{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OEWO5SV3G3DDOJC4WIMRIUAGG6","short_pith_number":"pith:OEWO5SV3","schema_version":"1.0","canonical_sha256":"712ceecabb36c637245cb2191450063780c6e3d172077b9d008c11394d87d72c","source":{"kind":"arxiv","id":"2511.09026","version":2},"attestation_state":"computed","paper":{"title":"DeepVRegulome: DNABERT-based deep-learning framework for predicting the functional impact of short genomic variants on the human regulome","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"q-bio.GN","authors_text":"Alisa Yurovsky, Han Liu, Matthew Obusan, Max Chao, Nimisha Papineni, Pallavi Surana, Pratik Dutta, Ramana V Davuluri, Rekha Sathian, Yanrong Ji, Zhihan Zhou","submitted_at":"2025-11-12T06:25:31Z","abstract_excerpt":"Whole-genome sequencing (WGS) has revealed numerous non-coding short variants whose functional impacts remain poorly understood. Despite recent advances in deep-learning genomic approaches, accurately predicting and prioritizing clinically relevant mutations in gene regulatory regions remains a major challenge. We developed DeepVRegulome, a computational framework integrating 464 fine-tuned DNABERT models (458 transcription factor, 4 histone mark, and 2 splice site models) trained on ENCODE and GENCODE datasets. The framework pairs these deep learning models with a suite of analytical tools: q"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2511.09026","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2025-11-12T06:25:31Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"8a2eadd66faa58bd6e6dd3b078f94679777cd58e550fc02479a716dede4b8b54","abstract_canon_sha256":"cbfc527401ada89a962dec896aacb5c58f2985ee7556a674adaa4fe9f91c2b97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T01:25:31.420278Z","signature_b64":"tYh7dtnuS9V42qW/iPAve33WTf7/T0PJu0sqkeuChhtogd7FvXcT2PkkDDxMor1zyW1wlIGX2c2b9SrRwWWrDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"712ceecabb36c637245cb2191450063780c6e3d172077b9d008c11394d87d72c","last_reissued_at":"2026-07-29T01:25:31.419354Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T01:25:31.419354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepVRegulome: DNABERT-based deep-learning framework for predicting the functional impact of short genomic variants on the human regulome","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"q-bio.GN","authors_text":"Alisa Yurovsky, Han Liu, Matthew Obusan, Max Chao, Nimisha Papineni, Pallavi Surana, Pratik Dutta, Ramana V Davuluri, Rekha Sathian, Yanrong Ji, Zhihan Zhou","submitted_at":"2025-11-12T06:25:31Z","abstract_excerpt":"Whole-genome sequencing (WGS) has revealed numerous non-coding short variants whose functional impacts remain poorly understood. Despite recent advances in deep-learning genomic approaches, accurately predicting and prioritizing clinically relevant mutations in gene regulatory regions remains a major challenge. We developed DeepVRegulome, a computational framework integrating 464 fine-tuned DNABERT models (458 transcription factor, 4 histone mark, and 2 splice site models) trained on ENCODE and GENCODE datasets. The framework pairs these deep learning models with a suite of analytical tools: q"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.09026","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2511.09026/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2511.09026","created_at":"2026-07-29T01:25:31.419747+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.09026v2","created_at":"2026-07-29T01:25:31.419747+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.09026","created_at":"2026-07-29T01:25:31.419747+00:00"},{"alias_kind":"pith_short_12","alias_value":"OEWO5SV3G3DD","created_at":"2026-07-29T01:25:31.419747+00:00"},{"alias_kind":"pith_short_16","alias_value":"OEWO5SV3G3DDOJC4","created_at":"2026-07-29T01:25:31.419747+00:00"},{"alias_kind":"pith_short_8","alias_value":"OEWO5SV3","created_at":"2026-07-29T01:25:31.419747+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OEWO5SV3G3DDOJC4WIMRIUAGG6","json":"https://pith.science/pith/OEWO5SV3G3DDOJC4WIMRIUAGG6.json","graph_json":"https://pith.science/api/pith-number/OEWO5SV3G3DDOJC4WIMRIUAGG6/graph.json","events_json":"https://pith.science/api/pith-number/OEWO5SV3G3DDOJC4WIMRIUAGG6/events.json","paper":"https://pith.science/paper/OEWO5SV3"},"agent_actions":{"view_html":"https://pith.science/pith/OEWO5SV3G3DDOJC4WIMRIUAGG6","download_json":"https://pith.science/pith/OEWO5SV3G3DDOJC4WIMRIUAGG6.json","view_paper":"https://pith.science/paper/OEWO5SV3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.09026&json=true","fetch_graph":"https://pith.science/api/pith-number/OEWO5SV3G3DDOJC4WIMRIUAGG6/graph.json","fetch_events":"https://pith.science/api/pith-number/OEWO5SV3G3DDOJC4WIMRIUAGG6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OEWO5SV3G3DDOJC4WIMRIUAGG6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OEWO5SV3G3DDOJC4WIMRIUAGG6/action/storage_attestation","attest_author":"https://pith.science/pith/OEWO5SV3G3DDOJC4WIMRIUAGG6/action/author_attestation","sign_citation":"https://pith.science/pith/OEWO5SV3G3DDOJC4WIMRIUAGG6/action/citation_signature","submit_replication":"https://pith.science/pith/OEWO5SV3G3DDOJC4WIMRIUAGG6/action/replication_record"}},"created_at":"2026-07-29T01:25:31.419747+00:00","updated_at":"2026-07-29T01:25:31.419747+00:00"}