{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31699904", "kind": "science-record", "revision": 8, "content_hash": "sha256:c09f385ea411510fd0a59e70feed1e8322476b7a63e3ef324f35b911ad21aeaf", "created_at": "2026-11-01T15:40:51Z", "updated_at": "2026-11-01T22:44:19Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Reproducibility, Specificity and Accuracy of Relative Quantification Using Spectral Library-based Data-independent Acquisition.", "doi": "10.1074/mcp.RA119.001714", "pmid": "31699904", "authors": ["Katalin Barkovits", "Sandra Pacharra", "Kathy Pfeiffer", "Simone Steinbach", "Martin Eisenacher", "Katrin Marcus", "Julian Uszkoreit"], "journal": "Molecular & cellular proteomics : MCP", "year": 2020, "abstract": "Currently data-dependent acquisition (DDA) is the method of choice for mass spectrometry-based proteomics discovery experiments, but data-independent acquisition (DIA) is steadily becoming more important. One of the most important requirements to perform a DIA analysis is the availability of suitable spectral libraries for peptide identification and quantification. Several studies were performed addressing the evaluation of spectral library performance for protein identification in DIA measurements. But so far only few experiments estimate the effect of these libraries on the quantitative level.In this work we created a gold standard spike-in sample set with known contents and ratios of proteins in a complex protein matrix that allowed a detailed comparison of DIA quantification data obtained with different spectral library approaches. We used in-house generated sample-specific spectral libraries created using varying sample preparation approaches and repeated DDA measurement. In addition, two different search engines were tested for protein identification from DDA data and subsequent library generation. In total, eight different spectral libraries were generated, and the quantification results compared with a library free method, as well as a default DDA analysis. Not only the number of identifications on peptide and protein level in the spectral libraries and the corresponding DIA analysis results was inspected, but also the number of expected and identified differentially abundant protein groups and their ratios.We found, that while libraries of prefractionated samples were generally larger, there was no significant increase in DIA identifications compared with repetitive non-fractionated measurements. Furthermore, we show that the accuracy of the quantification is strongly dependent on the applied spectral library and whether the quantification is based on peptide or protein level. Overall, the reproducibility and accuracy of DIA quantification is superior to DDA in all applied approaches.Data has been deposited to the ProteomeXchange repository with identifiers PXD012986, PXD012987, PXD012988 and PXD014956.", "claims": [{"id": "claim-method", "statement": "Afterward, an analysis of variance (ANOVA) model was fitted to the transformed data. As a post-hoc test Tukey's honest significance test was conducted, to determine, which spike-in states were significantly differential. Finally, the ANOVA p values were corrected for multiple testing using the Benjamini-Hochberg procedure.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31699904", "locator": "sections[17] \"Statistical Analysis\" paragraph 2", "quote": "Afterward, an analysis of variance (ANOVA) model was fitted to the transformed data. As a post-hoc test Tukey's honest significance test was conducted, to determine, which spike-in states were significantly differential. Finally, the ANOVA p values were corrected for multiple testing using the Benjamini-Hochberg procedure."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Data has been deposited to the ProteomeXchange repository (https://www.ebi.ac.uk/pride/archive) with identifiers PXD012986, PXD012987, PXD012988, and PXD014956.\n\nReviewer access data is provided in the respective document.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31699904", "locator": "sections[32] \"DATA AVAILABILITY\" paragraphs 1-3", "quote": "Data has been deposited to the ProteomeXchange repository (https://www.ebi.ac.uk/pride/archive) with identifiers PXD012986, PXD012987, PXD012988, and PXD014956.\n\nReviewer access data is provided in the respective document."}], "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:31699904"], "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:PXD012986"], "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:PXD012986"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31699904", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1074/mcp.RA119.001714", "sha256": "sha256:2b6fb6aaa3479e46b98f714252dafc8f40308fb8ce3430bb5948aa64200fc4d2", "bytes": 85514, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1074/mcp.RA119.001714", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6944235", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD012986", "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=PXD012986", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD012986", "version": null, "note": "Data has been deposited to the ProteomeXchange repository (https://www.ebi.ac.uk/pride/archive) with identifiers PXD012986, PXD012987, PXD012988, and PXD014956.\n\nReviewer access data is provided in the respective document.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data has been deposited to the ProteomeXchange repository (https://www.ebi.ac.uk/pride/archive) with identifiers PXD012986, PXD012987, PXD012988, and PXD014956.\n\nReviewer access data is provided in the respective document.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Reproducibility, specificity and accuracy of DIA quantification - DDA analysis", "resolution_checked_at": "2026-10-31T18:35:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:PXD012987", "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=PXD012987", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD012987", "version": null, "note": "Data has been deposited to the ProteomeXchange repository (https://www.ebi.ac.uk/pride/archive) with identifiers PXD012986, PXD012987, PXD012988, and PXD014956.\n\nReviewer access data is provided in the respective document.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data has been deposited to the ProteomeXchange repository (https://www.ebi.ac.uk/pride/archive) with identifiers PXD012986, PXD012987, PXD012988, and PXD014956.\n\nReviewer access data is provided in the respective document.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Reproducibility, specificity and accuracy of DIA quantification - Spectral Libraries", "resolution_checked_at": "2026-11-01T15:39:58Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:PXD012988", "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=PXD012988", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD012988", "version": null, "note": "Data has been deposited to the ProteomeXchange repository (https://www.ebi.ac.uk/pride/archive) with identifiers PXD012986, PXD012987, PXD012988, and PXD014956.\n\nReviewer access data is provided in the respective document.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data has been deposited to the ProteomeXchange repository (https://www.ebi.ac.uk/pride/archive) with identifiers PXD012986, PXD012987, PXD012988, and PXD014956.\n\nReviewer access data is provided in the respective document.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Reproducibility, specificity and accuracy of DIA quantification - DIA analysis", "resolution_checked_at": "2026-11-01T15:39:58Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:31699904:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:94dd730701a6049323856261234d1f083c9f9bb68b7ae1a4b442033948cc9cc9", "bytes": 1113, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[1]#TI", "version": null, "note": "Composition of the gold standard spike-in sample set consisting of a constant C2C12 cell lysate background and varying amounts of 13 non-mouse spike-in proteins. Shown are the pmol amounts of the spike-in proteins for each of the five sample states", "structure": {"pmcid": "PMC6944235", "section_index": 7, "section_title": "Sample Preparation", "row_count": 14, "column_count": 7}, "table": {"label": "Table I", "caption": "Composition of the gold standard spike-in sample set consisting of a constant C2C12 cell lysate background and varying amounts of 13 non-mouse spike-in proteins. Shown are the pmol amounts of the spike-in proteins for each of the five sample states", "rows": [["", "UniProt accession", "Amount of spike-in proteins (pmol)"], ["Sample 1", "Sample 2", "Sample 3", "Sample 4", "Sample 5"], ["α-synuclein (pmol)", "P37840", "1", "10", "0.5", "0.1", "5"], ["β-lactoglobulin (pmol)", "P02754", "0.5", "0.1", "5", "10", "1"], ["Fibrinogen (pmol)", "P02671, P02675, P02679", "10", "5", "1", "0.5", "0.1"], ["α, β, γ each"], ["Glucose oxidase (pmol)", "P13006", "0.1", "1", "10", "5", "0.5"], ["Hemoglobin (pmol)", "P69905, P68871", "0.5", "5", "10", "1", "0.1"], ["α, β each"], ["Lipase (pmol)", "P20261, P32946, P32947", "0.1", "0.5", "1", "5", "10"], ["1, 2, 3 each"], ["Lysozyme (pmol)", "P00698", "5", "10", "0.1", "0.5", "1"], ["Myoglobin (pmol)", "P68082", "1", "0.1", "5", "10", "0.5"], ["C2C12 lysate (μg)", "", "20", "20", "20", "20", "20"]], "row_count": 14, "column_count": 7, "numeric_cells": 60, "header_rows": 2, "locator": "section[7]/table-wrap[1]#TI"}}, {"id": "asset:table:pmid:31699904:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:94dd730701a6049323856261234d1f083c9f9bb68b7ae1a4b442033948cc9cc9", "bytes": 1113, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[1]#TI", "version": null, "note": "Composition of the gold standard spike-in sample set consisting of a constant C2C12 cell lysate background and varying amounts of 13 non-mouse spike-in proteins. Shown are the pmol amounts of the spike-in proteins for each of the five sample states", "structure": {"pmcid": "PMC6944235", "section_index": 8, "section_title": "Sample Preparation", "row_count": 14, "column_count": 7}, "table": {"label": "Table I", "caption": "Composition of the gold standard spike-in sample set consisting of a constant C2C12 cell lysate background and varying amounts of 13 non-mouse spike-in proteins. Shown are the pmol amounts of the spike-in proteins for each of the five sample states", "rows": [["", "UniProt accession", "Amount of spike-in proteins (pmol)"], ["Sample 1", "Sample 2", "Sample 3", "Sample 4", "Sample 5"], ["α-synuclein (pmol)", "P37840", "1", "10", "0.5", "0.1", "5"], ["β-lactoglobulin (pmol)", "P02754", "0.5", "0.1", "5", "10", "1"], ["Fibrinogen (pmol)", "P02671, P02675, P02679", "10", "5", "1", "0.5", "0.1"], ["α, β, γ each"], ["Glucose oxidase (pmol)", "P13006", "0.1", "1", "10", "5", "0.5"], ["Hemoglobin (pmol)", "P69905, P68871", "0.5", "5", "10", "1", "0.1"], ["α, β each"], ["Lipase (pmol)", "P20261, P32946, P32947", "0.1", "0.5", "1", "5", "10"], ["1, 2, 3 each"], ["Lysozyme (pmol)", "P00698", "5", "10", "0.1", "0.5", "1"], ["Myoglobin (pmol)", "P68082", "1", "0.1", "5", "10", "0.5"], ["C2C12 lysate (μg)", "", "20", "20", "20", "20", "20"]], "row_count": 14, "column_count": 7, "numeric_cells": 60, "header_rows": 2, "locator": "section[7]/table-wrap[1]#TI"}}, {"id": "asset:table:pmid:31699904:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e041fdfd9c2728fd38f951b81194a98cdbccc99e747ca84318518f83478361e5", "bytes": 1314, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#TII", "version": null, "note": "Overview of analyzed DIA libraries. The names of each library consists of the spike-in types (MM: master mix, i.e. mixture of background and spike-ins in fixed amount, GS: gold standard, i.e. the same samples as measured by DIA), the digest type (IS: in-solution, F: fragmented and therefore in-gel), whether fractionation was performed and on which level (Prot: protein fraction, Pep: peptide fractionation), finally, the number represents the number of MS runs for the library. The libraries generated by Pulsar instead of ProteomeDiscoverer are indicated by the respective prefix", "structure": {"pmcid": "PMC6944235", "section_index": 14, "section_title": "Spectral Library Generation", "row_count": 9, "column_count": 6}, "table": {"label": "Table II", "caption": "Overview of analyzed DIA libraries. The names of each library consists of the spike-in types (MM: master mix, i.e. mixture of background and spike-ins in fixed amount, GS: gold standard, i.e. the same samples as measured by DIA), the digest type (IS: in-solution, F: fragmented and therefore in-gel), whether fractionation was performed and on which level (Prot: protein fraction, Pep: peptide fractionation), finally, the number represents the number of MS runs for the library. The libraries generated by Pulsar instead of ProteomeDiscoverer are indicated by the respective prefix", "rows": [["Name", "Spike-in type", "Digest type", "Fractionation", "No of runs", "Software"], ["MM IS 6", "Constant", "In-solution", "No", "6", "PD+SN11"], ["GS IS 15", "Varying", "In-solution", "No", "15", "PD+SN11"], ["GS IS 30", "Varying", "In-solution", "No", "30", "PD+SN11"], ["MM F Prot 20", "Constant", "In-gel", "Protein", "20", "PD+SN11"], ["MM F Pep 16", "Constant", "In-solution", "Peptide", "16", "PD+SN11"], ["IS and F all 78", "Combined", "Combined", "Combined", "78", "PD+SN11"], ["Pulsar GS IS 15", "Varying", "In-solution", "No", "15", "SN Pulsar"], ["Pulsar MM F Prot 20", "Constant", "In-gel", "Protein", "20", "SN Pulsar"]], "row_count": 9, "column_count": 6, "numeric_cells": 22, "header_rows": 1, "locator": "section[14]/table-wrap[1]#TII"}}, {"id": "asset:table:pmid:31699904:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:379baa766afcdc138863bf98198b3ec83e815035c06f058db5576f58ebec9bc8", "bytes": 819, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[29]/table-wrap[1]#TIII", "version": null, "note": "False positive rate. Number of FP and resulting FP rate after correlation and low-fold change filtering on protein and peptide level", "structure": {"pmcid": "PMC6944235", "section_index": 29, "section_title": "Specificity", "row_count": 12, "column_count": 5}, "table": {"label": "Table III", "caption": "False positive rate. Number of FP and resulting FP rate after correlation and low-fold change filtering on protein and peptide level", "rows": [["", "Protein level", "Peptide level"], ["FP (filtered)", "FP rate", "FP (filtered)", "FP rate"], ["DDA", "5", "20.00%", "124", "42.61%"], ["DirectDIA", "13", "28.89%", "118", "35.22%"], ["MM IS 6", "8", "25.00%", "119", "40.61%"], ["GS IS 15", "5", "14.29%", "123", "34.36%"], ["GS IS 30", "6", "16.22%", "125", "32.81%"], ["MM F Prot 20", "14", "29.79%", "167", "43.04%"], ["MM F Pep 16", "12", "30.77%", "129", "43.58%"], ["IS and F all 78", "14", "28.57%", "226", "42.56%"], ["Pulsar GS IS 15", "12", "26.67%", "188", "40.26%"], ["Pulsar MM F Prot 20", "14", "30.43%", "214", "43.50%"]], "row_count": 12, "column_count": 5, "numeric_cells": 48, "header_rows": 2, "locator": "section[29]/table-wrap[1]#TIII"}}, {"id": "asset:table:pmid:31699904:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:dbf262192c1ccc72e11e4be1520f7bc41580036247fe4d38c82e8890bb0f6997", "bytes": 1081, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[29]/table-wrap[2]#TIV", "version": null, "note": "AUCs and mean absolute percentage errors. Table showing the AUC of the ROCs and the mean absolute percentage error (MAPE) of the respective method on the peptide and protein level. The MAPE was calculated between the median of achieved and expected protein/peptide fold changes, on log2 transformed ratios. The values can be interpreted as deviation between the achieved and expected ratio in percent", "structure": {"pmcid": "PMC6944235", "section_index": 29, "section_title": "Specificity", "row_count": 12, "column_count": 5}, "table": {"label": "Table IV", "caption": "AUCs and mean absolute percentage errors. Table showing the AUC of the ROCs and the mean absolute percentage error (MAPE) of the respective method on the peptide and protein level. The MAPE was calculated between the median of achieved and expected protein/peptide fold changes, on log2 transformed ratios. The values can be interpreted as deviation between the achieved and expected ratio in percent", "rows": [["", "Peptide", "Protein"], ["AUC", "MAPE", "AUC", "MAPE"], ["DDA", "0.61", "65.20%", "0.88", "57.77%"], ["DirectDIA", "0.92", "16.16%", "0.87", "21.67%"], ["MM IS 6", "0.85", "18.45%", "0.97", "23.15%"], ["GS IS 15", "0.92", "13.99%", "0.95", "22.84%"], ["GS IS 30", "0.88", "17.08%", "0.87", "25.92%"], ["MM F Prot 20", "0.73", "16.10%", "0.82", "21.41%"], ["MM F Pep 16", "0.68", "15.39%", "0.80", "27.21%"], ["IS and F all 78", "0.63", "15.12%", "0.93", "27.52%"], ["Pulsar GS IS 15", "0.76", "13.78%", "0.88", "17.69%"], ["Pulsar MM F Prot 20", "0.63", "12.91%", "0.94", "19.53%"]], "row_count": 12, "column_count": 5, "numeric_cells": 48, "header_rows": 2, "locator": "section[29]/table-wrap[2]#TIV"}}], "gaps": ["asset:data:geo:PXD012986 not downloaded", "asset:data:geo:PXD012986 licence not read", "asset:data:geo:PXD012987 not downloaded", "asset:data:geo:PXD012987 licence not read", "asset:data:geo:PXD012988 not downloaded", "asset:data:geo:PXD012988 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Afterward, an analysis of variance (ANOVA) model was fitted to the transformed data. As a post-hoc test Tukey's honest significance test was conducted, to determine, which spike-in states were significantly differential. Finally, the ANOVA p values were corrected for multiple testing using the Benjamini-Hochberg procedure."}}, {"id": "method-2", "family": "correlation_analysis", "specific": "pearson", "label": "Correlation analysis", "dsl_operations": ["pearson_r"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 0.8, "band": "high", "quote": "Pearson's correlation"}}], "targets": [], "gaps": []}, "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": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: anova."}, "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": ["PXD012986", "PXD012987", "PXD012988", "and PXD014956"], "resolved_accessions": ["PXD012986", "PXD012987", "PXD012988"], "statements": ["Data has been deposited to the ProteomeXchange repository (https://www.ebi.ac.uk/pride/archive) with identifiers PXD012986, PXD012987, PXD012988, and PXD014956.\n\nReviewer access data is provided in the respective document."], "basis": "The paper names PXD012986, PXD012987, PXD012988 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": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "assets": ["source:pmid:31699904", "data:geo:PXD012986", "asset:table:pmid:31699904:1", "asset:table:pmid:31699904:2", "asset:table:pmid:31699904:3", "asset:table:pmid:31699904:4", "asset:table:pmid:31699904:5"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD012986"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:16:49Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 61252, "completion_tokens": 1283, "cached_tokens": 776}}, "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:31699904", "type": "paper", "label": "pmid:31699904"}, {"id": "source:pmid:31699904", "type": "manuscript", "label": "PMID 31699904 full text"}, {"id": "data:geo:PXD012986", "type": "dataset", "label": "GEO PXD012986"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31699904", "type": "paper", "label": "pmid:31699904"}, {"id": "source:pmid:31699904", "type": "manuscript", "label": "PMID 31699904 full text"}, {"id": "data:geo:PXD012986", "type": "dataset", "label": "GEO PXD012986"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31699904", "type": "extraction", "used": ["source:pmid:31699904"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD012986", "type": "accession_resolution", "used": ["data:geo:PXD012986"], "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:31699904", "parent_hash": "sha256:1e37ba98c8b9b1bf4af7202cb5b44fbec4df1de801f1bcc1b79a95183f25e56a", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:PXD012986 licence not read", "asset:data:geo:PXD012986 not downloaded", "asset:data:geo:PXD012987 licence not read", "asset:data:geo:PXD012987 not downloaded", "asset:data:geo:PXD012988 licence not read", "asset:data:geo:PXD012988 not downloaded", "execution.not_run", "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": ["cquisition (DDA) is the method of choice for mass spectrometry-based proteomics discovery experiments, but", "for the DDA and DIA analyses as described in Mass Spectrometric Acquisition. Generation of the Gold Standard", "cribed in the prior paragraphs a total of 78 LC-MS/MS runs were analyzed for the spectral library", "t a common replicate number, resulting in 15 LC-MS/MS runs per method. For the retention time alig"], "order_basis": "paper_text_order:154", "id": "assay:1"}, {"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["10 min. As spike-in proteins we chose 13 non-mouse proteins with varying physico-chemical prope", "ate background and varying amounts of 13 non-mouse spike-in proteins. Shown are the pmol amount", "tions, which could be detected and mapped to mouse proteins. To account for these FP, the abund", "ity, specificity and accuracy, we used whole mouse cell lysate as constant background, represen"], "order_basis": "paper_text_order:3550", "id": "assay:2"}, {"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Afterward, an analysis of variance (ANOVA) model was fitted to the transformed data. As a post-hoc test Tukey's honest significance test was conducted, to determine, which spike-in states were significantly differential. Finally, the ANOVA p values were corrected for multiple testing using the Benjamini-Hochberg procedure."], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"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":"2026-11-04T00:47:31+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}}}