compareMS2 2.0: An Improved Software for Comparing Tandem Mass Spectrometry Datasets.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:36173614", "kind": "science-record", "revision": 3, "content_hash": "sha256:0eacef9f5255986a534e1c4b955d9526fa88ec42e5d08f193a0493a148c4dc17", "created_at": "2026-11-01T18:15:27Z", "updated_at": "2026-11-01T21:29:02Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "compareMS2 2.0: An Improved Software for Comparing Tandem Mass Spectrometry Datasets.", "doi": "10.1021/acs.jproteome.2c00457", "pmid": "36173614", "authors": ["Rob Marissen", "Madhushri S Varunjikar", "Jeroen F J Laros", "Josef D Rasinger", "Benjamin A Neely", "Magnus Palmblad"], "journal": "Journal of proteome research", "year": 2023, "abstract": "It has long been known that biological species can be identified from mass spectrometry data alone. Ten years ago, we described a method and software tool, compareMS2, for calculating a distance between sets of tandem mass spectra, as routinely collected in proteomics. This method has seen use in species identification and mixture characterization in food and feed products, as well as other applications. Here, we present the first major update of this software, including a new metric, a graphical user interface and additional functionality. The data have been deposited to ProteomeXchange with dataset identifier PXD034932.", "claims": [{"id": "claim-method", "statement": "There are many measures of spectral similarity. compareMS2 supports the cosine score (dot product) and spectral angle.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36173614", "locator": "sections[4] \"Comparing Pairs of Spectra\" paragraph 2", "quote": "There are many measures of spectral similarity. compareMS2 supports the cosine score (dot product) and spectral angle."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE16 partner repository with the dataset identifier PXD034932 and 10.6019/PXD034932.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36173614", "locator": "sections[10] \"Testing\" paragraph 2", "quote": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE16 partner repository with the dataset identifier PXD034932 and 10.6019/PXD034932."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The paper presents the first major update of compareMS2, including a new metric, a graphical user interface, and additional functionality.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:36173614", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Here, we present the first major update of this software, including a new metric, a graphical user interface and additional functionality."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "The paper presents the first major update of compareMS2, including a new metric, a graphical user interface, and additional functionality.", "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:36173614"], "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:36173614", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1021/acs.jproteome.2c00457", "sha256": "sha256:a313a1c3b308741fbb78a052f82c191baa7a9eba2d43cc2d83770b0a11eb9506", "bytes": 24831, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1021/acs.jproteome.2c00457", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9903320", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Cosine score (dot product) and spectral angle", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "There are many measures of spectral similarity. compareMS2 supports the cosine score (dot product) and spectral angle."}}], "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": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (Cosine score (dot product) and spectral angle), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "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": ["PXD034932 and 10.6019/PXD034932"], "resolved_accessions": [], "statements": ["The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE16 partner repository with the dataset identifier PXD034932 and 10.6019/PXD034932."], "basis": "The paper names PXD034932 and 10.6019/PXD034932, but the accession does not resolve in the repository (no reason recorded), so the data cannot be reached from here. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:36173614"], "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": "2026-11-01T18:07:06Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 7594, "completion_tokens": 1089, "cached_tokens": 264}}, "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:36173614", "type": "paper", "label": "pmid:36173614"}, {"id": "source:pmid:36173614", "type": "manuscript", "label": "PMID 36173614 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:36173614", "type": "paper", "label": "pmid:36173614"}, {"id": "source:pmid:36173614", "type": "manuscript", "label": "PMID 36173614 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-36173614", "type": "extraction", "used": ["source:pmid:36173614"], "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:36173614", "parent_hash": "sha256:744b3abc037155defc33d7f6389077b266802aa1e8d217fa479d9ec16c2854d8", "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": "data_generation", "definition_id": "mass_spectrometry", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["0: An Improved Software for Comparing Tandem Mass Spectrometry Datasets.", "at biological species can be identified from mass spectrometry data alone. Ten years ago, we described a me", "ndem mass spectra, as routinely collected in proteomics. This method has seen use in species identif"], "order_basis": "paper_text_order:13", "id": "assay:1"}]}