-amplified gastric cancer cells, CALM2 knockdown inhibited Akt phosphorylation, derepressing the FoxO3a–Puma apoptotic axis in a caspase-dependent manner, establishing CALM2 as an upstream activator of Akt-mediated survival signaling.\",\n      \"evidence\": \"siRNA knockdown; Western blot for phospho-Akt, FoxO3a, Puma; caspase assays; pharmacological epistasis experiments\",\n      \"pmids\": [\"36460225\"],\n      \"confidence\": \"Medium\",\n      \"gaps\": [\n        \"Whether calmodulin directly activates Akt or acts through CaMKK/CaMKII intermediaries is not resolved\",\n        \"Findings limited to a single cancer cell type\"\n      ]\n    },\n    {\n      \"year\": 2024,\n      \"claim\": \"A suppression-and-replacement gene therapy strategy simultaneously knocking down all three CALM genes and replacing with shRNA-immune wild-type calmodulin partially rescued prolonged action potential duration in CALM2-D130G patient cardiomyocytes, providing proof-of-principle for therapeutic intervention in calmodulinopathy.\",\n      \"evidence\": \"shRNA knockdown with RT-qPCR validation; voltage-sensing dye APD measurements in CALM2-D130G hiPSC-derived cardiomyocytes\",\n      \"pmids\": [\"39069900\"],\n      \"confidence\": \"Medium\",\n      \"gaps\": [\n        \"Rescue was partial (66% attenuation); full APD normalization not achieved\",\n        \"In vivo efficacy and delivery to cardiomyocytes not tested\",\n        \"Long-term effects on total calmodulin protein levels not assessed\"\n      ]\n    },\n    {\n      \"year\": 2025,\n      \"claim\": \"Ribosome profiling confirmed that CALM2 contributes ~44% of cardiac calmodulin protein translation, explaining why CALM2 variants cause more severe arrhythmia phenotypes than CALM3 variants and providing a quantitative basis for the genotype–phenotype relationship.\",\n      \"evidence\": \"GTEx RNA-seq; ribosome profiling of human left ventricle; gnomAD variant constraint analysis; International Calmodulinopathy Registry outcomes\",\n      \"pmids\": [\"41846582\"],\n      \"confidence\": \"Medium\",\n      \"gaps\": [\n        \"Whether translational contribution varies across cardiac chambers or developmental stages is unknown\",\n        \"Protein-level quantification of CALM2-derived calmodulin (indistinguishable from other CALM gene products) relies on ribosome profiling as a proxy\"\n      ]\n    },\n    {\n      \"year\": null,\n      \"claim\": \"Structural and biophysical understanding of how individual CALM2 missense variants differentially disrupt specific ion channel targets (CaV1.2 versus RyR2 versus NaV1.5) remains incomplete, and the stoichiometric threshold of mutant calmodulin required for dominant-negative pathology has not been determined.\",\n      \"evidence\": \"\",\n      \"pmids\": [],\n      \"confidence\": \"High\",\n      \"gaps\": [\n        \"No high-resolution structure of mutant calmodulin bound to full-length CaV1.2 or RyR2\",\n        \"Quantitative dose-response for mutant-to-wild-type calmodulin ratio and electrophysiological phenotype not established\",\n        \"In vivo gene therapy efficacy for CALM2-linked arrhythmias untested\"\n      ]\n    }\n  ],\n  \"mechanism_profile\": {\n    \"molecular_activity\": [\n      {\"term_id\": \"GO:0098772\", \"supporting_discovery_ids\": [0, 1, 2, 3, 4]},\n      {\"term_id\": \"GO:0140299\", \"supporting_discovery_ids\": [0, 2, 4]}\n    ],\n    \"localization\": [\n      {\"term_id\": \"GO:0005829\", \"supporting_discovery_ids\": [4]}\n    ],\n    \"pathway\": [\n      {\"term_id\": \"GO:0162582\", \"supporting_discovery_ids\": [2, 3, 7]},\n      {\"term_id\": \"R-HSA-162582\", \"supporting_discovery_ids\": [2, 3, 7]},\n      {\"term_id\": \"R-HSA-5357801\", \"supporting_discovery_ids\": [7, 8]},\n      {\"term_id\": \"R-HSA-1643685\", \"supporting_discovery_ids\": [0, 2, 3, 6]}\n    ],\n    \"complexes\": [],\n    \"partners\": [\n      \"CACNA1C\",\n      \"RYR2\",\n      \"SCN5A\",\n      \"AKT1\",\n      \"E2F5\"\n    ],\n    \"other_free_text\": []\n  }\n}\n```\n\nWait, I made an error in the pathway section — I included a malformed GO id. Let me fix that:\n\n```json\n{\n  \"mechanistic_narrative\": \"CALM2 is one of three human genes (CALM1, CALM2, CALM3) encoding the identical calmodulin protein, a ubiquitous Ca²⁺ sensor that undergoes a conformational change upon Ca²⁺ binding to regulate diverse downstream targets including ion channels and kinases [PMID:9278050]. In the human heart, CALM2 contributes approximately 44% of total calmodulin mRNA and translated protein, making it a dominant source of cardiac calmodulin [PMID:41846582]. Heterozygous missense variants in CALM2 reduce Ca²⁺ binding affinity and impair Ca²⁺-dependent inactivation of the L-type Ca²⁺ channel (CaV1.2) in a dominant-negative manner, prolonging action potential duration and causing long-QT syndrome and catecholaminergic polymorphic ventricular tachycardia, with allele-specific CRISPR knockout rescuing the electrophysiological phenotype in patient-derived cardiomyocytes [PMID:23388215, PMID:26969752, PMID:28335032]. In cancer cell contexts, CALM2 knockdown inhibits Akt signaling to derepress the FoxO3a–Puma apoptotic axis and downregulates E2F5-mediated cell cycle progression [PMID:36460225, PMID:33788723].\",\n  \"teleology\": [\n    {\n      \"year\": 1997,\n      \"claim\": \"The demonstration that calmodulin undergoes a large Ca²⁺-dependent conformational change around target peptides — sufficient to drive FRET between flanking fluorophores — established calmodulin as a bona fide intramolecular Ca²⁺ switch and enabled genetically encoded Ca²⁺ indicators for live-cell imaging.\",\n      \"evidence\": \"Recombinant calmodulin-M13 fusion protein with GFP variants; FRET measurements in HeLa cells\",\n      \"pmids\": [\"9278050\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\n        \"This study used calmodulin generically without distinguishing contributions of CALM1, CALM2, or CALM3\",\n        \"Conformational dynamics on full-length channel targets were not assessed\"\n      ]\n    },\n    {\n      \"year\": 1998,\n      \"claim\": \"Genomic characterization of CALM2 defined its gene structure, promoter elements, and relative transcriptional activity compared with CALM1 and CALM3, showing CALM2 was moderately transcribed in proliferating cells.\",\n      \"evidence\": \"Genomic library screening, nuclear run-on assays, and luciferase reporter assays in human teratoma cells\",\n      \"pmids\": [\"9681195\"],\n      \"confidence\": \"Medium\",\n      \"gaps\": [\n        \"Transcriptional analysis limited to a single teratoma cell line; tissue-specific regulation uncharacterized\",\n        \"Post-transcriptional control of CALM2 mRNA not addressed\"\n      ]\n    },\n    {\n      \"year\": 2012,\n      \"claim\": \"Genetic linkage of calmodulin missense mutations to catecholaminergic polymorphic ventricular tachycardia, combined with biochemical evidence of reduced Ca²⁺ binding and aberrant RyR2 interaction, established calmodulin genes as direct genetic determinants of lethal cardiac arrhythmia.\",\n      \"evidence\": \"Genome-wide linkage in affected families; recombinant calmodulin Ca²⁺ binding and RYR2 peptide interaction assays\",\n      \"pmids\": [\"23040497\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\n        \"Initial study focused on CALM1; CALM2 variants were identified shortly after but not in this cohort\",\n        \"Full-length RyR2 channel interaction not tested\"\n      ]\n    },\n    {\n      \"year\": 2013,\n      \"claim\": \"De novo CALM2 missense mutations were directly shown to reduce Ca²⁺ binding affinity of recombinant calmodulin and alter RyR2 calmodulin-binding-domain interaction at low Ca²⁺, establishing CALM2-specific pathogenicity in infant arrhythmias.\",\n      \"evidence\": \"Exome sequencing of parent–child trios; recombinant protein Ca²⁺ affinity assays and RYR2 peptide binding\",\n      \"pmids\": [\"23388215\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\n        \"Effects on L-type Ca²⁺ channel inactivation not yet tested for these specific CALM2 variants\",\n        \"Dominant-negative mechanism versus haploinsufficiency not resolved\"\n      ]\n    },\n    {\n      \"year\": 2016,\n      \"claim\": \"The CALM2-E141G variant was shown to cause an 11-fold reduction in Ca²⁺ affinity and channel-specific consequences — dominant loss of CaV1.2 inactivation and mild NaV1.5 late current enhancement without RyR2 effects — revealing that individual CALM2 mutations differentially affect distinct ion channel targets.\",\n      \"evidence\": \"Recombinant protein Ca²⁺ binding assays; patch-clamp electrophysiology on CaV1.2, NaV1.5, and RyR2 in heterologous expression systems\",\n      \"pmids\": [\"26969752\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\n        \"Mechanism by which the same Ca²⁺-binding deficit selectively affects CaV1.2 but not RyR2 is unknown\",\n        \"No structural data explaining variant-specific channel selectivity\"\n      ]\n    },\n    {\n      \"year\": 2017,\n      \"claim\": \"CRISPR-Cas9 allele-specific knockout of the CALM2-N98S mutant allele in patient iPSC-derived cardiomyocytes rescued prolonged action potential duration and impaired L-type Ca²⁺ channel inactivation, definitively proving a dominant-negative mechanism for CALM2-linked long-QT syndrome.\",\n      \"evidence\": \"hiPSC-derived cardiomyocytes; patch-clamp action potential and LTCC current recordings; allele-specific CRISPR-Cas9 knockout\",\n      \"pmids\": [\"28335032\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\n        \"Whether the dominant-negative mechanism generalizes to all CALM2 arrhythmia variants is untested\",\n        \"Stoichiometric threshold of mutant versus wild-type calmodulin required to produce pathology is unknown\"\n      ]\n    },\n    {\n      \"year\": 2021,\n      \"claim\": \"CALM2 knockdown in hepatocellular carcinoma cells suppressed proliferation, migration, and in vivo tumor growth through downregulation of E2F5, positioning CALM2 as an upstream regulator of E2F5-dependent cell cycle progression in a cancer context.\",\n      \"evidence\": \"siRNA knockdown; transcriptomic profiling; proliferation and invasion assays; xenograft tumor formation\",\n      \"pmids\": [\"33788723\"],\n      \"confidence\": \"Medium\",\n      \"gaps\": [\n        \"Mechanistic link between calmodulin and E2F5 transcription not characterized\",\n        \"Whether calmodulin's Ca²⁺-sensing activity is required for E2F5 regulation is unknown\"\n      ]\n    },\n    {\n      \"year\": 2022,\n      \"claim\": \"In HER2-amplified gastric cancer cells, CALM2 knockdown inhibited Akt phosphorylation, derepressing the FoxO3a–Puma apoptotic axis in a caspase-dependent manner, establishing CALM2 as an upstream activator of Akt-mediated survival signaling.\",\n      \"evidence\": \"siRNA knockdown; Western blot for phospho-Akt, FoxO3a, Puma; caspase assays; pharmacological epistasis experiments\",\n      \"pmids\": [\"36460225\"],\n      \"confidence\": \"Medium\",\n      \"gaps\": [\n        \"Whether calmodulin directly activates Akt or acts through CaMKK/CaMKII intermediaries is not resolved\",\n        \"Findings limited to a single cancer cell type\"\n      ]\n    },\n    {\n      \"year\": 2024,\n      \"claim\": \"A suppression-and-replacement gene therapy strategy simultaneously knocking down all three CALM genes and replacing with shRNA-immune wild-type calmodulin partially rescued prolonged action potential duration in CALM2-D130G patient cardiomyocytes, providing proof-of-principle for therapeutic intervention in calmodulinopathy.\",\n      \"evidence\": \"shRNA knockdown with RT-qPCR validation; voltage-sensing dye APD measurements in CALM2-D130G hiPSC-derived cardiomyocytes\",\n      \"pmids\": [\"39069900\"],\n      \"confidence\": \"Medium\",\n      \"gaps\": [\n        \"Rescue was partial (66% attenuation); full APD normalization not achieved\",\n        \"In vivo efficacy and delivery to cardiomyocytes not tested\",\n        \"Long-term effects on total calmodulin protein levels not assessed\"\n      ]\n    },\n    {\n      \"year\": 2025,\n      \"claim\": \"Ribosome profiling confirmed that CALM2 contributes ~44% of cardiac calmodulin protein translation, explaining why CALM2 variants cause more severe arrhythmia phenotypes than CALM3 variants and providing a quantitative basis for the genotype–phenotype relationship.\",\n      \"evidence\": \"GTEx RNA-seq; ribosome profiling of human left ventricle; gnomAD variant constraint analysis; International Calmodulinopathy Registry outcomes\",\n      \"pmids\": [\"41846582\"],\n      \"confidence\": \"Medium\",\n      \"gaps\": [\n        \"Whether translational contribution varies across cardiac chambers or developmental stages is unknown\",\n        \"Protein-level quantification of CALM2-derived calmodulin (indistinguishable from other CALM gene products) relies on ribosome profiling as a proxy\"\n      ]\n    },\n    {\n      \"year\": null,\n      \"claim\": \"Structural and biophysical understanding of how individual CALM2 missense variants differentially disrupt specific ion channel targets (CaV1.2 versus RyR2 versus NaV1.5) remains incomplete, and the stoichiometric threshold of mutant calmodulin required for dominant-negative pathology has not been determined.\",\n      \"evidence\": \"\",\n      \"pmids\": [],\n      \"confidence\": \"High\",\n      \"gaps\": [\n        \"No high-resolution structure of mutant calmodulin bound to full-length CaV1.2 or RyR2\",\n        \"Quantitative dose-response for mutant-to-wild-type calmodulin ratio and electrophysiological phenotype not established\",\n        \"In vivo gene therapy efficacy for CALM2-linked arrhythmias untested\"\n      ]\n    }\n  ],\n  \"mechanism_profile\": {\n    \"molecular_activity\": [\n      {\"term_id\": \"GO:0098772\", \"supporting_discovery_ids\": [0, 1, 2, 3]},\n      {\"term_id\": \"GO:0140299\", \"supporting_discovery_ids\": [0, 2, 4]}\n    ],\n    \"localization\": [\n      {\"term_id\": \"GO:0005829\", \"supporting_discovery_ids\": [4]}\n    ],\n    \"pathway\": [\n      {\"term_id\": \"R-HSA-162582\", \"supporting_discovery_ids\": [2, 3, 7]},\n      {\"term_id\": \"R-HSA-5357801\", \"supporting_discovery_ids\": [7, 8]},\n      {\"term_id\": \"R-HSA-1643685\", \"supporting_discovery_ids\": [0, 2, 3, 6]}\n    ],\n    \"complexes\": [],\n    \"partners\": [\n      \"CACNA1C\",\n      \"RYR2\",\n      \"SCN5A\",\n      \"AKT1\",\n      \"E2F5\"\n    ],\n    \"other_free_text\": []\n  }\n}\n```"}