{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31891941", "kind": "science-record", "revision": 7, "content_hash": "sha256:e739335632d499ce310764674d882f8c59fafdf89de2cea97f7d7e85388f0db0", "created_at": "2026-11-01T15:40:54Z", "updated_at": "2026-11-01T22:01:09Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Shannon entropy approach reveals relevant genes in Alzheimer's disease.", "doi": "10.1371/journal.pone.0226190", "pmid": "31891941", "authors": ["Alfonso Monaco", "Nicola Amoroso", "Loredana Bellantuono", "Eufemia Lella", "Angela Lombardi", "Anna Monda", "Andrea Tateo", "Roberto Bellotti", "Sabina Tangaro"], "journal": "PloS one", "year": 2019, "abstract": "Alzheimer's disease (AD) is the most common type of dementia and affects millions of people worldwide. Since complex diseases are often the result of combinations of gene interactions, microarray data and gene co-expression analysis can provide tools for addressing complexity. Our study aimed to find groups of interacting genes that are relevant in the development of AD. In this perspective, we implemented a method proposed in a previous work to detect gene communities linked to AD. Our strategy combined co-expression network analysis with the study of Shannon entropy of the betweenness. We analyzed the publicly available GSE1297 dataset, achieved from the GEO database in NCBI, containing hippocampal gene expression of 9 control and 22 AD human subjects. Co-expressed genes were clustered into different communities. Two communities of interest (composed by 72 and 39 genes) were found by calculating the correlation coefficient between communities and clinical features. The detected communities resulted stable, replicated on two independent datasets and mostly enriched in pathways closely associated with neuro-degenative diseases. A comparison between our findings and other module detection techniques showed that the detected communities were more related to AD phenotype. Lastly, the hub genes within the two communities of interest were identified by means of a centrality analysis and a bootstrap procedure. The communities of the hub genes presented even stronger correlation with clinical features. These findings and further explorations on the detected genes could shed light on the genetic aspects related with physiological aspects of Alzheimer's disease.", "claims": [{"id": "claim-method", "statement": "The association, between the communities found in the step 2 of the pipeline and clinical phenotype, was investigated by means of Pearson’s correlation analysis.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31891941", "locator": "sections[7] \"1.5 Correlation analysis of gene modules with clinical phenotype\" paragraph 2", "quote": "The association, between the communities found in the step 2 of the pipeline and clinical phenotype, was investigated by means of Pearson’s correlation analysis."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data underlying the results presented in the study are available from the GEO database in NCBI (Gene Expression Omnibus, https://www.ncbi.nlm.nih.gov/geo/). The data entry number of database is GSE1297.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31891941", "locator": "sections[25] \"Data Availability\" paragraph 2", "quote": "The data underlying the results presented in the study are available from the GEO database in NCBI (Gene Expression Omnibus, https://www.ncbi.nlm.nih.gov/geo/). The data entry number of database is GSE1297."}], "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:31891941"], "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:GSE1297"], "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:GSE1297"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31891941", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1371/journal.pone.0226190", "sha256": "sha256:edf5867195b475d46301742edd6d66cb8cfed064817047dec591e0be3e69fce9", "bytes": 64115, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1371/journal.pone.0226190", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6938408", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE1297", "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=GSE1297", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE1297", "version": null, "note": "The data underlying the results presented in the study are available from the GEO database in NCBI (Gene Expression Omnibus, https://www.ncbi.nlm.nih.gov/geo/). The data entry number of database is GSE1297.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data underlying the results presented in the study are available from the GEO database in NCBI (Gene Expression Omnibus, https://www.ncbi.nlm.nih.gov/geo/). The data entry number of database is GSE1297.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM21203", "GSM21204", "GSM21205", "GSM21206", "GSM21207", "GSM21208", "GSM21209", "GSM21210", "GSM21211", "GSM21212", "GSM21213", "GSM21214", "GSM21215", "GSM21216", "GSM21217", "GSM21218", "GSM21219", "GSM21220", "GSM21221", "GSM21222", "GSM21223", "GSM21224", "GSM21225", "GSM21226", "GSM21227", "GSM21228", "GSM21229", "GSM21230", "GSM21231", "GSM21232", "GSM21233"], "sample_count": 31, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Incipient Alzheimer's Disease: Microarray Correlation Analyses", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE29378", "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=GSE29378", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE29378", "version": null, "note": "The data underlying the results presented in the study are available from the GEO database in NCBI (Gene Expression Omnibus, https://www.ncbi.nlm.nih.gov/geo/). The data entry number of database is GSE1297.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data underlying the results presented in the study are available from the GEO database in NCBI (Gene Expression Omnibus, https://www.ncbi.nlm.nih.gov/geo/). The data entry number of database is GSE1297.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM726083", "GSM726084", "GSM726085", "GSM726086", "GSM726087", "GSM726088", "GSM726089", "GSM726090", "GSM726091", "GSM726092", "GSM726093", "GSM726094", "GSM726095", "GSM726096", "GSM726097", "GSM726098", "GSM726099", "GSM726100", "GSM726101", "GSM726102", "GSM726103", "GSM726104", "GSM726105", "GSM726106", "GSM726107", "GSM726108", "GSM726109", "GSM726110", "GSM726111", "GSM726112", "GSM726113", "GSM726114", "GSM726115", "GSM726116", "GSM726117", "GSM726118", "GSM726119", "GSM726120", "GSM726121", "GSM726122", "GSM726123", "GSM726124", "GSM726125", "GSM726126", "GSM726127", "GSM726128", "GSM726129", "GSM726130", "GSM726131", "GSM726132", "GSM726133", "GSM726134", "GSM726135", "GSM726136", "GSM726137", "GSM726138", "GSM726139", "GSM726140", "GSM726141", "GSM726142", "GSM726143", "GSM726144", "GSM726145"], "sample_count": 63, "group_sizes": null, "group_sizes_basis": null, "platform": "6947", "taxon": "Homo sapiens", "title": "Genes and Pathways Underlying Regional and Cell Type Changes in Alzheimer's Disease", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE48350", "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=GSE48350", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE48350", "version": null, "note": "The data underlying the results presented in the study are available from the GEO database in NCBI (Gene Expression Omnibus, https://www.ncbi.nlm.nih.gov/geo/). The data entry number of database is GSE1297.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data underlying the results presented in the study are available from the GEO database in NCBI (Gene Expression Omnibus, https://www.ncbi.nlm.nih.gov/geo/). The data entry number of database is GSE1297.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1176196", "GSM1176197", "GSM1176198", "GSM1176199", "GSM1176200", "GSM1176201", "GSM1176202", "GSM1176203", "GSM1176204", "GSM1176205", "GSM1176206", "GSM1176207", "GSM1176208", "GSM1176209", "GSM1176210", "GSM1176211", "GSM1176212", "GSM1176213", "GSM1176214", "GSM1176215", "GSM1176216", "GSM1176217", "GSM1176218", "GSM1176219", "GSM1176220", "GSM1176221", "GSM1176222", "GSM1176223", "GSM1176224", "GSM1176225", "GSM1176226", "GSM1176227", "GSM1176228", "GSM1176229", "GSM1176230", "GSM1176231", "GSM1176232", "GSM1176233", "GSM1176234", "GSM1176235", "GSM1176236", "GSM1176237", "GSM1176238", "GSM1176239", "GSM1176240", "GSM1176241", "GSM1176242", "GSM1176243", "GSM1176244", "GSM1176245", "GSM1176246", "GSM1176247", "GSM1176248", "GSM1176249", "GSM1176250", "GSM1176251", "GSM1176252", "GSM1176253", "GSM1176254", "GSM1176255", "GSM1176256", "GSM1176257", "GSM1176258", "GSM1176259", "GSM1176260", "GSM1176261", "GSM1176262", "GSM1176263", "GSM1176264", "GSM1176265", "GSM1176266", "GSM1176267", "GSM1176268", "GSM1176269", "GSM1176270", "GSM1176271", "GSM1176272", "GSM1176273", "GSM1176274", "GSM1176275", "GSM300166", "GSM300167", "GSM300168", "GSM300169", "GSM300170", "GSM300171", "GSM300172", "GSM300173", "GSM300174", "GSM300175", "GSM300176", "GSM300177", "GSM300178", "GSM300179", "GSM300180", "GSM300181", "GSM300182", "GSM300183", "GSM300185", "GSM300186", "GSM300187", "GSM300188", "GSM300189", "GSM300190", "GSM300191", "GSM300192", "GSM300193", "GSM300194", "GSM300195", "GSM300196", "GSM300197", "GSM300198", "GSM300199", "GSM300200", "GSM300201", "GSM300202", "GSM300203", "GSM300204", "GSM300205", "GSM300206", "GSM300207", "GSM300208", "GSM300209", "GSM300210", "GSM300211", "GSM300212", "GSM300213", "GSM300214", "GSM300215", "GSM300216", "GSM300217", "GSM300218", "GSM300219", "GSM300220", "GSM300221", "GSM300222", "GSM300223", "GSM300224", "GSM300225", "GSM300226", "GSM300227", "GSM300228", "GSM300229", "GSM300230", "GSM300231", "GSM300232", "GSM300233", "GSM300234", "GSM300235", "GSM300236", "GSM300237", "GSM300238", "GSM300239", "GSM300240", "GSM300241", "GSM300242", "GSM300243", "GSM300244", "GSM300245", "GSM300246", "GSM300247", "GSM300248", "GSM300249", "GSM300250", "GSM300251", "GSM300252", "GSM300253", "GSM300254", "GSM300255", "GSM300256", "GSM300258", "GSM300259", "GSM300260", "GSM300261", "GSM300262", "GSM300263", "GSM300264", "GSM300265", "GSM300266", "GSM300267", "GSM300268", "GSM300269", "GSM300270", "GSM300271", "GSM300272", "GSM300273", "GSM300274", "GSM300275", "GSM300276", "GSM300277", "GSM300278", "GSM300279", "GSM300280", "GSM300281", "GSM300282", "GSM300283", "GSM300284", "GSM300285", "GSM300286", "GSM300287", "GSM300288", "GSM300289", "GSM300290", "GSM300291", "GSM300292", "GSM300293", "GSM300294", "GSM300295", "GSM300296", "GSM300297", "GSM300298", "GSM300299", "GSM300300", "GSM300301", "GSM300302", "GSM300303", "GSM300304", "GSM300305", "GSM300306", "GSM300307", "GSM300308", "GSM300309", "GSM300310", "GSM300311", "GSM300312", "GSM300313", "GSM300314", "GSM300315", "GSM300316", "GSM300317", "GSM300318", "GSM300319", "GSM300320", "GSM300321", "GSM300322", "GSM300323", "GSM300324", "GSM300325", "GSM300326", "GSM300327", "GSM300328", "GSM300329", "GSM300330", "GSM300331", "GSM300332", "GSM300333", "GSM300335", "GSM300338", "GSM300339", "GSM300340", "GSM300341", "GSM318840", "GSM350078"], "sample_count": 253, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Alzheimer's Disease Dataset", "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:31891941:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c4b3bb0daf3ac74c78885fd1af7313f85fe3733ed443968ce90f66bafec01a19", "bytes": 504, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[16]/table-wrap[1]#pone.0226190.t001", "version": null, "note": "Results of correlation test between the first principal component of C1 and C2 communities and clinical features.The results show significant correlation (p-value < 0.05) of both gene communities with MMSE and NFT.", "structure": {"pmcid": "PMC6938408", "section_index": 16, "section_title": "2.3 Community detection through Fast Greedy algorithm and correlation analysis with clinical phenotype", "row_count": 3, "column_count": 3}, "table": {"label": "Table 1", "caption": "Results of correlation test between the first principal component of C1 and C2 communities and clinical features.The results show significant correlation (p-value < 0.05) of both gene communities with MMSE and NFT.", "rows": [["Community", "MMSE", "NFT"], ["C1", "r = -0.46; p = 0.03", "r = 0.59; p = 0.004"], ["C2", "r = 0.47; p = 0.02", "r = -0.46; p = 0.03"]], "row_count": 3, "column_count": 3, "numeric_cells": 4, "header_rows": 1, "locator": "section[16]/table-wrap[1]#pone.0226190.t001"}}, {"id": "asset:table:pmid:31891941:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5dac310ea2245e54f5e81489dc1947ed39d935dbb6f832d64e61c0201cc69272", "bytes": 1848, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#pone.0226190.t002", "version": null, "note": "Results of gene set enrichment analysis for C1 community.In the third column overlaps with gene set in the selected MSigDB gene set collection are reported. The fourth column displays the false discovery rate (FDR) analog of hypergeometric p-value after correction for multiple hypothesis testing according to Benjamini and Hochberg [43]. The table shows seven most significant enrichments.", "structure": {"pmcid": "PMC6938408", "section_index": 17, "section_title": "2.4 Gene set enrichment analysis", "row_count": 8, "column_count": 4}, "table": {"label": "Table 2", "caption": "Results of gene set enrichment analysis for C1 community.In the third column overlaps with gene set in the selected MSigDB gene set collection are reported. The fourth column displays the false discovery rate (FDR) analog of hypergeometric p-value after correction for multiple hypothesis testing according to Benjamini and Hochberg [43]. The table shows seven most significant enrichments.", "rows": [["Gene Set Name", "Description", "Genes in overlap", "FDR p-value"], ["BLALOCK ALZHEIMER’S DISEASE DN", "Genes down-regulated in brain from patients with Alzheimer’s disease—Homo sapiens", "32", "1.25 ⋅ 10−28"], ["HALLMARK OXIDATIVE PHOSPHORYLATION", "Genes encoding proteins involved in oxidative phosphorylation—Homo sapiens", "11", "3.87 ⋅ 10−11"], ["GO ELECTRON TRANSPORT CHAIN", "A process in which a series of electron carriers operate together to transfer electrons from donors to any of several different terminal electron acceptors to generate a transmembrane electrochemical gradient—Homo sapiens", "9", "5.24 ⋅ 10−11"], ["GO CELLULAR RESPIRATION", "The enzymatic release of energy from inorganic and organic compounds (especially carbohydrates and fats) which either requires oxygen (aerobic respiration) or does not (anaerobic respiration)—Homo sapiens", "9", "1.24 ⋅ 10−9"], ["GO ORGANONITROGEN COMPOUND METABOLIC P C PROCESS", "The chemical reactions and pathways involving organonitrogen compound—Homo sapiens", "19", "6.23 ⋅ 10−9"], ["KEGG PARKINSONS DISEASE", "Parkinson’s disease—Homo sapiens", "19", "1.38 ⋅ 10−8"], ["BLALOCK ALZHEIMER’S DISEASE UP", "Genes up-regulated in brain from patients with Alzheimer’s disease—Homo sapiens", "18", "1.38 ⋅ 10−8"]], "row_count": 8, "column_count": 4, "numeric_cells": 14, "header_rows": 1, "locator": "section[17]/table-wrap[1]#pone.0226190.t002"}}, {"id": "asset:table:pmid:31891941:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f3281256ea8b9c7bf2411a7fdd8cbef59860f93853a432b78c6c3b69db75be6d", "bytes": 1138, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[2]#pone.0226190.t003", "version": null, "note": "Results of gene set enrichment analysis for C2 community.In the third column the genes in the overlapping gene sets are reported. The fourth column indicates the false discovery rate (FDR) analog of hypergeometric p-value after correction for multiple hypothesis testing according to Benjamini and Hochberg [43]. he table shows the top three significant enrichments.", "structure": {"pmcid": "PMC6938408", "section_index": 17, "section_title": "2.4 Gene set enrichment analysis", "row_count": 4, "column_count": 4}, "table": {"label": "Table 3", "caption": "Results of gene set enrichment analysis for C2 community.In the third column the genes in the overlapping gene sets are reported. The fourth column indicates the false discovery rate (FDR) analog of hypergeometric p-value after correction for multiple hypothesis testing according to Benjamini and Hochberg [43]. he table shows the top three significant enrichments.", "rows": [["Gene Set Name", "Description", "Genes in overlap", "FDR p-value"], ["BLALOCK ALZHEIMER’S DISEASE DN", "Genes down-regulated in brain from patients with Alzheimer’s disease—Homo sapiens", "22", "1.07 ⋅ 10−22"], ["HALLMARK OXIDATIVE PHOSPHORYLATION", "Genes encoding proteins involved in oxidative phosphorylation—Homo sapiens", "9", "1.23 ⋅ 10−10"], ["KIM BIPOLAR DISORDER OLIGODENDROCYTE DENSITY CORR UP", "Genes whose expression significantly and positively correlated with oligodendrocyte density in layer VI of BA9 brain region in patients with bipolar disorder—Homo sapiens", "11", "5.49 ⋅ 10−9"]], "row_count": 4, "column_count": 4, "numeric_cells": 6, "header_rows": 1, "locator": "section[17]/table-wrap[2]#pone.0226190.t003"}}, {"id": "asset:table:pmid:31891941:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:758edd5df2027601d8b697a49c4fd394378a62ca39cc2729cb99802254ef54ce", "bytes": 1125, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[20]/table-wrap[1]#pone.0226190.t004", "version": null, "note": "Summary table of the results obtained through the proposed community detection methods.In the fourth column the number of genes in common with C1 and C2 communities is shown in bold. We reported only significant correlations (p-value < 0.05).", "structure": {"pmcid": "PMC6938408", "section_index": 20, "section_title": "2.7 Identification of gene communities through traditional clustering methods and network reconstruction algorithms", "row_count": 13, "column_count": 6}, "table": {"label": "Table 4", "caption": "Summary table of the results obtained through the proposed community detection methods.In the fourth column the number of genes in common with C1 and C2 communities is shown in bold. We reported only significant correlations (p-value < 0.05).", "rows": [["Method", "Number of communities", "AD-related communities", "Number of genes in AD-related communities", "Correlation coefficient with NFT", "Correlation coefficient with MMSE"], ["Our method", "127", "C1", "71", "0.59", "−0.46"], ["C2", "39", "−0.46", "0.47"], ["WGCNA", "21", "Blue module", "637(87)", "0.43", "−0.43"], ["Affinity propagation", "233", "A1", "31(7)", "0.45", "−0.43"], ["A2", "39(23)", "0.45", "−0.43"], ["Agglomerative clustering", "Between 2 and 30", "None", "", "", ""], ["Fuzzy c-means", "Between 2 and 7", "None", "", "", ""], ["ARACNE", "674", "AR1", "8(2)", "−0.45", "0.44"], ["AR2", "7(5)", "−0.43", "0.43"], ["GENIE3", "675", "G1", "9(3)", "−0.44", "0.44"], ["G2", "7(2)", "−0.44", "0.46"], ["SPACE", "24", "S1", "25(2)", "0.44", "−0.44"]], "row_count": 13, "column_count": 6, "numeric_cells": 38, "header_rows": 1, "locator": "section[20]/table-wrap[1]#pone.0226190.t004"}}], "gaps": ["asset:data:geo:GSE1297 not downloaded", "asset:data:geo:GSE1297 licence not read", "asset:data:geo:GSE29378 not downloaded", "asset:data:geo:GSE29378 licence not read", "asset:data:geo:GSE48350 not downloaded", "asset:data:geo:GSE48350 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": 0.8, "band": "high", "quote": "principal component analysis"}}, {"id": "method-2", "family": "correlation_analysis", "specific": "pearson", "label": "Correlation analysis", "dsl_operations": ["pearson_r"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 0.8, "band": "high", "quote": "Pearson correlation"}}, {"id": "method-3", "family": "clustering", "specific": "hierarchical", "label": "Clustering", "dsl_operations": ["hierarchical_cluster"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["feature_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "hierarchical clustering"}}, {"id": "method-4", "family": "network_analysis", "specific": "centrality", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "centrality"}}, {"id": "method-5", "family": null, "specific": null, "label": "Pearson’s correlation analysis", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The association, between the communities found in the step 2 of the pipeline and clinical phenotype, was investigated by means of Pearson’s correlation analysis."}}], "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": ["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": ["GSE1297", "GSE48350", "GSE29378"], "resolved_accessions": ["GSE1297", "GSE48350", "GSE29378"], "statements": ["The data underlying the results presented in the study are available from the GEO database in NCBI (Gene Expression Omnibus, https://www.ncbi.nlm.nih.gov/geo/). The data entry number of database is GSE1297."], "basis": "The paper names GSE1297, GSE48350, GSE29378 in GEO database in NCBI (Gene Expression Omnibus) 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:31891941", "data:geo:GSE1297", "asset:table:pmid:31891941:1", "asset:table:pmid:31891941:2", "asset:table:pmid:31891941:3", "asset:table:pmid:31891941:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE1297"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:17:34Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 47395, "completion_tokens": 1287, "cached_tokens": 656}}, "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:31891941", "type": "paper", "label": "pmid:31891941"}, {"id": "source:pmid:31891941", "type": "manuscript", "label": "PMID 31891941 full text"}, {"id": "data:geo:GSE1297", "type": "dataset", "label": "GEO GSE1297"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31891941", "type": "paper", "label": "pmid:31891941"}, {"id": "source:pmid:31891941", "type": "manuscript", "label": "PMID 31891941 full text"}, {"id": "data:geo:GSE1297", "type": "dataset", "label": "GEO GSE1297"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31891941", "type": "extraction", "used": ["source:pmid:31891941"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE1297", "type": "accession_resolution", "used": ["data:geo:GSE1297"], "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:31891941", "parent_hash": "sha256:39721252a06c7ac303a52ad89f6301d3a14d5a50fe3a83ad2394767a392bc990", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE1297 licence not read", "asset:data:geo:GSE1297 not downloaded", "asset:data:geo:GSE29378 licence not read", "asset:data:geo:GSE29378 not downloaded", "asset:data:geo:GSE48350 licence not read", "asset:data:geo:GSE48350 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": 0.93, "evidence": ["result of combinations of gene interactions, microarray data and gene co-expression analysis can pro"], "order_basis": "paper_text_order:212", "id": "assay:1"}, {"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": 0.8, "evidence": ["principal component analysis"], "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":"2026-11-04T01:32:17+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}}}