{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32806782", "kind": "science-record", "revision": 8, "content_hash": "sha256:a23ff4157c8b75ddafb58f83bf7c370c3751339c44e3436e3e1eacd94aae7bbc", "created_at": "2026-11-01T15:41:08Z", "updated_at": "2026-11-01T22:02:03Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "A Linear Regression and Deep Learning Approach for Detecting Reliable Genetic Alterations in Cancer Using DNA Methylation and Gene Expression Data.", "doi": "10.3390/genes11080931", "pmid": "32806782", "authors": ["Saurav Mallik", "Soumita Seth", "Tapas Bhadra", "Zhongming Zhao"], "journal": "Genes", "year": 2020, "abstract": "DNA methylation change has been useful for cancer biomarker discovery, classification, and potential treatment development. So far, existing methods use either differentially methylated CpG sites or combined CpG sites, namely differentially methylated regions, that can be mapped to genes. However, such methylation signal mapping has limitations. To address these limitations, in this study, we introduced a combinatorial framework using linear regression, differential expression, deep learning method for accurate biological interpretation of DNA methylation through integrating DNA methylation data and corresponding TCGA gene expression data. We demonstrated it for uterine cervical cancer. First, we pre-filtered outliers from the data set and then determined the predicted gene expression value from the pre-filtered methylation data through linear regression. We identified differentially expressed genes (DEGs) by Empirical Bayes test using Limma. Then we applied a deep learning method, \"nnet\" to classify the cervical cancer label of those DEGs to determine all classification metrics including accuracy and area under curve (AUC) through 10-fold cross validation. We applied our approach to uterine cervical cancer DNA methylation dataset (NCBI accession ID: GSE30760, 27,578 features covering 63 tumor and 152 matched normal samples). After linear regression and differential expression analysis, we obtained 6287 DEGs with false discovery rate (FDR) <0.001. After performing deep learning analysis, we obtained average classification accuracy 90.69% (±1.97%) of the uterine cervical cancerous labels. This performance is better than that of other peer methods. We performed in-degree and out-degree hub gene network analysis using Cytoscape. We reported five top in-degree genes (PAIP2, GRWD1, VPS4B, CRADD and LLPH) and five top out-degree genes (MRPL35, FAM177A1, STAT4, ASPSCR1 and FABP7). After that, we performed KEGG pathway and Gene Ontology enrichment analysis of DEGs using tool WebGestalt(WEB-based Gene SeT AnaLysis Toolkit). In summary, our proposed framework that integrated linear regression, differential expression, deep learning provides a robust approach to better interpret DNA methylation analysis and gene expression data in disease study.", "claims": [{"id": "claim-method", "statement": "In this regard, we applied Pearson’s correlation analysis on the DEGs identified by our method for finding out the active edges among genes having correlation value ≥0.8 or ≤−0.8.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32806782", "locator": "sections[9] \"2.4. Hub Gene Finding\" paragraph 2", "quote": "In this regard, we applied Pearson’s correlation analysis on the DEGs identified by our method for finding out the active edges among genes having correlation value ≥0.8 or ≤−0.8."}], "state": "complete"}, {"id": "claim-data-access", "statement": "In this study, we used a cervical cancer methylation dataset(NCBI accession ID: GSE30760) [14,15,16]. This dataset included 63 uterine cervical tumor samples and 152 matched normal samples.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32806782", "locator": "sections[3] \"2.1. Data Collection\" paragraph 2", "quote": "In this study, we used a cervical cancer methylation dataset(NCBI accession ID: GSE30760) [14,15,16]. This dataset included 63 uterine cervical tumor samples and 152 matched normal samples."}], "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:32806782"], "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:GSE30760"], "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:GSE30760"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32806782", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/genes11080931", "sha256": "sha256:09d1f3c1aa468697b7b953722052b2a1c0e44759d5b7e776182acb93e973198c", "bytes": 39572, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/genes11080931", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7465138", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE30760", "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=GSE30760", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE30760", "version": null, "note": "In this study, we used a cervical cancer methylation dataset(NCBI accession ID: GSE30760) [14,15,16]. This dataset included 63 uterine cervical tumor samples and 152 matched normal samples.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "In this study, we used a cervical cancer methylation dataset(NCBI accession ID: GSE30760) [14,15,16]. This dataset included 63 uterine cervical tumor samples and 152 matched normal samples.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM763063", "GSM763064", "GSM763065", "GSM763066", "GSM763067", "GSM763068", "GSM763069", "GSM763070", "GSM763071", "GSM763072", "GSM763073", "GSM763074", "GSM763075", "GSM763076", "GSM763077", "GSM763078", "GSM763079", "GSM763080", "GSM763081", "GSM763082", "GSM763083", "GSM763084", "GSM763085", "GSM763086", "GSM763087", "GSM763088", "GSM763089", "GSM763090", "GSM763091", "GSM763092", "GSM763093", "GSM763094", "GSM763095", "GSM763096", "GSM763097", "GSM763098", "GSM763099", "GSM763100", "GSM763101", "GSM763102", "GSM763103", "GSM763104", "GSM763105", "GSM763106", "GSM763107", "GSM763108", "GSM763109", "GSM763110", "GSM763111", "GSM763112", "GSM763113", "GSM763114", "GSM763115", "GSM763116", "GSM763117", "GSM763118", "GSM763119", "GSM763120", "GSM763121", "GSM763122", "GSM763123", "GSM763124", "GSM763125", "GSM763126", "GSM763127", "GSM763128", "GSM763129", "GSM763130", "GSM763131", "GSM763132", "GSM763133", "GSM763134", "GSM763135", "GSM763136", "GSM763137", "GSM763138", "GSM763139", "GSM763140", "GSM763141", "GSM763142", "GSM763143", "GSM763144", "GSM763145", "GSM763146", "GSM763147", "GSM763148", "GSM763149", "GSM763150", "GSM763151", "GSM763152", "GSM763153", "GSM763154", "GSM763155", "GSM763156", "GSM763157", "GSM763158", "GSM763159", "GSM763160", "GSM763161", "GSM763162", "GSM763163", "GSM763164", "GSM763165", "GSM763166", "GSM763167", "GSM763168", "GSM763169", "GSM763170", "GSM763171", "GSM763172", "GSM763173", "GSM763174", "GSM763175", "GSM763176", "GSM763177", "GSM763178", "GSM763179", "GSM763180", "GSM763181", "GSM763182", "GSM763183", "GSM763184", "GSM763185", "GSM763186", "GSM763187", "GSM763188", "GSM763189", "GSM763190", "GSM763191", "GSM763192", "GSM763193", "GSM763194", "GSM763195", "GSM763196", "GSM763197", "GSM763198", "GSM763199", "GSM763200", "GSM763201", "GSM763202", "GSM763203", "GSM763204", "GSM763205", "GSM763206", "GSM763207", "GSM763208", "GSM763209", "GSM763210", "GSM763211", "GSM763212", "GSM763213", "GSM763214", "GSM763220", "GSM763221", "GSM763222", "GSM763223", "GSM763224", "GSM763225", "GSM763226", "GSM763227", "GSM763228", "GSM763229", "GSM763230", "GSM763231", "GSM763232", "GSM763233", "GSM763234", "GSM763235", "GSM763236", "GSM763237", "GSM763238", "GSM763239", "GSM763240", "GSM763241", "GSM763242", "GSM763243", "GSM763244", "GSM763245", "GSM763246", "GSM763247", "GSM763248", "GSM763249", "GSM763250", "GSM763251", "GSM763252", "GSM763253", "GSM763254", "GSM763255", "GSM763256", "GSM763257", "GSM763258", "GSM763259", "GSM763260", "GSM763261", "GSM763262", "GSM763263", "GSM763264", "GSM763265", "GSM763266", "GSM763267", "GSM763268", "GSM763269", "GSM763270", "GSM763271", "GSM763272", "GSM763273", "GSM763274", "GSM763275", "GSM763276", "GSM763277", "GSM763278", "GSM763279", "GSM763280", "GSM763281", "GSM763282"], "sample_count": 215, "group_sizes": null, "group_sizes_basis": null, "platform": "8490", "taxon": "Homo sapiens", "title": "Cervical cancer", "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:32806782:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:bbb454d550ac6647f5b5bcf924445f2e9130c7ba426d0439d12e5384620f4a38", "bytes": 1545, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#genes-11-00931-t001", "version": null, "note": "List of differentially expressed genes (false discovery rate (FDR) sorted).", "structure": {"pmcid": "PMC7465138", "section_index": 11, "section_title": "3. Results and Discussion", "row_count": 26, "column_count": 4}, "table": {"label": "Table 1", "caption": "List of differentially expressed genes (false discovery rate (FDR) sorted).", "rows": [["Gene Symbol", "t-Score", "p-Value", "FDR"], ["ADCY2", "45.22", "5.64×10−119", "5.95×10−115"], ["PTPN6", "32.50", "1.43×10−89", "7.55×10−86"], ["LHFPL2", "32.09", "1.63×10−88", "5.71×10−85"], ["VAV1", "30.24", "1.41×10−83", "3.72×10−80"], ["EYA4", "−29.40", "2.97×10−81", "6.27×10−78"], ["PNPLA2", "29.02", "3.38×10−80", "5.94×10−77"], ["ARID3A", "−28.71", "2.37×10−79", "3.56×10−76"], ["HOXD10", "28.19", "6.97×10−78", "9.20×10−75"], ["TWIST1", "27.69", "1.85×10−76", "2.17×10−73"], ["BHMT", "26.49", "5.42×10−73", "5.72×10−70"], ["TSLP", "26.25", "2.76×10−72", "2.65×10−69"], ["ACCN4", "26.16", "5.23×10−72", "4.60×10−69"], ["HOXA6", "25.94", "2.22×10−71", "1.80×10−68"], ["PRR5", "25.67", "1.40×10−70", "1.06×10−67"], ["NODAL", "25.45", "6.44×10−70", "4.53×10−67"], ["EFCAB1", "25.41", "8.60×10−70", "5.45×10−67"], ["WNT2", "25.40", "8.86×10−70", "5.45×10−67"], ["PC", "25.40", "9.31×10−70", "5.45×10−67"], ["S100A8", "25.23", "2.84×10−69", "1.58×10−66"], ["VWCE", "24.89", "3.05×10−68", "1.61×10−65"], ["IGFBP2", "24.86", "3.61×10−68", "1.81×10−65"], ["ZNF385A", "24.74", "8.36×10−68", "4.01×10−65"], ["C1orf220", "24.71", "1.04×10−67", "4.75×10−65"], ["COG2", "24.63", "1.85×10−67", "8.15×10−65"], ["QRFP", "−24.51", "4.16×10−67", "1.76×10−64"]], "row_count": 26, "column_count": 4, "numeric_cells": 79, "header_rows": 1, "locator": "section[11]/table-wrap[1]#genes-11-00931-t001"}}, {"id": "asset:table:pmid:32806782:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f6c6d157e48bf00fd61e59bf25b98df6322e1901fa67f9d8c53a9e9ff698d504", "bytes": 511, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[2]#genes-11-00931-t002", "version": null, "note": "Values of disease classification metrics by proposed method.", "structure": {"pmcid": "PMC7465138", "section_index": 11, "section_title": "3. Results and Discussion", "row_count": 7, "column_count": 2}, "table": {"label": "Table 2", "caption": "Values of disease classification metrics by proposed method.", "rows": [["Metrics", "Average Value (std *)"], ["Average accuracy", "90.69% (±1.97%)"], ["Average sensitivity", "73.97% (±1.06%)"], ["Average specificity", "97.63% (±1.71%)"], ["Average precision", "93.38% (±4.17%)"], ["Average overall error rate", "9.30% (±1.97%)"], ["Area under curve (AUC)", "0.858"]], "row_count": 7, "column_count": 2, "numeric_cells": 6, "header_rows": 1, "locator": "section[11]/table-wrap[2]#genes-11-00931-t002"}}, {"id": "asset:table:pmid:32806782:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5ab67ef25fab3289d597e825ac5e051d9b86e2c3ba5873f5626ae077678523b9", "bytes": 931, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[3]#genes-11-00931-t003", "version": null, "note": "Top 10 hub genes according to the in-degree centrality from our proposed method.", "structure": {"pmcid": "PMC7465138", "section_index": 11, "section_title": "3. Results and Discussion", "row_count": 11, "column_count": 7}, "table": {"label": "Table 3", "caption": "Top 10 hub genes according to the in-degree centrality from our proposed method.", "rows": [["Gene Symbol", "In-Degree", "Out-Degree", "Average Shortest Path Length", "Betweenness Centrality", "Closeness Centrality", "Clustering Coefficient"], ["PAIP2", "439", "32", "3.587", "0.802", "0.279", "0.188"], ["GRWD1", "425", "66", "3.435", "11.001", "0.291", "0.178"], ["VPS4B", "406", "68", "3.460", "2.276", "0.289", "0.191"], ["CRADD", "406", "178", "3.087", "11.003", "0.324", "0.152"], ["LLPH", "403", "40", "3.545", "2.313", "0.282", "0.182"], ["NDUFA4", "390", "89", "3.556", "1.927", "0.281", "0.168"], ["NDUFB6", "372", "111", "3.294", "4.661", "0.304", "0.175"], ["ZKSCAN4", "372", "88", "3.364", "1.434", "0.297", "0.200"], ["SMARCD1", "365", "43", "3.515", "0.734", "0.284", "0.214"], ["TMED10", "348", "39", "3.546", "4.124", "0.282", "0.193"]], "row_count": 11, "column_count": 7, "numeric_cells": 61, "header_rows": 1, "locator": "section[11]/table-wrap[3]#genes-11-00931-t003"}}, {"id": "asset:table:pmid:32806782:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:fb487bc0e44834495f2005abaca49b911bd8eaf4f3dcc778f705fb211ce5dccc", "bytes": 935, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[4]#genes-11-00931-t004", "version": null, "note": "Top 10 hub genes according to the out-degree centrality from our proposed method.", "structure": {"pmcid": "PMC7465138", "section_index": 11, "section_title": "3. Results and Discussion", "row_count": 11, "column_count": 7}, "table": {"label": "Table 4", "caption": "Top 10 hub genes according to the out-degree centrality from our proposed method.", "rows": [["Gene Symbol", "In-Degree", "Out-Degree", "Average Shortest Path Length", "Betweenness Centrality", "Closeness Centrality", "Clustering Coefficient"], ["MRPL35", "239", "376", "2.765", "9.354", "0.362", "0.141"], ["FAM177A1", "21", "339", "3.002", "0.263", "0.333", "0.225"], ["STAT4", "94", "332", "2.872", "2.744", "0.348", "0.211"], ["ASPSCR1", "68", "329", "2.888", "1.132", "0.346", "0.212"], ["FABP7", "204", "315", "2.779", "3.008", "0.360", "0.171"], ["HNRNPA0", "65", "311", "3.010", "1.230", "0.332", "0.191"], ["ANGPTL4", "18", "299", "2.887", "0.364", "0.346", "0.249"], ["DDX19A", "86", "283", "2.993", "1.385", "0.334", "0.218"], ["TRNT1", "40", "282", "3.119", "0.477", "0.321", "0.221"], ["PFDN1", "52", "274", "3.005", "0.526", "0.333", "0.243"]], "row_count": 11, "column_count": 7, "numeric_cells": 63, "header_rows": 1, "locator": "section[11]/table-wrap[4]#genes-11-00931-t004"}}, {"id": "asset:table:pmid:32806782:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e13572049fb6617cd5e9e74be92076472c1bbe63cee07fe83eb47a1d8ca2ca41", "bytes": 1046, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[5]#genes-11-00931-t005", "version": null, "note": "Top significant KEGG Pathways (FDR sorted).", "structure": {"pmcid": "PMC7465138", "section_index": 11, "section_title": "3. Results and Discussion", "row_count": 11, "column_count": 4}, "table": {"label": "Table 5", "caption": "Top significant KEGG Pathways (FDR sorted).", "rows": [["KEGG Pathway Name *", "#Genes", "Enriched p-Value", "FDR"], ["hsa05205 Proteoglycans in cancer", "198", "6.65×10−8", "2.16×10−5"], ["hsa04550 Signaling pathways regulating pluripotency of stem cells", "139", "1.32×10−7", "2.16×10−5"], ["hsa05166 Human T-cell leukemia virus 1 infection", "255", "6.95×10−7", "7.29×10−5"], ["hsa04510 Focal adhesion", "199", "8.94×10−7", "7.29×10−5"], ["hsa05200 Pathways in cancer", "524", "1.26×10−6", "8.19×10−5"], ["hsa04015 Rap1 signaling pathway", "206", "1.93×10−6", "1.05×10−4"], ["hsa04514 Cell adhesion molecules (CAMs)", "144", "2.31×10−7", "1.07×10−4"], ["hsa04611 Platelet activation", "123", "7.22×10−6", "2.94×10−4"], ["hsa04072 Phospholipase D signaling pathway", "146", "1.02×10−5", "3.69×10−4"], ["hsa04640 Hematopoietic cell lineage", "97", "4.01×10−5", "1.31×10−3"]], "row_count": 11, "column_count": 4, "numeric_cells": 40, "header_rows": 1, "locator": "section[11]/table-wrap[5]#genes-11-00931-t005"}}, {"id": "asset:table:pmid:32806782:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2eb96e3b6d559880a3150c3c0b8439bb60ebec2da2a19ccef7be213fb84d5897", "bytes": 904, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[6]#genes-11-00931-t006", "version": null, "note": "Top significant GO-BP term enriched (FDR sorted).", "structure": {"pmcid": "PMC7465138", "section_index": 11, "section_title": "3. Results and Discussion", "row_count": 11, "column_count": 4}, "table": {"label": "Table 6", "caption": "Top significant GO-BP term enriched (FDR sorted).", "rows": [["GO-BP Term Name *", "#Genes", "Enriched p-Value", "FDR"], ["GO:0008283 cell proliferation", "1986", "0", "0"], ["GO:0006928 movement of cell or subcellular component", "1967", "0", "0"], ["GO:0009891 positive regulation of biosynthetic process", "1949", "0", "0"], ["GO:0016192 vesicle-mediated transport", "1942", "0", "0"], ["GO:0006955 immune response", "1919", "0", "0"], ["GO:0031328 positive regulation of cellular biosynthetic process", "1919", "0", "0"], ["GO:0006915 apoptotic process", "1911", "0", "0"], ["GO:0010628 positive regulation of gene expression", "1911", "0", "0"], ["GO:2000026 regulation of multicellular organismal development", "1908", "0", "0"], ["GO:0006468 protein phosphorylation", "1860", "0", "0"]], "row_count": 11, "column_count": 4, "numeric_cells": 40, "header_rows": 1, "locator": "section[11]/table-wrap[6]#genes-11-00931-t006"}}, {"id": "asset:table:pmid:32806782:7", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1def3b4e0b6f112d45f9b72d1dd5109ff06f9519c922cd86faf6af7fcfd8f38c", "bytes": 829, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[7]#genes-11-00931-t007", "version": null, "note": "Top significant GO-CC term enriched (FDR sorted).", "structure": {"pmcid": "PMC7465138", "section_index": 11, "section_title": "3. Results and Discussion", "row_count": 11, "column_count": 4}, "table": {"label": "Table 7", "caption": "Top significant GO-CC term enriched (FDR sorted).", "rows": [["GO-CC Term Name *", "#Genes", "Enriched p-Value", "FDR"], ["GO:0005783 endoplasmic reticulum", "1861", "0", "0"], ["GO:0097458 neuron part", "1690", "0", "0"], ["GO:0031984 intrinsic component of plasma membrane", "1673", "0", "0"], ["GO:0031984 organelle subcompartment", "1661", "0", "0"], ["GO:0098805 whole membrane", "1630", "0", "0"], ["GO:0005887 integral component of plasma membrane", "1596", "0", "0"], ["GO:0005794 Golgi apparatus", "1516", "0", "0"], ["GO:0044433 cytoplasmic vesicle part", "1462", "0", "0"], ["GO:0044463 cell projection part", "1425", "0", "0"], ["GO:0120038 plasma membrane bounded cell projection part", "1425", "0", "0"]], "row_count": 11, "column_count": 4, "numeric_cells": 40, "header_rows": 1, "locator": "section[11]/table-wrap[7]#genes-11-00931-t007"}}, {"id": "asset:table:pmid:32806782:8", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6082646ca1a3e90332c396d63eb74829513df7a62c9adbce1368b8df25c44011", "bytes": 1080, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[8]#genes-11-00931-t008", "version": null, "note": "Top significant GO-MF term enriched (FDR sorted).", "structure": {"pmcid": "PMC7465138", "section_index": 11, "section_title": "3. Results and Discussion", "row_count": 11, "column_count": 4}, "table": {"label": "Table 8", "caption": "Top significant GO-MF term enriched (FDR sorted).", "rows": [["GO-MF Term Name *", "#Genes", "Enriched p-Value", "FDR"], ["GO:0042802 identical protein binding", "1696", "0", "0"], ["GO:0005102 signaling receptor binding", "1538", "0", "0"], ["GO:0019904 protein domain specific binding", "684", "0", "0"], ["GO:0044212 transcription regulatory region DNA binding", "896", "1.33×10−15", "6.25×10−13"], ["GO:0001067 regulatory region nucleic acid binding", "898", "2.00×10−15", "7.50×10−13"], ["GO:0003690 double-stranded DNA binding", "915", "1.02×10−14", "3.16×10−12"], ["GO:0008134 transcription factor binding", "638", "1.18×10−14", "3.16×10−12"], ["GO:0016301 kinase activity", "845", "2.19×10−14", "5.00×10−12"], ["GO:1990837 sequence-specific double-stranded DNA binding", "823", "2.49×10−14", "5.00×10−12"], ["GO:0000976 transcription regulatory region sequence-specific DNA binding", "781", "2.66×10−14", "5.00×10−12"]], "row_count": 11, "column_count": 4, "numeric_cells": 40, "header_rows": 1, "locator": "section[11]/table-wrap[8]#genes-11-00931-t008"}}], "gaps": ["asset:data:geo:GSE30760 not downloaded", "asset:data:geo:GSE30760 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 0.7, "band": "medium", "quote": "Limma"}}, {"id": "method-2", "family": "regression_modelling", "specific": "ols", "label": "Regression modelling", "dsl_operations": ["ols_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["predictors_and_outcome"], "evidence": {"score": 0.7, "band": "medium", "quote": "Linear Regression"}}, {"id": "method-3", "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": "In this regard, we applied Pearson’s correlation analysis on the DEGs identified by our method for finding out the active edges among genes having correlation value ≥0.8 or ≤−0.8."}}], "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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "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": ["GSE30760"], "resolved_accessions": ["GSE30760"], "statements": ["In this study, we used a cervical cancer methylation dataset(NCBI accession ID: GSE30760) [14,15,16]. This dataset included 63 uterine cervical tumor samples and 152 matched normal samples."], "basis": "The paper names GSE30760 in NCBI and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:32806782", "data:geo:GSE30760", "asset:table:pmid:32806782:1", "asset:table:pmid:32806782:2", "asset:table:pmid:32806782:3", "asset:table:pmid:32806782:4", "asset:table:pmid:32806782:5", "asset:table:pmid:32806782:6", "asset:table:pmid:32806782:7", "asset:table:pmid:32806782:8"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE30760"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:21:54Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 30410, "completion_tokens": 1331, "cached_tokens": 792}}, "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:32806782", "type": "paper", "label": "pmid:32806782"}, {"id": "source:pmid:32806782", "type": "manuscript", "label": "PMID 32806782 full text"}, {"id": "data:geo:GSE30760", "type": "dataset", "label": "GEO GSE30760"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32806782", "type": "paper", "label": "pmid:32806782"}, {"id": "source:pmid:32806782", "type": "manuscript", "label": "PMID 32806782 full text"}, {"id": "data:geo:GSE30760", "type": "dataset", "label": "GEO GSE30760"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32806782", "type": "extraction", "used": ["source:pmid:32806782"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE30760", "type": "accession_resolution", "used": ["data:geo:GSE30760"], "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:32806782", "parent_hash": "sha256:1a7bd400a0a8f2ba77911eef236a62bbf603b568a3c555c845966e40b1090d50", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE30760 licence not read", "asset:data:geo:GSE30760 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["Limma"], "order_basis": "analysis_only", "id": "assay:1"}]},"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":"2026-11-04T01:42:42+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}}}