{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HDVKKXRYRQOUTYXD4FRG7ASAHX","short_pith_number":"pith:HDVKKXRY","schema_version":"1.0","canonical_sha256":"38eaa55e388c1d49e2e3e1626f82403df352e5b9ed2fe7eecd34c4e613749565","source":{"kind":"arxiv","id":"2507.07666","version":1},"attestation_state":"computed","paper":{"title":"Machine Learning-Driven Enzyme Mining: Opportunities, Challenges, and Future Perspectives","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.BM","authors_text":"David Medina-Ortiz, Felix Moorhoff, Jing Zhao, Mehdi D. Davari, Sizhe Qiu, Wenjuan Dong, Yanzi Zhang","submitted_at":"2025-07-10T11:47:58Z","abstract_excerpt":"Enzyme mining is rapidly evolving as a data-driven strategy to identify biocatalysts with tailored functions from the vast landscape of uncharacterized proteins. The integration of machine learning into these workflows enables high-throughput prediction of enzyme functions, including Enzyme Commission numbers, Gene Ontology terms, substrate specificity, and key catalytic properties such as kinetic parameters, optimal temperature, pH, solubility, and thermophilicity. This review provides a systematic overview of state-of-the-art machine learning models and highlights representative case studies"},"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":"2507.07666","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"q-bio.BM","submitted_at":"2025-07-10T11:47:58Z","cross_cats_sorted":[],"title_canon_sha256":"a7a39ad2dc2940b4f2dbf607ad9e24bc9a3b9ca620821302bfab82ac2b3d82e6","abstract_canon_sha256":"aae54b4697e8ed88e336d759c415a39268e8d33f820d152ceb062894ce6651e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:02.686743Z","signature_b64":"2zGSSc5s8/Ry8GVemU/ARlNxUUUW23E+8Sqn+0wREp/jjV4gfVBRAPe8Ha9nOmaZ3WVAneJE4sUu+iB2U3o2Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38eaa55e388c1d49e2e3e1626f82403df352e5b9ed2fe7eecd34c4e613749565","last_reissued_at":"2026-07-05T11:35:02.686368Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:02.686368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Machine Learning-Driven Enzyme Mining: Opportunities, Challenges, and Future Perspectives","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.BM","authors_text":"David Medina-Ortiz, Felix Moorhoff, Jing Zhao, Mehdi D. Davari, Sizhe Qiu, Wenjuan Dong, Yanzi Zhang","submitted_at":"2025-07-10T11:47:58Z","abstract_excerpt":"Enzyme mining is rapidly evolving as a data-driven strategy to identify biocatalysts with tailored functions from the vast landscape of uncharacterized proteins. The integration of machine learning into these workflows enables high-throughput prediction of enzyme functions, including Enzyme Commission numbers, Gene Ontology terms, substrate specificity, and key catalytic properties such as kinetic parameters, optimal temperature, pH, solubility, and thermophilicity. This review provides a systematic overview of state-of-the-art machine learning models and highlights representative case studies"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07666","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/2507.07666/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":"2507.07666","created_at":"2026-07-05T11:35:02.686427+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.07666v1","created_at":"2026-07-05T11:35:02.686427+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07666","created_at":"2026-07-05T11:35:02.686427+00:00"},{"alias_kind":"pith_short_12","alias_value":"HDVKKXRYRQOU","created_at":"2026-07-05T11:35:02.686427+00:00"},{"alias_kind":"pith_short_16","alias_value":"HDVKKXRYRQOUTYXD","created_at":"2026-07-05T11:35:02.686427+00:00"},{"alias_kind":"pith_short_8","alias_value":"HDVKKXRY","created_at":"2026-07-05T11:35:02.686427+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/HDVKKXRYRQOUTYXD4FRG7ASAHX","json":"https://pith.science/pith/HDVKKXRYRQOUTYXD4FRG7ASAHX.json","graph_json":"https://pith.science/api/pith-number/HDVKKXRYRQOUTYXD4FRG7ASAHX/graph.json","events_json":"https://pith.science/api/pith-number/HDVKKXRYRQOUTYXD4FRG7ASAHX/events.json","paper":"https://pith.science/paper/HDVKKXRY"},"agent_actions":{"view_html":"https://pith.science/pith/HDVKKXRYRQOUTYXD4FRG7ASAHX","download_json":"https://pith.science/pith/HDVKKXRYRQOUTYXD4FRG7ASAHX.json","view_paper":"https://pith.science/paper/HDVKKXRY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.07666&json=true","fetch_graph":"https://pith.science/api/pith-number/HDVKKXRYRQOUTYXD4FRG7ASAHX/graph.json","fetch_events":"https://pith.science/api/pith-number/HDVKKXRYRQOUTYXD4FRG7ASAHX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HDVKKXRYRQOUTYXD4FRG7ASAHX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HDVKKXRYRQOUTYXD4FRG7ASAHX/action/storage_attestation","attest_author":"https://pith.science/pith/HDVKKXRYRQOUTYXD4FRG7ASAHX/action/author_attestation","sign_citation":"https://pith.science/pith/HDVKKXRYRQOUTYXD4FRG7ASAHX/action/citation_signature","submit_replication":"https://pith.science/pith/HDVKKXRYRQOUTYXD4FRG7ASAHX/action/replication_record"}},"created_at":"2026-07-05T11:35:02.686427+00:00","updated_at":"2026-07-05T11:35:02.686427+00:00"}