{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QVEWCRQCIR65MR2J64BOVQARJJ","short_pith_number":"pith:QVEWCRQC","schema_version":"1.0","canonical_sha256":"8549614602447dd64749f702eac0114a6e31a4e6c0ffc6f953afa7898a6b8471","source":{"kind":"arxiv","id":"2503.16214","version":2},"attestation_state":"computed","paper":{"title":"Targeting Neurodegeneration: Three Machine Learning Methods for G9a Inhibitors Discovery Using PubChem and Scikit-learn","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.QM","authors_text":"Konstantin Nikolic, Mariya L. Ivanova, Nicola Russo","submitted_at":"2025-03-20T15:01:29Z","abstract_excerpt":"In light of the increasing interest in G9a's role in neuroscience, three machine learning (ML) models, that are time efficient and cost effective, were developed to support researchers in this area. The models are based on data provided by PubChem and performed by algorithms interpreted by the scikit-learn Python-based ML library. The first ML model aimed to predict the efficacy magnitude of active G9a inhibitors. The ML models were trained with 3,112 and tested with 778 samples. The Gradient Boosting Regressor perform the best, achieving 17.81% means relative error (MRE), 21.48% mean absolute"},"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":"2503.16214","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2025-03-20T15:01:29Z","cross_cats_sorted":[],"title_canon_sha256":"2d0e5d12208ab46dd1c6076fabc813d5372653e17e4000980caac4ef4cecaa33","abstract_canon_sha256":"a583dbcbeaa9c96e470fe04d1a7888fc9f5001da05d167584c7e8fe07ad94737"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:24.122353Z","signature_b64":"1rOyhh5c7Faw0MgGFBg7KA8KNnPdgnmRn23XG+Umu34AbAV1YCYOEPhj2AB/klzCVM0Lse9hHnkoguDh0Cj0Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8549614602447dd64749f702eac0114a6e31a4e6c0ffc6f953afa7898a6b8471","last_reissued_at":"2026-07-05T11:51:24.121840Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:24.121840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Targeting Neurodegeneration: Three Machine Learning Methods for G9a Inhibitors Discovery Using PubChem and Scikit-learn","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.QM","authors_text":"Konstantin Nikolic, Mariya L. Ivanova, Nicola Russo","submitted_at":"2025-03-20T15:01:29Z","abstract_excerpt":"In light of the increasing interest in G9a's role in neuroscience, three machine learning (ML) models, that are time efficient and cost effective, were developed to support researchers in this area. The models are based on data provided by PubChem and performed by algorithms interpreted by the scikit-learn Python-based ML library. The first ML model aimed to predict the efficacy magnitude of active G9a inhibitors. The ML models were trained with 3,112 and tested with 778 samples. The Gradient Boosting Regressor perform the best, achieving 17.81% means relative error (MRE), 21.48% mean absolute"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16214","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/2503.16214/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":"2503.16214","created_at":"2026-07-05T11:51:24.121899+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.16214v2","created_at":"2026-07-05T11:51:24.121899+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16214","created_at":"2026-07-05T11:51:24.121899+00:00"},{"alias_kind":"pith_short_12","alias_value":"QVEWCRQCIR65","created_at":"2026-07-05T11:51:24.121899+00:00"},{"alias_kind":"pith_short_16","alias_value":"QVEWCRQCIR65MR2J","created_at":"2026-07-05T11:51:24.121899+00:00"},{"alias_kind":"pith_short_8","alias_value":"QVEWCRQC","created_at":"2026-07-05T11:51:24.121899+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.01137","citing_title":"Comparative analysis of computational approaches for predicting Transthyretin (TTR) transcription activators and human dopamine D1 receptor antagonists","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QVEWCRQCIR65MR2J64BOVQARJJ","json":"https://pith.science/pith/QVEWCRQCIR65MR2J64BOVQARJJ.json","graph_json":"https://pith.science/api/pith-number/QVEWCRQCIR65MR2J64BOVQARJJ/graph.json","events_json":"https://pith.science/api/pith-number/QVEWCRQCIR65MR2J64BOVQARJJ/events.json","paper":"https://pith.science/paper/QVEWCRQC"},"agent_actions":{"view_html":"https://pith.science/pith/QVEWCRQCIR65MR2J64BOVQARJJ","download_json":"https://pith.science/pith/QVEWCRQCIR65MR2J64BOVQARJJ.json","view_paper":"https://pith.science/paper/QVEWCRQC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.16214&json=true","fetch_graph":"https://pith.science/api/pith-number/QVEWCRQCIR65MR2J64BOVQARJJ/graph.json","fetch_events":"https://pith.science/api/pith-number/QVEWCRQCIR65MR2J64BOVQARJJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QVEWCRQCIR65MR2J64BOVQARJJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QVEWCRQCIR65MR2J64BOVQARJJ/action/storage_attestation","attest_author":"https://pith.science/pith/QVEWCRQCIR65MR2J64BOVQARJJ/action/author_attestation","sign_citation":"https://pith.science/pith/QVEWCRQCIR65MR2J64BOVQARJJ/action/citation_signature","submit_replication":"https://pith.science/pith/QVEWCRQCIR65MR2J64BOVQARJJ/action/replication_record"}},"created_at":"2026-07-05T11:51:24.121899+00:00","updated_at":"2026-07-05T11:51:24.121899+00:00"}