{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:27077079", "kind": "science-record", "revision": 6, "content_hash": "sha256:5f829534fe87377e0065baa85919f10e55c53bd00ccb4de29e2dc51c265b8739", "created_at": "2026-11-01T15:40:17Z", "updated_at": "2026-11-01T21:20:31Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Data set for transcriptional response to depletion of the Shoc2 scaffolding protein.", "doi": "10.1016/j.dib.2016.03.012", "pmid": "27077079", "authors": ["Eric C Rouchka", "Myoungkun Jeoung", "Eun Ryoung Jang", "Jinpeng Liu", "Chi Wang", "Xiaohong Li", "Emilia Galperin"], "journal": "Data in brief", "year": 2016, "abstract": "The Suppressor of Clear, Caenorhabditis elegans Homolog (SHOC2) is a scaffold protein that positively modulates activity of the RAS/ERK1/2 MAP kinase signaling cascade. We set out to understand the ERK1/2 pathway transcriptional response transduced through the SHOC2 scaffolding module. This data article describes raw gene expression within triplicates of kidney fibroblast-like Cos1 cell line expressing non-targeting shRNA (Cos-NT) and triplicates of Cos1 cells depleted of SHOC2 using shRNA (Cos-LV1) upon activation of ERK1/2 pathway by the Epidermal Growth Factor Receptor (EGFR). The data referred here is available in NCBI׳s Gene Expression Omnibus (GEO), accession GEO: GSE67063 as well as NCBI׳s Sequence Read Archive (SRA), accession SRA: SRP056324. A complete analysis of the results can be found in \"Shoc2-tranduced ERK1/2 motility signals - Novel insights from functional genomics\"(Jeoung et al., 2016) [1].", "claims": [{"id": "claim-method", "statement": "Differentially expressed genes were identified by comparing the combined alignments of samples 4, 5 and 6 (LV1) to the combined alignments of samples 1, 2 and 3 (NT) using cuffdiff2 (version 2.1.1) [11] with the multithreading option -p 8 and the minimum alignment count of 7 (--min-alignment-count 7) to determine gene expression levels in Fragments Per Kilobase of transcript per Megabase (FPKM) and differential expression between the two conditions. A false-discovery rate (FDR) corrected q-value cutoff of 0.05 was used to determine differentially expressed genes. Data is available in the Gene Expression Omnibus (GEO) [2], [3] accession GEO: GSE637063 through the direct link http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE67063 as well as through NCBI׳s Sequence Read Archive [4] through the direct link http://www.ncbi.nlm.nih.gov/sra?term=SRP056324.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:27077079", "locator": "sections[9] \"Data acquisition\" paragraph 6", "quote": "Differentially expressed genes were identified by comparing the combined alignments of samples 4, 5 and 6 (LV1) to the combined alignments of samples 1, 2 and 3 (NT) using cuffdiff2 (version 2.1.1) [11] with the multithreading option -p 8 and the minimum alignment count of 7 (--min-alignment-count 7) to determine gene expression levels in Fragments Per Kilobase of transcript per Megabase (FPKM) and differential expression between the two conditions."}, {"asset": "source:pmid:27077079", "locator": "sections[9] \"Data acquisition\" paragraph 6", "quote": "A false-discovery rate (FDR) corrected q-value cutoff of 0.05 was used to determine differentially expressed genes."}, {"asset": "source:pmid:27077079", "locator": "sections[5] \"Data\" paragraph 2", "quote": "Data is available in the Gene Expression Omnibus (GEO) [2], [3] accession GEO: GSE637063 through the direct link http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE67063 as well as through NCBI׳s Sequence Read Archive [4] through the direct link http://www.ncbi.nlm.nih.gov/sra?term=SRP056324."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data referred here is available in NCBI׳s Gene Expression Omnibus (GEO), accession GEO: GSE67063 as well as NCBI׳s Sequence Read Archive (SRA), accession SRA: SRP056324.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:27077079", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The data referred here is available in NCBI׳s Gene Expression Omnibus (GEO), accession GEO: GSE67063 as well as NCBI׳s Sequence Read Archive (SRA), accession SRA: SRP056324."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "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:27077079"], "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": "blocked", "blocked_on": "data:accession_absent", "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": [], "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": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:27077079", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2016.03.012", "sha256": "sha256:c5ef25b0a4e70eebfdaad701a95542f934fae0ea8c155d7d38d713840a54a88b", "bytes": 17454, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2016.03.012", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4816878", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:27077079:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:cec9c331c610e178fa47b8f9cf1ae2a8eb662929d01e6f94d3cbe14953ae94e2", "bytes": 589, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[1]#t0005", "version": null, "note": "Sample information.", "structure": {"pmcid": "PMC4816878", "section_index": 7, "section_title": "Experimental design", "row_count": 7, "column_count": 4}, "table": {"label": "Table 1", "caption": "Sample information.", "rows": [["Sample number", "Sample name", "Sample description", "GEO sample ID"], ["1", "Cos-NT1", "Non-targeting, replicate 1", "GSM1637966"], ["2", "Cos-NT2", "Non-targeting, replicate 2", "GSM1637967"], ["3", "Cos-NT3", "Non-targeting, replicate 3", "GSM1637968"], ["4", "Cos-LV1", "SHOC2-depleted, replicate 1", "GSM1637969"], ["5", "Cos-LV2", "SHOC2-depleted, replicate 2", "GSM1637970"], ["6", "Cos-LV3", "SHOC2-depleted, replicate 3", "GSM1637971"]], "row_count": 7, "column_count": 4, "numeric_cells": 18, "header_rows": 1, "locator": "section[7]/table-wrap[1]#t0005"}}, {"id": "asset:table:pmid:27077079:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4d04a4c807080492bf84b16f33145573e30f09fe4a30f0e02bc87a920c958622", "bytes": 858, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#t0010", "version": null, "note": "Read trimming and alignment information.", "structure": {"pmcid": "PMC4816878", "section_index": 9, "section_title": "Data acquisition", "row_count": 7, "column_count": 7}, "table": {"label": "Table 2", "caption": "Read trimming and alignment information.", "rows": [["Sample name", "Raw reads", "Raw bases", "Reads after trimming", "Bases after trimming", "Aligned reads", "% Raw reads aligned (%)"], ["Cos-NT1", "42,952,132", "2,154,871,134", "38,607,172", "1,501,729,353", "36,207,885", "84.3"], ["Cos-NT2", "38,735,131", "1,942,967,564", "34,782,083", "1,355,688,866", "32,331,306", "83.5"], ["Cos-NT3", "44,044,083", "2,209,603,724", "39,381,284", "1,528,332,458", "36,772,731", "83.5"], ["Cos-LV1", "43,474,834", "2,180,981,048", "39,011,336", "1,518,169,588", "36,519,959", "84.0"], ["Cos-LV2", "48,201,304", "2,417,879,938", "43,104,467", "1,675,700,194", "39,878,182", "82.7"], ["Cos-LV3", "40,265,842", "2,019,730,082", "35,969,848", "1,396,805,479", "33,394,305", "82.9"]], "row_count": 7, "column_count": 7, "numeric_cells": 36, "header_rows": 1, "locator": "section[9]/table-wrap[1]#t0010"}}, {"id": "asset:table:pmid:27077079:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b877c9d2dde0aa84d2263240498502b41f18fe7001fd7770d9e597e3b1d5f870", "bytes": 1175, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[2]#t0015", "version": null, "note": "RNA-Seq pipeline commands.", "structure": {"pmcid": "PMC4816878", "section_index": 9, "section_title": "Data acquisition", "row_count": 16, "column_count": 2}, "table": {"label": "Table 3", "caption": "RNA-Seq pipeline commands.", "rows": [["Task", "Command"], ["QA/QC", "fastqc <fastqFN> -o <FASTQC_DIRECTORY>"], ["Trimming", "java –classpath Trimmomatic-0.27.far TrimmomaticSE /"], ["–phred33 <fastqIN_FN> <fastqOUT_FN> SLIDINGWINDOW:3:20"], ["Alignment", "tophat2 -p 4 -o <outputdir> -G genes.gtf /"], ["--no-coverage-search ChSa <trimmed_fastq_file>"], ["Transcript detection", "cufflinks -p 4 -o <CUFF_OUT_FN> -G genes.gtf <CONDITION_DIR>/accepted_hits.bam"], ["Transcript merging", "cuffmerge –o cuffmerg_out –s cs1.fa samples.gtf.txt"], ["Differential expression", "cuffdiff -o cuffdiff_out -p 8 --min-alignment-count 7/"], ["-u cuffmerg_out_gtf/merged.gtf /"], ["Cos-NT.1_1.fastq.trim.tophat2.newFasta/accepted_hits.bam,/"], ["Cos-NT#2_1.fastq.trim.NewFasta.tophat2/accepted_hits.bam,/"], ["Cos-NT.3_1.fastq.trim.tophat2.newFasta/accepted_hits.bam/"], ["Cos-LV1#4_1.fastq.trim.NewFasta.tophat2/accepted_hits.bam,/"], ["Cos-LV1.5_1.fastq.trim.tophat2.newFasta/accepted_hits.bam,/"], ["Cos-LV1.6_1.fastq.trim.tophat2.newFasta/accepted_hits.bam"]], "row_count": 16, "column_count": 2, "numeric_cells": 11, "header_rows": 1, "locator": "section[9]/table-wrap[2]#t0015"}}, {"id": "asset:table:pmid:27077079:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a4adab485486b66a6336bcfe7ddb3911ec26c597e4f5763fefc7fe32bdd3d11e", "bytes": 451, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[3]#t0020", "version": null, "note": "Differentially expressed genes (DEGs) as determined by cuffdiff, NT (control) vs. LV1 (SHOC2 depleted) (q-value ≤ 0.05).", "structure": {"pmcid": "PMC4816878", "section_index": 9, "section_title": "Data acquisition", "row_count": 4, "column_count": 4}, "table": {"label": "Table 4", "caption": "Differentially expressed genes (DEGs) as determined by cuffdiff, NT (control) vs. LV1 (SHOC2 depleted) (q-value ≤ 0.05).", "rows": [["Method", "Up-regulated", "Down-regulated", "Total"], ["Genes with Ensembl ID", "1443", "1700", "3143"], ["Unique Ensembl IDs", "1367", "1678", "3045"], ["C. sabaeus ESTs", "386", "378", "764"]], "row_count": 4, "column_count": 4, "numeric_cells": 9, "header_rows": 1, "locator": "section[9]/table-wrap[3]#t0020"}}, {"id": "asset:table:pmid:27077079:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6e279f98602b7ddb000bdb1b3a735d9388a6354513c905954f0eaaac762c5df3", "bytes": 1589, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[4]#t0025", "version": null, "note": "Top 20 differentially expressed genes (out of 853) (fold change >1.5, FDR <0.05).", "structure": {"pmcid": "PMC4816878", "section_index": 9, "section_title": "Data acquisition", "row_count": 21, "column_count": 6}, "table": {"label": "Table 5", "caption": "Top 20 differentially expressed genes (out of 853) (fold change >1.5, FDR <0.05).", "rows": [["Symbol", "Log2CPM", "FPKM", "Log ratio", "p-Value", "FDR"], ["AMOT", "10.37994", "11758", "0.683", "7.23E−61", "3.08E−58"], ["GLA", "8.609800", "5982", "−1.307", "5.02E−153", "6.15E−150"], ["LGALS3BP", "8.017922", "4571", "−1.613", "8.44E−184", "4.13E−180"], ["MYC", "7.994633", "4089", "−1.234", "1.21E−153", "1.69E−150"], ["NCAPG2", "8.166777", "2593", "0.590", "1.78E−47", "4.59E−45"], ["NEFM", "7.523503", "2574", "−0.683", "3.22E−54", "1.21E−51"], ["NDRG1", "7.313191", "2566", "−1.487", "6.95E−179", "2.27E−175"], ["SLIT2", "8.260966", "2254", "1.096", "4.64E−171", "1.14E−167"], ["SLC39A10", "7.265485", "2199", "−1.038", "2.58E−31", "2.87E−29"], ["MLLT4", "7.894645", "2118", "0.591", "1.82E−33", "2.35E−31"], ["NPTX1", "7.196138", "2049", "−0.807", "1.50E−35", "2.20E−33"], ["KRT8", "5.567323", "1816", "−0.880", "6.29E−51", "1.99E−48"], ["TRIB1", "6.685121", "1736", "−1.387", "8.78E−162", "1.43E−158"], ["TMEM164", "6.816386", "1661", "−0.813", "1.84E−63", "9.46E−61"], ["SORD", "6.845924", "1637", "−0.759", "2.26E-49", "6.71E−47"], ["CLU", "6.777606", "1627", "−0.779", "1.41E−47", "3.73E−45"], ["ADCY3", "6.811043", "1562", "−0.720", "2.13E−40", "4.08E−38"], ["CXCR4", "6.573526", "1514", "−1.437", "1.12E−109", "1.10E−106"], ["ALDH1A2", "6.423321", "1487", "−2.044", "1.57E−238", "1.54E−234"], ["TLE4", "7.369268", "1437", "0.714", "1.21E−55", "4.75E−53"]], "row_count": 21, "column_count": 6, "numeric_cells": 102, "header_rows": 1, "locator": "section[9]/table-wrap[4]#t0025"}}, {"id": "asset:table:pmid:27077079:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:40424c9c4b800aac859b9d419fd4fa7707d531c37dc35e485b4a1e4c347fc2cd", "bytes": 694, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#t0030", "version": null, "note": "Down-regulated genes (n=57) cross-listed as transcription factors in Transfac.", "structure": {"pmcid": "PMC4816878", "section_index": 10, "section_title": "Transcription factor analysis", "row_count": 10, "column_count": 6}, "table": {"label": "Table 6", "caption": "Down-regulated genes (n=57) cross-listed as transcription factors in Transfac.", "rows": [["AHCTF1", "GTF2A1L", "MAF", "NFIX", "SALL4", "TFEB"], ["AR", "GTF2E2", "MAFA", "NKX1-2", "SOX5", "TP53"], ["CAV1", "GTF2F2", "MAMSTR", "NKX6-1", "SP1", "TRIM21"], ["CDH1", "HES5", "MEF2C", "NR2F2", "SP4", "UBE3A"], ["DACH2", "HES7", "MITF", "OLIG2", "SREBF1", "XBP1"], ["E2F4", "HIVEP3", "MLX", "OVOL2", "STAT5B", "ZBTB7B"], ["E2F5", "JUNB", "MYB", "PITX3", "TBX1", "ZNF143"], ["ELF4", "KLF6", "MYC", "POU3F2", "TCEAL3", ""], ["FOXN2", "KLF9", "MYPOP", "POU3F3", "TCF24", ""], ["GHR", "LSR", "NFATC2", "PRR5", "TFB2M", ""]], "row_count": 10, "column_count": 6, "numeric_cells": 6, "header_rows": 0, "locator": "section[10]/table-wrap[1]#t0030"}}, {"id": "asset:table:pmid:27077079:7", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:15771845b85cf5bb9eaf8a7051635727b77d606923640ccbed42ef176605414d", "bytes": 727, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[2]#t0035", "version": null, "note": "Up-regulated genes (n=60) cross-listed as transcription factors in Transfac.", "structure": {"pmcid": "PMC4816878", "section_index": 10, "section_title": "Transcription factor analysis", "row_count": 10, "column_count": 6}, "table": {"label": "Table 7", "caption": "Up-regulated genes (n=60) cross-listed as transcription factors in Transfac.", "rows": [["ACE2", "DMRT3", "FOXP2", "LBX1", "PBRM1", "TCEANC2"], ["ATF5", "EBF2", "GTF2A1", "LMX1B", "PBXIP1", "TCF7L2"], ["BARD1", "ELP2", "GTF2H5", "LZTFL1", "PIR", "TFAP2A"], ["BCLAF1", "EPAS1", "GTF2I", "MTF1", "POU2F1", "TP73"], ["CDX2", "ETV3", "GTF3C3", "NFAT5", "PPARD", "TRRAP"], ["CNOT4", "FHL1", "HINFP", "NFKBIZ", "PRDM16", "TWIST2"], ["CNOT6", "FLI1", "IFI16", "NFYA", "SALL2", "VIM"], ["CREBBP", "FOXC1", "ISL1", "NFYC", "SPEN", "XRCC4"], ["CTBP1", "FOXF2", "KLF12", "NR2F1", "SUPT16H", "YAP1"], ["DACH1", "FOXO4", "L3MBTL1", "NR6A1", "TAX1BP3", "ZEB1"]], "row_count": 10, "column_count": 6, "numeric_cells": 5, "header_rows": 0, "locator": "section[10]/table-wrap[2]#t0035"}}, {"id": "asset:table:pmid:27077079:8", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:58a27c118b6d809436f696d46803cbd44214a8707461725ec0a6a95fde1f08d9", "bytes": 407, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[3]#t0040", "version": null, "note": "Down-regulated genes (n=22) cross-listed as transcription co-factors in TcoF.", "structure": {"pmcid": "PMC4816878", "section_index": 10, "section_title": "Transcription factor analysis", "row_count": 4, "column_count": 6}, "table": {"label": "Table 8", "caption": "Down-regulated genes (n=22) cross-listed as transcription co-factors in TcoF.", "rows": [["AGO2", "EYA2", "HMGA2", "NAB2", "SAP30", "THAP1"], ["BCL3", "FHL2", "MAML3", "NUP62", "SIAH2", "TRIB3"], ["EID2", "HDAC8", "MBD2", "PTRF", "SSBP2", ""], ["ERBB4", "HDAC9", "MTA3", "NAB2", "TGFB1", ""]], "row_count": 4, "column_count": 6, "numeric_cells": 2, "header_rows": 0, "locator": "section[10]/table-wrap[3]#t0040"}}, {"id": "asset:table:pmid:27077079:9", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:616691f2b006776410ba612314b001451472e0ce914b57a991a349450dd0b5b1", "bytes": 486, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[4]#t0045", "version": null, "note": "Up-regulated genes (n=32) cross-listed as transcription co-factors in TcoF.", "structure": {"pmcid": "PMC4816878", "section_index": 10, "section_title": "Transcription factor analysis", "row_count": 5, "column_count": 7}, "table": {"label": "Table 9", "caption": "Up-regulated genes (n=32) cross-listed as transcription co-factors in TcoF.", "rows": [["ATN1", "CRY1", "HIPK2", "PEX14", "POGZ", "SSBP3", "TXNIP"], ["BRD8", "CTBP1", "KDM5A", "PHF1", "RING1", "STK36", "YAP1"], ["CBX8", "ELP2", "MED20", "PIR", "SMAD6", "TAF9B", ""], ["CHD4", "ERCC6", "MED21", "PNRC1", "SMAD7", "TLE4", ""], ["CHD8", "HCFC1", "NSD1", "PNRC2", "SNIP1", "TRRAP", ""]], "row_count": 5, "column_count": 7, "numeric_cells": 4, "header_rows": 0, "locator": "section[10]/table-wrap[4]#t0045"}}, {"id": "asset:table:pmid:27077079:10", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b46ae4beb1f7da31a0bbba3993ca2e5e3edd1214cea77ad86282c4d2c65cd381", "bytes": 911, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#t0050", "version": null, "note": "Gene Ontology Molecular Function (GO:MF) enriched categories determined by Panther.", "structure": {"pmcid": "PMC4816878", "section_index": 11, "section_title": "Categorical enrichment", "row_count": 12, "column_count": 3}, "table": {"label": "Table 10", "caption": "Gene Ontology Molecular Function (GO:MF) enriched categories determined by Panther.", "rows": [["GO Molecular Function", "# of genes", "Percentage (%)"], ["Binding (GO:0005488)", "272", "32.60"], ["Catalytic activity (GO:0003824)", "211", "25.30"], ["Nucleic acid binding transcription factor activity (GO:0001071)", "102", "12.20"], ["Receptor activity (GO:0004872)", "89", "10.70"], ["Transporter activity (GO:0005215)", "62", "7.40"], ["Structural molecule activity (GO:0005198)", "45", "5.40"], ["Enzyme regulator activity (GO:0030234)", "42", "5.00"], ["Protein binding transcription factor activity (GO:0000988)", "8", "1.00"], ["Translation regulator activity (GO:0045182)", "1", "0.10"], ["Channel regulator activity (GO:0016247)", "1", "0.10"], ["Antioxidant activity (GO:0016209)", "1", "0.10"]], "row_count": 12, "column_count": 3, "numeric_cells": 33, "header_rows": 1, "locator": "section[11]/table-wrap[1]#t0050"}}, {"id": "asset:table:pmid:27077079:11", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:57635f9113027cf550a445344ae58e266b5a7714070bad4c1983db62b5cc716b", "bytes": 642, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[2]#t0055", "version": null, "note": "Gene Ontology Cellular Component (GO:CC) enriched categories determined by Panther.", "structure": {"pmcid": "PMC4816878", "section_index": 11, "section_title": "Categorical enrichment", "row_count": 9, "column_count": 3}, "table": {"label": "Table 11", "caption": "Gene Ontology Cellular Component (GO:CC) enriched categories determined by Panther.", "rows": [["GO Cellular Component", "# of genes", "Percentage (%)"], ["Cell part (GO:0044464)", "130", "36.00"], ["Organelle (GO:0043226)", "74", "20.50"], ["Membrane (GO:0016020)", "53", "14.70"], ["Extracellular region (GO:0005576)", "48", "13.30"], ["Extracellular matrix (GO:0031012)", "26", "7.20"], ["Macromolecular complex (GO:0032991)", "22", "6.10"], ["Synapse (GO:0045202)", "4", "1.10"], ["Cell junction (GO:0030054)", "4", "1.10"]], "row_count": 9, "column_count": 3, "numeric_cells": 24, "header_rows": 1, "locator": "section[11]/table-wrap[2]#t0055"}}, {"id": "asset:table:pmid:27077079:12", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:12a60223e5a0ce26b37f2954d80a669c8bebc665bc4aab0488b346aa5dd4e4fe", "bytes": 1463, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[3]#t0060", "version": null, "note": "Panther Protein Class enriched categories.", "structure": {"pmcid": "PMC4816878", "section_index": 11, "section_title": "Categorical enrichment", "row_count": 29, "column_count": 3}, "table": {"label": "Table 12", "caption": "Panther Protein Class enriched categories.", "rows": [["Panther Protein Class", "# of Genes", "Percentage (%)"], ["Nucleic acid binding (PC00171)", "102", "11.30"], ["Transcription factor (PC00218)", "98", "10.80"], ["Receptor (PC00197)", "92", "10.20"], ["Hydrolase (PC00121)", "72", "7.90"], ["Transferase (PC00220)", "67", "7.40"], ["Signaling molecule (PC00207)", "63", "7.00"], ["Transporter (PC00227)", "53", "5.80"], ["Enzyme modulator (PC00095)", "53", "5.80"], ["Cytoskeletal protein (PC00085)", "34", "3.80"], ["Oxidoreductase (PC00176)", "34", "3.80"], ["Kinase (PC00137)", "29", "3.20"], ["Protease (PC00190)", "28", "3.10"], ["Extracellular matrix protein (PC00102)", "27", "3.00"], ["Cell adhesion molecule (PC00069)", "22", "2.40"], ["Defense/immunity protein (PC00090)", "19", "2.10"], ["Transfer/carrier protein (PC00219)", "18", "2.00"], ["Membrane traffic protein (PC00150)", "18", "2.00"], ["Calcium-binding protein (PC00060)", "17", "1.90"], ["Phosphatase (PC00181)", "11", "1.20"], ["Ligase (PC00142)", "10", "1.10"], ["Structural protein (PC00211)", "10", "1.10"], ["Cell junction protein (PC00070)", "8", "0.90"], ["Transmembrane receptor regulatory/adaptor protein (PC00226)", "6", "0.70"], ["Lyase (PC00144)", "6", "0.70"], ["Surfactant (PC00212)", "4", "0.40"], ["Chaperone (PC00072)", "3", "0.30"], ["Storage protein (PC00210)", "1", "0.10"], ["Isomerase (PC00135)", "1", "0.10"]], "row_count": 29, "column_count": 3, "numeric_cells": 84, "header_rows": 1, "locator": "section[11]/table-wrap[3]#t0060"}}, {"id": "asset:table:pmid:27077079:13", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c8d33ab0c3d98c32746b5db73587ea98f15fc14aa5f55b8fc65d55b7cd7da5a4", "bytes": 994, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[4]#t0065", "version": null, "note": "Gene Ontology Biological Process (GO:BP) enriched categories determined by Panther.", "structure": {"pmcid": "PMC4816878", "section_index": 11, "section_title": "Categorical enrichment", "row_count": 15, "column_count": 3}, "table": {"label": "Table 13", "caption": "Gene Ontology Biological Process (GO:BP) enriched categories determined by Panther.", "rows": [["Panther Biological Process", "# of genes", "Percentage (%)"], ["Metabolic process (GO:0008152)", "351", "22.00"], ["Cellular process (GO:0009987)", "324", "20.30"], ["Biological regulation (GO:0065007)", "210", "13.10"], ["Developmental process (GO:0032502)", "166", "10.40"], ["Localization (GO:0051179)", "125", "7.80"], ["Multicellular organismal process (GO:0032501)", "109", "6.80"], ["Response to stimulus (GO:0050896)", "93", "5.80"], ["Immune system process (GO:0002376)", "75", "4.70"], ["Cellular component organization or biogenesis (GO:0071840)", "49", "3.10"], ["Biological adhesion (GO:0022610)", "38", "2.40"], ["Apoptotic process (GO:0006915)", "30", "1.90"], ["Reproduction (GO:0000003)", "23", "1.40"], ["Locomotion (GO:0040011)", "5", "0.30"], ["Growth (GO:0040007)", "1", "0.10"]], "row_count": 15, "column_count": 3, "numeric_cells": 42, "header_rows": 1, "locator": "section[11]/table-wrap[4]#t0065"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "cuffdiff2 differential expression analysis using an FDR-corrected q-value cutoff of 0.05; source data are available through GEO accession GSE67063 and SRA accession SRP056324", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "reordered", "quote": "Differentially expressed genes were identified by comparing the combined alignments of samples 4, 5 and 6 (LV1) to the combined alignments of samples 1, 2 and 3 (NT) using cuffdiff2 (version 2.1.1) [11] with the multithreading option -p 8 and the minimum alignment count of 7 (--min-alignment-count 7) to determine gene expression levels in Fragments Per Kilobase of transcript per Megabase (FPKM) and differential expression between the two conditions. A false-discovery rate (FDR) corrected q-value cutoff of 0.05 was used to determine differentially expressed genes. Data is available in the Gene Expression Omnibus (GEO) [2], [3] accession GEO: GSE637063 through the direct link http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE67063 as well as through NCBI׳s Sequence Read Archive [4] through the direct link http://www.ncbi.nlm.nih.gov/sra?term=SRP056324."}}], "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": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (cuffdiff2 differential expression analysis using an FDR-corrected q-value cutoff of 0.05; source data are available through GEO accession GSE67063 and SRA accession SRP056324), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "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": "R4", "reachable": false, "accessions": ["GEO: GSE67063", "SRA: SRP056324"], "resolved_accessions": [], "statements": ["The data referred here is available in NCBI׳s Gene Expression Omnibus (GEO), accession GEO: GSE67063 as well as NCBI׳s Sequence Read Archive (SRA), accession SRA: SRP056324."], "basis": "The paper names GEO: GSE67063, SRA: SRP056324, but the accession does not resolve in the repository (no reason recorded, no reason recorded), so the data cannot be reached from here. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:27077079", "asset:table:pmid:27077079:1", "asset:table:pmid:27077079:2", "asset:table:pmid:27077079:3", "asset:table:pmid:27077079:4", "asset:table:pmid:27077079:5", "asset:table:pmid:27077079:6", "asset:table:pmid:27077079:7", "asset:table:pmid:27077079:8", "asset:table:pmid:27077079:9", "asset:table:pmid:27077079:10", "asset:table:pmid:27077079:11", "asset:table:pmid:27077079:12", "asset:table:pmid:27077079:13"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:07:55Z", "independence": "same_provider"}, "evidence_check": {"method": "reordered", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 15687, "completion_tokens": 2189, "cached_tokens": 648}}, "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:27077079", "type": "paper", "label": "pmid:27077079"}, {"id": "source:pmid:27077079", "type": "manuscript", "label": "PMID 27077079 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:27077079", "type": "paper", "label": "pmid:27077079"}, {"id": "source:pmid:27077079", "type": "manuscript", "label": "PMID 27077079 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-27077079", "type": "extraction", "used": ["source:pmid:27077079"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "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:27077079", "parent_hash": "sha256:6be0b92080463ea768e3181dba8d0bdeebe962f0bfad3d0081862515b06b3f7e", "fork_of": null, "generation": 5}, "gaps": ["execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"role": "data_generation", "definition_id": "transfection", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["like Cos1 cell line expressing non-targeting shRNA (Cos-NT) and triplicates of Cos1 cells deple", "icates of Cos1 cells depleted of SHOC2 using shRNA (Cos-LV1) upon activation of ERK1/2 pathway", "d with lentiviruses that carry non-targeting shRNA (NT) or lentiviruses carrying the shRNA targ", "ting shRNA (NT) or lentiviruses carrying the shRNA targeting SHOC2 (LV1). The stable cells (Cos"], "order_basis": "paper_text_order:460", "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": 0.93, "evidence": ["zer (Agilent Technologies, Santa Clara, CA). RNA-Seq libraries were constructed in the University"], "order_basis": "paper_text_order:2454", "id": "assay:2"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T01:50:32+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}}}