Predicting the targets of IRF8 and NFATc1 during osteoclast differentiation using the machine learning method framework cTAP.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34991467", "kind": "science-record", "revision": 5, "content_hash": "sha256:156df7abc50e3a4867b687d951c206ae2bff1b42eb10409d43d76a423ca8d870", "created_at": "2026-11-01T17:36:42Z", "updated_at": "2026-11-01T22:48:10Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Predicting the targets of IRF8 and NFATc1 during osteoclast differentiation using the machine learning method framework cTAP.", "doi": "10.1186/s12864-021-08159-z", "pmid": "34991467", "authors": ["Honglin Wang", "Pujan Joshi", "Seung-Hyun Hong", "Peter F Maye", "David W Rowe", "Dong-Guk Shin"], "journal": "BMC genomics", "year": 2022, "abstract": "BACKGROUND: Interferon regulatory factor-8 (IRF8) and nuclear factor-activated T cells c1 (NFATc1) are two transcription factors that have an important role in osteoclast differentiation. Thanks to ChIP-seq technology, scientists can now estimate potential genome-wide target genes of IRF8 and NFATc1. However, finding target genes that are consistently up-regulated or down-regulated across different studies is hard because it requires analysis of a large number of high-throughput expression studies from a comparable context.\nMETHOD: We have developed a machine learning based method, called, Cohort-based TF target prediction system (cTAP) to overcome this problem. This method assumes that the pathway involving the transcription factors of interest is featured with multiple \"functional groups\" of marker genes pertaining to the concerned biological process. It uses two notions, Gene-Present Sufficiently (GP) and Gene-Absent Insufficiently (GA), in addition to log2 fold changes of differentially expressed genes for the prediction. Target prediction is made by applying multiple machine-learning models, which learn the patterns of GP and GA from log2 fold changes and four types of Z scores from the normalized cohort's gene expression data. The learned patterns are then associated with the putative transcription factor targets to identify genes that consistently exhibit Up/Down gene regulation patterns within the cohort. We applied this method to 11 publicly available GEO data sets related to osteoclastgenesis.\nRESULT: Our experiment identified a small number of Up/Down IRF8 and NFATc1 target genes as relevant to osteoclast differentiation. The machine learning models using GP and GA produced NFATc1 and IRF8 target genes different than simply using a log2 fold change alone. Our literature survey revealed that all predicted target genes have known roles in bone remodeling, specifically related to the immune system and osteoclast formation and functions, suggesting confidence and validity in our method.\nCONCLUSION: cTAP was motivated by recognizing that biologists tend to use Z score values present in data sets for the analysis. However, using cTAP effectively presupposes assembling a sizable cohort of gene expression data sets within a comparable context. As public gene expression data repositories grow, the need to use cohort-based analysis method like cTAP will become increasingly important.", "claims": [{"id": "claim-method", "statement": "For computational experiments, we used four well-established machine-learning models, SVM, LR, Gaussian NB and NN, to classify gene regulation patterns and compared their performances.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34991467", "locator": "sections[12] \"Training and evaluation\" paragraph 2", "quote": "For computational experiments, we used four well-established machine-learning models, SVM, LR, Gaussian NB and NN, to classify gene regulation patterns and compared their performances."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All data analyzed during this study are included in this article. Data and codes are available at https://github.uconn.edu/how17003/cTAP.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34991467", "locator": "sections[18] \"notes\" paragraph 1", "quote": "All data analyzed during this study are included in this article. Data and codes are available at https://github.uconn.edu/how17003/cTAP."}], "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:34991467"], "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:GSE111237"], "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:GSE111237"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34991467", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12864-021-08159-z", "sha256": "sha256:bf6a84bcf01790b578b395fa7d5bdf6c7994bcddd94e12cef67ba90f5dbef068", "bytes": 58217, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12864-021-08159-z", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8740472", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE111237", "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=GSE111237", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE111237", "version": null, "note": "All data analyzed during this study are included in this article. Data and codes are available at https://github.uconn.edu/how17003/cTAP.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data analyzed during this study are included in this article. Data and codes are available at https://github.uconn.edu/how17003/cTAP.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3026946", "GSM3026947", "GSM3026948", "GSM3026949", "GSM3026950", "GSM3026951", "GSM3026952", "GSM3026953", "GSM3026954", "GSM3026955", "GSM3026956", "GSM3026957", "GSM3026958", "GSM3026959", "GSM3026960", "GSM3026961", "GSM3026962", "GSM3026963"], "sample_count": 18, "group_sizes": null, "group_sizes_basis": null, "platform": "6885", "taxon": "Mus musculus", "title": "Gene expression profiling reveals that ERα controls the mitochondrial biogenesis in LysM-Cre targeted cells", "resolution_checked_at": "2026-11-01T17:30:42Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE135479", "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=GSE135479", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE135479", "version": null, "note": "All data analyzed during this study are included in this article. Data and codes are available at https://github.uconn.edu/how17003/cTAP.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data analyzed during this study are included in this article. Data and codes are available at https://github.uconn.edu/how17003/cTAP.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4011085", "GSM4011086"], "sample_count": 2, "group_sizes": null, "group_sizes_basis": null, "platform": "21103", "taxon": "Mus musculus", "title": "Identification of a novel role for FoxO3 isoform2 in osteoclastic inhibition", "resolution_checked_at": "2026-11-01T17:30:42Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE142866", "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=GSE142866", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE142866", "version": null, "note": "All data analyzed during this study are included in this article. Data and codes are available at https://github.uconn.edu/how17003/cTAP.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data analyzed during this study are included in this article. Data and codes are available at https://github.uconn.edu/how17003/cTAP.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4246812", "GSM4246813", "GSM4246814", "GSM4246815", "GSM4246816", "GSM4246817"], "sample_count": 6, "group_sizes": null, "group_sizes_basis": null, "platform": "17021", "taxon": "Mus musculus", "title": "Ethyl acetate fraction of Lentinula edodes (LEA) inhibits osteoclastogenesis by suppressing NFATc1 expression", "resolution_checked_at": "2026-11-01T17:30:42Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE149887", "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=GSE149887", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE149887", "version": null, "note": "All data analyzed during this study are included in this article. Data and codes are available at https://github.uconn.edu/how17003/cTAP.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data analyzed during this study are included in this article. Data and codes are available at https://github.uconn.edu/how17003/cTAP.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4516348", "GSM4516349", "GSM4516350", "GSM4516351", "GSM4516352", "GSM4516353", "GSM4516354", "GSM4516355", "GSM4516356", "GSM4516357", "GSM4516358", "GSM4516359"], "sample_count": 12, "group_sizes": null, "group_sizes_basis": null, "platform": "21103", "taxon": "Mus musculus", "title": "Differential gene expression in mouse myeloid cells", "resolution_checked_at": "2026-11-01T17:30:42Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE152986", "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=GSE152986", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE152986", "version": null, "note": "All data analyzed during this study are included in this article. Data and codes are available at https://github.uconn.edu/how17003/cTAP.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data analyzed during this study are included in this article. Data and codes are available at https://github.uconn.edu/how17003/cTAP.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4631363", "GSM4631364", "GSM4631365", "GSM4631366", "GSM4631367", "GSM4631368", "GSM4631369", "GSM4631370", "GSM4631371", "GSM4631372", "GSM4631373", "GSM4631374"], "sample_count": 12, "group_sizes": null, "group_sizes_basis": null, "platform": "17791", "taxon": "Mus musculus", "title": "Expression data from RAW264.7 murine cell line", "resolution_checked_at": "2026-11-01T17:30:42Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE17563", "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=GSE17563", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE17563", "version": null, "note": "All data analyzed during this study are included in this article. Data and codes are available at https://github.uconn.edu/how17003/cTAP.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data analyzed during this study are included in this article. Data and codes are available at https://github.uconn.edu/how17003/cTAP.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM437715", "GSM437716", "GSM437717"], "sample_count": 3, "group_sizes": null, "group_sizes_basis": null, "platform": "339", "taxon": "Mus musculus", "title": "Gene expression profiles during osteoclastogenesis", "resolution_checked_at": "2026-11-01T17:30:42Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE20850", "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=GSE20850", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE20850", "version": null, "note": "All data analyzed during this study are included in this article. Data and codes are available at https://github.uconn.edu/how17003/cTAP.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data analyzed during this study are included in this article. Data and codes are available at https://github.uconn.edu/how17003/cTAP.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM521418", "GSM521419"], "sample_count": 2, "group_sizes": null, "group_sizes_basis": null, "platform": "1261", "taxon": "Mus musculus", "title": "Expression data from cultured macrophages and osteoclasts", "resolution_checked_at": "2026-11-01T17:30:42Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE30160", "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=GSE30160", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE30160", "version": null, "note": "All data analyzed during this study are included in this article. Data and codes are available at https://github.uconn.edu/how17003/cTAP.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data analyzed during this study are included in this article. Data and codes are available at https://github.uconn.edu/how17003/cTAP.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM746855", "GSM746856", "GSM746857", "GSM746858", "GSM746859", "GSM746860"], "sample_count": 6, "group_sizes": null, "group_sizes_basis": null, "platform": "1261", "taxon": "Mus musculus", "title": "The RANK IVVY Motif-regulated Genes in Osteoclastogenesis", "resolution_checked_at": "2026-11-01T17:30:42Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE37219", "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=GSE37219", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE37219", "version": null, "note": "All data analyzed during this study are included in this article. Data and codes are available at https://github.uconn.edu/how17003/cTAP.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data analyzed during this study are included in this article. Data and codes are available at https://github.uconn.edu/how17003/cTAP.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM913972", "GSM913973", "GSM913974", "GSM913975"], "sample_count": 4, "group_sizes": null, "group_sizes_basis": null, "platform": "8321", "taxon": "Mus musculus", "title": "Comparison expression data from wild-type and NFATc1-deficient osteoclasts", "resolution_checked_at": "2026-11-01T17:30:42Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE57468", "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=GSE57468", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE57468", "version": null, "note": "All data analyzed during this study are included in this article. Data and codes are available at https://github.uconn.edu/how17003/cTAP.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data analyzed during this study are included in this article. Data and codes are available at https://github.uconn.edu/how17003/cTAP.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1383260", "GSM1383261", "GSM1383262", "GSM1383263", "GSM1387103", "GSM1387104", "GSM1387105", "GSM1387106"], "sample_count": 8, "group_sizes": null, "group_sizes_basis": null, "platform": "6885", "taxon": "Mus musculus", "title": "Genome-wide expression profiling in bone marrow-derived macrophage (BMM) cells upon RANKL treatment", "resolution_checked_at": "2026-11-01T17:30:42Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE72846", "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=GSE72846", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE72846", "version": null, "note": "All data analyzed during this study are included in this article. Data and codes are available at https://github.uconn.edu/how17003/cTAP.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data analyzed during this study are included in this article. Data and codes are available at https://github.uconn.edu/how17003/cTAP.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1873361", "GSM1873362"], "sample_count": 2, "group_sizes": null, "group_sizes_basis": null, "platform": "17021", "taxon": "Mus musculus", "title": "Targeted proteolysis of the histone H3 tail facilitates epigentic reporgramming during differentiation", "resolution_checked_at": "2026-11-01T17:30:42Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE76988", "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=GSE76988", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE76988", "version": null, "note": "All data analyzed during this study are included in this article. Data and codes are available at https://github.uconn.edu/how17003/cTAP.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data analyzed during this study are included in this article. Data and codes are available at https://github.uconn.edu/how17003/cTAP.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2042144", "GSM2042145", "GSM2042146", "GSM2042147"], "sample_count": 4, "group_sizes": null, "group_sizes_basis": null, "platform": "13112", "taxon": "Mus musculus", "title": "STAT5 is a key transcription factor IL-3-mediated inhibition of RANKL-induced osteoclastogenesis", "resolution_checked_at": "2026-11-01T17:30:42Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE111237 not downloaded", "asset:data:geo:GSE111237 licence not read", "asset:data:geo:GSE135479 not downloaded", "asset:data:geo:GSE135479 licence not read", "asset:data:geo:GSE142866 not downloaded", "asset:data:geo:GSE142866 licence not read", "asset:data:geo:GSE149887 not downloaded", "asset:data:geo:GSE149887 licence not read", "asset:data:geo:GSE152986 not downloaded", "asset:data:geo:GSE152986 licence not read", "asset:data:geo:GSE17563 not downloaded", "asset:data:geo:GSE17563 licence not read", "asset:data:geo:GSE20850 not downloaded", "asset:data:geo:GSE20850 licence not read", "asset:data:geo:GSE30160 not downloaded", "asset:data:geo:GSE30160 licence not read", "asset:data:geo:GSE37219 not downloaded", "asset:data:geo:GSE37219 licence not read", "asset:data:geo:GSE57468 not downloaded", "asset:data:geo:GSE57468 licence not read", "asset:data:geo:GSE72846 not downloaded", "asset:data:geo:GSE72846 licence not read", "asset:data:geo:GSE76988 not downloaded", "asset:data:geo:GSE76988 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "machine_learning", "specific": "support_vector_machine", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "For computational experiments, we used four well-established machine-learning models, SVM, LR, Gaussian NB and NN, to classify gene regulation patterns and compared their performances."}}], "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": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: support_vector_machine."}, "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": ["GSE111237", "GSE142866", "GSE149887", "GSE152986", "GSE17563", "GSE20850", "GSE30160", "GSE37219", "GSE57468", "GSE76988", "GSE72846", "GSE135479"], "resolved_accessions": ["GSE111237", "GSE142866", "GSE149887", "GSE152986", "GSE17563", "GSE20850", "GSE30160", "GSE37219", "GSE57468", "GSE76988", "GSE72846", "GSE135479"], "statements": ["All data analyzed during this study are included in this article. Data and codes are available at https://github.uconn.edu/how17003/cTAP."], "basis": "The paper names GSE111237, GSE142866, GSE149887, GSE152986, GSE17563, GSE20850, GSE30160, GSE37219, GSE57468, GSE76988, GSE72846, GSE135479 in NCBI GEO and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "assets": ["source:pmid:34991467", "data:geo:GSE111237"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE111237"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T17:14:20Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 16677, "completion_tokens": 2925, "cached_tokens": 256}}, "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:34991467", "type": "paper", "label": "pmid:34991467"}, {"id": "source:pmid:34991467", "type": "manuscript", "label": "PMID 34991467 full text"}, {"id": "data:geo:GSE111237", "type": "dataset", "label": "GEO GSE111237"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34991467", "type": "paper", "label": "pmid:34991467"}, {"id": "source:pmid:34991467", "type": "manuscript", "label": "PMID 34991467 full text"}, {"id": "data:geo:GSE111237", "type": "dataset", "label": "GEO GSE111237"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34991467", "type": "extraction", "used": ["source:pmid:34991467"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE111237", "type": "accession_resolution", "used": ["data:geo:GSE111237"], "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:34991467", "parent_hash": "sha256:a36d6734674d1375d17daf322611771f73ed4daa542c86b6c637aae78571b140", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE111237 licence not read", "asset:data:geo:GSE111237 not downloaded", "asset:data:geo:GSE135479 licence not read", "asset:data:geo:GSE135479 not downloaded", "asset:data:geo:GSE142866 licence not read", "asset:data:geo:GSE142866 not downloaded", "asset:data:geo:GSE149887 licence not read", "asset:data:geo:GSE149887 not downloaded", "asset:data:geo:GSE152986 licence not read", "asset:data:geo:GSE152986 not downloaded", "asset:data:geo:GSE17563 licence not read", "asset:data:geo:GSE17563 not downloaded", "asset:data:geo:GSE20850 licence not read", "asset:data:geo:GSE20850 not downloaded", "asset:data:geo:GSE30160 licence not read", "asset:data:geo:GSE30160 not downloaded", "asset:data:geo:GSE37219 licence not read", "asset:data:geo:GSE37219 not downloaded", "asset:data:geo:GSE57468 licence not read", "asset:data:geo:GSE57468 not downloaded", "asset:data:geo:GSE72846 licence not read", "asset:data:geo:GSE72846 not downloaded", "asset:data:geo:GSE76988 licence not read", "asset:data:geo:GSE76988 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "chip_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["ole in osteoclast differentiation. Thanks to ChIP-seq technology, scientists can now estimate pote"], "order_basis": "paper_text_order:279", "id": "assay:1"}, {"role": "analysis", "definition_id": "machine_learning", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["train_classifier", "cross_validate", "roc_auc"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["For computational experiments, we used four well-established machine-learning models, SVM, LR, Gaussian NB and NN, to classify gene regulation patterns and compared their performances."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}