{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2009:GRTMJWMV34JRCX2KE564ALXYSR","short_pith_number":"pith:GRTMJWMV","schema_version":"1.0","canonical_sha256":"3466c4d995df13115f4a277dc02ef8947d33934b1fb452ca541a07b95c5cb139","source":{"kind":"arxiv","id":"0901.3198","version":1},"attestation_state":"computed","paper":{"title":"On subset seeds for protein alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.QM","authors_text":"Anna Gambin, Eugenia Furletova (IMPB), Ewa Szczurek (MPI), Gregory Kucherov (LIFL, INRIA Lille - Nord Europe), Laurent No\\'e (LIFL, Mikhail A. Roytberg (IMPB), Slawomir Lasota","submitted_at":"2009-01-21T07:59:27Z","abstract_excerpt":"We apply the concept of subset seeds proposed in [1] to similarity search in protein sequences. The main question studied is the design of efficient seed alphabets to construct seeds with optimal sensitivity/selectivity trade-offs. We propose several different design methods and use them to construct several alphabets. We then perform a comparative analysis of seeds built over those alphabets and compare them with the standard BLASTP seeding method [2], [3], as well as with the family of vector seeds proposed in [4]. While the formalism of subset seeds is less expressive (but less costly to im"},"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":"0901.3198","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2009-01-21T07:59:27Z","cross_cats_sorted":[],"title_canon_sha256":"ffe1f17f738e22150f2d4682bf49a16b22fd7367fa4388412cc86e59bedfbf47","abstract_canon_sha256":"31f21cb8c31d34925d038b13e359be4d5839106b4b32d350ab088912b8a13daf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:31:31.396999Z","signature_b64":"1OxqFmgW8/YcOnOBGfn7MsqgywaSBEh6M2jlzCLzfWJ0hxvY+k83A/rlozwdXrMOogMVTY9aZbeiM4/WaLFODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3466c4d995df13115f4a277dc02ef8947d33934b1fb452ca541a07b95c5cb139","last_reissued_at":"2026-05-18T04:31:31.396434Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:31:31.396434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On subset seeds for protein alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.QM","authors_text":"Anna Gambin, Eugenia Furletova (IMPB), Ewa Szczurek (MPI), Gregory Kucherov (LIFL, INRIA Lille - Nord Europe), Laurent No\\'e (LIFL, Mikhail A. Roytberg (IMPB), Slawomir Lasota","submitted_at":"2009-01-21T07:59:27Z","abstract_excerpt":"We apply the concept of subset seeds proposed in [1] to similarity search in protein sequences. The main question studied is the design of efficient seed alphabets to construct seeds with optimal sensitivity/selectivity trade-offs. We propose several different design methods and use them to construct several alphabets. We then perform a comparative analysis of seeds built over those alphabets and compare them with the standard BLASTP seeding method [2], [3], as well as with the family of vector seeds proposed in [4]. While the formalism of subset seeds is less expressive (but less costly to im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"0901.3198","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":"0901.3198","created_at":"2026-05-18T04:31:31.396510+00:00"},{"alias_kind":"arxiv_version","alias_value":"0901.3198v1","created_at":"2026-05-18T04:31:31.396510+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.0901.3198","created_at":"2026-05-18T04:31:31.396510+00:00"},{"alias_kind":"pith_short_12","alias_value":"GRTMJWMV34JR","created_at":"2026-05-18T12:25:59.703012+00:00"},{"alias_kind":"pith_short_16","alias_value":"GRTMJWMV34JRCX2K","created_at":"2026-05-18T12:25:59.703012+00:00"},{"alias_kind":"pith_short_8","alias_value":"GRTMJWMV","created_at":"2026-05-18T12:25:59.703012+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/GRTMJWMV34JRCX2KE564ALXYSR","json":"https://pith.science/pith/GRTMJWMV34JRCX2KE564ALXYSR.json","graph_json":"https://pith.science/api/pith-number/GRTMJWMV34JRCX2KE564ALXYSR/graph.json","events_json":"https://pith.science/api/pith-number/GRTMJWMV34JRCX2KE564ALXYSR/events.json","paper":"https://pith.science/paper/GRTMJWMV"},"agent_actions":{"view_html":"https://pith.science/pith/GRTMJWMV34JRCX2KE564ALXYSR","download_json":"https://pith.science/pith/GRTMJWMV34JRCX2KE564ALXYSR.json","view_paper":"https://pith.science/paper/GRTMJWMV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=0901.3198&json=true","fetch_graph":"https://pith.science/api/pith-number/GRTMJWMV34JRCX2KE564ALXYSR/graph.json","fetch_events":"https://pith.science/api/pith-number/GRTMJWMV34JRCX2KE564ALXYSR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GRTMJWMV34JRCX2KE564ALXYSR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GRTMJWMV34JRCX2KE564ALXYSR/action/storage_attestation","attest_author":"https://pith.science/pith/GRTMJWMV34JRCX2KE564ALXYSR/action/author_attestation","sign_citation":"https://pith.science/pith/GRTMJWMV34JRCX2KE564ALXYSR/action/citation_signature","submit_replication":"https://pith.science/pith/GRTMJWMV34JRCX2KE564ALXYSR/action/replication_record"}},"created_at":"2026-05-18T04:31:31.396510+00:00","updated_at":"2026-05-18T04:31:31.396510+00:00"}