{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34575702", "kind": "science-record", "revision": 6, "content_hash": "sha256:8fc92b3721112d908f835e5d20094626876820827a99991a48fcdc78b65b47e7", "created_at": "2026-11-01T15:41:54Z", "updated_at": "2026-11-01T21:26:19Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Differential Expression of Estrogen-Responsive Genes in Women with Psoriasis.", "doi": "10.3390/jpm11090925", "pmid": "34575702", "authors": ["Vladimir Sobolev", "Anna Soboleva", "Elena Denisova", "Malika Denieva", "Eugenia Dvoryankova", "Elkhan Suleymanov", "Olga V Zhukova", "Nikolay Potekaev", "Irina Korsunskaya", "Alexandre Mezentsev"], "journal": "Journal of personalized medicine", "year": 2021, "abstract": "In women, the flow of psoriasis is influenced by each phase of a woman's life cycle. According to previous findings, significant changes in the levels of sex hormones affect the severity of the disease. Aim: The aim of this study was to identify the estrogen-responsive genes that could be responsible for the exacerbation of psoriasis in menopausal women. Methods: Skin samples of lesional skin donated by psoriasis patients (n = 5) were compared with skin samples of healthy volunteers (n = 5) using liquid chromatography-tandem mass spectrometry (LC-MS/MS). The set of differentially expressed proteins was subjected to protein ontology analysis to identify differentially expressed estrogen-responsive proteins. The expression of discovered proteins was validated by qPCR and ELISA on four groups of female participants. The first group included ten psoriasis patients without menopause; the second included eleven postmenopausal patients; the third included five healthy volunteers without menopause; and the fourth included six postmenopausal volunteers. Moreover, the participants' blood samples were used to assess the levels of estradiol, progesterone, and testosterone. Results: We found that the levels of estradiol and progesterone were significantly lower and the levels of testosterone were significantly higher in the blood of patients compared to the control. The protein ontology analysis of LC-MS/MS data identified six proteins, namely HMOX1, KRT19, LDHA, HSPD1, MAPK1, and CA2, differentially expressed in the lesional skin of female patients compared to male patients. ELISA and qPCR experiments confirmed differential expression of the named proteins and their mRNA. The genes encoding the named proteins were differentially expressed in patients compared to volunteers. However, KRT19 and LDHA were not differentially expressed when we compared patients with and without menopause. All genes, except MAPK1, were differentially expressed in patients with menopause compared to the volunteers with menopause. HMOX1, KRT19, HSPD1, and LDHA were differentially expressed in patients without menopause compared to the volunteers without menopause. However, no significant changes were found when we compared healthy volunteers with and without menopause. Conclusion: Our experiments discovered a differential expression of six estrogen-controlled genes in the skin of female patients. Identification of these genes and assessment of the changes in their expression provide insight into the biological effects of estrogen in lesional skin. The results of proteomic analysis are available via ProteomeXchange with identifier PXD021673.", "claims": [{"id": "claim-method", "statement": "Due to small sample size, the data of LC–MS/MS were analyzed with non-parametric statistics using the Mann–Whitney U test.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34575702", "locator": "sections[10] \"2.8. Statistical Analysis\" paragraph 2", "quote": "Due to small sample size, the data of LC–MS/MS were analyzed with non-parametric statistics using the Mann–Whitney U test."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The mass spectrometry proteomics data were deposited to the ProteomeXchange Consortium via the PRIDE partner repository [15] with the dataset identifier PXD021673.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34575702", "locator": "sections[22] \"Data Availability Statement\" paragraph 2", "quote": "The mass spectrometry proteomics data were deposited to the ProteomeXchange Consortium via the PRIDE partner repository [15] with the dataset identifier PXD021673."}], "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:34575702"], "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:PXD021673"], "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:PXD021673"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34575702", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/jpm11090925", "sha256": "sha256:a9644b5caf8b781d4a2ac45a4773aaf4b0439d036e0eeef60472e743a7a35d32", "bytes": 63727, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/jpm11090925", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8465408", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD021673", "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=PXD021673", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD021673", "version": null, "note": "The mass spectrometry proteomics data were deposited to the ProteomeXchange Consortium via the PRIDE partner repository [15] with the dataset identifier PXD021673.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The mass spectrometry proteomics data were deposited to the ProteomeXchange Consortium via the PRIDE partner repository [15] with the dataset identifier PXD021673.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "LC-MS/MS analysis of lesional and normally looking psoriatic skin", "resolution_checked_at": "2026-10-31T18:35:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:34575702:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f375b934092ef49e1c9aeeeba0d120e228d58b38d4c4f1d9a2758f87742e25d8", "bytes": 3112, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#jpm-11-00925-t001", "version": null, "note": "Clinical characteristics of psoriasis patients and volunteers that participated in the LC–MS/MS, qPCR, and ELISA studies.", "structure": {"pmcid": "PMC8465408", "section_index": 4, "section_title": "2.2. Clinical Samples", "row_count": 51, "column_count": 6}, "table": {"label": "Table 1", "caption": "Clinical characteristics of psoriasis patients and volunteers that participated in the LC–MS/MS, qPCR, and ELISA studies.", "rows": [["ID", "Age", "Medical History", "ID", "Age", "Medical History"], ["", "", "LC-MS male patients", "", "", "qPCR/ELISA patients"], ["1", "30", "not reported", "", "", "with menopause"], ["2", "40", "stage 1 arterial hyperten-", "1", "46", "gastritis, cholecystitis,"], ["", "", "sion, hyperuricemia,", "", "", "pancreatitis,"], ["", "", "obesity,", "", "", "hypertension, coronary"], ["3", "68", "psoriatic arthritis,", "", "", "artery disease, angina"], ["", "", "hypertension, stage 2,", "", "", "pectoris, urolithiasis"], ["", "", "bronchitis, dyscirculatory", "2", "46", "hypertension, stage 2,"], ["", "", "encephalopathy,", "", "", "kidney cyst"], ["", "", "hyperuricemia, obesity", "3", "47", "cholecystitis,"], ["", "", "1st degree", "", "", "cholelithiasis"], ["", "", "", "4", "48", "type II diabetes, obesity"], ["", "", "LC-MS female patients", "", "", "stage 3,"], ["1", "48", "stage 2 hypertension", "", "", "arterial hypertension, no-"], ["2", "60", "stage 2 hypertension", "", "", "dular Hashimoto’s thy-"], ["", "", "", "", "", "roiditis, uterine fibroids,"], ["", "", "LC-MS male volunteers", "", "", "cerebrovascular"], ["1", "53", "phlebeurysm", "", "", "disease, discirculatory"], ["2", "77", "arthrosclerosis", "", "", "encephalopathy arte-"], ["", "", "", "", "", "rial hypertension"], ["", "", "LC-MS female volunteers", "5", "51", "tachycardia"], ["1", "39", "white line hernia", "", "", "nodular Hashimoto’s"], ["2", "60", "incisional ventral hernia", "", "", "thyroiditis,"], ["3", "79", "arthrosclerosis, abdomi-", "", "", "osteochondrosis"], ["", "", "nal aortic aneurysm,", "", "", "dorsopathy"], ["", "", "chronic pyelonephritis,", "6", "51", "hypertension, stage 2;"], ["", "", "dyslipidemia,", "7", "53", "hypertension, stage 2;"], ["", "", "hypertension", "", "", "depression;"], ["", "", "", "8", "53", "nodular goiter;"], ["", "", "qPCR/ELISA patients,", "9", "53", "hypertension, stage 2"], ["", "", "without menopause", "", "", "type 2 diabetes, osteo-"], ["1", "19", "not reported", "", "", "arthritis; dorsopathy;"], ["2", "21", "erysipelas, obesity stage", "10", "54", "not reported"], ["", "", "4, cholecystitis, uterine", "", "", "qPCR/ELISA volunteers"], ["", "", "fibroids", "", "", "without menopause"], ["3", "28", "not reported", "1", "26", "not reported"], ["4", "30", "goiter, euthyroid sick", "2", "28", "not reported"], ["", "", "syndrome,", "3", "29", "not reported"], ["5", "32", "bilateral otitis media,", "4", "32", "not reported"], ["", "", "cholecystitis", "5", "33", "not reported"], ["", "", "vaginal yeast infection", "6", "38", "not reported"], ["6", "32", "not reported", "", "", ""], ["7", "32", "diffuse goiter, grade 2;", "", "", "qPCR/ELISA volunteers"], ["8", "36", "depression", "", "", "with menopause"], ["9", "42", "gastritis, pyelonephritis;", "", "", ""], ["", "", "insulin resistance,", "1", "43", "not reported"], ["", "", "hypertension, stage 2,", "2", "49", "not reported"], ["", "", "cerebrovascular disease,", "3", "50", "not reported"], ["", "", "cholecystitis", "4", "55", "not reported"], ["10", "43", "not reported", "5", "57", "not reported"]], "row_count": 51, "column_count": 6, "numeric_cells": 96, "header_rows": 1, "locator": "section[4]/table-wrap[1]#jpm-11-00925-t001"}}, {"id": "asset:table:pmid:34575702:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:93199496984709e8504290310c37b9caab665f8dbdc2a23ae0be9e6794e7e6a6", "bytes": 1127, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[8]/table-wrap[1]#jpm-11-00925-t002", "version": null, "note": "Gene-specific primers used in the qPCR experiments.", "structure": {"pmcid": "PMC8465408", "section_index": 8, "section_title": "2.6. Quantitative PCR", "row_count": 15, "column_count": 5}, "table": {"label": "Table 2", "caption": "Gene-specific primers used in the qPCR experiments.", "rows": [["Gene", "Reference Sequence", "Primer Name", "Primer Sequence", "Product Size, bp"], ["CA2", "NM_000067.3", "CA2 forward", "GGCTGGTTGGTGCTTTGTTT", "118"], ["", "", "CA2 re-verse", "TTGTGAGTGCTCATCACCCT", ""], ["HMOX1", "NM_002133.3", "HMOX1 forward", "GGCCTAAACTTCAGAGGGGG", "99"], ["", "", "HMOX1 reverse", "AGACAGCTGCCACATTAGGG", ""], ["HSPD1", "NM_002156.5", "HSPD1 forward", "CTGGCACGCTCTATAGCCAA", "142"], ["", "", "HSPD1 reverse", "CAGGGGTGGTCACAGGTTTA", ""], ["KRT19", "NM_002276.5", "KRT19 forward", "CCACTACTACACGACCATCCA", "89"], ["", "", "KRT19 reverse", "GTCGATCTGCAGGACAATCC", ""], ["LDHA", "NM_005566.4", "LDHA forward", "TAAGCTGTCATGGGTGGGTC", "100"], ["", "", "LDHA reverse", "GGGTGCAGAGTCTTCAGAGAG", ""], ["MAPK1", "NM_002745.5", "MAPK1 forward", "CAGTTCTTGACCCCTGGTCC", "186"], ["", "", "MAPK1 reverse", "TACATACTGCCGCAGGTCAC", ""], ["18S RNA", "NR_003286.2", "18S RNA forward", "CTACCACATCCAAGGAAGCA", "103"], ["", "", "18S RNA reverse", "TTTTTCGTCACTACCTCCCCG", ""]], "row_count": 15, "column_count": 5, "numeric_cells": 20, "header_rows": 1, "locator": "section[8]/table-wrap[1]#jpm-11-00925-t002"}}, {"id": "asset:table:pmid:34575702:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6fc0747a3d33645033862ed1cebae2ba5fa83cbba00c010ee2657d925f638e5c", "bytes": 896, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#jpm-11-00925-t003", "version": null, "note": "The levels of sex hormones in blood samples of qPCR/ELISA participants with and without menopause. pM and nM are concentrations (pmol/L and nmol/L, respectively).", "structure": {"pmcid": "PMC8465408", "section_index": 12, "section_title": "3.1. The Blood of Female Psoriasis Patients Contains Less Estradiol and Progesterone, and More Testosterone Compared to the Healthy Volunteers", "row_count": 11, "column_count": 5}, "table": {"label": "Table 3", "caption": "The levels of sex hormones in blood samples of qPCR/ELISA participants with and without menopause. pM and nM are concentrations (pmol/L and nmol/L, respectively).", "rows": [["Group of Participants", "N", "Estradiol, pM", "Progesterone, nM", "Testosterone, nM"], ["Volunteers without", "6", "480.63 ± 157.43", "8.18 ± 2.47", "0.406 ± 0.078"], ["menopause", "", "", "", ""], ["Volunteers with", "5", "53.8 ± 15.91", "0.973 ± 0.206", "0.733 ± 0.061"], ["menopause", "", "", "", ""], ["p-value", "", "0.026", "0.018", "0.018"], ["Patients without", "10", "116.32 ± 45.85", "0.159 ± 0.013", "1.708 ± 0.362"], ["menopause", "", "", "", ""], ["Patients with", "10", "14.51 ± 0.44", "0.110 ± 0.011", "3.428 ± 0.368"], ["menopause", "", "", "", ""], ["p-value", "", "0.0495", "0.011", "0.005"]], "row_count": 11, "column_count": 5, "numeric_cells": 22, "header_rows": 1, "locator": "section[12]/table-wrap[1]#jpm-11-00925-t003"}}, {"id": "asset:table:pmid:34575702:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:80a64938d20b1fbb4a826f80e3c25c87fb8c913e24db843ded61661cabb7ec42", "bytes": 2449, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#jpm-11-00925-t004", "version": null, "note": "The ontology analysis of proteins differentially expressed in female lesional and uninvolved skin. The analyzed proteins were differentially expressed in female lesional and uninvolved skin and were not differentially expressed in male lesional and uninvolved skincompared to the skin of healthy volunteers.", "structure": {"pmcid": "PMC8465408", "section_index": 13, "section_title": "3.2. LC–MS/MS Study Identifies Six Estrogen-Responsive Proteins That Are Differentially Expressed in Male and Female Psoriatic Skin", "row_count": 15, "column_count": 4}, "table": {"label": "Table 4", "caption": "The ontology analysis of proteins differentially expressed in female lesional and uninvolved skin. The analyzed proteins were differentially expressed in female lesional and uninvolved skin and were not differentially expressed in male lesional and uninvolved skincompared to the skin of healthy volunteers.", "rows": [["Term", "Genes", "p-Value", "FDR"], ["Translational initiation", "RPL30, RPL10, RPS7, RPS8, RPL11, RPL13A, RPL23A, RPS15, RPS27, RPS19, RPL14, EIF3C, RPL28, EIF3D, EIF4G1, RPS12", "8.59 × 10−15", "6.62 × 10−12"], ["Nuclear-transcribed mRNA catabolic process, nonsense- mediated decay", "RPL30, RPL10, RPS7, RPS8, RPL11, RPL13A, RPL23A, RPS15, RPS27, RPS19, RPL14, RPL28, EIF4G1, RPS12", "6.03 × 10−13", "1.89 × 10−10"], ["SRP-dependent cotranslational protein targeting to membrane", "RPL30, RPL10, RPS7, RPS8, RPL11, RPL13A, RPL23A, RPS15, RPS27, RPS19, RPL14, RPL28, RPS12", "7.37 × 10−13", "1.89 × 10−10"], ["Viral transcription", "RPL30, RPL10, RPS7, RPS8, RPL11, RPL13A, RPL23A, RPS15, RPS27, RPS19, RPL14, RPL28, RPS12", "6.20 × 10−12", "1.19 × 10−9"], ["Translation", "RPL30, RPL10, RPS7, RPS8, RPL11, RPL13A, SARS, RPL23A, RPS15, RPS27, RPS19, RPL14, RPL28, EIF4G1, RPS12", "7.59 × 10−10", "1.17 × 10−7"], ["rRNA processing", "RPL30, RPL10, RPS7, RPS8, RPL11, RPL13A, DDX21, RPL23A, RPS15, RPS27, RPS19, RPL14, RPL28, RPS12", "1.03 × 10−9", "1.32 × 10−7"], ["Cell-cell adhesion", "LDHA, AHNAK, HSPA5, RPL14, TACSTD2, EFHD2, RPL23A, TAGLN2, ENO1, ALDOA, SPTBN2, EIF4G1", "1.24 × 10−6", "1.37 × 10−4"], ["Regulation of mRNA stability", "PSMD6, PSMD7, PSMD13, PSMC1, PSMD3, HSPB1, HSPA1B, EIF4G1", "4.20 × 10−6", "4.04 × 10−4"], ["Response to estrogen", "LDHA, KRT19, CA2, HMOX1, MAPK1, HSPD1", "5.83 × 10−5", "4.81 × 10−3"], ["Glycolytic process", "GPI, LDHA, PGAM1, ENO1, ALDOA", "6.24 × 10−5", "4.81 × 10−3"], ["Regulation of cellular amino acid metabolic process", "PSMD6, PSMD7, PSMD13, PSMC1, PSMD3", "3.09 × 10−4", "0.022"], ["Canonical glycolysis", "GPI, PGAM1, ENO1, ALDOA", "5.88 × 10−4", "0.038"], ["Antigen processing and presentation of exogenous peptide antigen via MHC class I, TAP-dependent", "PSMD6, PSMD7, PSMD13, PSMC1, PSMD3", "6.95 × 10−4", "0.041"], ["NIK/NF-κB signaling", "PSMD6, PSMD7, PSMD13, PSMC1, PSMD3", "8.29 × 10−4", "0.046"]], "row_count": 15, "column_count": 4, "numeric_cells": 40, "header_rows": 1, "locator": "section[13]/table-wrap[1]#jpm-11-00925-t004"}}, {"id": "asset:table:pmid:34575702:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:78c3bd318025b89e49819b387fd044e3007c251848649d4146628ffc205a33f7", "bytes": 1892, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[2]#jpm-11-00925-t005", "version": null, "note": "The ontology analysis of proteins differentially expressed in male lesional and uninvolved skin. The analyzed proteins were differentially expressed in male lesional and uninvolved skin and were not differentially expressed in female lesional and uninvolved skin compared to the skin of healthy volunteers.", "structure": {"pmcid": "PMC8465408", "section_index": 13, "section_title": "3.2. LC–MS/MS Study Identifies Six Estrogen-Responsive Proteins That Are Differentially Expressed in Male and Female Psoriatic Skin", "row_count": 12, "column_count": 4}, "table": {"label": "Table 5", "caption": "The ontology analysis of proteins differentially expressed in male lesional and uninvolved skin. The analyzed proteins were differentially expressed in male lesional and uninvolved skin and were not differentially expressed in female lesional and uninvolved skin compared to the skin of healthy volunteers.", "rows": [["Term", "Genes", "p-Value", "FDR"], ["SRP-dependent cotran- slational protein targe- ting to membrane", "RPS28, RPS16, RPL32, RPL23, RPL37A, RPL35A, FAU, RPL8, SRP14, RPL17, RPL19", "4.74 × 10−9", "4.95 × 10−6"], ["Translational initiation", "RPS28, RPS16, RPL32, EIF6, RPL23, RPL37A, RPL35A, FAU, RPL8, RPL17, RPL19", "1.79 × 10−7", "9.32 × 10−5"], ["Viral transcription", "RPS28, RPS16, RPL32, RPL23, RPL37A, RPL35A, FAU, RPL8, RPL17, RPL19", "3.32 × 10−7", "1.16 × 10−4"], ["Nuclear-transcribed mRNA catabolic process, nonsense- mediated decay", "RPS28, RPS16, RPL32, RPL23, RPL37A, RPL35A, FAU, RPL8, RPL17, RPL19", "5.57 × 10−7", "1.45 × 10−4"], ["Translation", "RPS28, RPS16, RPL32, RPL23, RPL37A, RPL35A, FAU, RPL8, RPL17, SLC25A6, RPL19", "4.33 × 10−5", "0.009"], ["Negative regulation of endopeptidase activity", "CSTB, CSTA, ITIH2, SERPIND1, SERPINF1, SERPINH1, SERPING1, COL6A3", "6.01 × 10−5", "0.010"], ["rRNA processing", "RPS28, RPS16, RPL32, RPL23, RPL37A, RPL35A, FAU, RPL8, RPL17, RPL19", "6.56 × 10−5", "0.010"], ["Regulation of comple- ment activation", "CFH, C9, C8B, PHB2, C8A", "9.86 × 10−5", "0.013"], ["Complement activation alternative pathway", "CFH, C9, C8B, C8A", "1.43 × 10−4", "0.017"], ["Cell-cell adhesion", "CNN2, PDLIM1, LAD1, DDX3X, ATIC, CTTN, RUVBL1, CHMP4B, PARK7, CNN3", "3.86 × 10−4", "0.040"], ["DNA duplex unwinding", "DDX3X, XRCC5, DDX1, RUVBL2, RUVBL1", "4.47 × 10−4", "0.042"]], "row_count": 12, "column_count": 4, "numeric_cells": 28, "header_rows": 1, "locator": "section[13]/table-wrap[2]#jpm-11-00925-t005"}}], "gaps": ["asset:data:geo:PXD021673 not downloaded", "asset:data:geo:PXD021673 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": "PCA"}}, {"id": "method-2", "family": null, "specific": null, "label": "Mann–Whitney U test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Due to small sample size, the data of LC–MS/MS were analyzed with non-parametric statistics using the Mann–Whitney U test."}}], "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": ["PXD021673"], "resolved_accessions": ["PXD021673"], "statements": ["The mass spectrometry proteomics data were deposited to the ProteomeXchange Consortium via the PRIDE partner repository [15] with the dataset identifier PXD021673."], "basis": "The paper names PXD021673 in ProteomeXchange Consortium via the PRIDE partner repository 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:34575702", "data:geo:PXD021673", "asset:table:pmid:34575702:1", "asset:table:pmid:34575702:2", "asset:table:pmid:34575702:3", "asset:table:pmid:34575702:4", "asset:table:pmid:34575702:5"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD021673"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:35:11Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 49765, "completion_tokens": 750, "cached_tokens": 520}}, "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:34575702", "type": "paper", "label": "pmid:34575702"}, {"id": "source:pmid:34575702", "type": "manuscript", "label": "PMID 34575702 full text"}, {"id": "data:geo:PXD021673", "type": "dataset", "label": "GEO PXD021673"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34575702", "type": "paper", "label": "pmid:34575702"}, {"id": "source:pmid:34575702", "type": "manuscript", "label": "PMID 34575702 full text"}, {"id": "data:geo:PXD021673", "type": "dataset", "label": "GEO PXD021673"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34575702", "type": "extraction", "used": ["source:pmid:34575702"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD021673", "type": "accession_resolution", "used": ["data:geo:PXD021673"], "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:34575702", "parent_hash": "sha256:350c68f448f37dc23b4c872392dc0091dd39d5c5accc941f71eceb392412f8e3", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:PXD021673 licence not read", "asset:data:geo:PXD021673 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "mass_spectrometry", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["s (n = 5) using liquid chromatography-tandem mass spectrometry (LC-MS/MS). The set of differentially expres", "uid chromatography-tandem mass spectrometry (LC-MS/MS). The set of differentially expressed protei", "he control. The protein ontology analysis of LC-MS/MS data identified six proteins, namely HMOX1,", "or Cancer Research, Frederick, MD, USA). The mass spectrometry proteomics data were deposited to the Proteo"], "order_basis": "paper_text_order:564", "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": ["sion of discovered proteins was validated by qPCR and ELISA on four groups of female participa", "atients compared to male patients. ELISA and qPCR experiments confirmed differential expressio", "rs (mean age: 49.2 years). Skin biopsies for qPCR and ELISA assays were obtained from female p", "11 healthy volunteers that we identified as qPCR/ELISA participants. To distinguish the chang"], "order_basis": "paper_text_order:804", "id": "assay:2"}, {"role": "data_generation", "definition_id": "elisa", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["iscovered proteins was validated by qPCR and ELISA on four groups of female participants. The f", "f female patients compared to male patients. ELISA and qPCR experiments confirmed differential", "age: 49.2 years). Skin biopsies for qPCR and ELISA assays were obtained from female participant", "ealthy volunteers that we identified as qPCR/ELISA participants. To distinguish the changes in"], "order_basis": "paper_text_order:813", "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": ["PCA"], "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":"2026-11-04T02:14:56+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}}}