{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:27942460", "kind": "science-record", "revision": 6, "content_hash": "sha256:cb833244d7edf2a4e11cef1d793cd1d7c3c47552f10017661eb675647ad75759", "created_at": "2026-11-01T15:40:21Z", "updated_at": "2026-11-01T21:20:44Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Transcription profiling data set of different states of Mycoplasma gallisepticum.", "doi": "10.1016/j.gdata.2016.11.021", "pmid": "27942460", "authors": ["Tatiana A Semashko", "Alexander A Arzamasov", "Gleb Y Fisunov", "Vadim M Govorun"], "journal": "Genomics data", "year": 2017, "abstract": "Mycoplasma gallisepticum belongs to class Mollicutes and causes chronic respiratory disease in birds. It has a reduced genome, lack of cell wall and many metabolic pathways, and also easy to culture and non-pathogenic to humans. Aforementioned made it is a convenient model for studying of systems biology of minimal cell. Studying the transcriptomic level of M. gallisepticum is interesting for both understanding of common principles of transcription regulation of minimal cell and response to definite influence for pathogen bacteria. For rapid investigation of gene expression we developed microarray design including 3366 probes for 678 genes. They included 665 protein coding sequences and 13 antisense RNAs from 816 genes and 17 ncRNAs present in Mycoplasma gallisepticum. The study was performed on Agilent one-color microarray with custom design and random-T7 polymerase primer for cDNA synthesis. Here we present the data for transcription profiling of M. gallisepticum under different types of exposures: genetic knock-out mutants, cell culture exposed to sublethal concentrations of antibiotics and well-characterized heat stress effect. Mutants have transposon insertion to hypothetical membrane protein, lactate dehydrogenase, helicase with unknown function, 1-deoxy-d-xylulose 5-phosphate reductoisomerase or potential sigma factor. For inhibition of important cell systems, treatment with carbonyl cyanide m-chlorophenylhydrazone (CCCP), novobiocin or tetracycline were chosen. Data are available via NCBI Gene Expression Omnibus (GEO) with the accession number GSE85777 (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE85777).", "claims": [{"id": "claim-method", "statement": "Spearman correlation coefficient between biological repeats ranges between 0.93 and 1.00.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:27942460", "locator": "sections[4] \"Experimental design\" paragraph 6", "quote": "Spearman correlation coefficient between biological repeats ranges between 0.93 and 1.00."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Data are available via NCBI Gene Expression Omnibus (GEO) with accession number GSE85777 (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE85777)", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:27942460", "locator": "sections[2] \"Direct link to deposited data\" paragraph 2", "quote": "Data are available via NCBI Gene Expression Omnibus (GEO) with accession number GSE85777 (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE85777)"}], "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:27942460"], "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:GSE85777"], "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:GSE85777"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:27942460", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.gdata.2016.11.021", "sha256": "sha256:bdc8cdafa69ebf504d7e0686a691f21d712b4cf46ba0b56af2d882f2cf2541d5", "bytes": 11245, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.gdata.2016.11.021", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5137179", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE85777", "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=GSE85777", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE85777", "version": null, "note": "Data are available via NCBI Gene Expression Omnibus (GEO) with accession number GSE85777 (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE85777)", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data are available via NCBI Gene Expression Omnibus (GEO) with accession number GSE85777 (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE85777)", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2283924", "GSM2283925", "GSM2283926", "GSM2283927", "GSM2283928", "GSM2283929", "GSM2283930", "GSM2283931", "GSM2283932", "GSM2283933", "GSM2283934", "GSM2283935", "GSM2283936", "GSM2283937", "GSM2283938", "GSM2283939", "GSM2283940", "GSM2283941", "GSM2283942", "GSM2283943"], "sample_count": 20, "group_sizes": null, "group_sizes_basis": null, "platform": "22328", "taxon": "Mycoplasmoides gallisepticum", "title": "Transcription profiling of different state of Mycoplasma gallisepticum", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:27942460:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5c6ef779442a03a1cb50dd1c05775952587aa4f34fdb230f7fad876586ef45b9", "bytes": 2560, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#t0005", "version": null, "note": "Description of samples for transcription profiling.", "structure": {"pmcid": "PMC5137179", "section_index": 4, "section_title": "Experimental design", "row_count": 21, "column_count": 3}, "table": {"label": "Table 1", "caption": "Description of samples for transcription profiling.", "rows": [["Sample name", "Clone", "Treatment"], ["C_1", "WT", "Cell culture in exponential growth phase"], ["C_2", "WT", "Cell culture in exponential growth phase"], ["Tn_5UTR_03380_1", "CR1, Transposon insertion to 5′ UTR of hypothetical protein GCW_03380", "Cell culture in exponential growth phase"], ["Tn_5UTR_03380_2", "CR1, Transposon insertion to 5′ UTR of hypothetical protein GCW_03380", "Cell culture in exponential growth phase"], ["Tn_RBS_00390_1", "CR19, Transposon insertion to RBS of lactate dehydrogenase GCW_00390", "Cell culture in exponential growth phase"], ["Tn_RBS_00390_2", "CR19, Transposon insertion to RBS of lactate dehydrogenase GCW_00390", "Cell culture in exponential growth phase"], ["Tn_03935_1", "CR30, Transposon insertion to helicase SNF2 GCW_03935", "Cell culture in exponential growth phase"], ["Tn_03935_2", "CR30, Transposon insertion to helicase SNF2 GCW_03935", "Cell culture in exponential growth phase"], ["Tn_00495_1", "CR86, Transposon insertion to 1-deoxy-D-xylulose 5-phosphate reductoisomerase GCW_00495", "Cell culture in exponential growth phase"], ["Tn_00495_2", "CR86, Transposon insertion to 1-deoxy-D-xylulose 5-phosphate reductoisomerase GCW_00495", "Cell culture in exponential growth phase"], ["Tn_00440_1", "5.3, Transposon insertion to potential sigma factor GCW_00440", "Cell culture in exponential growth phase"], ["Tn_00440_2", "5.3, Transposon insertion to potential sigma factor GCW_00440", "Cell culture in exponential growth phase"], ["cccp_1", "WT", "Cell culture in exponential growth phase under treatment with sublethal concentrations of CCCP"], ["cccp_2", "WT", "Cell culture in exponential growth phase under treatment with sublethal concentrations of CCCP"], ["novo_1", "WT", "Cell culture in exponential growth phase under treatment with sublethal concentrations of novobiocin"], ["novo_2", "WT", "Cell culture in exponential growth phase under treatment with sublethal concentrations of novobiocin"], ["tet_1", "WT", "Cell culture in exponential growth phase under treatment with sublethal concentrations of tetracycline"], ["tet_2", "WT", "Cell culture in exponential growth phase under treatment with sublethal concentrations of tetracycline"], ["HS_1", "WT", "Cell culture in exponential growth phase under heat stress at 46 °C during 15 min"], ["HS_2", "WT", "Cell culture in exponential growth phase under heat stress at 46 °C during 15 min"]], "row_count": 21, "column_count": 3, "numeric_cells": 32, "header_rows": 1, "locator": "section[4]/table-wrap[1]#t0005"}}, {"id": "asset:table:pmid:27942460:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:dca76466bfc48f692d1a75386159216b510dac7b999efc19f01a4c850e470c13", "bytes": 7020, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#t0010", "version": null, "note": "RT-qPCR primers.", "structure": {"pmcid": "PMC5137179", "section_index": 13, "section_title": "Validation of microarray data by quantitative RT-PCR", "row_count": 95, "column_count": 4}, "table": {"label": "Table 2", "caption": "RT-qPCR primers.", "rows": [["S6_ID", "gene_name", "for", "rev"], ["GCW_02785", "clpB", "GAAAGATTACAGGCAAAAGGTG", "GCGCTCTTCCTCTTAGTACTGC"], ["GCW_03075", "dnaK", "TTACTCCAGAAGAAGTTTCTGC", "TAACTTCGAAAGTACCATCAGC"], ["GCW_02105", "lon", "TTGTTAAGATCTCACTTGGTGG", "ATCCCTTCAACATAGTTAGCAG"], ["GCW_02710", "groEL", "ACAACAGCTACAATCTTAACTC", "CCCTTGAACTCTAAACCATCAG"], ["GCW_00415", "dnaJ", "TCTTTAGCTTTGAAGGTGTGAG", "GTGAAAGTAGTTCATCGTCTGC"], ["GCW_00845", "dnaJ2", "CATGTAGTGATTGTAATGGCGA", "GGTTATCGCGTAGTTCAAACAC"], ["GCW_01610", "dnaJ4", "CCCGATGTTAATAAAGCTCCTG", "TCAATCTTACGACTCATCTCAG"], ["GCW_01620", "dnaJ5", "AGCTGAGTTTCAGATTGAAGAC", "TAAGCTGATCTAACATCATCAC"], ["GCW_01900", "dnaJ6", "GCGTATGAAGTTCTATCTAACCC", "TTAGCTTGATTTGCACTAGCAC"], ["GCW_04075", "dnaJ7", "AGTTAAGAGACTAATTAATCGACCAG", "CAACATTACCCTTACCAAAGAACTC"], ["GCW_01905", "grpE", "TTAGAGTTTGCTTCACTTGACC", "GTTTGAGGTTGTTCTTGTTCAC"], ["GCW_02005", "hrcA", "AATGATCGGTTAGTTGATACCC", "TTCAATCCCAATATCTTGACCA"], ["GCW_02100", "tig", "GAAAACCCAGAAGTTAGCGTAG", "CTCTAATTCGTAGTTTTTCGCC"], ["GCW_03080", "GCW_03080", "CAGATGCAATTACGGTTGTAGG", "TGATTTACGTATTCCAAACGCT"], ["GCW_02930", "GCW_02930", "GCAAAGTTACTGTAACACCAGG", "CGGCATTAACCATTATTTCACC"], ["GCW_00085", "GCW_00085", "CCAATATAATAGCGAAATGGCTG", "GTTAATTAAAGCCACTTCAGCG"], ["GCW_01140", "dps", "AACTTTCACTGAAATATCAAAGGTG", "TTTCATCTAAGATTGGTTGAACACG"], ["GCW_01335", "16S", "AAGTAACGACTAACTATGTGCC", "TAGGGTATCTAATCCTATTTGCTCC"], ["GCW_00395", "23S", "AGAAATACGTAGTCGATGGAAG", "GAGTTCCTTAGCTATAGTTCACTC"], ["GCW_02860", "eno", "GCGATCTTAGCAGTATCAATGG", "ACCTTCATCACCTTTGTTAGTA"], ["GCW_01780", "gapd", "ACGACTTAACTGATGCTAAGAC", "TGGTTCACGTTGTAAACTACAG"], ["GCW_03290", "tpiA", "TATTCGTACATTTGGCTTTGGC", "CTGATCTTTAAGTACAGCTTTGGTC"], ["GCW_01315", "tuf", "TCAAAATCGTCACTATGCACAC", "TCTGATTACTGGAGTGTTATCACC"], ["GCW_00475", "tsf", "AGTTAGCTGATCAAAAAGCAAC", "TTAACAATAACTCCAATGCGGC"], ["GCW_01635", "osmC", "AGCTAAAGTTGGTAGAGAAGGTC", "ATTCTTTAGCCTTAGCTTCTGG"], ["GCW_03005", "GCW_03005", "ATTCATCAGCAACTAAAGTACC", "TCATCAATTACGATTCTTCCAG"], ["GCW_00065", "glpF", "CAGCTAAAAGAATCATAGTGCC", "GTGGTGTGGTTATTAGTATCCAAG"], ["GCW_00075", "glpO", "GATGAATTGCTACTGAAGAGGTG", "ATTCATGGTGGTTTTGATCCTG"], ["GCW_90066", "glpK", "CTCGTTGAGATCACAAACTAGG", "TCTCAGGGACTAAGATTCGTTG"], ["GCW_01615", "gpsA", "TAATGTAGCTAAGGGAATGGACG", "TGTTCAAAAACAATCCCAGTCC"], ["GCW_02750", "acoA", "GTCTTCTGTGTAAACAACAACC", "CGATTGGATCTGATTTCTTAGCTTC"], ["GCW_02745", "acoB", "CTAAAGCTTTAATTCCACCACCC", "GTATTATACGGTCAAGACGCTG"], ["GCW_02740", "aceF", "TAAACCGATCTTCTTAGAGCGAG", "TACCGTAAGCAAGTTAAGGATG"], ["GCW_00390", "ldh", "CGATTACTGCTTCAATTCCAAC", "CTTCAACAGAGTCAGAATTAACACC"], ["GCW_02760", "ackA", "GAAGCACCATTTCCTAAGTGAC", "AGATCTATGAATTAGCCAAGCTC"], ["GCW_01785", "pgk", "CTAAAAACAGTCCAGAACTAGG", "TAAAGGTATTAACCATTCCCCC"], ["GCW_03700", "fba", "GACCATGGTACTTATGAAGGTG", "AAGTAGGGGGATAAATTCCGTG"], ["GCW_03575", "pgi", "CCAGAAGTAAAGATAACCAAAGCC", "ATTATTCCCAACATACTCCGTG"], ["GCW_02725", "pfkA", "GTGGTGATGGTTCATATCAAGG", "AGATCTACGATCTCTTGGGTTG"], ["GCW_03285", "gpmI", "GAGATCACTATTCAAGACAATGACAG", "ACACCACCATCAAAAAAGAAGG"], ["GCW_02720", "pykF", "CCTTATTATGAAGTACCTTACTGGG", "TCTGTCATTGGGAAATAGTGAG"], ["GCW_00160", "tktA1", "AGAATACAAACAAAGCTCACGG", "CACCTTCCCAAATAAATTACGG"], ["GCW_03235", "tktA2", "AGATTACTGAAACGATCCTTGC", "AAAGTTATCGATCTGATCTCGC"], ["GCW_00795", "rpiB", "ATATTCGTAGCTGATCATACAGG", "CAGTTATCATGTTGAATCGCAAG"], ["GCW_03495", "eutD", "GAAGTTGATGGTGAAGTATGTGG", "AACAGATTCACCTACACCTGAG"], ["GCW_03255", "prsA", "CAGCATTTATTCTTCACTTCACC", "CAGATTTACTAACCAAAGCAGG"], ["GCW_02735", "lpd", "AACTTGATCATTAACTACCCGAC", "CAATCATTAGTTGTGATCGGTG"], ["GCW_03295", "cpsG", "ATCTTTACTGGTCAACATGGAG", "GTAATAAGCAAAGATGATCCCC"], ["GCW_02755", "GCW_02755", "AATACTGTGGTGGAATTGAAGG", "TCAGTGTCAACTAAGTATCCCA"], ["GCW_02490", "GCW_02490", "GAATCTAAGCAATCAGCATACGG", "GAAATCACCTACATAATACGGCTTG"], ["GCW_02495", "GCW_02495", "CGTGAGATAAAATTGAAGGTGC", "TGTATAGGTGAGTGTCATCTGG"], ["GCW_01270", "hatA", "ATGAGAACAGAATGTGAGATGG", "GGTTTGTACCGATTTCTCTTCC"], ["GCW_03695", "rpoE", "GGCTTCATTAATTGATAAGGCT", "CCTTCATTGCTAATTTCAGGAGA"], ["GCW_01075", "spoT", "TTATCATCTTCAGTAACCGCAC", "GTGAAATGACATTCTTCTTGAGG"], ["GCW_02645", "GCW_02645", "TATGACCAAAATAAGGAAGTTGCC", "CTTAGAATCTGGTAACAAGTGGAAG"], ["GCW_02635", "GCW_02635", "CAAGAGGTTAAAAGTGAGATCTGTG", "GCTGTTGTTCTTCTAGTTCGTG"], ["GCW_00440", "GCW_00440", "GTACAACCGATTTGATTCCAAG", "AGTTCTTTTACGATATCACAGATCC"], ["GCW_04025", "hprK", "AGAAGTATATGGTGAAGGGGTTC", "GTTCGTTCGAAATTATAAGGTTGG"], ["GCW_03690", "GCW_03690", "GATTAAGCTGGTTAAACGATCTCC", "GTAACTTCTGAATCCCTTCAACC"], ["GCW_03310", "deoC2", "AAGTTTATGAAGCCAAAACCTC", "CTTATTTTGACTGGCTTGTTGC"], ["GCW_03745", "manA", "TTCTACCCCATTTTGAATACCG", "CTAGTGAGTTAAACTGTTTGGC"], ["GCW_03735", "fruA", "TTCCAAACCACAATCAAACCAG", "TTAATGTGAATGCGACTACACC"], ["GCW_00765", "ptsG1", "TGACGAAAATGGACAAAGAGTG", "ATAGATTGGATTAGTGAAGGGTGG"], ["GCW_03100", "ptsG2", "CCTTTGGTATTCTAAGACTAGTAGC", "GGTTAATCTGTTCAGATAAACTGC"], ["GCW_04065", "gyrA", "ATGATGCTTCAGAACAAGAACC", "CAATCTCAGATTTAGCCCGAAC"], ["GCW_04070", "gyrB", "AATAACATTCACACCAACCAAGG", "TAATCTTAGCAGCTTCTTCTGGA"], ["GCW_02325", "parC", "AAACAACCCTAATCCCAAACC", "CTTAAACTAATGCCAGGACCA"], ["GCW_02330", "parE", "CATGACTTCCACCTTCAGAG", "CATTTATTGCCAAAGACGGGA"], ["GCW_03410", "ruvA", "TGCTTCAATCACGATCTCTG", "GCACTGTTAACGATCAATGG"], ["GCW_03405", "ruvB", "TTGTGGGTGATAACGAATGG", "AGCCAGAATAAAGCATTAGACC"], ["GCW_03920", "ligA", "CTTAGGGATGATCTCAGCAG", "GTTACACCTCTAAGTTTCCCA"], ["GCW_00470", "uvrA", "AAACCCTGCTTCACTTACTG", "TTTCCACTACCAGAAACTCC"], ["GCW_00205", "uvrB", "TGTGTTGTCGGAATTAACCT", "ATCGCTTTAGTCATCTCATCAG"], ["GCW_02010", "uvrC", "TATGAAGTGATCTATCGCAGGT", "AGTGACGATCTTATCTGTTTGG"], ["GCW_92149", "uvrD", "GTGTTGTAAGTTATGGTCCGA", "CAGTGGTTTGACGATCATAGG"], ["GCW_02695", "recA", "TGGTATGAGAATCAACTACCTG", "GTAATCCCGAGGTTACAACTG"], ["GCW_01370", "mutM", "GAACGTCATGTGTTAGTACGA", "GCATAAATATTACCGATCCCAG"], ["GCW_03930", "msrA", "AAAGCCGCTACGATACTGTG", "TTATGCCAACTACAAACCAG"], ["GCW_02085", "nfo", "ATTATGTTGTTCACGCTCCT", "ATCAGCCATTGTTTCAAGAC"], ["GCW_00810", "hup1", "AGGCGGAATTCTAGTTTGTG", "ATTATCGCTGAATGTACTGGAG"], ["GCW_02335", "hup2", "ATTTGTGCGAATCTACTGCA", "AATGGCAGACGAAACTAACC"], ["GCW_03435", "ung", "TGATTAATTCTTCCCAACCCAG", "GTAATCATTGGTCAAGATCCGT"], ["GCW_03245", "umuC", "CCAAGTCTAATGGTTCTATCGT", "ATCGCTTGCAGATATCTCAC"], ["GCW_00770", "putA", "CAAAAGCAGGTTATGAATATCGC", "CTTTGATAATGGAGTGTTTAGGG"], ["GCW_02665", "potD", "CAACTGCTTTATTAAACTCTGACTC", "CATTAACCCCTTCAAGACCAAC"], ["GCW_03110", "spxA", "TCATGTATTGGCTGTACGAGAG", "CCATCAATCTTTTAGGAATCCCTG"], ["GCW_93946", "GCW_93946", "GAATGTCTTCGTGTTAAGTGTC", "AAAGCTAATGGGTTGATTGCTC"], ["GCW_02245", "mraW", "TCGAGTTATCAACTAGATCGAG", "GGAAATATCTTCTTGCAGGATG"], ["GCW_03090", "mscL", "AACGTCATCTTAGTTTCAGCAC", "CTTCAACACTTTGAGGTTCTGG"], ["GCW_03085", "GCW_03085", "ATTATCTGTGTCCTTTCATCCG", "CACTTACTTGAGCTAAGAAAGCAG"], ["GCW_93751", "GCW_93751", "CAATAGTTTCAGGAAGACACGG", "ACAGCATCACCATTATTTCCAG"], ["GCW_02300", "GCW_02300", "TAAGTCTTCAGTTTGCTTCACG", "TACTCTTCTAGTTGCTAGTTGTCC"], ["GCW_92301", "GCW_92301", "TATCAAAGCCTTTCTAGCAACG", "CACTATAAGTAGGTTTAGCTCAGG"], ["GCW_01560", "GCW_01560", "AATCTAATCCAGGGACAGTTTC", "GTGGCTACTAGAACATCATATCTAGG"]], "row_count": 95, "column_count": 4, "numeric_cells": 113, "header_rows": 1, "locator": "section[13]/table-wrap[1]#t0010"}}], "gaps": ["asset:data:geo:GSE85777 not downloaded", "asset:data:geo:GSE85777 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "correlation_analysis", "specific": "spearman", "label": "Correlation analysis", "dsl_operations": ["spearman_rho"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Spearman correlation coefficient between biological repeats ranges between 0.93 and 1.00."}}], "targets": [], "gaps": []}, "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": ["spearman_rho"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: spearman."}, "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": ["GSE85777"], "resolved_accessions": ["GSE85777"], "statements": ["Data are available via NCBI Gene Expression Omnibus (GEO) with accession number GSE85777 (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE85777)"], "basis": "The paper names GSE85777 in NCBI Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["spearman_rho"], "assets": ["source:pmid:27942460", "data:geo:GSE85777", "asset:table:pmid:27942460:1", "asset:table:pmid:27942460:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE85777"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:08:59Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 9935, "completion_tokens": 786, "cached_tokens": 656}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:27942460", "type": "paper", "label": "pmid:27942460"}, {"id": "source:pmid:27942460", "type": "manuscript", "label": "PMID 27942460 full text"}, {"id": "data:geo:GSE85777", "type": "dataset", "label": "GEO GSE85777"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:27942460", "type": "paper", "label": "pmid:27942460"}, {"id": "source:pmid:27942460", "type": "manuscript", "label": "PMID 27942460 full text"}, {"id": "data:geo:GSE85777", "type": "dataset", "label": "GEO GSE85777"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-27942460", "type": "extraction", "used": ["source:pmid:27942460"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE85777", "type": "accession_resolution", "used": ["data:geo:GSE85777"], "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:27942460", "parent_hash": "sha256:5441836e31b611439177e2583aee9fd45bb5afadf5d69995c9adb3eb65e8f35a", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:GSE85777 licence not read", "asset:data:geo:GSE85777 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["nvestigation of gene expression we developed microarray design including 3366 probes for 678 genes.", "The study was performed on Agilent one-color microarray with custom design and random-T7 polymerase", "fferent state of this bacteria. We developed microarray design including 3366 probes for 678 genes (", "epresentation of RNA fragments inside genes. Microarray with selected oligos was made by Agilent tec"], "order_basis": "paper_text_order:631", "id": "assay:1"}, {"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["rrelation of normalized fold expression from RT-qPCR (x-axis) and logarithm of fold changes genes", "lation of normalized fold expression from RT-qPCR (x-axis) and logarithm of fold changes genes"], "order_basis": "paper_text_order:4753", "id": "assay:2"}, {"role": "analysis", "definition_id": "correlation_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["spearman_rho"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Spearman correlation coefficient between biological repeats ranges between 0.93 and 1.00."], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T00:47:36+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}}}