iSeqSearch: incremental protein search for iBlast/iMMSeqs2/iDiamond.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40313391", "kind": "science-record", "revision": 3, "content_hash": "sha256:f6a2e9f166005f9a328a565606a6c254eb714325c5dea51a0f86695c8a5771c1", "created_at": "2026-11-01T20:30:28Z", "updated_at": "2026-11-01T22:13:59Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "iSeqSearch: incremental protein search for iBlast/iMMSeqs2/iDiamond.", "doi": "10.7717/peerj.19171", "pmid": "40313391", "authors": ["Hyunwoo Yoo", "Mohammadsaleh Refahi", "Robi Polikar", "Bahrad A Sokhansanj", "James R Brown", "Gail L Rosen"], "journal": "PeerJ", "year": 2025, "abstract": "Background: The advancement of sequencing technology has led to a rapid increase in the amount of DNA and protein sequence data; consequently, the size of genomic and proteomic databases is constantly growing. As a result, database searches need to be continually updated to account for the new data being added. However, continually re-searching the entire existing dataset wastes resources. Incremental database search can address this problem.\nMethods: One recently introduced incremental search method is iBlast, which wraps the BLAST sequence search method with an algorithm to reuse previously processed data and thereby increase search efficiency. The iBlast wrapper, however, must be generalized to support better performing DNA/protein sequence search methods that have been developed, namely MMseqs2 and Diamond. To address this need, we propose iSeqsSearch, which extends iBlast by incorporating support for MMseqs2 (iMMseqs2) and Diamond (iDiamond), thereby providing a more generalized and broadly effective incremental search framework. Moreover, the previously published iBlast wrapper has to be revised to be more robust and usable by the general community.\nResults: iMMseqs2 and iDiamond, which apply the incremental approach, perform nearly identical to MMseqs2 and Diamond. Notably, when comparing ranking comparison methods such as the Pearson correlation, we observe a high concordance of over 0.9, indicating similar results. Moreover, in some cases, our incremental approach, iSeqsSearch, which extends the iBlast merge function to iMMseqs2 and iDiamond, provides more hits compared to the conventional MMseqs2 and Diamond methods.\nConclusion: The incremental approach using iMMseqs2 and iDiamond demonstrates efficiency in terms of reusing previously processed data while maintaining high accuracy and concordance in search results. This method can reduce resource waste in continually growing genomic and proteomic database searches. The sample codes and data are available at GitHub and Zenodo (https://github.com/EESI/Incremental-Protein-Search; DOI: 10.5281/zenodo.14675319).", "claims": [{"id": "claim-method", "statement": "This study implements an incremental method that utilizes Spouge statistics by Park et al. (2012).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40313391", "locator": "sections[2] \"MATERIALS & METHODS\" paragraph 2", "quote": "This study implements an incremental method that utilizes Spouge statistics by Park et al. (2012)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The following information was supplied regarding data availability:The Incremental-Protein-Search is available at GitHub and Zenodo:- https://github.com/EESI/Incremental-Protein-Search - ece303, & yoohw2. (2025). EESI/Incremental-Protein-Search: iSeqSearch (v1.0.1). Zenodo. https://doi.org/10.5281/zenodo.14675319.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40313391", "locator": "sections[8] \"Additional Information and Declarations\" paragraph 5", "quote": "The following information was supplied regarding data availability:The Incremental-Protein-Search is available at GitHub and Zenodo:- https://github.com/EESI/Incremental-Protein-Search - ece303, & yoohw2. (2025). EESI/Incremental-Protein-Search: iSeqSearch (v1.0.1). Zenodo. https://doi.org/10.5281/zenodo.14675319."}], "state": "complete"}, {"id": "claim-target-result", "statement": "iMMseqs2 and iDiamond, which apply the incremental approach, perform nearly identical to MMseqs2 and Diamond.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:40313391", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "iMMseqs2 and iDiamond, which apply the incremental approach, perform nearly identical to MMseqs2 and Diamond."}, {"asset": "source:pmid:40313391", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "Notably, when comparing ranking comparison methods such as the Pearson correlation, we observe a high concordance of over 0.9, indicating similar results."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "iMMseqs2 and iDiamond, which apply the incremental approach, perform nearly identical to MMseqs2 and Diamond.", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:40313391"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:accession_absent", "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "complete", "blocked_on": null, "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40313391", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.7717/peerj.19171", "sha256": "sha256:3e65b06045764c6e7124e5275889d1f00761ac1573adab4ceaf38f2f34856edc", "bytes": 24135, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.7717/peerj.19171", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12045279", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "correlation_analysis", "specific": "pearson", "label": "Correlation analysis", "dsl_operations": ["pearson_r"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 0.7, "band": "medium", "quote": "Pearson correlation"}}, {"id": "method-2", "family": "sequence_alignment", "specific": "blast", "label": "Sequence alignment / homology", "dsl_operations": ["sequence_align", "alignment_identity"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["sequence_records"], "evidence": {"score": 0.7, "band": "medium", "quote": "BLAST"}}, {"id": "method-3", "family": null, "specific": null, "label": "Spouge statistics", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "This study implements an incremental method that utilizes Spouge statistics by Park et al. (2012)."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["pearson_r"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pearson."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["The following information was supplied regarding data availability:The Incremental-Protein-Search is available at GitHub and Zenodo:- https://github.com/EESI/Incremental-Protein-Search - ece303, & yoohw2. (2025). EESI/Incremental-Protein-Search: iSeqSearch (v1.0.1). Zenodo. https://doi.org/10.5281/zenodo.14675319."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["pearson_r"], "assets": ["source:pmid:40313391"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:51:29Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 6529, "completion_tokens": 1460, "cached_tokens": 0}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:40313391", "type": "paper", "label": "pmid:40313391"}, {"id": "source:pmid:40313391", "type": "manuscript", "label": "PMID 40313391 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40313391", "type": "paper", "label": "pmid:40313391"}, {"id": "source:pmid:40313391", "type": "manuscript", "label": "PMID 40313391 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40313391", "type": "extraction", "used": ["source:pmid:40313391"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}, {"id": "agent:minimax-reader", "type": "software", "label": "MiniMax literature reader"}], "source_run_id": "reading-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:40313391", "parent_hash": "sha256:4b4e59f233510357479ab1716608bbf83f1dcffbc5d0b5fcbfe4eef62da9222e", "fork_of": null, "generation": 2}, "gaps": ["execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"role": "analysis", "definition_id": "correlation_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pearson_r"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["Pearson correlation"], "order_basis": "analysis_only", "id": "assay:1"}]}