{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:29164149", "kind": "science-record", "revision": 7, "content_hash": "sha256:0c13f7815c1b8918bca0dcce991a4c729c0f436c20e5672477fe81d40624dcfb", "created_at": "2026-11-01T15:40:29Z", "updated_at": "2026-11-01T21:21:10Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Bioinformatics Genes and Pathway Analysis for Chronic Neuropathic Pain after Spinal Cord Injury.", "doi": "10.1155/2017/6423021", "pmid": "29164149", "authors": ["Guan Zhang", "Ping Yang"], "journal": "BioMed research international", "year": 2017, "abstract": "It is well known spinal cord injury (SCI) can cause chronic neuropathic pain (NP); however its underlying molecular mechanisms remain elusive. This study aimed to disclose differentially expressed genes (DEGs) and activated signaling pathways in association with SCI induced chronic NP, in order to identify its diagnostic and therapeutic targets. Microarray dataset GSE5296 has been downloaded from Gene Expression Omnibus (GEO) database. Significant analysis of microarray (SAM), Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis, and pathway network analysis have been used to compare changes of DEGs and signaling pathways between the SCI and sham-injury group. As a result, DEGs analysis showed there were 592 DEGs with significantly altered expression; among them Ccl3 expression showed the highest upregulation which implicated its association with SCI induced chronic NP. Moreover, KEGG analysis found 209 pathways changed significantly; among them the most significantly activated one is MAPK signaling pathway, which is in line with KEGG analysis results. Our results show Ccl3 is highly associated with SCI induced chronic NP; as the exosomes with Ccl3 can be easily and efficiently detected in peripheral blood, Ccl3 may serve as a potential prognostic target for the diagnosis and treatment of SCI induced chronic NP.", "claims": [{"id": "claim-method", "statement": "Significant analysis of microarray (SAM) is used to study DEGs.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29164149", "locator": "sections[5] \"2.3. Analysis Methods\" paragraph 2", "quote": "Significant analysis of microarray (SAM) is used to study DEGs."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Microarray dataset GSE5296 has been downloaded from Gene Expression Omnibus (GEO) database.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29164149", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Microarray dataset GSE5296 has been downloaded from Gene Expression Omnibus (GEO) database."}], "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:29164149"], "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:GSE5296"], "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:GSE5296"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:29164149", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/2017/6423021", "sha256": "sha256:5dcfa31d9e1cdd2f70dd2521e2f83add55f50abf38d5b37a537df1543a395ae1", "bytes": 43722, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/2017/6423021", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5661087", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE5296", "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=GSE5296", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE5296", "version": null, "note": "Microarray dataset GSE5296 has been downloaded from Gene Expression Omnibus (GEO) database.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Microarray dataset GSE5296 has been downloaded from Gene Expression Omnibus (GEO) database.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM118664", "GSM118672", "GSM119764", "GSM119765", "GSM119766", "GSM119767", "GSM119768", "GSM119769", "GSM119770", "GSM119771", "GSM119772", "GSM119773", "GSM119774", "GSM119775", "GSM119776", "GSM119777", "GSM119778", "GSM119779", "GSM119780", "GSM119781", "GSM119782", "GSM119783", "GSM119784", "GSM119785", "GSM119786", "GSM119787", "GSM119788", "GSM119789", "GSM119790", "GSM119791", "GSM119792", "GSM119793", "GSM119794", "GSM119795", "GSM119796", "GSM119797", "GSM119798", "GSM119799", "GSM119800", "GSM119801", "GSM119802", "GSM119803", "GSM119804", "GSM119805", "GSM119806", "GSM119807", "GSM119808", "GSM119809", "GSM119810", "GSM119811", "GSM119812", "GSM119813", "GSM119814", "GSM119815", "GSM119816", "GSM119817", "GSM119818", "GSM119819", "GSM119820", "GSM119821", "GSM119822", "GSM119823", "GSM119824", "GSM119825", "GSM119826", "GSM119827", "GSM119828", "GSM119829", "GSM119830", "GSM119831", "GSM119832", "GSM119833", "GSM119834", "GSM119835", "GSM119836", "GSM119837", "GSM119838", "GSM119839", "GSM119840", "GSM119841", "GSM119842", "GSM119843", "GSM119844", "GSM119845", "GSM119846", "GSM119847", "GSM119848", "GSM119849", "GSM119850", "GSM119851", "GSM119852", "GSM119853", "GSM119854", "GSM119855", "GSM119856", "GSM120018"], "sample_count": 96, "group_sizes": null, "group_sizes_basis": null, "platform": "1261", "taxon": "Mus musculus", "title": "Spinal Cord Injury Murine Model", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:29164149:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d450e320c0b8f28e621b6cd06c5d70af3f2b3a9609c3fd8fd75f3ec27da3bf68", "bytes": 1609, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[8]/table-wrap[1]#tab1", "version": null, "note": "Top 10 significantly enriched up- and downregulated DEGs. The P values associated with each term are calculated by the Fisher Exact Test which represents the “degree of enrichment.” Q-value is the correction for multiple comparison by Benjamini and Hochberg [33]. The rank was according to the difference determined by d Score, fold change, and P value. The top ten largest differences in DEGs were screen with fold change > 2 and P < 0.05, and the maximum change of gene expression profile was upregulation of Ccl3.", "structure": {"pmcid": "PMC5661087", "section_index": 8, "section_title": "3.2. Screening of Differentially Expressed Genes from T8 Lesion Centre (Ccl3 Was the Maximum Changed Gene Expression Profile among the 592 DEGs)", "row_count": 11, "column_count": 10}, "table": {"label": "Table 1", "caption": "Top 10 significantly enriched up- and downregulated DEGs. The P values associated with each term are calculated by the Fisher Exact Test which represents the “degree of enrichment.” Q-value is the correction for multiple comparison by Benjamini and Hochberg [33]. The rank was according to the difference determined by d Score, fold change, and P value. The top ten largest differences in DEGs were screen with fold change > 2 and P < 0.05, and the maximum change of gene expression profile was upregulation of Ccl3.", "rows": [["DEGs", "Accession number", "Signal of control", "Signal of experimental", "d Score", "Fold change", "P value", "q-value", "Expression change", "Rank"], ["Ccl3", "NM_011337", "5.37", "8.81", "10.04", "10.91", "2.20E − 05", "0", "Up", "1"], ["Atf3", "NM_007498", "6.12", "9.18", "10.10", "8.37", "2.20E − 05", "0", "Up", "2"], ["Plek", "NM_019549", "6.67", "9.20", "8.10", "5.77", "2.20E − 05", "0", "Up", "3"], ["Ctla2b", "NM_001145801", "5.45", "7.90", "8.08", "5.45", "2.20E − 05", "0", "Up", "4"], ["Bcl2a1a", "NM_007534", "7.23", "9.59", "8.37", "5.14", "2.20E − 05", "0", "Up", "5"], ["Ch25h", "NM_009890", "6.82", "9.13", "8.27", "4.95", "2.20E − 05", "0", "Up", "6"], ["Plek", "NM_019549", "5.87", "8.12", "7.58", "4.76", "2.20E − 05", "0", "Up", "7"], ["Tnfaip3", "NM_001166402", "5.75", "7.45", "8.12", "3.24", "2.20E − 05", "0", "Up", "8"], ["Tgif1", "NM_001164074", "6.05", "7.59", "8.52", "2.91", "2.20E − 05", "0", "Up", "9"], ["Gpr84", "NM_030720", "6.31", "7.83", "7.92", "2.86", "2.20E − 05", "0", "Up", "10"]], "row_count": 11, "column_count": 10, "numeric_cells": 82, "header_rows": 1, "locator": "section[8]/table-wrap[1]#tab1"}}, {"id": "asset:table:pmid:29164149:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:42dd2a847fa3d7c4ff6276fb141a74eb49475f11a03b87c9157e491f7188864a", "bytes": 1352, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#tab2", "version": null, "note": "Top 10 GO terms and KEGG pathways enrichment results of DEGs. Significantly enriched GO terms and KEGG pathways with FDR < 0.05 were screened out. KEGG biological pathway enrichment analysis found that MAPK signaling pathway (enrichment score = 5.68, P = 3.38E − 74, and FDR = 8.78E − 72) was the most important one among the 209 pathways according to the enrichment score.", "structure": {"pmcid": "PMC5661087", "section_index": 9, "section_title": "3.3. KEGG Pathway Enrichment Analysis from T8 Lesion Centre (MAPK Signaling Pathway Was the Most Important among the 209 Pathways)", "row_count": 11, "column_count": 6}, "table": {"label": "Table 2", "caption": "Top 10 GO terms and KEGG pathways enrichment results of DEGs. Significantly enriched GO terms and KEGG pathways with FDR < 0.05 were screened out. KEGG biological pathway enrichment analysis found that MAPK signaling pathway (enrichment score = 5.68, P = 3.38E − 74, and FDR = 8.78E − 72) was the most important one among the 209 pathways according to the enrichment score.", "rows": [["Pathway ID", "Pathway name", "Enrichment score", "P value", "FDR", "Rank"], ["4010", "MAPK signaling pathway", "5.68", "3.38E − 74", "8.78E − 72", "1"], ["1100", "Metabolic pathways", "2.73", "3.22E − 65", "4.19E − 63", "2"], ["4151", "PI3K-Akt signaling pathway", "4.31", "8.74E − 57", "7.57E − 55", "3"], ["5200", "Pathways in cancer", "4.36", "2.57E − 53", "1.67E − 51", "4"], ["4380", "Osteoclast differentiation", "6.77", "2.20E − 52", "1.14E − 50", "5"], ["5166", "HTLV-I infection", "4.54", "6.12E − 52", "2.65E − 50", "6"], ["4810", "Regulation of actin cytoskeleton", "5.06", "3.43E − 49", "1.28E − 47", "7"], ["4062", "Chemokine signaling pathway", "5.26", "6.63E − 49", "2.15E − 47", "8"], ["4510", "Focal adhesion", "5.11", "2.31E − 47", "6.68E − 46", "9"], ["5205", "Proteoglycans in cancer", "4.73", "3.22E − 45", "8.36E − 44", "10"]], "row_count": 11, "column_count": 6, "numeric_cells": 50, "header_rows": 1, "locator": "section[9]/table-wrap[1]#tab2"}}, {"id": "asset:table:pmid:29164149:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:20e1a0c85bd9a2c5f341b65e4268d4c8afa036e928ad2bfbb07c0f3394c1aa24", "bytes": 1168, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#tab3", "version": null, "note": "The top 10 altered pathways of network analyses. The outdegree and indegree represent, respectively, the number of upstream and downstream signal pathways. The degree represents the sum of the outdegree and indegree. In the top 10 altered pathway interaction nets with 111 nodes and 404 relationships between each other, MAPK signaling pathway was the most important one with the largest degree (outdegree = 5, indegree = 39, and degree = 44).", "structure": {"pmcid": "PMC5661087", "section_index": 10, "section_title": "3.4. Pathway Network Analyses from T8 Lesion Centre (MAPK Signaling Pathway Was Also the Most Important Pathway)", "row_count": 11, "column_count": 6}, "table": {"label": "Table 3", "caption": "The top 10 altered pathways of network analyses. The outdegree and indegree represent, respectively, the number of upstream and downstream signal pathways. The degree represents the sum of the outdegree and indegree. In the top 10 altered pathway interaction nets with 111 nodes and 404 relationships between each other, MAPK signaling pathway was the most important one with the largest degree (outdegree = 5, indegree = 39, and degree = 44).", "rows": [["Pathway ID", "Pathway name", "Outdegree", "Indegree", "Degree", "Rank"], ["4010", "MAPK signaling pathway", "5", "39", "44", "1"], ["4210", "Apoptosis", "3", "29", "32", "2"], ["5200", "Pathways in cancer", "28", "0", "28", "3"], ["4110", "Cell cycle", "3", "20", "23", "4"], ["10", "Glycolysis/gluconeogenesis", "5", "15", "20", "5"], ["4020", "Calcium signaling pathway", "5", "14", "19", "6"], ["4115", "p53 signaling pathway", "2", "17", "19", "7"], ["4310", "Wnt signaling pathway", "8", "9", "17", "8"], ["4060", "Cytokine-cytokine receptor interaction", "0", "16", "16", "9"], ["620", "Pyruvate metabolism", "7", "8", "15", "10"]], "row_count": 11, "column_count": 6, "numeric_cells": 51, "header_rows": 1, "locator": "section[10]/table-wrap[1]#tab3"}}, {"id": "asset:table:pmid:29164149:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7200530ff6e793c15c954fae62d8b619221c3fa065331ab2998297fbd3eedc24", "bytes": 2467, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#tab4", "version": null, "note": "Top 10 DEGs and pathways between sham-injury and injury in lesion centre at different time points. At different time points, top 10 DEGs and pathways between sham-injury and injury in lesion centre are showed, respectively.", "structure": {"pmcid": "PMC5661087", "section_index": 11, "section_title": "3.5. Systematic Analysis of DEGs and Altered Pathway in Different Section and Time Points by SAM and KEGG", "row_count": 12, "column_count": 3}, "table": {"label": "Table 4", "caption": "Top 10 DEGs and pathways between sham-injury and injury in lesion centre at different time points. At different time points, top 10 DEGs and pathways between sham-injury and injury in lesion centre are showed, respectively.", "rows": [["Time point", "Top 10 DEGs between sham-injury and injury in lesion centre", "Top 10 pathways between sham-injury and injury in lesion centre"], ["0.5 h", "Npas4, Gm2083, Socs3, Socs3, Fosb, Ccl3, II6, Cyr61, Ptgs2, Myh1", "Pathways in cancer, MAPK signaling pathway, Transcriptional misregulation in cancer, focal adhesion, proteoglycans in cancer, PI3K-Akt signaling pathway, hippo signaling pathway, HTLV-I infection, regulation of actin cytoskeleton, metabolic pathways"], [""], ["4 h", "Ucn2, Gm2083, Atf3, Hspa1b, Hspa1b, Ccl3, C330006P03Rik, Hspa1a, Hspa1b, Egr3", "Metabolic pathways, MAPK signaling pathway, pathways in cancer, PI3K-Akt signaling pathway, HTLV-I infection, focal adhesion, proteoglycans in cancer, osteoclast differentiation, transcriptional misregulation in cancer, olfactory transduction"], [""], ["24 h", "Gm2083, Socs3, Chi3l3, Adam8, Gp49a, Hmox1, Serpine1, Tgm1, A130040M12Rik, Tnc", "Metabolic pathways, MAPK signaling pathway, pathways in cancer, HTLV-I infection, PI3K-Akt signaling pathway, focal adhesion, protein processing in endoplasmic reticulum, regulation of actin cytoskeleton, Epstein-Barr virus infection, proteoglycans in cancer"], [""], ["3 d", "Gpnmb, Cd36, Abca1, Cd5l, Cd36, Ccnb1, Thbs1, Rrm2, Rrm2, Sprr1a", "Metabolic pathways, HTLV-I infection, pathways in cancer, focal adhesion, regulation of actin cytoskeleton, PI3K-Akt signaling pathway, proteoglycans in cancer, MAPK signaling pathway, lysosome, osteoclast differentiation"], [""], ["7 d", "Gpnmb, Gp49a, Cd36, Cd36, Ms4a7, Cd5l, C3ar1, Clec7a, Cd68, Atp6v0d2", "Focal adhesion, PI3K-Akt signaling pathway, metabolic pathways, pathways in cancer, proteoglycans in cancer, MAPK signaling pathway, regulation of actin cytoskeleton, osteoclast differentiation, HTLV-I infection, tuberculosis"], [""], ["28 d", "Gpnmb, Clec7a, Cst7, Gp49a, Lgals3, Cd68, C3ar1, Ms4a7, Sprr1a, Cd48", "Metabolic pathways, MAPK signaling pathway, pathways in cancer, HTLV-I infection, focal adhesion, proteoglycans in cancer, PI3K-Akt signaling pathway, regulation of actin cytoskeleton, chemokine signaling pathway, phagosome"]], "row_count": 12, "column_count": 3, "numeric_cells": 14, "header_rows": 1, "locator": "section[11]/table-wrap[1]#tab4"}}, {"id": "asset:table:pmid:29164149:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f0db91065da59e7098c0c48428f7b98218fa064555b45dd7284bdf3333fd6723", "bytes": 1546, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[2]#tab5", "version": null, "note": "Top 10 DEGs and pathways between sham-injury and injury in different sections. By processing data from all time points in each section, top 10 DEGs and pathways between sham-injury and injury are showed, respectively.", "structure": {"pmcid": "PMC5661087", "section_index": 11, "section_title": "3.5. Systematic Analysis of DEGs and Altered Pathway in Different Section and Time Points by SAM and KEGG", "row_count": 6, "column_count": 3}, "table": {"label": "Table 5", "caption": "Top 10 DEGs and pathways between sham-injury and injury in different sections. By processing data from all time points in each section, top 10 DEGs and pathways between sham-injury and injury are showed, respectively.", "rows": [["Section", "Top 10 DEGs between sham-injury and injury", "Top 10 pathways between sham-injury and injury"], ["rostral regions", "Ccl3, Plek, Slc15a3, Bcl2a1a, Plek, Tlr2, Ccl4, Clec7a, Plek, Palld", "Osteoclast differentiation, cytokine-cytokine receptor interaction, PI3K-Akt signaling pathway, phagosome, Chagas disease (American trypanosomiasis), leishmaniasis, toll-like receptor signaling pathway, chemokine signaling pathway, tuberculosis, transcriptional misregulation in cancer"], [""], ["lesion centre", "Ccl3, Atf3, Plek, Ctla2b, Bcl2a1a, Ch25h, Plek, Tnfaip3, Tgif1, Gpr84", "MAPK signaling pathway, metabolic pathways, PI3K-Akt signaling pathway, pathways in cancer, osteoclast differentiation, HTLV-I infection, regulation of actin cytoskeleton, chemokine signaling pathway, Focal adhesion, proteoglycans in cancer"], [""], ["caudal regions", "Atf3, Tlr2, Irgm1, Trim30d, S1pr3, Bcl2a1a, Slc45a3, Plek, Trim30a, Zfp36l1", "Tuberculosis, phagosome, Staphylococcus aureus infection, leishmaniasis, osteoclast differentiation, antigen processing and presentation, herpes simplex infection, Fc gamma R-mediated phagocytosis, viral myocarditis, Toll-like receptor signaling pathway"]], "row_count": 6, "column_count": 3, "numeric_cells": 5, "header_rows": 1, "locator": "section[11]/table-wrap[2]#tab5"}}], "gaps": ["asset:data:geo:GSE5296 not downloaded", "asset:data:geo:GSE5296 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "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 correlation"}}, {"id": "method-2", "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": 0.7, "band": "medium", "quote": "pathway enrichment"}}, {"id": "method-3", "family": null, "specific": null, "label": "Significant analysis of microarray (SAM)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Significant analysis of microarray (SAM) is used to study DEGs."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["pearson_r"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pearson."}, "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": ["GSE5296"], "resolved_accessions": ["GSE5296"], "statements": ["Microarray dataset GSE5296 has been downloaded from Gene Expression Omnibus (GEO) database."], "basis": "The paper names GSE5296 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["pearson_r"], "assets": ["source:pmid:29164149", "data:geo:GSE5296", "asset:table:pmid:29164149:1", "asset:table:pmid:29164149:2", "asset:table:pmid:29164149:3", "asset:table:pmid:29164149:4", "asset:table:pmid:29164149:5"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE5296"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:10:46Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 35624, "completion_tokens": 1130, "cached_tokens": 11776}}, "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:29164149", "type": "paper", "label": "pmid:29164149"}, {"id": "source:pmid:29164149", "type": "manuscript", "label": "PMID 29164149 full text"}, {"id": "data:geo:GSE5296", "type": "dataset", "label": "GEO GSE5296"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:29164149", "type": "paper", "label": "pmid:29164149"}, {"id": "source:pmid:29164149", "type": "manuscript", "label": "PMID 29164149 full text"}, {"id": "data:geo:GSE5296", "type": "dataset", "label": "GEO GSE5296"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-29164149", "type": "extraction", "used": ["source:pmid:29164149"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE5296", "type": "accession_resolution", "used": ["data:geo:GSE5296"], "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:29164149", "parent_hash": "sha256:ea39ec7cf919968bb9bf65a6c8de9e51ab2f78cbea6fff16329a003c73f76042", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE5296 licence not read", "asset:data:geo:GSE5296 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"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": ["tify its diagnostic and therapeutic targets. Microarray dataset GSE5296 has been downloaded from Gen", "ibus (GEO) database. Significant analysis of microarray (SAM), Kyoto Encyclopedia of Genes and Genom", "of laminectomy only. Significant analysis of microarray (SAM) is used to study DEGs. P = 0.05 was us", "t be noted that SAM (significant analysis of microarray) is used to study DEGs (differentially expre"], "order_basis": "paper_text_order:400", "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": ["he spinal cord total RNA samples from C57BL6 mouse model of contusion injury in comparison with sampl", "he spinal cord total RNA samples from C57BL6 mouse model of contusion injury in comparison with"], "order_basis": "paper_text_order:1644", "id": "assay:2"}, {"role": "analysis", "definition_id": "correlation_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pearson_r"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["Pearson correlation"], "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":"2026-11-04T00:32:49+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}}}