{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BYEWDEGONR2RW2VVYN7CK3FRED","short_pith_number":"pith:BYEWDEGO","schema_version":"1.0","canonical_sha256":"0e096190ce6c751b6ab5c37e256cb120f6cf0066be9730fc0031ab507197262f","source":{"kind":"arxiv","id":"2505.19740","version":1},"attestation_state":"computed","paper":{"title":"Machine Learning Algorithm for Noise Reduction and Disease-Causing Gene Feature Extraction in Gene Sequencing Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Weichen Si, Yihao Ou, Zhen Tian","submitted_at":"2025-05-26T09:23:09Z","abstract_excerpt":"In this study, we propose a machine learning-based method for noise reduction and disease-causing gene feature extraction in gene sequencing DeepSeqDenoise algorithm combines CNN and RNN to effectively remove the sequencing noise, and improves the signal-to-noise ratio by 9.4 dB. We screened 17 key features by feature engineering, and constructed an integrated learning model to predict disease-causing genes with 94.3% accuracy. We successfully identified 57 new candidate disease-causing genes in a cardiovascular disease cohort validation, and detected 3 missed variants in clinical applications"},"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":"2505.19740","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T09:23:09Z","cross_cats_sorted":[],"title_canon_sha256":"b6fb9ede302a81248e6cbf4d625aeb11c060dd978c1607cc8122fd3e020dfe6a","abstract_canon_sha256":"eda0d41613fd926258fe52270cc6b326bd46bfb0d30305e11af8375e07820440"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:35.528207Z","signature_b64":"4lcuI3isAPIu3+phgErOMuhxDo/w6jfzz+ODKugzp4LrCOiWzGSuwD+Chfp1yt4BzRfo6vZyxCBnpAI9Ot/DCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e096190ce6c751b6ab5c37e256cb120f6cf0066be9730fc0031ab507197262f","last_reissued_at":"2026-07-05T11:09:35.527756Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:35.527756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Machine Learning Algorithm for Noise Reduction and Disease-Causing Gene Feature Extraction in Gene Sequencing Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Weichen Si, Yihao Ou, Zhen Tian","submitted_at":"2025-05-26T09:23:09Z","abstract_excerpt":"In this study, we propose a machine learning-based method for noise reduction and disease-causing gene feature extraction in gene sequencing DeepSeqDenoise algorithm combines CNN and RNN to effectively remove the sequencing noise, and improves the signal-to-noise ratio by 9.4 dB. We screened 17 key features by feature engineering, and constructed an integrated learning model to predict disease-causing genes with 94.3% accuracy. We successfully identified 57 new candidate disease-causing genes in a cardiovascular disease cohort validation, and detected 3 missed variants in clinical applications"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19740","kind":"arxiv","version":1},"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/2505.19740/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":"2505.19740","created_at":"2026-07-05T11:09:35.527811+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19740v1","created_at":"2026-07-05T11:09:35.527811+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19740","created_at":"2026-07-05T11:09:35.527811+00:00"},{"alias_kind":"pith_short_12","alias_value":"BYEWDEGONR2R","created_at":"2026-07-05T11:09:35.527811+00:00"},{"alias_kind":"pith_short_16","alias_value":"BYEWDEGONR2RW2VV","created_at":"2026-07-05T11:09:35.527811+00:00"},{"alias_kind":"pith_short_8","alias_value":"BYEWDEGO","created_at":"2026-07-05T11:09:35.527811+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/BYEWDEGONR2RW2VVYN7CK3FRED","json":"https://pith.science/pith/BYEWDEGONR2RW2VVYN7CK3FRED.json","graph_json":"https://pith.science/api/pith-number/BYEWDEGONR2RW2VVYN7CK3FRED/graph.json","events_json":"https://pith.science/api/pith-number/BYEWDEGONR2RW2VVYN7CK3FRED/events.json","paper":"https://pith.science/paper/BYEWDEGO"},"agent_actions":{"view_html":"https://pith.science/pith/BYEWDEGONR2RW2VVYN7CK3FRED","download_json":"https://pith.science/pith/BYEWDEGONR2RW2VVYN7CK3FRED.json","view_paper":"https://pith.science/paper/BYEWDEGO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19740&json=true","fetch_graph":"https://pith.science/api/pith-number/BYEWDEGONR2RW2VVYN7CK3FRED/graph.json","fetch_events":"https://pith.science/api/pith-number/BYEWDEGONR2RW2VVYN7CK3FRED/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BYEWDEGONR2RW2VVYN7CK3FRED/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BYEWDEGONR2RW2VVYN7CK3FRED/action/storage_attestation","attest_author":"https://pith.science/pith/BYEWDEGONR2RW2VVYN7CK3FRED/action/author_attestation","sign_citation":"https://pith.science/pith/BYEWDEGONR2RW2VVYN7CK3FRED/action/citation_signature","submit_replication":"https://pith.science/pith/BYEWDEGONR2RW2VVYN7CK3FRED/action/replication_record"}},"created_at":"2026-07-05T11:09:35.527811+00:00","updated_at":"2026-07-05T11:09:35.527811+00:00"}