{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30654742", "kind": "science-record", "revision": 6, "content_hash": "sha256:ef0c6b6bc1c51836b9b52f036a7f71788ae89e0f162a07d55f304c182e68a8a2", "created_at": "2026-11-01T15:40:40Z", "updated_at": "2026-11-01T21:21:54Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Peptimapper: proteogenomics workflow for the expert annotation of eukaryotic genomes.", "doi": "10.1186/s12864-019-5431-9", "pmid": "30654742", "authors": ["Laetitia Guillot", "Ludovic Delage", "Alain Viari", "Yves Vandenbrouck", "Emmanuelle Com", "Andrés Ritter", "Régis Lavigne", "Dominique Marie", "Pierre Peterlongo", "Philippe Potin", "Charles Pineau"], "journal": "BMC genomics", "year": 2019, "abstract": "BACKGROUND: Accurate structural annotation of genomes is still a challenge, despite the progress made over the past decade. The prediction of gene structure remains difficult, especially for eukaryotic species, and is often erroneous and incomplete. We used a proteogenomics strategy, taking advantage of the combination of proteomics datasets and bioinformatics tools, to identify novel protein coding-genes and splice isoforms, assign correct start sites, and validate predicted exons and genes.\nRESULTS: Our proteogenomics workflow, Peptimapper, was applied to the genome annotation of Ectocarpus sp., a key reference genome for both the brown algal lineage and stramenopiles. We generated proteomics data from various life cycle stages of Ectocarpus sp. strains and sub-cellular fractions using a shotgun approach. First, we directly generated peptide sequence tags (PSTs) from the proteomics data. Second, we mapped PSTs onto the translated genomic sequence. Closely located hits (i.e., PSTs locations on the genome) were then clustered to detect potential coding regions based on parameters optimized for the organism. Third, we evaluated each cluster and compared it to gene predictions from existing conventional genome annotation approaches. Finally, we integrated cluster locations into GFF files to use a genome viewer. We identified two potential novel genes, a ribosomal protein L22 and an aryl sulfotransferase and corrected the gene structure of a dihydrolipoamide acetyltransferase. We experimentally validated the results by RT-PCR and using transcriptomics data.\nCONCLUSIONS: Peptimapper is a complementary tool for the expert annotation of genomes. It is suitable for any organism and is distributed through a Docker image available on two public bioinformatics docker repositories: Docker Hub and BioShaDock. This workflow is also accessible through the Galaxy framework and for use by non-computer scientists at https://galaxy.protim.eu . Data are available via ProteomeXchange under identifier PXD010618.", "claims": [{"id": "claim-method", "statement": "Sensitivity was defined as the percent of expected proteins matched (true_pos/nref) and selectivity the percent of expected proteins among all proteins matched using our workflow (true_pos/nfound).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30654742", "locator": "sections[7] \"Step 2: PSTs mapping and clustering\" paragraph 2", "quote": "Sensitivity was defined as the percent of expected proteins matched (true_pos/nref) and selectivity the percent of expected proteins among all proteins matched using our workflow (true_pos/nfound)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets used and/or analysed during the current study are available from the corresponding author on reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30654742", "locator": "sections[25] \"Availability of data and materials\" paragraph 2", "quote": "The datasets used and/or analysed during the current study are available from the corresponding author on reasonable request."}], "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:30654742"], "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:PXD010618"], "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:PXD010618"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:30654742", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12864-019-5431-9", "sha256": "sha256:27646b2a31b3d0c7e5e335ae1e549c329d2fb4564fc9f735669975c0c293d4de", "bytes": 70599, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12864-019-5431-9", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6337836", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD010618", "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=PXD010618", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD010618", "version": null, "note": "The datasets used and/or analysed during the current study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analysed during the current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Peptimapper -  Peptimapper: proteogenomics workflow for the expert annotation of eukaryotic genomes", "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:30654742:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:58445caa65855db0b1699c1ddcb76145b0815d5a5aac6c99e7a9bd0a48f5adf9", "bytes": 2403, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#Tab1", "version": null, "note": "Comparison of tag quality between Peaks and PepNovo+, using Proteome Discoverer ™ peptide identifications as the expected sequences", "structure": {"pmcid": "PMC6337836", "section_index": 11, "section_title": "Step 1: From MS/MS spectra to PSTs", "row_count": 32, "column_count": 10}, "table": {"label": "Table 1", "caption": "Comparison of tag quality between Peaks and PepNovo+, using Proteome Discoverer ™ peptide identifications as the expected sequences", "rows": [["Peaks", "Proteome discoverer(MASCOT identifications)", "Pepnovo+"], ["ID", "Tag sequence", "Significant score >60%", "Rank", "Protein AC", "Reference Sequence", "e-value", "ID", "Tag sequence", "Significant score >1,5"], ["271", "WVQAAGAGASR", "23", "0", "Esi0085_0010", "SVVQAAGAGDAK", "5,65568E-06", "Spectrum271_scans", "QAAGAGA", "6,346"], ["271", "WVQAAGAGWK", "21.5", "1"], ["271", "WVQAAGAGTGR", "18.5", "2"], ["552", "(CamC)VGVSEETTTRHR", "31", "0", "Esi0091_0058", "cVGVSEETTTGVHR", "2,36909E-07", "Spectrum552_scans", "GVSEDD", "4,237"], ["552", "QMGVSEETTTRHR", "29", "1"], ["552", "V(CamC)GVSEETTTRHR", "17", "2"], ["577", "QFAGDDAPR", "43", "0", "Esi0203_0038", "AGFAGDDAPR", "1,69937E-06", "Spectrum578_scans", "GDDAPR", "7,539"], ["577", "K(MetOxM)AGDDAPR", "41", "1"], ["577", "AGFAGDDAPR", "11.5", "2"], ["642", "KAENPMSKR", "100", "0", "Esi0349_0012", "KAEDIDTIR", "1,01272E-05", "Spectrum643_scans", "DLDTLR", "4,727"], ["642", "KAQDPMSKR", "0.1", "1"], ["642", "QAKDPMSKR", "0.02", "2"], ["1118", "DGLVYGK(MetOxM)NEPPGAR", "38", "0", "Esi0327_0021", "ATLVYGQmNEPPGAR", "2,42457E-06", "Spectrum1119_scans", "EPPGAR", "1,396"], ["1118", "DGLVYGQFNEPPGAR", "37", "1"], ["1118", "DGLVYGQ(MetOxM)NEPPGVK", "8", "2"], ["2462", "DESAAVFAWK", "87,5", "0", "Esi0091_0058", "DESAAVFAWK", "1,64304E-05", "Spectrum2463_scans", "SAAVFA", "4,78"], ["2462", "DESAAVFAGTR", "8", "1"], ["2462", "LMSAAV(MetOxM)AGEK", "1.5", "2"], ["2479", "MDDLTNNALARK", "58", "0", "Esi0888_0002", "mVDLTPMAIAAGR", "4,70366E-07", "Spectrum2480_scans", "ALAAGR", "1,943"], ["2479", "(MetOxM)VDLTNNALAAGR", "39.5", "1"], ["2479", "MDDLTNGGALARK", "1", "2"], ["2558", "ED(MetOxM)ETE(CamC)AVNYDNLYQVMK", "48", "0", "Esi0349_0012", "TccEAEcAVNYDNLYQAMR", "1,01272E-05", "Spectrum2559_scans", "VNYDNL", "2,289"], ["2558", "DE(MetOxM)ETE(CamC)AVNYDNLYQVMK", "8.5", "1"], ["2558", "ED(MetOxM)ETE(CamC)AVNYDNLYQMVK", "8", "2"], ["2610", "TFQAGEVASALLGR", "32", "0", "Esi0327_0021", "FTQAGAEVSALLGR", "5,99619E-08", "Spectrum2610_scans", "SALLGR", "4,356"], ["2610", "FTQAGEVASALLGR", "25", "1"], ["2610", "TFKAGAGNGSALLGR", "10", "2"], ["3191", "VALTGLTLAEYFR", "53", "0", "Esi0327_0021", "VALTGLTIAEYFR", "", "Spectrum3196_scans", "LAEYFR", "4,471"], ["3191", "GLLTGLTLAEYFR", "25.5", "1"], ["3191", "AVLTGLTLAEYFR", "11", "2"]], "row_count": 32, "column_count": 10, "numeric_cells": 131, "header_rows": 2, "locator": "section[11]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:30654742:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f14d56315f5b398751356be3ea994de449233757ee493f631502f8aa127a1d0b", "bytes": 6365, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#Tab2", "version": null, "note": "Eukaryotic proteogenomics pipelines and Galaxy workflows", "structure": {"pmcid": "PMC6337836", "section_index": 17, "section_title": "Discussion", "row_count": 15, "column_count": 9}, "table": {"label": "Table 2", "caption": "Eukaryotic proteogenomics pipelines and Galaxy workflows", "rows": [["Name", "Pipeline Interface", "Database-driven for peptide identifi-cation", "de novo peptide inter-pretation", "User-friendly for biologists", "Results curation", "Results visuali-zation", "Description", "Revelance"], ["Peptimapper (released in 2018)", "Command line, Docker image, Galaxy tools", "–", "√", "√", "√", "√", "Peptide Sequence Tags (PSTs) obtained from partial interpretation of ion trap mass spectra are mapped onto the six-frame translation of genomic sequences giving hits. Hits are then clustered to detect potential coding regions. Clusters are evaluated and further compared to existing gene predictions. Clusters are available as GFF file to be uploaded into a genome viewer. https://galaxy.protim.eu https://hub.docker.com/r/dockerprotim/peptimapper/ or https://docker-ui.genouest.org/app/#/container/dockerprotim/peptimapper https://github.com/laeticlo/Ectoline", "Improves genome annotation"], ["IPAW (2018) [61]", "Command line", "√", "–", "–", "√", "–", "This is an Integrated Proteomics Analysis Workflow: i) Peptide spectra are searched in two different databases in parallel: VarDB filtered by class-specific FDR for SAAV peptides and 6FT of the human genome filtered by peptides pI. ii) SAAV candidates are curated by SpectrumAI and potential novel proteins are blasted onto public databases. ii) Curated results are validated by different controls. https://github.com/yafeng/proteogenomics_python", "Identification of Pseudogenes, lncRNAs, nsSNPs and somatic mutations"], ["JUMPg (2016) [62]", "Command line", "√", "–", "–", "√", "√", "This pipeline includes multiple customized databases construction, tag-based database search, peptide-spectrum match filtering, ans data visualization. https://github.com/gatechatl/JUMPg/", "Improves genome annotation"], ["PGMiner (2016) [63]", "Command line", "√", "–", "–", "√", "√", "This workflow allows acquisition of mass spectrometric data, peptide identification against preprocessed sequence databases, assignment of statistical confidence to identified peptides, and mapping confident peptides to gene models. https://github.com/olalonde/pgtools", "Improves genome annotation"], ["PROTEO-FORMER (2015) [64]", "Command line, Virtual machine, Galaxy tools", "√", "–", "√", "√", "√", "RIBO-seq NGS data are processed to delineates proteoforms. RIBO-seq-derived sequences are then translated and mapped to a public database, creating a custom search database for peptides to MS/MS matching.", "Identification of novel translation products"], ["PGTools (2015) [65]", "Command line", "√", "–", "–", "√", "√", "The software is divided into 2 phases: Phase 1 contains 8 modules to analyse MS/MS data using known proteins databases. Phase 2 contains 5 modules and 7 customized databases that allow MS/MS data to be analysed against the genome. That software includes applications, libraries, customized databases and visualization tools.", "Improves genome annotation"], ["NextSearch (2015) [66]", "Command line", "–", "–", "–", "√", "√", "Nucleotide EXon-graph Transcriptome Search identifies peptides by directly searching the nucleotide exon graph against tandem mass spectra. NextSearch outputs which are the proteome-genome/transcriptome mapping that can be visualized using public tools.", "Improves genome annotation"], ["ProteoAnnotator (2014) [52]", "Command line, Stand alone application", "√", "–", "√", "√", "√", "MS spectrum are queried by one or several proteomics databases search engines (MASCOT, OMSSA, X!Tandem or MSGF+) and results are converted into GFF adding genome coordinates and statistical confidence values. It exports mzIdentML files. http://www.proteoannotator.org", "Improves genome annotation"], ["Peppy (2013) [67]", "Command line, Stand alone application", "√", "–", "N/A", "√", "–", "This workflow generates a peptide database from a genome, tracks peptide loci, matches peptides to MS/MS spectra and assigns FDR confidence values to those matches. http://geneffects.com/peppy", "Improves genome annotation"], ["Protk (released in 2012)", "Command line, Galaxy tools", "√", "–", "√", "–", "√", "It is a suite of tools for proteomics providing the following analysis tasks: (i) MS/MS data search with X!Tandem, Mascot, OMSSA and MS-GF+; (ii) peptide and protein inference with Peptide Prophet, iProphet and Protein Prophet; (iii) conversion of pepXML or protXML to tabular format, and (iv) mapping of peptides to genomic coordinates https://github.com/iracooke/protk", "Improves genome annotation"], ["IggyPep (2010) [54]", "Web interface", "√", "√", "N/A", "–", "–", "The pipeline is based on a database system with advanced indexing and querying strategy, which holds the translated genome in all six reading frames. It can be queried with de novo sequences or partial peptide sequence tags (PSTs). It determines the ORF amino acid comprising these tags and compiles a fasta-formated sequence file for a database-driven search. www.iggypep.org (No more accessible)", "Improves genome annotation"], ["PepLine (2008) [18]", "Command line", "–", "√", "N/A", "√", "–", "Peptide Sequence Tags (PSTs) obtained from partial interpretation of QTOF mass spectra are mapped onto the six-frame translation of genomic sequences giving hits. Hits are then clustered to detect potential coding regions.www.grenoble.prabi.fr/protehome/software/pepline (no more accessible)", "Improves genome annotation"], ["Workflows for Proteomics Informed by Transcriptomics (2015) [57]", "Galaxy tools", "√", "–", "√", "√", "√", "Galaxy Integrated Omics (GIO) provides workflows for 4 common use cases: i) a standard search against a reference proteome; ii) PIT protein identification without a reference genome; iii) PIT protein identification using a genome guide; iiii) and PIT genome annotation. http://gio.sbcs.qmul.ac.uk", "Improves genome annotation"], ["Workflows for proteogenomics studies using Galaxy-P (2014–2018) [55, 56, 58, 59]", "Galaxy tools", "√", "–", "√", "√", "√", "These modular workflows incorporating both established and customized software tools that improve depth and quality of proteogenomic results. http://galaxyp.org", "Improves genome annotation"]], "row_count": 15, "column_count": 9, "numeric_cells": 17, "header_rows": 1, "locator": "section[17]/table-wrap[1]#Tab2"}}, {"id": "asset:table:pmid:30654742:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:8e03a2f28c94ae8ca93a5a5e845ef1adad8a8c9a5e6bfd1a843202b492ac4b27", "bytes": 2105, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[2]#Tab3", "version": null, "note": "Additional clusters currently under investigation", "structure": {"pmcid": "PMC6337836", "section_index": 17, "section_title": "Discussion", "row_count": 17, "column_count": 11}, "table": {"label": "Table 3", "caption": "Additional clusters currently under investigation", "rows": [["Cluster ID", "Contig", "Strand", "From", "To", "Strain", "Tot pep", "RNA data", "Genetic map", "Action", "Identification"], ["113", "sctg_117", "D", "265421", "281797", "EC494", "10", "ESTs+RNAseq", "LGUn", "probable new gene", "Esi0117_0046 similar sequence"], ["179", "sctg_136", "D", "16590", "18641", "EC494", "3", "ESTs+RNAseq", "LG16", "Esi0136_0001 model correction", "Ferredoxin"], ["750", "sctg_346", "D", "52096", "53724", "EC494", "3", "RNAseq", "LG15", "Esi0346_0010 model correction", "Esi0003_0041 similar sequence"], ["1034", "sctg_6", "D", "824608", "831877", "EC494", "3", "RNAseq", "LG04", "Esi0006_0137 model correction", "Conserved unknown protein"], ["1056", "sctg_62", "D", "30800", "38368", "EC494", "9", "RNAseq", "LG16", "Esi0062_0006 model correction", "Hypothetical protein"], ["1072", "sctg_634", "D", "21444", "27984", "EC494", "3", "ESTs+RNAseq", "LGUn", "probable new gene", "none"], ["1154", "sctg_77", "D", "414499", "420533", "EC494", "3", "No data", "LGUn", "probable new gene", "none"], ["120", "sctg_123", "R", "77652", "82101", "Ec32", "4", "RNAseq", "LG08", "probable new gene", "none"], ["220", "sctg_150", "D", "399071", "404913", "Ec32", "3", "No data", "LG11", "probable new gene", "none"], ["777", "sctg_43", "R", "146476", "147692", "Ec32", "3", "RNAseq", "LG03", "Esi0043_0035 model correction", "Catalase"], ["822", "sctg_48", "R", "267223", "267911", "Ec32", "5", "RNAseq", "LG23", "Esi0048_0051 model correction", "Hypothetical protein"], ["492", "sctg_253", "D", "215846", "216917", "Ec32", "3", "RNAseq", "LGUn", "probable new gene", "none"], ["567", "sctg_291", "R", "60813", "65620", "Ec32", "3", "RNAseq", "LG03", "Esi0291_0011 model correction", "mTERF domain-containing protein"], ["618", "sctg_310", "D", "63974", "71773", "Ec32", "3", "RNAseq", "LGUn", "probable new gene", "none"], ["697", "sctg_365", "R", "137829", "143627", "Ec32", "3", "RNAseq", "LGUn", "probable new gene", "none"], ["218", "sctg_87", "R", "471174", "478804", "Ec410", "3", "No data", "LG26", "probable new gene", "Retrotransposon integrase-like protein"]], "row_count": 17, "column_count": 11, "numeric_cells": 115, "header_rows": 1, "locator": "section[17]/table-wrap[2]#Tab3"}}], "gaps": ["asset:data:geo:PXD010618 not downloaded", "asset:data:geo:PXD010618 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Sensitivity and selectivity", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Sensitivity was defined as the percent of expected proteins matched (true_pos/nref) and selectivity the percent of expected proteins among all proteins matched using our workflow (true_pos/nfound)."}}], "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": "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 (Sensitivity and selectivity), 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": ["PXD010618"], "resolved_accessions": ["PXD010618"], "statements": ["The datasets used and/or analysed during the current study are available from the corresponding author on reasonable request."], "basis": "The paper names PXD010618 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:30654742", "data:geo:PXD010618", "asset:table:pmid:30654742:1", "asset:table:pmid:30654742:2", "asset:table:pmid:30654742:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD010618"]}, "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": "2026-10-31T18:13:33Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 55201, "completion_tokens": 2446, "cached_tokens": 792}}, "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:30654742", "type": "paper", "label": "pmid:30654742"}, {"id": "source:pmid:30654742", "type": "manuscript", "label": "PMID 30654742 full text"}, {"id": "data:geo:PXD010618", "type": "dataset", "label": "GEO PXD010618"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30654742", "type": "paper", "label": "pmid:30654742"}, {"id": "source:pmid:30654742", "type": "manuscript", "label": "PMID 30654742 full text"}, {"id": "data:geo:PXD010618", "type": "dataset", "label": "GEO PXD010618"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30654742", "type": "extraction", "used": ["source:pmid:30654742"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD010618", "type": "accession_resolution", "used": ["data:geo:PXD010618"], "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:30654742", "parent_hash": "sha256:27d37e424939a32d8c9d65f91cf0b65bbfd954557bfad8c7f952c3131a79b1c2", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:PXD010618 licence not read", "asset:data:geo:PXD010618 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ly validated the results by RT-PCR and using transcriptomics data. CONCLUSIONS: Peptimapper is a compleme", "clusters under investigation listed Table 3. RNA-sequencing and EST data have been incorporated in the b"], "order_basis": "paper_text_order:1600", "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":"2026-11-04T02:39:24+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}}}