{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:6KNKPTLXQG7SZ65LFXESLUYN45","short_pith_number":"pith:6KNKPTLX","schema_version":"1.0","canonical_sha256":"f29aa7cd7781bf2cfbab2dc925d30de773c5c7c5b2ea55f4fed43bf5b54d679b","source":{"kind":"arxiv","id":"1805.03771","version":1},"attestation_state":"computed","paper":{"title":"Transcription Factor-DNA Binding Via Machine Learning Ensembles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.GN","authors_text":"Charles Delisi, Mark Kon, Yue Fan","submitted_at":"2018-05-10T01:13:44Z","abstract_excerpt":"We present ensemble methods in a machine learning (ML) framework combining predictions from five known motif/binding site exploration algorithms. For a given TF the ensemble starts with position weight matrices (PWM's) for the motif, collected from the component algorithms. Using dimension reduction, we identify significant PWM-based subspaces for analysis. Within each subspace a machine classifier is built for identifying the TF's gene (promoter) targets (Problem 1). These PWM-based subspaces form an ML-based sequence analysis tool. Problem 2 (finding binding motifs) is solved by agglomeratin"},"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":"1805.03771","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2018-05-10T01:13:44Z","cross_cats_sorted":[],"title_canon_sha256":"689cd634f2a466692551b79a1095820f16c502a0eb1829bc5b3f8f7720a2d93a","abstract_canon_sha256":"21e0115f3b22df238fa2c3d0eac4330ffbfc7253eaae085980c67a6bc1dd712c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:18.822517Z","signature_b64":"VrMTEivgzXkZ9tUgvmoxEXht4j//7W/eB5n/Mo3tBSzqPJbWeK17f/rCAdBnT97IoqEjisfQhEpH4ciHZ3zzCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f29aa7cd7781bf2cfbab2dc925d30de773c5c7c5b2ea55f4fed43bf5b54d679b","last_reissued_at":"2026-05-18T00:16:18.822073Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:18.822073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transcription Factor-DNA Binding Via Machine Learning Ensembles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.GN","authors_text":"Charles Delisi, Mark Kon, Yue Fan","submitted_at":"2018-05-10T01:13:44Z","abstract_excerpt":"We present ensemble methods in a machine learning (ML) framework combining predictions from five known motif/binding site exploration algorithms. For a given TF the ensemble starts with position weight matrices (PWM's) for the motif, collected from the component algorithms. Using dimension reduction, we identify significant PWM-based subspaces for analysis. Within each subspace a machine classifier is built for identifying the TF's gene (promoter) targets (Problem 1). These PWM-based subspaces form an ML-based sequence analysis tool. Problem 2 (finding binding motifs) is solved by agglomeratin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.03771","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":""},"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":"1805.03771","created_at":"2026-05-18T00:16:18.822135+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.03771v1","created_at":"2026-05-18T00:16:18.822135+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.03771","created_at":"2026-05-18T00:16:18.822135+00:00"},{"alias_kind":"pith_short_12","alias_value":"6KNKPTLXQG7S","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"6KNKPTLXQG7SZ65L","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"6KNKPTLX","created_at":"2026-05-18T12:32:08.215937+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/6KNKPTLXQG7SZ65LFXESLUYN45","json":"https://pith.science/pith/6KNKPTLXQG7SZ65LFXESLUYN45.json","graph_json":"https://pith.science/api/pith-number/6KNKPTLXQG7SZ65LFXESLUYN45/graph.json","events_json":"https://pith.science/api/pith-number/6KNKPTLXQG7SZ65LFXESLUYN45/events.json","paper":"https://pith.science/paper/6KNKPTLX"},"agent_actions":{"view_html":"https://pith.science/pith/6KNKPTLXQG7SZ65LFXESLUYN45","download_json":"https://pith.science/pith/6KNKPTLXQG7SZ65LFXESLUYN45.json","view_paper":"https://pith.science/paper/6KNKPTLX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.03771&json=true","fetch_graph":"https://pith.science/api/pith-number/6KNKPTLXQG7SZ65LFXESLUYN45/graph.json","fetch_events":"https://pith.science/api/pith-number/6KNKPTLXQG7SZ65LFXESLUYN45/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6KNKPTLXQG7SZ65LFXESLUYN45/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6KNKPTLXQG7SZ65LFXESLUYN45/action/storage_attestation","attest_author":"https://pith.science/pith/6KNKPTLXQG7SZ65LFXESLUYN45/action/author_attestation","sign_citation":"https://pith.science/pith/6KNKPTLXQG7SZ65LFXESLUYN45/action/citation_signature","submit_replication":"https://pith.science/pith/6KNKPTLXQG7SZ65LFXESLUYN45/action/replication_record"}},"created_at":"2026-05-18T00:16:18.822135+00:00","updated_at":"2026-05-18T00:16:18.822135+00:00"}