{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:27602285", "kind": "science-record", "revision": 7, "content_hash": "sha256:b5764561863e768062a9650dbb2a1b03e3cd554f6918cfb21119ce26618f30c4", "created_at": "2026-11-01T15:40:20Z", "updated_at": "2026-11-01T21:59:08Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Temporal dynamics of the developing lung transcriptome in three common inbred strains of laboratory mice reveals multiple stages of postnatal alveolar development.", "doi": "10.7717/peerj.2318", "pmid": "27602285", "authors": ["Kyle J Beauchemin", "Julie M Wells", "Alvin T Kho", "Vivek M Philip", "Daniela Kamir", "Isaac S Kohane", "Joel H Graber", "Carol J Bult"], "journal": "PeerJ", "year": 2016, "abstract": "To characterize temporal patterns of transcriptional activity during normal lung development, we generated genome wide gene expression data for 26 pre- and post-natal time points in three common inbred strains of laboratory mice (C57BL/6J, A/J, and C3H/HeJ). Using Principal Component Analysis and least squares regression modeling, we identified both strain-independent and strain-dependent patterns of gene expression. The 4,683 genes contributing to the strain-independent expression patterns were used to define a murine Developing Lung Characteristic Subtranscriptome (mDLCS). Regression modeling of the Principal Components supported the four canonical stages of mammalian embryonic lung development (embryonic, pseudoglandular, canalicular, saccular) defined previously by morphology and histology. For postnatal alveolar development, the regression model was consistent with four stages of alveolarization characterized by episodic transcriptional activity of genes related to pulmonary vascularization. Genes expressed in a strain-dependent manner were enriched for annotations related to neurogenesis, extracellular matrix organization, and Wnt signaling. Finally, a comparison of mouse and human transcriptomics from pre-natal stages of lung development revealed conservation of pathways associated with cell cycle, axon guidance, immune function, and metabolism as well as organism-specific expression of genes associated with extracellular matrix organization and protein modification. The mouse lung development transcriptome data generated for this study serves as a unique reference set to identify genes and pathways essential for normal mammalian lung development and for investigations into the developmental origins of respiratory disease and cancer. The gene expression data are available from the Gene Expression Omnibus (GEO) archive (GSE74243). Temporal expression patterns of mouse genes can be investigated using a study specific web resource (http://lungdevelopment.jax.org).", "claims": [{"id": "claim-method", "statement": "Using Principal Component Analysis and least squares regression modeling, we identified both strain-independent and strain-dependent patterns of gene expression.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:27602285", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Using Principal Component Analysis and least squares regression modeling, we identified both strain-independent and strain-dependent patterns of gene expression."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The raw data has been supplied as Supplemental files.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:27602285", "locator": "sections[34] \"Data Availability\" paragraph 2", "quote": "The raw data has been supplied as Supplemental files."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The study used Principal Component Analysis and least squares regression modeling to identify strain-independent and strain-dependent gene-expression patterns; the 4,683 genes contributing to strain-independent patterns defined the murine Developing Lung Characteristic Subtranscriptome (mDLCS). The raw and processed source data are available through GEO accession GSE74243.", "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:27602285"], "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:GSE74243"], "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:GSE74243"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:27602285", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.7717/peerj.2318", "sha256": "sha256:036bb703b51643d7c44c0daf0edf6daf87da7af56c35154a2de1168cceab722a", "bytes": 109950, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.7717/peerj.2318", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4991849", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE74243", "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=GSE74243", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE74243", "version": null, "note": "The raw data has been supplied as Supplemental files.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The raw data has been supplied as Supplemental files.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1915262", "GSM1915263", "GSM1915264", "GSM1915265", "GSM1915266", "GSM1915267", "GSM1915268", "GSM1915269", "GSM1915270", "GSM1915271", "GSM1915272", "GSM1915273", "GSM1915274", "GSM1915275", "GSM1915276", "GSM1915277", "GSM1915278", "GSM1915279", "GSM1915280", "GSM1915281", "GSM1915282", "GSM1915283", "GSM1915284", "GSM1915285", "GSM1915286", "GSM1915287", "GSM1915288", "GSM1915289", "GSM1915290", "GSM1915291", "GSM1915292", "GSM1915293", "GSM1915294", "GSM1915295", "GSM1915296", "GSM1915297", "GSM1915298", "GSM1915299", "GSM1915300", "GSM1915301", "GSM1915302", "GSM1915303", "GSM1915304", "GSM1915305", "GSM1915306", "GSM1915307", "GSM1915308", "GSM1915309", "GSM1915310", "GSM1915311", "GSM1915312", "GSM1915313", "GSM1915314", "GSM1915315", "GSM1915316", "GSM1915317", "GSM1915318", "GSM1915319", "GSM1915320", "GSM1915321", "GSM1915322", "GSM1915323", "GSM1915324", "GSM1915325", "GSM1915326", "GSM1915327", "GSM1915328", "GSM1915329", "GSM1915330", "GSM1915331", "GSM1915332", "GSM1915333", "GSM1915334", "GSM1915335", "GSM1915336", "GSM1915337", "GSM1915338", "GSM1915339", "GSM1915340", "GSM1915341", "GSM1915342", "GSM1915343", "GSM1915344", "GSM1915345", "GSM1915346", "GSM1915347", "GSM1915348", "GSM1915349", "GSM1915350", "GSM1915351", "GSM1915352", "GSM1915353", "GSM1915354", "GSM1915355", "GSM1915356", "GSM1915357", "GSM1915358", "GSM1915359", "GSM1915360", "GSM1915361", "GSM1915362", "GSM1915363", "GSM1915364", "GSM1915365", "GSM1915366", "GSM1915367", "GSM1915368", "GSM1915369", "GSM1915370", "GSM1915371", "GSM1915372", "GSM1915373", "GSM1915374", "GSM1915375", "GSM1915376", "GSM1915377", "GSM1915378", "GSM1915379", "GSM1915380", "GSM1915381", "GSM1915382", "GSM1915383", "GSM1915384", "GSM1915385", "GSM1915386", "GSM1915387", "GSM1915388", "GSM1915389", "GSM1915390", "GSM1915391", "GSM1915392", "GSM1915393", "GSM1915394", "GSM1915395", "GSM1915396", "GSM1915397", "GSM1915398", "GSM1915399", "GSM1915400", "GSM1915401", "GSM1915402", "GSM1915403", "GSM1915404", "GSM1915405", "GSM1915406", "GSM1915407", "GSM1915408", "GSM1915409", "GSM1915410", "GSM1915411", "GSM1915412", "GSM1915413", "GSM1915414", "GSM1915415", "GSM1915416", "GSM1915417", "GSM1915418", "GSM1915419", "GSM1915420", "GSM1915421", "GSM1915422", "GSM1915423", "GSM1915424", "GSM1915425", "GSM1915426", "GSM1915427", "GSM1915428", "GSM1915429", "GSM1915430", "GSM1915431", "GSM1915432", "GSM1915433", "GSM1915434", "GSM1915435", "GSM1915436", "GSM1915437", "GSM1915438", "GSM1915439", "GSM1915440", "GSM1915441", "GSM1915442", "GSM1915443", "GSM1915444", "GSM1915445", "GSM1915446", "GSM1915447", "GSM1915448", "GSM1915449", "GSM1915450", "GSM1915451", "GSM1915452", "GSM1915453", "GSM1915454", "GSM1915455", "GSM1915456", "GSM1915457", "GSM1915458", "GSM1915459", "GSM1915460", "GSM1915461", "GSM1915462", "GSM1915463", "GSM1915464", "GSM1915465", "GSM1915466", "GSM1915467", "GSM1915468", "GSM1915469", "GSM1915470", "GSM1915471", "GSM1915472", "GSM1915473", "GSM1915474", "GSM1915475", "GSM1915476", "GSM1915477"], "sample_count": 216, "group_sizes": null, "group_sizes_basis": null, "platform": "20894", "taxon": "Mus musculus", "title": "Genome wide gene expression during lung development in three inbred mouse strains", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:27602285:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:0bb17b89ec9b2631504628bb953a3630ea50b4de6e6f1efff24b5250b7e9f76a", "bytes": 2740, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[6]/table-wrap[1]#table-1", "version": null, "note": "Summary of analysis results for lung development transcriptional profiling in three inbred mouse strainse.The cumulative variation in gene expression accounted for by the first 10 principal components is 80.9%. Pearson Correlation results are from the pairwise correlation of PCA scores as a function of strain. Regression results show the significance levels of the effect of three variables (developmental stage, strain, and stage by strain interaction) for each Principal Component. Tukey HSD connecting letters diagram indicates relatedness of strains for each component.", "structure": {"pmcid": "PMC4991849", "section_index": 6, "section_title": "Regression analysis", "row_count": 31, "column_count": 8}, "table": {"label": "Table 1", "caption": "Summary of analysis results for lung development transcriptional profiling in three inbred mouse strainse.The cumulative variation in gene expression accounted for by the first 10 principal components is 80.9%. Pearson Correlation results are from the pairwise correlation of PCA scores as a function of strain. Regression results show the significance levels of the effect of three variables (developmental stage, strain, and stage by strain interaction) for each Principal Component. Tukey HSD connecting letters diagram indicates relatedness of strains for each component.", "rows": [["Component", "Var. (%)", "Pearson Correlation (R2)", "Regression (Pval)", "Tukey HSD"], ["PC1", "55.1 (55.1)", "C57BL/6J-A/J", ".990***", "Stage", "<.0001†", "AJ", "A"], ["A/J-C3H/HeJ", ".993***", "Strain", "0.9131", "B6", "A"], ["C57BL/6J-C3H/HeJ", ".990***", "Stage*strain", "0.6566", "C3H", "A"], ["PC2", "6.1 (61.2)", "C57BL/6J-A/J", ".744***", "Stage", "<.0001†", "AJ", "A"], ["A/J-C3H/HeJ", ".839***", "Strain", "0.5970", "B6", "A"], ["C57BL/6J-C3H/HeJ", ".849***", "Stage*strain", "0.0038", "C3H", "A"], ["PC3", "4.98 (66.2)", "C57BL/6J-A/J", ".865***", "Stage", "<.0001†", "AJ", "A"], ["A/J-C3H/HeJ", ".739***", "Strain", "0.2229", "B6", "A"], ["C57BL/6J-C3H/HeJ", ".646***", "Stage*strain", "0.2090", "C3H", "A"], ["PC4", "3.53 (69.7)", "C57BL/6J-A/J", ".117", "Stage", "<.0001†", "AJ", "B"], ["A/J-C3H/HeJ", ".114", "Strain", "0.0072", "B6", "B"], ["C57BL/6J-C3H/HeJ", ".192", "Stage*strain", "0.0029", "C3H", "A"], ["PC5", "2.83 (72.5)", "C57BL/6J-A/J", ".379*", "Stage", "<.0001†", "AJ", "B"], ["A/J-C3H/HeJ", ".445**", "Strain", "<.0001†", "B6", "C"], ["C57BL/6J-C3H/HeJ", ".262", "Stage*strain", "<.0001†", "C3H", "A"], ["PC6", "2.27 (74.8)", "C57BL/6J-A/J", ".130", "Stage", "<.0001†", "AJ", "B"], ["A/J-C3H/HeJ", ".231", "Strain", "<.0001†", "B6", "A"], ["C57BL/6J-C3H/HeJ", ".214", "Stage*strain", "0.0006†", "C3H", "B"], ["PC7", "2.02 (76.8)", "C57BL/6J-A/J", ".522***", "Stage", "<.0001†", "AJ", "A"], ["A/J-C3H/HeJ", ".561***", "Strain", "<.0001†", "B6", "B"], ["C57BL/6J-C3H/HeJ", ".734***", "Stage*strain", "0.0385", "C3H", "A"], ["PC8", "1.55 (78.4)", "C57BL/6J-A/J", ".286", "Stage", "<.0001†", "AJ", "B"], ["A/J-C3H/HeJ", ".469***", "Strain", "<.0001†", "B6", "A"], ["C57BL/6J-C3H/HeJ", ".131", "Stage*strain", "0.0437", "C3H", "A"], ["PC9", "1.43 (79.8)", "C57BL/6J-A/J", ".344*", "Stage", "<.0001†", "AJ", "B"], ["A/J-C3H/HeJ", ".479***", "Strain", "<.0001†", "B6", "C"], ["C57BL/6J-C3H/HeJ", ".194", "Stage*strain", "<.0001†", "C3H", "A"], ["PC10", "1.08 (80.9)", "C57BL/6J-A/J", ".320", "Stage", "<.0001†", "AJ", "C"], ["A/J-C3H/HeJ", ".386**", "Strain", "<.0001†", "B6", "B"], ["C57BL/6J-C3H/HeJ", ".181", "Stage*strain", "<.0001†", "C3H", "A"]], "row_count": 31, "column_count": 8, "numeric_cells": 91, "header_rows": 1, "locator": "section[6]/table-wrap[1]#table-1"}}, {"id": "asset:table:pmid:27602285:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:0bc9995f64303792194e3926b83026261cc59d71dab2a70c6ee1fb416418d9ec", "bytes": 1176, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[1]#table-2", "version": null, "note": "Summary of strain-dependent expression patterns for lung development transcriptional profiling in three inbred mouse strains.Four classes of strain-dependent gene expression account for the strain effects observed on PC 4–10. The percentage of genes in each of the four classes is based on total number of genes with significant strain-differences by Tukey HSD (Q < 0.05). The patterns within classes reflect the expression levels of genes in the outlier strain relative to the indistinguishable strains. The percentages of genes for each pattern are based on the total of genes in the parent class.", "structure": {"pmcid": "PMC4991849", "section_index": 15, "section_title": "Strain-specific patterns of gene expression during lung development", "row_count": 9, "column_count": 3}, "table": {"label": "Table 2", "caption": "Summary of strain-dependent expression patterns for lung development transcriptional profiling in three inbred mouse strains.Four classes of strain-dependent gene expression account for the strain effects observed on PC 4–10. The percentage of genes in each of the four classes is based on total number of genes with significant strain-differences by Tukey HSD (Q < 0.05). The patterns within classes reflect the expression levels of genes in the outlier strain relative to the indistinguishable strains. The percentages of genes for each pattern are based on the total of genes in the parent class.", "rows": [["Classes (4)", "Patterns"], ["C3H≠AJ≈B6", "C3H > AJ ≈ B6", "C3H < AJ ≈ B6"], ["223 genes (28.6%)", "89 genes (39.9%)", "134 genes (60.1%)"], ["B6≠AJ≈C3H", "B6 > C3H ≈ AJ", "B6 < C3H ≈ AJ"], ["349 genes (44.7%)", "142 genes (40.7%)", "207 genes (59.3%)"], ["AJ≠B6≈C3H", "AJ > B6 ≈ C3H", "AJ < B6 ≈ C3H"], ["152 genes (19.5%)", "85 genes (55.9%)", "67 genes (44.1%)"], ["C3H≠AJ≠B6", "", ""], ["57 genes (7.3%)", "", ""]], "row_count": 9, "column_count": 3, "numeric_cells": 11, "header_rows": 1, "locator": "section[15]/table-wrap[1]#table-2"}}, {"id": "asset:table:pmid:27602285:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6f6d2a38cb362e2250bc83f84ff54f78524d48033aa716c953f7f8c4611f006f", "bytes": 3367, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[19]/table-wrap[1]#table-3", "version": null, "note": "Summary of Reactome pathway enrichment results for the 771 genes represented in both mouse and human embryonic developing lung characteristic subtranscriptomes.Entities refer to proteins, molecules, sequences, and other physical complexes associated with a given pathway in Reactome database; entities found are those associated with input gene sets and total entities refers to all entities in a given pathway. FDR represents multiple testing corrected p-values for enrichment.", "structure": {"pmcid": "PMC4991849", "section_index": 19, "section_title": "Comparative analysis of the mouse and human embryonic developing lung characteristic subtranscriptomes", "row_count": 45, "column_count": 5}, "table": {"label": "Table 3", "caption": "Summary of Reactome pathway enrichment results for the 771 genes represented in both mouse and human embryonic developing lung characteristic subtranscriptomes.Entities refer to proteins, molecules, sequences, and other physical complexes associated with a given pathway in Reactome database; entities found are those associated with input gene sets and total entities refers to all entities in a given pathway. FDR represents multiple testing corrected p-values for enrichment.", "rows": [["", "Entities found", "Entities total", "Percent total", "FDR"], ["Cell cycle", "92", "608", "15.1%", "8.97 × 10−14"], ["Cell cycle checkpoints", "22", "169", "13.0%", "1.80 × 10−2"], ["ATR response to replication stress", "8", "39", "20.5%", "4.77 × 10−2"], ["Mitotic G1-G1/S phases", "21", "139", "15.1%", "4.46 × 10−3"], ["Pre-replicative complex activation", "8", "33", "24.2%", "2.76 × 10−2"], ["Mitotic G2-G2/M phases", "23", "141", "16.3%", "7.50 × 10−4"], ["Polo-like kinase-mediated events", "9", "23", "39.1%", "6.70 × 10−4"], ["S phase", "16", "140", "11.4%", "9.08 × 10−2"], ["M phase", "51", "316", "16.1%", "2.84 × 10−8"], ["Resolution chromatid cohesion", "27", "128", "21.1%", "1.83 × 10−6"], ["Metabolism", "135", "3,163", "4.3%", "1.00 × 101"], ["Erythrocyte gas exchange", "4", "16", "25.0%", "1.40 × 10−1"], ["Surfactant metabolism", "7", "52", "13.5%", "1.96 × 10−1"], ["Immune system", "132", "1,841", "7.2%", "6.69 × 10−2"], ["Adaptive immune system", "75", "1,002", "7.5%", "1.18 × 10−1"], ["TCR signaling", "25", "145", "17.2%", "1.63 × 10−4"], ["MHC-II antigen presentation", "30", "141", "21.3%", "3.20 × 10−7"], ["Costimulation by CD28 family", "24", "96", "25.0%", "5.42 × 10−7"], ["PD-1 signaling", "17", "45", "37.8%", "3.20 × 10−7"], ["Cytokine signaling in immunity", "68", "678", "10.0%", "5.66 × 10−4"], ["Interferon signaling", "35", "289", "12.1%", "2.43 × 10−3"], ["Interferon gamma signaling", "21", "138", "15.2%", "3.77 × 10−2"], ["Antiviral mechanism IFN-stimulated", "13", "83", "15.7%", "3.60 × 10−2"], ["Interleukin signaling", "31", "358", "8.7%", "1.56 × 10−1"], ["DAP12 signaling", "33", "364", "9.1%", "9.02 × 10−2"], ["Developmental biology", "86", "904", "9.5%", "8.68 × 10−6"], ["Axon guidance", "66", "568", "11.6%", "8.68 × 10−6"], ["L1CAM interactions", "16", "124", "12.9%", "5.66 × 10−2"], ["NCAM signaling (neurite out-growth)", "29", "298", "9.7%", "6.69 × 10−2"], ["Semaphorin interactions", "11", "73", "15.1%", "6.69 × 10−2"], ["Signaling by robo receptor", "8", "38", "21.1%", "4.44 × 10−2"], ["Signal transduction", "211", "2,710", "7.79%", "3.42 × 10−1"], ["PIP3 Activates AKT sgnaling", "15", "121", "12.4%", "6.69 × 10−2"], ["IRS-mediated sgnaling", "28", "306", "9.2%", "1.21 × 10−1"], ["SCF-KIT sgnaling", "34", "339", "10.0%", "3.94 × 10−2"], ["EGFR signaling", "38", "376", "10.1%", "2.76 × 10−2"], ["FGFR signaling", "33", "356", "9.3%", "7.44 × 10−2"], ["PDGF signaling", "38", "392", "9.7%", "3.88 × 10−2"], ["ERBB2 signaling", "33", "360", "9.2%", "8.04 × 10−2"], ["ERBB4 signaling", "34", "345", "9.9%", "4.77 × 10−2"], ["Rho GT pase signaling", "64", "418", "15.3%", "1.52 × 10−9"], ["NGF signaling", "43", "478", "9.0%", "6.29 × 10−2"], ["Wnt signaling", "35", "326", "10.7%", "1.74 × 10−2"], ["IGF1R signaling", "29", "311", "9.3%", "9.40 × 10−2"]], "row_count": 45, "column_count": 5, "numeric_cells": 179, "header_rows": 1, "locator": "section[19]/table-wrap[1]#table-3"}}], "gaps": ["asset:data:geo:GSE74243 not downloaded", "asset:data:geo:GSE74243 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "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": 1.0, "band": "verbatim", "quote": "Using Principal Component Analysis and least squares regression modeling, we identified both strain-independent and strain-dependent patterns of gene expression."}}, {"id": "method-2", "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": 0.8, "band": "high", "quote": "ANOVA"}}, {"id": "method-3", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "pathway enrichment"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor"]}, "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": ["pca_fit"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pca."}, "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": ["GSE74243"], "resolved_accessions": ["GSE74243"], "statements": ["The raw data has been supplied as Supplemental files."], "basis": "The paper names GSE74243 in NCBI Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["pca_fit"], "assets": ["source:pmid:27602285", "data:geo:GSE74243", "asset:table:pmid:27602285:1", "asset:table:pmid:27602285:2", "asset:table:pmid:27602285:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE74243"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:29:15Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 218587, "completion_tokens": 3103, "cached_tokens": 1944}}, "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:27602285", "type": "paper", "label": "pmid:27602285"}, {"id": "source:pmid:27602285", "type": "manuscript", "label": "PMID 27602285 full text"}, {"id": "data:geo:GSE74243", "type": "dataset", "label": "GEO GSE74243"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:27602285", "type": "paper", "label": "pmid:27602285"}, {"id": "source:pmid:27602285", "type": "manuscript", "label": "PMID 27602285 full text"}, {"id": "data:geo:GSE74243", "type": "dataset", "label": "GEO GSE74243"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-27602285", "type": "extraction", "used": ["source:pmid:27602285"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE74243", "type": "accession_resolution", "used": ["data:geo:GSE74243"], "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:27602285", "parent_hash": "sha256:e1ba4f58a78db825d5e733c6915fca28dca4f16a8072b3590bb8c860ec18a58f", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE74243 licence not read", "asset:data:geo:GSE74243 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"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": ["nt expression patterns were used to define a murine Developing Lung Characteristic Subtranscript", "and Wnt signaling. Finally, a comparison of mouse and human transcriptomics from pre-natal sta", "x organization and protein modification. The mouse lung development transcriptome data generate", "(GSE74243). Temporal expression patterns of mouse genes can be investigated using a study spec"], "order_basis": "paper_text_order:637", "id": "assay:1"}, {"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["n between biological replicates (detected by microarray) did not significantly impact trends of stra", "s of strain-dependent expression detected by microarray (shown next to each gene name on left) as se", "essing Gene expression was assayed using the Affymetrix Mouse Gene 1.0 ST array platform (Affymetrix", "Affymetrix Mouse Gene 1.0 ST array platform (Affymetrix). The .CEL files from the arrays were deposi"], "order_basis": "paper_text_order:2198", "id": "assay:2"}, {"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["rends of strain-variation when quantified by qPCR. Each error bar constructed using one standa", "each gene name on left) as seen by comparing qPCR significance to regression significance.10.7"], "order_basis": "paper_text_order:17758", "id": "assay:3"}, {"role": "analysis", "definition_id": "principal_component_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pca_fit"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Using Principal Component Analysis and least squares regression modeling, we identified both strain-independent and strain-dependent patterns of gene expression."], "order_basis": "consumes_earlier_output", "id": "assay:4"}]},"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":"2026-11-04T01:48:50+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}}}