{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:28235076", "kind": "science-record", "revision": 8, "content_hash": "sha256:b8f8070f270f182d75f33bf0d5ab2b0cd3b4d3d19256bb4add8cae198ca36b20", "created_at": "2026-11-01T15:40:24Z", "updated_at": "2026-11-01T22:42:56Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Changes in plasma protein levels as an early indication of a bloodstream infection.", "doi": "10.1371/journal.pone.0172987", "pmid": "28235076", "authors": ["Pentti Kuusela", "Mayank Saraswat", "Sakari Joenväärä", "Johanna Kaartinen", "Asko Järvinen", "Risto Renkonen"], "journal": "PloS one", "year": 2017, "abstract": "Blood culture is the primary diagnostic test performed in a suspicion of bloodstream infection to detect the presence of microorganisms and direct the treatment. However, blood culture is slow and time consuming method to detect blood stream infections or separate septic and/or bacteremic patients from others with less serious febrile disease. Plasma proteomics, despite its challenges, remains an important source for early biomarkers for systemic diseases and might show changes before direct evidence from bacteria can be obtained. We have performed a plasma proteomic analysis, simultaneously at the time of blood culture sampling from ten blood culture positive and ten blood culture negative patients, and quantified 172 proteins with two or more unique peptides. Principal components analysis, Orthogonal Projections to Latent Structures Discriminant Analysis (OPLS-DA) and ROC curve analysis were performed to select protein(s) features which can classify the two groups of samples. We propose a number of candidates which qualify as potential biomarkers to select the blood culture positive cases from negative ones. Pathway analysis by two methods revealed complement activation, phagocytosis pathway and alterations in lipid metabolism as enriched pathways which are relevant for the condition. Data are available via ProteomeXchange with identifier PXD005022.", "claims": [{"id": "claim-method", "statement": "Differences between controls and cases were evaluated with ANOVA on a protein-to-protein basis.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:28235076", "locator": "sections[8] \"2.4.2 Data analysis\" paragraph 4", "quote": "Differences between controls and cases were evaluated with ANOVA on a protein-to-protein basis."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The raw files were converted with MSConvert (ProteoWizard) to mzML-files. The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD005022.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:28235076", "locator": "sections[20] \"Data Availability\" paragraph 2", "quote": "The raw files were converted with MSConvert (ProteoWizard) to mzML-files. The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD005022."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The study used principal components analysis, OPLS-DA, and ROC curve analysis to select protein features that could classify blood-culture-positive and blood-culture-negative samples, and the source mass-spectrometry proteomics data are available through ProteomeXchange under identifier PXD005022.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:28235076", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Principal components analysis, Orthogonal Projections to Latent Structures Discriminant Analysis (OPLS-DA) and ROC curve analysis were performed to select protein(s) features which can classify the two groups of samples."}, {"asset": "source:pmid:28235076", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Data are available via ProteomeXchange with identifier PXD005022."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The study used principal components analysis, OPLS-DA, and ROC curve analysis to select protein features that could classify blood-culture-positive and blood-culture-negative samples, and the source mass-spectrometry proteomics data are available through ProteomeXchange under identifier PXD005022.", "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:28235076"], "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:PXD005022"], "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:PXD005022"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:28235076", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1371/journal.pone.0172987", "sha256": "sha256:b83ea11804e0e29a4f0d7d193345d483efe9da04fd986d3f808dc39397cf318f", "bytes": 49424, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1371/journal.pone.0172987", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5325609", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD005022", "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=PXD005022", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD005022", "version": null, "note": "The raw files were converted with MSConvert (ProteoWizard) to mzML-files. The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD005022.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The raw files were converted with MSConvert (ProteoWizard) to mzML-files. The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD005022.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Quantitative proteomics of bloodstream infection", "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:28235076:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:33038560d245c56cd72d66d4118617819939569e9c29be552ed73891664ad1ab", "bytes": 3231, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#pone.0172987.t001", "version": null, "note": "Top 10 up- and downregulated proteins in plasma of ten patients with a positive blood culture (cases) and ten with a negative blood culture (controls) at the time point of blood culture sampling.The top proteins are according to the fold change in case versus controls. Only the proteins having less than 0.05 ANOVA p values are shown. Peptide count is the total peptides found for corresponding proteins and unique peptides is the number of unique peptides found out of the total peptides. Confidence score, ANOVA p value, maximum fold change, condition of the highest and lowest mean and full name of the protein are given in separate columns.", "structure": {"pmcid": "PMC5325609", "section_index": 12, "section_title": "3.2 Proteomic dataset", "row_count": 21, "column_count": 9}, "table": {"label": "Table 1", "caption": "Top 10 up- and downregulated proteins in plasma of ten patients with a positive blood culture (cases) and ten with a negative blood culture (controls) at the time point of blood culture sampling.The top proteins are according to the fold change in case versus controls. Only the proteins having less than 0.05 ANOVA p values are shown. Peptide count is the total peptides found for corresponding proteins and unique peptides is the number of unique peptides found out of the total peptides. Confidence score, ANOVA p value, maximum fold change, condition of the highest and lowest mean and full name of the protein are given in separate columns.", "rows": [["Accession", "Peptide count", "Unique peptides", "Confidence score", "Anova (p)", "Max fold change", "Highest mean condition", "Lowest mean condition", "Description"], ["Q9H497", "2", "2", "10.7157", "0.001182", "8.844932", "Case", "Control", "Torsin-3A"], ["P07339;C9JH19", "2", "2", "11.8647", "0.003668", "2.631503", "Case", "Control", "Cathepsin D"], ["Q96SN7;C9J2H9;C9J5L2;C9JQR7;C9JUY6", "4", "3", "27.6575", "0.000649", "2.027496", "Case", "Control", "Protein orai-2"], ["Q9Y4B5;J3QLE1", "3", "2", "20.227", "0.010045", "1.870043", "Case", "Control", "Microtubule cross-linking factor 1"], ["Q08AH1;E5RFK0", "3", "3", "18.8377", "0.019465", "1.84317", "Case", "Control", "Acyl-coenzyme A synthetase ACSM1, mitochondrial"], ["A0A087WU16;B2REA4;O75626", "4", "4", "26.6581", "7.38E-07", "1.77715", "Case", "Control", "PR domain zinc finger protein 1"], ["Q16531", "2", "2", "7.7408", "0.034509", "1.750108", "Case", "Control", "DNA damage-binding protein 1"], ["P02750", "40", "37", "186.9309", "0.00229", "1.640414", "Case", "Control", "Leucine-rich alpha-2-glycoprotein"], ["A0A0A0MTD1;A0A0A0MTC4;A0A0A0MTC5;A0A0A0MTC6;E5RJN7;E7EPX0;E7EVJ4;E9PH62;F8VPI7;G5EA18;Q9NUL3", "5", "4", "22.6587", "0.013193", "1.61796", "Case", "Control", "Double-stranded RNA-binding protein Staufen homolog 2"], ["P04217;M0R009", "48", "41", "261.3448", "0.001136", "1.596944", "Case", "Control", "Alpha-1B-glycoprotein"], ["O94782;C9JC88;C9JWX4", "3", "2", "16.0733", "0.001325", "5.967845", "Control", "Case", "Ubiquitin carboxyl-terminal hydrolase 1"], ["G3V1N2;P69905", "3", "3", "31.698", "0.000981", "5.127688", "Control", "Case", "HCG1745306, isoform CRA_a"], ["A0A075B702", "2", "2", "17.6117", "1.07E-05", "4.41976", "Control", "Case", "Protein TRAJ41 (Fragment)"], ["E9PLW5;R4GN25", "2", "2", "10.7804", "0.003909", "4.260173", "Control", "Case", "Putative protein N-methyltransferase FAM86B1"], ["P38935", "2", "2", "9.2636", "0.001711", "3.612221", "Control", "Case", "DNA-binding protein SMUBP-2"], ["O60309", "4", "3", "18.0095", "0.000957", "3.304585", "Control", "Case", "Leucine-rich repeat-containing protein 37A3"], ["E9PPB4", "2", "2", "18.3488", "0.002286", "3.190066", "Control", "Case", "Peroxisomal biogenesis factor 19"], ["Q7Z3I0;A0A075B7G4;Q8IYB9", "3", "2", "22.3658", "0.000508", "3.14666", "Control", "Case", "Putative uncharacterized protein DKFZp313E1411"], ["H0YFH1", "9", "2", "78.0417", "0.005951", "2.729399", "Control", "Case", "Alpha-2-macroglobulin (Fragment)"], ["P01617;A0A0A0MTQ6", "4", "2", "37.2069", "6.15E-05", "2.570449", "Control", "Case", "Ig kappa chain V-II region TEW"]], "row_count": 21, "column_count": 9, "numeric_cells": 134, "header_rows": 1, "locator": "section[12]/table-wrap[1]#pone.0172987.t001"}}, {"id": "asset:table:pmid:28235076:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e0c19a2527a7f2f4ca048356181c70c7076d5d75766e307971f6cc95d1aff731", "bytes": 3087, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#pone.0172987.t002", "version": null, "note": "Proteins significantly different in the S-Plot in cases versus controls are shown in the table.Uniprot accession or a group of accessions is given as primary Id. Peptides column represents the total number of peptides found for the said protein and unique peptides are number of unique peptides out of the total peptides for the given protein. Confidence score, ANOVA p value, highest and lowest mean condition, full name of the protein, covariance (p[1]) and correlation (p(corr)[1]) are given in various columns of the table.", "structure": {"pmcid": "PMC5325609", "section_index": 14, "section_title": "3.4 Orthogonal Projections to Latent Structures Discriminant Analysis (OPLS-DA)", "row_count": 15, "column_count": 11}, "table": {"label": "Table 2", "caption": "Proteins significantly different in the S-Plot in cases versus controls are shown in the table.Uniprot accession or a group of accessions is given as primary Id. Peptides column represents the total number of peptides found for the said protein and unique peptides are number of unique peptides out of the total peptides for the given protein. Confidence score, ANOVA p value, highest and lowest mean condition, full name of the protein, covariance (p[1]) and correlation (p(corr)[1]) are given in various columns of the table.", "rows": [["Primary accession", "All peptides", "Unique peptides", "Confidence score", "ANOVA p-value", "Fold change", "Highest mean", "Lowest mean", "Description", "p[1]", "p(corr)[1]"], ["A0A075B702", "2", "2", "17.6", "1.07E-05", "4.4", "Control", "Case", "Protein TRAJ41 (Fragment) OS = Homo sapiens GN = TRAJ41 PE = 4 SV = 1", "0.03", "0.81"], ["E9PLW5;R4GN25", "2", "2", "10.8", "3.91E-03", "4.3", "Control", "Case", "Putative protein N-methyltransferase FAM86B1 OS = Homo sapiens GN = FAM86B1 PE = 4 SV = 1", "0.02", "0.80"], ["P01617;A0A0A0MTQ6", "4", "2", "37.2", "6.15E-05", "2.6", "Control", "Case", "Ig kappa chain V-II region TEW OS = Homo sapiens PE = 1 SV = 1", "0.04", "0.79"], ["Q8IU89;H0YMG6;H0YN05", "4", "4", "31.0", "3.96E-04", "1.9", "Control", "Case", "Ceramide synthase 3 OS = Homo sapiens GN = CERS3 PE = 1 SV = 2", "0.03", "0.79"], ["P38935", "2", "2", "9.3", "1.71E-03", "3.6", "Control", "Case", "DNA-binding protein SMUBP-2 OS = Homo sapiens GN = IGHMBP2 PE = 1 SV = 3", "0.02", "0.77"], ["Q7Z3I0;A0A075B7G4;Q8IYB9", "3", "2", "22.4", "5.08E-04", "3.1", "Control", "Case", "Putative uncharacterized protein DKFZp313E1411 OS = Homo sapiens GN = DKFZp313E1411 PE = 2 SV = 1", "0.03", "0.76"], ["O94782;C9JC88;C9JWX4", "3", "2", "16.1", "1.33E-03", "6.0", "Control", "Case", "Ubiquitin carboxyl-terminal hydrolase 1 OS = Homo sapiens GN = USP1 PE = 1 SV = 1", "0.02", "0.74"], ["Q7RTY7;H0YGY6;H0YH00", "6", "3", "37.5", "2.47E-03", "2.3", "Control", "Case", "Ovochymase-1 OS = Homo sapiens GN = OVCH1 PE = 2 SV = 2", "0.03", "0.73"], ["E7EVV8;Q0VG06", "2", "2", "10.9", "1.17E-03", "1.8", "Control", "Case", "Fanconi anemia-associated protein of 100 kDa OS = Homo sapiens GN = FAAP100 PE = 1 SV = 1", "0.03", "0.70"], ["P02763", "48", "38", "239.3", "6.49E-03", "1.6", "Case", "Control", "Alpha-1-acid glycoprotein 1 OS = Homo sapiens GN = ORM1 PE = 1 SV = 1", "-0.30", "-0.71"], ["P07339;C9JH19", "2", "2", "11.9", "3.67E-03", "2.6", "Case", "Control", "Cathepsin D OS = Homo sapiens GN = CTSD PE = 1 SV = 1", "-0.06", "-0.72"], ["P04217;M0R009", "48", "41", "261.3", "1.14E-03", "1.6", "Case", "Control", "Alpha-1B-glycoprotein OS = Homo sapiens GN = A1BG PE = 1 SV = 4", "-0.23", "-0.75"], ["P02750", "40", "37", "186.9", "2.29E-03", "1.6", "Case", "Control", "Leucine-rich alpha-2-glycoprotein OS = Homo sapiens GN = LRG1 PE = 1 SV = 2", "-0.23", "-0.77"], ["A0A087WU16;B2REA4;O75626", "4", "4", "26.7", "7.38E-07", "1.8", "Case", "Control", "PR domain zinc finger protein 1 OS = Homo sapiens GN = PRDM1 PE = 1 SV = 1", "-0.04", "-0.81"]], "row_count": 15, "column_count": 11, "numeric_cells": 128, "header_rows": 1, "locator": "section[14]/table-wrap[1]#pone.0172987.t002"}}, {"id": "asset:table:pmid:28235076:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b787a5e945a1d051c4dbbd64e6e162563bed91610dd6be8765c34adaa221ad53", "bytes": 1773, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[16]/table-wrap[1]#pone.0172987.t003", "version": null, "note": "Proteins found to be significantly different in S-Plot were analyzed by ROC curve by Analyse-it program.Uniprot accession, full protein name (description), Area under the curve (AUC), 95% confidence interval (95% CI), standard error (SE), optimum threshold, sensitivity at that threshold and 1-specificity at that threshold and cost for the optimum threshold are shown in the table in various columns.", "structure": {"pmcid": "PMC5325609", "section_index": 16, "section_title": "3.6 ROC curve analysis", "row_count": 15, "column_count": 5}, "table": {"label": "Table 3", "caption": "Proteins found to be significantly different in S-Plot were analyzed by ROC curve by Analyse-it program.Uniprot accession, full protein name (description), Area under the curve (AUC), 95% confidence interval (95% CI), standard error (SE), optimum threshold, sensitivity at that threshold and 1-specificity at that threshold and cost for the optimum threshold are shown in the table in various columns.", "rows": [["Primary accession", "Description", "AUC", "95% CI", "SE"], ["A0A075B702", "Protein TRAJ41 (Fragment)", "0.98", "0.933 to 1.027", "0.02"], ["E9PLW5;R4GN25", "Putative protein N-methyltransferase FAM86B1", "1.00", "1 to 1", "0.00"], ["P01617;A0A0A0MTQ6", "Ig kappa chain V-II region TEW", "0.96", "0.886 to 1.034", "0.04"], ["Q8IU89;H0YMG6;H0YN05", "Ceramide synthase 3", "0.94", "0.818 to 1.062", "0.06"], ["P38935", "DNA-binding protein SMUBP-2", "0.97", "0.911 to 1.029", "0.03"], ["Q7Z3I0;A0A075B7G4;Q8IYB9", "Putative uncharacterized protein DKFZp313E1411", "0.98", "0.933 to 1.027", "0.02"], ["O94782;C9JC88;C9JWX4", "Ubiquitin carboxyl-terminal hydrolase 1", "0.97", "0.911 to 1.029", "0.03"], ["Q7RTY7;H0YGY6;H0YH00", "Ovochymase-1", "0.87", "0.712 to 1.028", "0.08"], ["E7EVV8;Q0VG06", "Fanconi anemia-associated protein of 100 kDa", "0.90", "0.748 to 1.052", "0.08"], ["P02763", "Alpha-1-acid glycoprotein 1", "0.83", "0.645 to 1.015", "0.09"], ["P07339;C9JH19", "Cathepsin D", "0.89", "0.694 to 1.086", "0.10"], ["P04217;M0R009", "Alpha-1B-glycoprotein", "0.85", "0.666 to 1.034", "0.09"], ["P02750", "Leucine-rich alpha-2-glycoprotein", "0.86", "0.696 to 1.024", "0.08"], ["A0A087WU16;B2REA4;O75626", "PR domain zinc finger protein 1", "0.99", "0.962 to 1.018", "0.01"]], "row_count": 15, "column_count": 5, "numeric_cells": 69, "header_rows": 1, "locator": "section[16]/table-wrap[1]#pone.0172987.t003"}}], "gaps": ["asset:data:geo:PXD005022 not downloaded", "asset:data:geo:PXD005022 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": "Differences between controls and cases were evaluated with ANOVA on a protein-to-protein basis."}}, {"id": "method-2", "family": "principal_component_analysis", "specific": "pca", "label": "Principal component analysis", "dsl_operations": ["pca_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["wide_numeric_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "Principal components analysis"}}, {"id": "method-3", "family": "diagnostic_evaluation", "specific": "roc", "label": "Diagnostic test evaluation", "dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["reference_standard_and_test"], "evidence": {"score": 0.7, "band": "medium", "quote": "ROC curve"}}], "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": ["PXD005022"], "resolved_accessions": ["PXD005022"], "statements": ["The raw files were converted with MSConvert (ProteoWizard) to mzML-files. The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD005022."], "basis": "The paper names PXD005022 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:28235076", "data:geo:PXD005022", "asset:table:pmid:28235076:1", "asset:table:pmid:28235076:2", "asset:table:pmid:28235076:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD005022"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:30:43Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 96342, "completion_tokens": 3200, "cached_tokens": 2105}}, "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:28235076", "type": "paper", "label": "pmid:28235076"}, {"id": "source:pmid:28235076", "type": "manuscript", "label": "PMID 28235076 full text"}, {"id": "data:geo:PXD005022", "type": "dataset", "label": "GEO PXD005022"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:28235076", "type": "paper", "label": "pmid:28235076"}, {"id": "source:pmid:28235076", "type": "manuscript", "label": "PMID 28235076 full text"}, {"id": "data:geo:PXD005022", "type": "dataset", "label": "GEO PXD005022"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-28235076", "type": "extraction", "used": ["source:pmid:28235076"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD005022", "type": "accession_resolution", "used": ["data:geo:PXD005022"], "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:28235076", "parent_hash": "sha256:8b5ae1049ad4846f501e28400f88ace799b2a44709fd4bfc36bfefacdf52645a", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:PXD005022 licence not read", "asset:data:geo:PXD005022 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": 0.83, "evidence": ["rs with less serious febrile disease. Plasma proteomics, despite its challenges, remains an importan", "can be obtained. We have performed a plasma proteomic analysis, simultaneously at the time of bloo"], "order_basis": "paper_text_order:392", "id": "assay:1"}, {"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": ["Differences between controls and cases were evaluated with ANOVA on a protein-to-protein basis."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"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":"2026-11-04T02:37:26+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}}}