{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31941798", "kind": "science-record", "revision": 3, "content_hash": "sha256:f42c768fab11102b6c08826d87840e1471749c3de22d127eea64184e00ef300f", "created_at": "2026-11-01T15:40:54Z", "updated_at": "2026-11-01T18:51:49Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Discovery of Species-unique Peptide Biomarkers of Bacterial Pathogens by Tandem Mass Spectrometry-based Proteotyping.", "doi": "10.1074/mcp.RA119.001667", "pmid": "31941798", "authors": ["Roger Karlsson", "Annika Thorsell", "Margarita Gomila", "Francisco Salvà-Serra", "Hedvig E Jakobsson", "Lucia Gonzales-Siles", "Daniel Jaén-Luchoro", "Susann Skovbjerg", "Johannes Fuchs", "Anders Karlsson", "Fredrik Boulund", "Anna Johnning", "Erik Kristiansson", "Edward R B Moore"], "journal": "Molecular & cellular proteomics : MCP", "year": 2020, "abstract": "Mass spectrometry (MS) and proteomics offer comprehensive characterization and identification of microorganisms and discovery of protein biomarkers that are applicable for diagnostics of infectious diseases. The use of biomarkers for diagnostics is widely applied in the clinic and the use of peptide biomarkers is increasingly being investigated for applications in the clinical laboratory. Respiratory-tract infections are a predominant cause for medical treatment, although, clinical assessments and standard clinical laboratory protocols are time-consuming and often inadequate for reliable diagnoses. Novel methods, preferably applied directly to clinical samples, excluding cultivation steps, are needed to improve diagnostics of infectious diseases, provide adequate treatment and reduce the use of antibiotics and associated development of antibiotic resistance. This study applied nano-liquid chromatography (LC) coupled with tandem MS, with a bioinformatics pipeline and an in-house database of curated high-quality reference genome sequences to identify species-unique peptides as potential biomarkers for four bacterial pathogens commonly found in respiratory tract infections (RTIs): Staphylococcus aureus; Moraxella catarrhalis; Haemophilus influenzae and Streptococcus pneumoniae The species-unique peptides were initially identified in pure cultures of bacterial reference strains, reflecting the genomic variation in the four species and, furthermore, in clinical respiratory tract samples, without prior cultivation, elucidating proteins expressed in clinical conditions of infection. For each of the four bacterial pathogens, the peptide biomarker candidates most predominantly found in clinical samples, are presented. Data are available via ProteomeXchange with identifier PXD014522. As proof-of-principle, the most promising species-unique peptides were applied in targeted tandem MS-analyses of clinical samples and their relevance for identifications of the pathogens, i.e. proteotyping, was validated, thus demonstrating their potential as peptide biomarker candidates for diagnostics of infectious diseases.", "claims": [{"id": "claim-data-access", "statement": "The mass spectrometry proteomics data (MSMS-spectra for all species-unique peptides presented in Tables I–IV, as well as raw-files and PD1.4 search files of representative clinical samples) have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the data set identifiers PXD014522.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31941798", "locator": "sections[22] \"DATA AVAILABILITY\" paragraph 2", "quote": "The mass spectrometry proteomics data (MSMS-spectra for all species-unique peptides presented in Tables I–IV, as well as raw-files and PD1.4 search files of representative clinical samples) have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the data set identifiers PXD014522."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "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:31941798"], "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": "complete", "blocked_on": null, "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": ["data:geo:PXD014522"], "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": ["data:geo:PXD014522"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31941798", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1074/mcp.RA119.001667", "sha256": "sha256:4690c590a2e1644dfcb8490810020c92fe35004edfc37edac9f233e7a5408c4b", "bytes": 53866, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1074/mcp.RA119.001667", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7050107", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD014522", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=PXD014522", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD014522", "version": null, "note": "The mass spectrometry proteomics data (MSMS-spectra for all species-unique peptides presented in Tables I–IV, as well as raw-files and PD1.4 search files of representative clinical samples) have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the data set identifiers PXD014522.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The mass spectrometry proteomics data (MSMS-spectra for all species-unique peptides presented in Tables I–IV, as well as raw-files and PD1.4 search files of representative clinical samples) have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the data set identifiers PXD014522.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Discovery of species-unique peptide biomarkers of bacterial pathogens by tandem mass spectrometry-based proteotyping", "resolution_checked_at": "2026-10-31T18:35:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:31941798:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5d72281cfac842e216541c4168af284db52a7cca38d5ac3aeed71fad3751fffd", "bytes": 1478, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[1]#TI", "version": null, "note": "The peptide biomarker candidates of S. aureus and the proteins from which they originate", "structure": {"pmcid": "PMC7050107", "section_index": 15, "section_title": "TCUP Bioinformatics Pipeline", "row_count": 17, "column_count": 5}, "table": {"label": "Table I", "caption": "The peptide biomarker candidates of S. aureus and the proteins from which they originate", "rows": [["Peptide sequence", "Number of times detected in 36 MS analyses of S. aureus cultures", "Number of times detected in unique clinical samples", "Protein (GenBank accession number and description)"], ["TVQPIDVDTIVASVEK", "36", "22", "AKJ16950.1", "2-oxoisovalerate dehydrogenase"], ["QAGVGAAVVAELSER", "36", "18"], ["ELINNIQSGQR", "36", "15", "AKJ17520.1", "Preprotein translocase subunit YajC"], ["LGISDGDVEETEDAPK", "36", "16", "AKJ17148.1", "Recombinase RecA"], ["ALLNNMVQGVSQGYVK", "36", "14", "AKJ18065.1", "50S ribosomal protein L6"], ["SNVNDATDYSSETPEGK", "36", "12", "AKJ17216.1", "Transketolase"], ["ANNVATDANHSYTSR", "36", "13", "AKJ17623.1", "Hypothetical protein"], ["ILAESPNLAISSSSR", "35", "10", "AKJ16422.1", "HAD family hydrolase"], ["NVVEIPLNDEEQSK", "31", "9", "AKJ16109.1", "Lactate dehydrogenase"], ["ATEATNATNNQSTQVSQATSQPINFQVQK", "24", "7", "AKJ16987.1", "Heme transporter IsdA"], ["IHLVGDEIANGQGIGR", "35", "8", "AKJ17576.1", "Pyruvate kinase"], ["NISNNVLVTIDAAQGK", "13", "6"], ["TAKPVAEVESQTEVTE", "26", "10", "AKJ16406.1", "DNA-directed RNA polymerase subunit beta'"], ["SQGVSEEELNESIDR", "29", "1", "AKJ16022.1", "Acetaldehyde dehydrogenase"], ["AEENGLTVVDAFNFEAPK", "16", "7", "AKJ18079.1", "50S ribosomal protein L4"], ["LLGINATIVMPETAPQAK", "1", "1", "AKJ17317.1", "Threonine dehydratase"]], "row_count": 17, "column_count": 5, "numeric_cells": 50, "header_rows": 1, "locator": "section[15]/table-wrap[1]#TI"}}, {"id": "asset:table:pmid:31941798:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:afb02aa3bf02621c0904a249652ade58f93f2926fac008d0ea6eee391e878998", "bytes": 1737, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[2]#TII", "version": null, "note": "The peptide biomarker candidates of M. catarrhalis and the proteins from which they originate", "structure": {"pmcid": "PMC7050107", "section_index": 15, "section_title": "TCUP Bioinformatics Pipeline", "row_count": 19, "column_count": 5}, "table": {"label": "Table II", "caption": "The peptide biomarker candidates of M. catarrhalis and the proteins from which they originate", "rows": [["Peptide sequence", "Number of times detected in number of 33 MS analyses of M. catarrhalis cultures", "Number of times detected in unique clinical samples", "Protein (GenBank accession number and description)"], ["VVLAGDTVVSDR", "33", "14", "WP_003666427.1", "TonB-dependent receptor"], ["QIVSNAGDEASVIVNEVK*", "33", "18", "WP_063454121.1", "Chaperonin GroEL"], ["AIAQVGSISANSDATIGELISK", "29", "16"], ["ELSNTAAETQPK", "33", "18", "WP_003659702.1", "30S ribosomal protein S1"], ["VDATVDAQNPTK", "24", "16", "WP_003660336.1", "Hypothetical protein"], ["QSDVGQLTGK", "5", "9"], ["FNATAALGGYGSK", "31", "12", "WP_063454085.1", "Cell surface protein"], ["THTSALAEENQQASIPR", "33", "12", "WP_063454087.1", "Cell division protein FtsZ"], ["YVVEGANMPLDAQAIDIVR", "17", "11", "WP_049156084.1", "NADP-specific glutamate dehydrogenase"], ["SQIYQTTASVSGAR", "33", "9", "WP_003657351.1", "Ohr family peroxiredoxin"], ["LLNETTGQVVPK", "33", "8", "WP_003657987.1", "DUF4377 domain-containing protein"], ["SSENVVVVSVR", "33", "10", "WP_063454071.1", "Electron transfer flavoprotein subunit beta"], ["AISYGNSADAQPYVGAK", "33", "10", "WP_003658939.1", "Porin family protein"], ["GLPVSNSGAPISVPVGQATLGR", "31", "8", "WP_003658974.1", "F0F1 ATP synthase subunit beta"], ["VNYNGDTDTVTLSGVAK", "33", "13", "WP_003656943.1", "Peptidoglycan-binding protein LysM"], ["AVATQQATVSAEYLQK", "5", "10", "WP_003657125.1", "ABC transporter substrate-binding protein"], ["ADSGLSESEIEEMIR", "32", "12", "WP_003669031.1", "Molecular chaperone DnaK"], ["LGAQEAELVSNSK", "33", "7", "WP_003660298.1", "CTP synthase"]], "row_count": 19, "column_count": 5, "numeric_cells": 55, "header_rows": 1, "locator": "section[15]/table-wrap[2]#TII"}}, {"id": "asset:table:pmid:31941798:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:01c72c8f9548d8455d2e37abf01f492c695d1b6fed424ddfab6689514b430c68", "bytes": 1193, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[3]#TIII", "version": null, "note": "The peptide biomarker candidates of H. influenzae and the proteins from which they originate", "structure": {"pmcid": "PMC7050107", "section_index": 15, "section_title": "TCUP Bioinformatics Pipeline", "row_count": 17, "column_count": 5}, "table": {"label": "Table III", "caption": "The peptide biomarker candidates of H. influenzae and the proteins from which they originate", "rows": [["Peptide sequence", "Number of times detected 26 MS analyses of H. influenzae cultures", "Number of times detected in unique clinical samples", "Protein (GenBank accession number and description)"], ["GVAADAISATGYGK*", "22", "22", "WP_038441355.1", "Porin OmpA"], ["ANLKPQAQATLDSIYGEMSQVK", "5", "6"], ["ADSVANYFVAK", "−", "5"], ["GSYEVLDGLDVYGK", "12", "3"], ["LSQERADSVANYFVAK**", "−", "2"], ["AVVYNNEGTNVELGGR*", "22", "14", "WP_058222193.1", "Porin"], ["YDANNIIAGIAYGR*", "13", "6"], ["ATHNFGDGFYAQGYLETR", "15", "5"], ["AVVYNNEGTKVELGGR", "−", "5"], ["QQVNGALSTLGYR", "18", "1"], ["YVPTNGNTVGYTFK", "−", "4"], ["LSVIAEQSNSTR*", "4", "1"], ["SADLTNEVAVGDVVEAK", "4", "6", "WP_011272719.1", "30S ribosomal protein S1"], ["SADLTSEVAVGDVVEAK", "11", "2"], ["TSPTQNLSLDAFVAR", "9", "5", "WP_058222202.1WP_050846043.1", "ShlB/FhaC/HecB family hemolysin secretion/activation protein"], ["AQYIVEQVIGQAR", "26/29", "2", "WP_011272712.1", "Pyruvate dehydrogenase (acetyl-transferring), homodimeric type"]], "row_count": 17, "column_count": 5, "numeric_cells": 35, "header_rows": 1, "locator": "section[15]/table-wrap[3]#TIII"}}, {"id": "asset:table:pmid:31941798:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:af438d43debd6e353217e25d65586ffeb445d05f6dfbf7a8acb22fb5b98b12a4", "bytes": 1660, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[4]#TIV", "version": null, "note": "The peptide biomarker candidates of S. pneumoniae and the proteins from which they originate", "structure": {"pmcid": "PMC7050107", "section_index": 15, "section_title": "TCUP Bioinformatics Pipeline", "row_count": 19, "column_count": 5}, "table": {"label": "Table IV", "caption": "The peptide biomarker candidates of S. pneumoniae and the proteins from which they originate", "rows": [["Peptide sequence", "Number of times detected in 21 MS analyses of S. pneumoniae cultures", "Number of times detected in unique clinical samples", "Protein (GenBank accession number and description)"], ["VSDVAESTGEFTSEQFEK*", "21", "22", "WP_000064115.1", "Asp23/Gls24 family envelope stress response protein"], ["GAANGVVSHENTR*", "−", "9"], ["EEAPVASQSK", "−", "9", "WP_001035310.1", "Hypothetical protein"], ["SADQQAEEDYAR", "−", "8"], ["APLQSELDTK", "−", "3"], ["LKEIDESDSEDYVK", "−", "3"], ["NVEIIEDDKQGVIR", "1", "10", "WP_000245505.1", "30S ribosomal protein S8"], ["NLPVGSDGTFTPEDYVGR", "20", "8", "WP_001291372.1", "Methionine–tRNA ligase"], ["TLELEIAESDVK", "−", "5", "WP_000458177.1", "Hypothetical protein"], ["DIGLANDGSIVGINYAK", "12", "5", "WP_000927809.1", "Sugar ABC transporter substrate-binding protein"], ["IAELEYEVQR", "−", "6", "WP_001008677.1", "Asp-tRNA(Asn)/Glu-tRNA(Gln) amidotransferase subunit GatB"], ["AVAAADAADAGAAK", "3", "3", "WP_001196960.1", "50S ribosomal protein L7/L12"], ["GQDWVIAAEVVTKPEVK", "16", "5", "WP_000116461.1", "Trigger factor"], ["TLSPEEYAVTQENQTER", "−", "6", "WP_000998307.1", "Peptide-methionine (R)-S-oxide reductase"], ["KDEAEAAFATIR", "−", "3", "WP_001284361.1", "Thiol-activated toxin pneumolysin"], ["SQPSSETELSGNKQEQER", "16", "2", "WP_078148305.1", "Sialidase"], ["IGVISVVEDGDEALAK", "−", "2", "WP_000808063.1", "Elongation factor Ts"], ["VAYFNEIDTYSEVK", "−", "2", "WP_000685088.1", "Nucleotide sugar dehydrogenase"]], "row_count": 19, "column_count": 5, "numeric_cells": 43, "header_rows": 1, "locator": "section[15]/table-wrap[4]#TIV"}}, {"id": "asset:table:pmid:31941798:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:be33a5395b837feaf2819ae360cabdfd44d9cc390df13e87444ebbe415800572", "bytes": 522, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[16]/table-wrap[1]#TV", "version": null, "note": "Number of strains analyzed, corresponding number of MS analyses and the resulting number of species-unique peptides found for each of the species", "structure": {"pmcid": "PMC7050107", "section_index": 16, "section_title": "Generation of Targeted Database and MS-inclusion Lists", "row_count": 5, "column_count": 4}, "table": {"label": "Table V", "caption": "Number of strains analyzed, corresponding number of MS analyses and the resulting number of species-unique peptides found for each of the species", "rows": [["Species", "Number of strains", "Number of MS analyses", "Number of species-unique peptides"], ["S. aureus", "12", "36", "5,847"], ["M. catarrhalis", "11", "33", "5,810"], ["H. influenzae", "9", "26", "2,978"], ["S. pneumoniae", "7", "21", "782"]], "row_count": 5, "column_count": 4, "numeric_cells": 12, "header_rows": 1, "locator": "section[16]/table-wrap[1]#TV"}}], "gaps": ["asset:data:geo:PXD014522 not downloaded", "asset:data:geo:PXD014522 licence not read"]}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "operations"]}, "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": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (not named), 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": "R1", "reachable": true, "accessions": ["PXD014522"], "resolved_accessions": ["PXD014522"], "statements": ["The mass spectrometry proteomics data (MSMS-spectra for all species-unique peptides presented in Tables I–IV, as well as raw-files and PD1.4 search files of representative clinical samples) have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the data set identifiers PXD014522."], "basis": "The paper names PXD014522 in ProteomeXchange Consortium via the PRIDE partner repository and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:31941798", "data:geo:PXD014522", "asset:table:pmid:31941798:1", "asset:table:pmid:31941798:2", "asset:table:pmid:31941798:3", "asset:table:pmid:31941798:4", "asset:table:pmid:31941798:5"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD014522"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:17:45Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 38984, "completion_tokens": 877, "cached_tokens": 13064}}, "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:31941798", "type": "paper", "label": "pmid:31941798"}, {"id": "source:pmid:31941798", "type": "manuscript", "label": "PMID 31941798 full text"}, {"id": "data:geo:PXD014522", "type": "dataset", "label": "GEO PXD014522"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31941798", "type": "paper", "label": "pmid:31941798"}, {"id": "source:pmid:31941798", "type": "manuscript", "label": "PMID 31941798 full text"}, {"id": "data:geo:PXD014522", "type": "dataset", "label": "GEO PXD014522"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31941798", "type": "extraction", "used": ["source:pmid:31941798"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD014522", "type": "accession_resolution", "used": ["data:geo:PXD014522"], "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:31941798", "parent_hash": "sha256:9351e5ea0396e52c63af5b6168bd70141ae4414dd1d5a3daa2c91b189e5fa0c9", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:PXD014522 licence not read", "asset:data:geo:PXD014522 not downloaded", "execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique"], "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": ["Biomarkers of Bacterial Pathogens by Tandem Mass Spectrometry-based Proteotyping.", "Mass spectrometry (MS) and proteomics offer comprehensive char", "Mass spectrometry (MS) and proteomics offer comprehensive characterization and ide"], "order_basis": "paper_text_order:36", "id": "assay:1"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T03:50:33+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}