{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34531741", "kind": "science-record", "revision": 7, "content_hash": "sha256:383acd71a13773e6ad0199e87a473205af3956ac55ce0d7f877ec6716e28a15f", "created_at": "2026-11-01T15:41:52Z", "updated_at": "2026-11-01T22:04:44Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of Novel Gene Signatures using Next-Generation Sequencing Data from COVID-19 Infection Models: Focus on Neuro-COVID and Potential Therapeutics.", "doi": "10.3389/fphar.2021.688227", "pmid": "34531741", "authors": ["Peter Natesan Pushparaj", "Angham Abdulrahman Abdulkareem", "Muhammad Imran Naseer"], "journal": "Frontiers in pharmacology", "year": 2021, "abstract": "SARS-CoV-2 is the causative agent for coronavirus disease-19 (COVID-19) and belongs to the family Coronaviridae that causes sickness varying from the common cold to more severe illnesses such as severe acute respiratory syndrome, sudden stroke, neurological complications (Neuro-COVID), multiple organ failure, and mortality in some patients. The gene expression profiles of COVID-19 infection models can be used to decipher potential therapeutics for COVID-19 and related pathologies, such as Neuro-COVID. Here, we used the raw RNA-seq reads (Single-End) in quadruplicates derived using Illumina Next Seq 500 from SARS-CoV-infected primary human bronchial epithelium (NHBE) and mock-treated NHBE cells obtained from the Gene Expression Omnibus (GEO) (GSE147507), and the quality control (QC) was evaluated using the CLC Genomics Workbench 20.0 (Qiagen, United States) before the RNA-seq analysis using BioJupies web tool and iPathwayGuide for gene ontologies (GO), pathways, upstream regulator genes, small molecules, and natural products. Additionally, single-cell transcriptomics data (GSE163005) of meta clusters of immune cells from the cerebrospinal fluid (CSF), such as T-cells/natural killer cells (NK) (TcMeta), dendritic cells (DCMeta), and monocytes/granulocyte (monoMeta) cell types for comparison, namely, Neuro-COVID versus idiopathic intracranial hypertension (IIH), were analyzed using iPathwayGuide. L1000 fireworks display (L1000FWD) and L1000 characteristic direction signature search engine (L1000 CDS2) web tools were used to uncover the small molecules that could potentially reverse the COVID-19 and Neuro-COVID-associated gene signatures. We uncovered small molecules such as camptothecin, importazole, and withaferin A, which can potentially reverse COVID-19 associated gene signatures. In addition, withaferin A, trichostatin A, narciclasine, camptothecin, and JQ1 have the potential to reverse Neuro-COVID gene signatures. Furthermore, the gene set enrichment analysis (GSEA) preranked method and Metascape web tool were used to decipher and annotate the gene signatures that were potentially reversed by these small molecules. In conclusion, our study unravels a rapid approach for applying next-generation knowledge discovery (NGKD) platforms to discover small molecules with therapeutic potential against COVID-19 and its related disease pathologies.", "claims": [{"id": "claim-method", "statement": "GSEA against a ranked list of genes was performed using the GSEA preranked method (Subramanian et al., 2005).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34531741", "locator": "sections[9] \"Gene Set Enrichment Analysis (GSEA) Preranked\" paragraph 2", "quote": "GSEA against a ranked list of genes was performed using the GSEA preranked method (Subramanian et al., 2005)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Publicly available datasets were analyzed in this study. This data can be found here: Gene Expression Omnibus GSE147507 and GSE163005.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34531741", "locator": "sections[16] \"Data Availability Statement\" paragraph 2", "quote": "Publicly available datasets were analyzed in this study. This data can be found here: Gene Expression Omnibus GSE147507 and GSE163005."}], "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:34531741"], "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:GSE147507"], "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:GSE147507"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34531741", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fphar.2021.688227", "sha256": "sha256:8fee3cee5874fd27bfbd96991a5abc290a09d5a9da5cec48605593a3e4cded02", "bytes": 53741, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fphar.2021.688227", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8438179", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE147507", "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=GSE147507", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE147507", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: Gene Expression Omnibus GSE147507 and GSE163005.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: Gene Expression Omnibus GSE147507 and GSE163005.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4432378", "GSM4432379", "GSM4432380", "GSM4432381", "GSM4432382", "GSM4432383", "GSM4432384", "GSM4432385", "GSM4432386", "GSM4432387", "GSM4432388", "GSM4432389", "GSM4432390", "GSM4432391", "GSM4432392", "GSM4432393", "GSM4432394", "GSM4432395", "GSM4432396", "GSM4432397", "GSM4462336", "GSM4462337", "GSM4462338", "GSM4462339", "GSM4462340", "GSM4462341", "GSM4462342", "GSM4462343", "GSM4462344", "GSM4462345", "GSM4462346", "GSM4462347", "GSM4462348", "GSM4462349", "GSM4462350", "GSM4462351", "GSM4462352", "GSM4462353", "GSM4462354", "GSM4462355", "GSM4462356", "GSM4462357", "GSM4462358", "GSM4462359", "GSM4462360", "GSM4462361", "GSM4462362", "GSM4462363", "GSM4462364", "GSM4462365", "GSM4462366", "GSM4462367", "GSM4462368", "GSM4462369", "GSM4462370", "GSM4462371", "GSM4462372", "GSM4462373", "GSM4462374", "GSM4462375", "GSM4462376", "GSM4462377", "GSM4462378", "GSM4462379", "GSM4462380", "GSM4462381", "GSM4462382", "GSM4462383", "GSM4462384", "GSM4462385", "GSM4462386", "GSM4462387", "GSM4462388", "GSM4462389", "GSM4462390", "GSM4462391", "GSM4462392", "GSM4462393", "GSM4462394", "GSM4462395", "GSM4462396", "GSM4462397", "GSM4462398", "GSM4462399", "GSM4462400", "GSM4462401", "GSM4462402", "GSM4462403", "GSM4462404", "GSM4462405", "GSM4462406", "GSM4462407", "GSM4462408", "GSM4462409", "GSM4462410", "GSM4462411", "GSM4462412", "GSM4462413", "GSM4462414", "GSM4462415", "GSM4462416", "GSM4486157", "GSM4486158", "GSM4486159", "GSM4486160", "GSM4486161", "GSM4486162", "GSM4486163", "GSM4486164", "GSM4486165"], "sample_count": 110, "group_sizes": null, "group_sizes_basis": null, "platform": "18573;28369", "taxon": "Mustela putorius furo; Homo sapiens", "title": "Transcriptional response to SARS-CoV-2 infection", "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:GSE163005", "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=GSE163005", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE163005", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: Gene Expression Omnibus GSE147507 and GSE163005.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: Gene Expression Omnibus GSE147507 and GSE163005.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4970057", "GSM4970058", "GSM4970059", "GSM4970060", "GSM4970061", "GSM4970062", "GSM4970063", "GSM4970064", "GSM4970065", "GSM4970066", "GSM4970067", "GSM4970068", "GSM4970069", "GSM4970070", "GSM4970071", "GSM4970072", "GSM4970073", "GSM4970074", "GSM4970075", "GSM4970076", "GSM4970077", "GSM4970078", "GSM4970079", "GSM4970080", "GSM4970081", "GSM4970082", "GSM4970083", "GSM4970084", "GSM4970085", "GSM4970086", "GSM4970087", "GSM4970088", "GSM4970089", "GSM4970090", "GSM4970091", "GSM4970092", "GSM4970093", "GSM4970094"], "sample_count": 38, "group_sizes": null, "group_sizes_basis": null, "platform": "18573;24676", "taxon": "Homo sapiens", "title": "Characterizing cerebrospinal fluid immunity in neurological manifestations of COVID-19", "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:34531741:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5c37ef07aa9967bd82957bd140d0add2473334f84dbdf44c687f164f5be19f85", "bytes": 735, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#T1", "version": null, "note": "Top identified pathways and their associated p-values are given in the table.", "structure": {"pmcid": "PMC8438179", "section_index": 12, "section_title": "iPathwayGuide Analysis of DEGs From COVID-19 and Neuro-COVID Infection Models", "row_count": 6, "column_count": 5}, "table": {"label": "TABLE 1", "caption": "Top identified pathways and their associated p-values are given in the table.", "rows": [["Pathway name", "Pathway ID", "p-value", "p-value (FDR)", "p-value (Bonferroni)"], ["Cytokine-cytokine receptor interaction", "04060", "6.711e−8", "2.0202e−5", "2.020e−5"], ["Staphylococcus aureus infection", "05150", "4.009e−7", "6.034e−5", "1.207e−4"], ["Viral protein interaction with cytokine and cytokine receptor", "04061", "1.050e−7", "1.053e−4", "3.160e−4"], ["Systemic lupus erythematosus", "05322", "3.414e−4", "0.026", "0.103"], ["Herpes simplex virus 1 infection", "05168", "6.444e−4", "0.039", "0.194"]], "row_count": 6, "column_count": 5, "numeric_cells": 21, "header_rows": 1, "locator": "section[12]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:34531741:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:73fe0aedd3d89a5936e8d25865fcc149d39767f5617f4b4a216f82250992fb3b", "bytes": 579, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[2]#T2", "version": null, "note": "Top identified upstream regulators activated based on Bonferroni correction were listed in the table.", "structure": {"pmcid": "PMC8438179", "section_index": 12, "section_title": "iPathwayGuide Analysis of DEGs From COVID-19 and Neuro-COVID Infection Models", "row_count": 6, "column_count": 6}, "table": {"label": "TABLE 2", "caption": "Top identified upstream regulators activated based on Bonferroni correction were listed in the table.", "rows": [["Upstream regulator (u)", "DTA (u)", "DT (u)", "p-value", "p-value (FDR)", "p-value (Bonferroni)"], ["IL17A", "13", "17", "1.139e−6", "0.001", "0.001"], ["TNF", "23", "28", "1.857e−6", "0.001", "0.002"], ["STAT2", "9", "9", "5.589e−6", "0.002", "0.007"], ["IRF9", "8", "8", "2.248e−5", "0.007", "0.028"], ["TLR4", "8", "8", "8.493e−5", "0.021", "0.106"]], "row_count": 6, "column_count": 6, "numeric_cells": 26, "header_rows": 1, "locator": "section[12]/table-wrap[2]#T2"}}, {"id": "asset:table:pmid:34531741:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:cc60e72ff86d33296d08a2ae45d251a01972b1f72eafbbcdbf4c735868a2115a", "bytes": 1133, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[3]#T3", "version": null, "note": "Top identified biological processes for each pruning type.", "structure": {"pmcid": "PMC8438179", "section_index": 12, "section_title": "iPathwayGuide Analysis of DEGs From COVID-19 and Neuro-COVID Infection Models", "row_count": 7, "column_count": 8}, "table": {"label": "TABLE 3", "caption": "Top identified biological processes for each pruning type.", "rows": [["Pruning type: none", "Pruning type: high specificity", "Pruning type: smallest common denominator"], ["Go term", "p-value", "p-value (FDR)", "p-value (Bonferroni)", "Go term", "p-value", "Go term", "p-value"], ["Keratinization", "6.600e−9", "4.710e−5", "4.710e−5", "Cornification", "1.713e−4", "Keratinization", "4.710e−5"], ["Cornification", "2.400e−8", "8.563e−5", "1.713e−4", "Acute-phase response", "0.033", "Acute-phase response", "0.100"], ["Humoral immune response", "2.900e−7", "6.898e−4", "0.002", "Peptide cross-linking", "0.209", "Humoral immune response", "0.167"], ["DNA replication initiation", "9.000e−6", "0.002", "0.064", "Double-strand break repair via break-induced replication", "0.371", "Peptide cross-linking", "0.371"], ["Acute-phase response", "9.300e−6", "0.012", "0.066", "Antimicrobial humoral immune response mediated by antimicrobial peptide", "0.371", "Double-strand break repair via break-induced replication", "0.371"]], "row_count": 7, "column_count": 8, "numeric_cells": 25, "header_rows": 2, "locator": "section[12]/table-wrap[3]#T3"}}, {"id": "asset:table:pmid:34531741:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4bd65f68f71305b78b62e679cdf92bb2a392ef84df4f0fe4b34d8e9212d66295", "bytes": 1137, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[4]#T4", "version": null, "note": "Top identified molecular functions for each pruning type.", "structure": {"pmcid": "PMC8438179", "section_index": 12, "section_title": "iPathwayGuide Analysis of DEGs From COVID-19 and Neuro-COVID Infection Models", "row_count": 7, "column_count": 8}, "table": {"label": "TABLE 4", "caption": "Top identified molecular functions for each pruning type.", "rows": [["Pruning type: none", "Pruning type: high specificity", "Pruning type: smallest common denominator"], ["Go term", "p-value", "p-value (FDR)", "p-value (Bonferroni)", "Go term", "p-value", "Go term", "p-value"], ["Cytokine activity", "1.200e−7", "1.691e−4", "1.691e−4", "Cytokine activity", "0.061", "Cytokine activity", "1.691e−4"], ["Receptor regulator activity", "6.500e−7", "4.579e−4", "9.158e−4", "Chemokine activity", "0.061", "Serine hydrolase activity", "0.341"], ["Signaling receptor activator activity", "4.500e−6", "0.002", "0.006", "DNA replication origin binding", "0.341", "DNA replication origin binding", "0.341"], ["Receptor-ligand activity", "7.900e−6", "0.003", "0.011", "2’-5’-Oligodenylate synthetase activity", "0.341", "2’-5’-Oligodenylate synthetase activity", "0.341"], ["Chemokine activity", "6.000e−5", "0.017", "0.085", "Structural constituent of skin epidermis", "0.341", "Structural constituent of skin epidermis", "0.341"]], "row_count": 7, "column_count": 8, "numeric_cells": 27, "header_rows": 2, "locator": "section[12]/table-wrap[4]#T4"}}, {"id": "asset:table:pmid:34531741:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1070fad613596f673b427e54e108f9ab34c2f32aae68043728474ad3f424135c", "bytes": 959, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[5]#T5", "version": null, "note": "Top identified cellular components for each pruning type.", "structure": {"pmcid": "PMC8438179", "section_index": 12, "section_title": "iPathwayGuide Analysis of DEGs From COVID-19 and Neuro-COVID Infection Models", "row_count": 7, "column_count": 8}, "table": {"label": "TABLE 5", "caption": "Top identified cellular components for each pruning type.", "rows": [["Pruning type: none", "Pruning type: high specificity", "Pruning type: smallest common denominator"], ["Go term", "p-value", "p-value (FDR)", "p-value (Bonferroni)", "Go term", "p-value", "Go term", "p-value"], ["Cornified envelope", "3.600e−5", "0.024", "0.033", "Cornified envelope", "0.033", "Cornified envelope", "0.024"], ["Intermediate filament", "5.200e−5", "0.024", "0.048", "Intermediate filament", "0.279", "Intermediate filament", "0.024"], ["DNA packaging complex", "2.700e−4", "0.082", "0.247", "Blood microparticle", "0.485", "DNA packaging complex", "0.082"], ["Intermediate filament cytoskeleton", "0.001", "0.209", "0.924", "MCM complex", "0.492", "Blood microparticle", "0.364"], ["Extracellular matrix", "0.001", "0.209", "1.000", "Nucleosome", "0.492", "MCM complex", "0.470"]], "row_count": 7, "column_count": 8, "numeric_cells": 25, "header_rows": 2, "locator": "section[12]/table-wrap[5]#T5"}}, {"id": "asset:table:pmid:34531741:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f134bfa032bf8c8429f0938911d466c29cd4d2a7ea2f81d506825d1d52644295", "bytes": 1709, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[6]#T6", "version": null, "note": "Natural products and drugs with opposite molecular signatures based on L1000FWD web-based tool for querying gene expression signatures (SARS-CoV-2-NHBE vs. Mock-NHBE) against signatures created from human cell lines treated with over 20,000 small molecules and drugs for the LINCS project.", "structure": {"pmcid": "PMC8438179", "section_index": 12, "section_title": "iPathwayGuide Analysis of DEGs From COVID-19 and Neuro-COVID Infection Models", "row_count": 11, "column_count": 7}, "table": {"label": "TABLE 6", "caption": "Natural products and drugs with opposite molecular signatures based on L1000FWD web-based tool for querying gene expression signatures (SARS-CoV-2-NHBE vs. Mock-NHBE) against signatures created from human cell lines treated with over 20,000 small molecules and drugs for the LINCS project.", "rows": [["Signature ID", "Drug or natural product", "Similarity SCORE", "p-value", "q-value", "Z-score", "Combined score"], ["CPC006_PC3_6H:BRD-A36630025-001-02-6:0.35", "SN-38", "−0.0598", "1.04e−11", "2.02e−08", "1.79", "−19.61"], ["CPC011_A549_24H:BRD-K97514127-045-02-0:10", "Vinorelbine", "−0.0598", "2.32e−11", "3.82e−08", "1.72", "−18.26"], ["CPC015_MCF7_24H:BRD-K52075715-001-03-4:10", "Oxibendazole", "−0.0573", "2.91e−10", "3.37e−07", "1.67", "−15.88"], ["CPC019_HT29_6H:BRD-K67870070-001-01-4:10", "SA-247615", "−0.0560", "7.96e−11", "1.22e−07", "1.69", "−17.05"], ["ERG005_VCAP_6H:BRD-K88378636-001-02-8:20", "Withaferin A", "−0.0547", "1.28e−09", "1.19e−06", "1.65", "−14.71"], ["CPC012_MCF7_24H:BRD-K69496360-001-01-5:10", "BRD-K69496360", "−0.0522", "1.03e−08", "5.72e−06", "1.73", "−13.81"], ["CPC015_MCF7_24H:BRD-K47869605-001-18-9:10", "Podophyllotoxin", "−0.0509", "1.78e−08", "8.35e−06", "1.67", "−12.97"], ["CPC001_HCC515_24H:BRD-K82823804-001-01-7:10", "SA-792987", "−0.0509", "3.61e−08", "1.44e−05", "1.81", "−13.45"], ["MUC.CP003_MCF7_24H:BRD-K02407574-001-04-8:3.3333", "Parbendazole", "−0.0496", "8.46e−08", "2.85e−05", "1.62", "−11.45"], ["CPC002_PC3_6H:BRD-K06926592-001-01-7:10", "Tretinoin", "−0.0496", "7.24e−08", "2.54e−05", "1.79", "−12.80"]], "row_count": 11, "column_count": 7, "numeric_cells": 64, "header_rows": 1, "locator": "section[12]/table-wrap[6]#T6"}}, {"id": "asset:table:pmid:34531741:7", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5fba5657342b385e83526f493a6d6e9ffd325baa21a3c91402e4e8ffc31f9195", "bytes": 1676, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#T7", "version": null, "note": "Top small molecules with opposite molecular signatures based on L1000FWD web-based tool for querying gene expression signatures (Neuro-COVID vs. IIH-Tc Meta) against signatures created from human cell lines treated with over 20,000 small molecules and drugs for the LINCS project.", "structure": {"pmcid": "PMC8438179", "section_index": 13, "section_title": "L1000FWD and L1000CDS2 Analyses", "row_count": 11, "column_count": 7}, "table": {"label": "TABLE 7", "caption": "Top small molecules with opposite molecular signatures based on L1000FWD web-based tool for querying gene expression signatures (Neuro-COVID vs. IIH-Tc Meta) against signatures created from human cell lines treated with over 20,000 small molecules and drugs for the LINCS project.", "rows": [["Signature ID", "Drug or natural product", "Similarity score", "p-value", "q-value", "Z-score", "Combined score"], ["ERG005_VCAP_6H:BRD-K88378636-001-02-8:20", "Withaferin A", "−0.0492", "3.55e−16", "1.52e−11", "1.65", "−25.55"], ["CPC012_VCAP_24H:BRD-A59985574-003-01-9:10", "Topotecan", "−0.0303", "6.34e−05", "4.35e−01", "1.75", "−7.36"], ["CPC012_VCAP_24H:BRD-K62459624-001-08-7:10", "BRD-K62459624", "−0.0293", "1.66e−04", "8.86e−01", "1.77", "−6.69"], ["CPC006_HCC515_6H:BRD-K16406336-311-01-2:10", "Methylene-blue", "−0.0303", "8.54e−04", "1.00e+00", "1.77", "−5.43"], ["CPC011_PC3_6H:BRD-K04548931-003-11-6:10", "Pidorubicine", "−0.0278", "1.04e−03", "1.00e+00", "1.77", "−5.27"], ["NMH002_NPC_24H:BRD-K32610195-001-14-9:10", "Androstenedione", "−0.0269", "1.58e−03", "1.00e+00", "1.63", "−4.57"], ["CPC012_VCAP_24H:BRD-K56196992-001-01-2:10", "BRD-K56196992", "−0.0269", "9.60e−03", "1.00e+00", "1.72", "−3.47"], ["CPC015_NPC_24H:BRD-K14920963-304-01-9:10", "Erythrosine", "−0.0269", "1.51e−03", "1.00e+00", "1.75", "−4.93"], ["CPC013_SKB_24H:BRD-K16798053-001-01-0:10", "ST-4029573", "−0.0269", "4.94e−04", "1.00e+00", "1.76", "−5.82"], ["CPC004_PC3_6H:BRD-A41519720-001-03-0:10", "Ezetimibe", "−0.0264", "1.21e−02", "1.00e+00", "1.78", "−3.42"]], "row_count": 11, "column_count": 7, "numeric_cells": 63, "header_rows": 1, "locator": "section[13]/table-wrap[1]#T7"}}, {"id": "asset:table:pmid:34531741:8", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:41afe37f6803b24d06163f7ff895b588fc6dc53beec2d3f940b9de4171a862a8", "bytes": 1667, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[2]#T8", "version": null, "note": "Top small molecules with opposite molecular signatures based on L1000FWD web-based tool for querying gene expression signatures (Neuro-COVID vs. IIH-DC Meta) against signatures created from human cell lines treated with over 20,000 small molecules and drugs for the LINCS project.", "structure": {"pmcid": "PMC8438179", "section_index": 13, "section_title": "L1000FWD and L1000CDS2 Analyses", "row_count": 11, "column_count": 7}, "table": {"label": "TABLE 8", "caption": "Top small molecules with opposite molecular signatures based on L1000FWD web-based tool for querying gene expression signatures (Neuro-COVID vs. IIH-DC Meta) against signatures created from human cell lines treated with over 20,000 small molecules and drugs for the LINCS project.", "rows": [["Signature ID", "Drug or natural product", "Similarity score", "p-value", "q-value", "Z-score", "Combined score"], ["ERG005_VCAP_6H:BRD-K88378636-001-02-8:20", "Withaferin A", "−0.0587", "2.84e−19", "1.21e−14", "1.65", "−30.67"], ["CPC015_NPC_24H:BRD-K14920963-304-01-9:10", "Erythrosine", "−0.0304", "2.85e−04", "7.64e−01", "1.75", "−6.19"], ["CPC006_HCC515_6H:BRD-K16406336-311-01-2:10", "Methylene-blue", "−0.0330", "3.94e−04", "8.88e−01", "1.77", "−6.02"], ["CPC012_HCC515_6H:BRD-K56653679-001-01-2:10", "MD-041", "−0.0317", "4.22e−04", "9.03e−01", "1.72", "−5.81"], ["CVD001_HUH7_6H:BRD-K81142122-001-14-1:10", "STK-249718", "−0.0323", "3.91e−04", "8.88e-01", "1.62", "−5.52"], ["CPC004_HT29_6H:BRD-K77830450-001-02-4:10", "Forskolin", "−0.0264", "1.31e−03", "1.00e+00", "1.90", "−5.47"], ["CPC013_SKB_24H:BRD-K16798053-001-01-0:10", "ST-4029573", "−0.0277", "9.86e−04", "1.00e+00", "1.76", "−5.29"], ["CPC014_HA1E_6H:BRD-U66370498-000-01-0:10", "Androstanol", "−0.0264", "1.43e−03", "1.00e+00", "1.77", "−5.03"], ["CPC005_A375_24H:BRD-A78360835-001-01-1:10", "Cercosporin", "−0.0290", "2.06e−03", "1.00e+00", "1.82", "−4.90"], ["CPC014_HCC515_6H:BRD-A80960055-001-01-7:10", "Celastrol", "−0.0290", "2.78e−03", "1.00e+00", "1.72", "−4.40"]], "row_count": 11, "column_count": 7, "numeric_cells": 63, "header_rows": 1, "locator": "section[13]/table-wrap[2]#T8"}}, {"id": "asset:table:pmid:34531741:9", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:204b53dea11480eb4458be2aa831b7da3e45fb61412140aaa15dd52e87923bc0", "bytes": 1680, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[3]#T9", "version": null, "note": "Top small molecules with opposite molecular signatures based on L1000FWD web-based tool for querying gene expression signatures (Neuro-COVID vs. IIH-monoMeta) against signatures created from human cell lines treated with over 20,000 small molecules and drugs for the LINCS project.", "structure": {"pmcid": "PMC8438179", "section_index": 13, "section_title": "L1000FWD and L1000CDS2 Analyses", "row_count": 11, "column_count": 7}, "table": {"label": "TABLE 9", "caption": "Top small molecules with opposite molecular signatures based on L1000FWD web-based tool for querying gene expression signatures (Neuro-COVID vs. IIH-monoMeta) against signatures created from human cell lines treated with over 20,000 small molecules and drugs for the LINCS project.", "rows": [["Signature ID", "Drug or natural product", "Similarity score", "p-value", "q-value", "Z-score", "combined score"], ["ERG005_VCAP_6H:BRD-K88378636-001-02-8:20", "Withaferin A", "−0.0533", "2.68e−13", "1.06e−08", "1.65", "−20.79"], ["CPC006_SNUC5_6H:BRD-A19633847-050-20-6:10", "Perhexiline", "−0.0414", "4.51e−08", "3.85e−04", "1.80", "−13.23"], ["CPC013_SKB_24H:BRD-K16798053-001-01-0:10", "ST-4029573", "−0.0382", "2.01e−07", "8.62e−04", "1.76", "−11.79"], ["CPC017_SKB_24H:BRD-A20968261-001-01-3:10", "WAY-213613", "−0.0414", "2.81e−07", "1.00e−03", "1.68", "−11.01"], ["CPC006_CORL23_6H:BRD-A04706586-236-01-7:10", "Bucladesine", "−0.0358", "2.08e−06", "4.95e−03", "1.84", "−10.48"], ["CPC007_A375_24H:BRD-K03067624-003-19-3:10", "Emetine", "−0.0398", "1.42e−06", "3.80e−03", "1.78", "−10.42"], ["CPC007_A375_6H:BRD-K03067624-003-19-3:10", "emetine", "−0.0374", "3.86e−06", "8.48e−03", "1.81", "−9.79"], ["CPC012_MCF7_6H:BRD-K41652870-001-01-9:10", "BRD-K41652870", "−0.0366", "7.70e−06", "1.32e−02", "1.75", "−8.97"], ["CPC005_A375_24H:BRD-A78360835-001-01-1:10", "Cercosporin", "−0.0358", "2.49e−05", "2.74e−02", "1.83", "−8.40"], ["CPC006_PL21_6H:BRD-K78659596-001-01-3:10", "MLN-2238", "−0.0334", "3.27e−05", "3.33e−02", "1.85", "−8.28"]], "row_count": 11, "column_count": 7, "numeric_cells": 64, "header_rows": 1, "locator": "section[13]/table-wrap[3]#T9"}}, {"id": "asset:table:pmid:34531741:10", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:48b525b7446e93cc9ea9228463916324256f3cff22d1b2652f2a31814be974a2", "bytes": 872, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[4]#T10", "version": null, "note": "Top small molecules identified by the L1000CDS2 query that reverse the Neuro-COVID vs. IIH-TcMeta gene signature.", "structure": {"pmcid": "PMC8438179", "section_index": 13, "section_title": "L1000FWD and L1000CDS2 Analyses", "row_count": 11, "column_count": 6}, "table": {"label": "TABLE 10", "caption": "Top small molecules identified by the L1000CDS2 query that reverse the Neuro-COVID vs. IIH-TcMeta gene signature.", "rows": [["Rank", "Overlap", "Perturbation", "Cell line", "Dose", "Time (h)"], ["1", "0.0358", "T5212475", "VCAP", "10.0 µm", "24.0"], ["2", "0.0353", "BRD-K56411643", "VCAP", "10.0 µm", "24.0"], ["3", "0.0278", "F3055", "A375", "10.0 µm", "6.0"], ["4", "0.0254", "Narciclasine", "HA1E", "10.0 µm", "24.0"], ["5", "0.0249", "Ro 31-8220 mesylate", "HCC515", "10.0 µm", "24.0"], ["6", "0.0244", "Erythrosine sodium", "HA1E", "10.0 µm", "24.0"], ["7", "0.0244", "Parthenolide", "A375", "20.0 µm", "24.0"], ["8", "0.0239", "Teniposide", "A375", "1.25 µm", "24.0"], ["9", "0.0239", "Daunorubicin", "A549", "10.0 µm", "6.0"], ["10", "0.0239", "EI-293", "PC3", "10.0 µm", "6.0"]], "row_count": 11, "column_count": 6, "numeric_cells": 50, "header_rows": 1, "locator": "section[13]/table-wrap[4]#T10"}}, {"id": "asset:table:pmid:34531741:11", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f8010c57f846235d071fd9e5f33ae9a0a6c2d71605ac82d702bfe13fd1e33713", "bytes": 871, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[5]#T11", "version": null, "note": "Top small molecules identified by the L1000CDS2 query that reverse the Neuro-COVID vs. IIH-DCMeta gene signature.", "structure": {"pmcid": "PMC8438179", "section_index": 13, "section_title": "L1000FWD and L1000CDS2 Analyses", "row_count": 11, "column_count": 6}, "table": {"label": "TABLE 11", "caption": "Top small molecules identified by the L1000CDS2 query that reverse the Neuro-COVID vs. IIH-DCMeta gene signature.", "rows": [["Rank", "Overlap", "Perturbation", "Cell line", "Dose", "Time (h)"], ["1", "0.0337", "Trichostatin A", "A375", "10.0 µm", "24.0"], ["2", "0.0304", "Narciclasine", "HA1E", "10.0 µm", "24.0"], ["3", "0.0297", "Camptothecin (S,+)", "PC3", "10.0 µm", "24.0"], ["4", "0.0277", "Erythrosine sodium", "HA1E", "10.0 µm", "24.0"], ["5", "0.0277", "Vorinostat", "A375", "11.1 µm", "24.0"], ["6", "0.0271", "F3055", "A375", "10.0 µm", "6.0"], ["7", "0.0264", "Parthenolide", "A375", "20.0 µm", "24.0"], ["8", "0.0257", "Curcumin", "MCF7", "48.0 µm", "24.0"], ["9", "0.0257", "BRD-K56411643", "VCAP", "10.0 µm", "24.0"], ["10", "0.0257", "Celastrol", "HME1", "10 µm", "3"]], "row_count": 11, "column_count": 6, "numeric_cells": 46, "header_rows": 1, "locator": "section[13]/table-wrap[5]#T11"}}, {"id": "asset:table:pmid:34531741:12", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4ecb25a66fda4fcadbd7da565f3a8bcbe665bae94167c33bcbb74bcea95e0449", "bytes": 881, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[6]#T12", "version": null, "note": "Top small molecules identified by the L1000CDS2 query that reverse the Neuro-COVID vs. IIH-monoMeta gene signature.", "structure": {"pmcid": "PMC8438179", "section_index": 13, "section_title": "L1000FWD and L1000CDS2 Analyses", "row_count": 11, "column_count": 6}, "table": {"label": "TABLE 12", "caption": "Top small molecules identified by the L1000CDS2 query that reverse the Neuro-COVID vs. IIH-monoMeta gene signature.", "rows": [["Rank", "Overlap", "Perturbation", "Cell line", "Dose", "Time (h)"], ["1", "0.0398", "Trichostatin A", "A375", "10.0 µm", "24.0"], ["2", "0.0390", "Narciclasine", "A375", "10.0 µm", "24.0"], ["3", "0.0366", "Parthenolide", "A375", "20.0 µm", "24.0"], ["4", "0.0350", "HY-10518", "VCAP", "10.0 µm", "24.0"], ["5", "0.0334", "Vorinostat", "A375", "11.1 µm", "24.0"], ["6", "0.0326", "Teniposide", "A375", "1.25 µm", "24.0"], ["7", "0.0326", "BRD-K56411643", "VCAP", "10.0 µm", "24.0"], ["8", "0.0326", "BL-081", "VCAP", "10.0 µm", "24.0"], ["9", "0.0326", "Camptothecin (S,+)", "PC3", "10.0 µm", "24.0"], ["10", "0.0310", "Erythrosine sodium", "HA1E", "10.0 µm", "24.0"]], "row_count": 11, "column_count": 6, "numeric_cells": 48, "header_rows": 1, "locator": "section[13]/table-wrap[6]#T12"}}], "gaps": ["asset:data:geo:GSE147507 not downloaded", "asset:data:geo:GSE147507 licence not read", "asset:data:geo:GSE163005 not downloaded", "asset:data:geo:GSE163005 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": "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": 0.8, "band": "high", "quote": "limma"}}, {"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": "dendrogram"}}, {"id": "method-4", "family": null, "specific": null, "label": "GSEA preranked method", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "GSEA against a ranked list of genes was performed using the GSEA preranked method (Subramanian et al., 2005)."}}], "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": ["GSE147507", "GSE163005"], "resolved_accessions": ["GSE147507", "GSE163005"], "statements": ["Publicly available datasets were analyzed in this study. This data can be found here: Gene Expression Omnibus GSE147507 and GSE163005."], "basis": "The paper names GSE147507, GSE163005 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": ["pca_fit"], "assets": ["source:pmid:34531741", "data:geo:GSE147507", "asset:table:pmid:34531741:1", "asset:table:pmid:34531741:2", "asset:table:pmid:34531741:3", "asset:table:pmid:34531741:4", "asset:table:pmid:34531741:5", "asset:table:pmid:34531741:6", "asset:table:pmid:34531741:7", "asset:table:pmid:34531741:8", "asset:table:pmid:34531741:9", "asset:table:pmid:34531741:10", "asset:table:pmid:34531741:11", "asset:table:pmid:34531741:12"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE147507"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:34:57Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 41530, "completion_tokens": 2295, "cached_tokens": 784}}, "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:34531741", "type": "paper", "label": "pmid:34531741"}, {"id": "source:pmid:34531741", "type": "manuscript", "label": "PMID 34531741 full text"}, {"id": "data:geo:GSE147507", "type": "dataset", "label": "GEO GSE147507"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34531741", "type": "paper", "label": "pmid:34531741"}, {"id": "source:pmid:34531741", "type": "manuscript", "label": "PMID 34531741 full text"}, {"id": "data:geo:GSE147507", "type": "dataset", "label": "GEO GSE147507"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34531741", "type": "extraction", "used": ["source:pmid:34531741"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE147507", "type": "accession_resolution", "used": ["data:geo:GSE147507"], "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:34531741", "parent_hash": "sha256:0861c7282dcf5c3a412c3b47f75e159df8b2ab4c3287affcadf089a845f46be9", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE147507 licence not read", "asset:data:geo:GSE147507 not downloaded", "asset:data:geo:GSE163005 licence not read", "asset:data:geo:GSE163005 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "amplicon_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["dentification of Novel Gene Signatures using Next-Generation Sequencing Data from COVID-19 Infection Models: Focus o"], "order_basis": "paper_text_order:1", "id": "assay:1"}, {"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": [", such as Neuro-COVID. Here, we used the raw RNA-seq reads (Single-End) in quadruplicates derived", "ench 20.0 (Qiagen, United States) before the RNA-seq analysis using BioJupies web tool and iPathw", "erials and Methods BioJupies Analysis of the RNA-seq Data BioJupies is a freely available web-bas", "ication (http://biojupies.cloud) that has 14 RNA-seq analysis library plug-ins and provides the u"], "order_basis": "paper_text_order:643", "id": "assay:2"}, {"role": "data_generation", "definition_id": "scrna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "unsupported", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["lecules, and natural products. Additionally, single-cell transcriptomics data (GSE163005) of meta clusters of immune"], "order_basis": "paper_text_order:1169", "id": "assay:3"}, {"role": "analysis", "definition_id": "principal_component_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pca_fit"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["Principal component analysis"], "order_basis": "consumes_earlier_output", "id": "assay:4"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:36:10+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}}}