TFmapper: A Tool for Searching Putative Factors Regulating Gene Expression Using ChIP-seq Data.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30416387", "kind": "science-record", "revision": 6, "content_hash": "sha256:eac5bf6cb47ebf311aa5024b5f92c6e81a096e8e356333a654cc0ea4c049ebf1", "created_at": "2026-11-01T15:40:38Z", "updated_at": "2026-11-01T21:21:46Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "TFmapper: A Tool for Searching Putative Factors Regulating Gene Expression Using ChIP-seq Data.", "doi": "10.7150/ijbs.28850", "pmid": "30416387", "authors": ["Jianming Zeng", "Gang Li"], "journal": "International journal of biological sciences", "year": 2018, "abstract": "Background: Next-generation sequencing coupled to chromatin immunoprecipitation (ChIP-seq), DNase I hypersensitivity (DNase-seq) and the transposase-accessible chromatin assay (ATAC-seq) has generated enormous amounts of data, markedly improved our understanding of the transcriptional and epigenetic control of gene expression. To take advantage of the availability of such datasets and provide clues on what factors, including transcription factors, epigenetic regulators and histone modifications, potentially regulates the expression of a gene of interest, a tool for simultaneous queries of multiple datasets using symbols or genomic coordinates as search terms is needed. Results: In this study, we annotated the peaks of thousands of ChIP-seq datasets generated by ENCODE project, or ChIP-seq/DNase-seq/ATAC-seq datasets deposited in Gene Expression Omnibus (GEO) and curated by Cistrome project; We built a MySQL database called TFmapper containing the annotations and associated metadata, allowing users without bioinformatics expertise to search across thousands of datasets to identify factors targeting a genomic region/gene of interest in a specified sample through a web interface. Users can also visualize multiple peaks in genome browsers and download the corresponding sequences. Conclusion: TFmapper will help users explore the vast amount of publicly available ChIP-seq/DNase-seq/ATAC-seq data and perform integrative analyses to understand the regulation of a gene of interest. The web server is freely accessible at http://www.tfmapper.org/.", "claims": [{"id": "claim-method", "statement": "the enrichment scores, the p- and q- values for ChIP-seq peaks called by Model-based Analysis for ChIP-Seq (MACS2) 15, 16;", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30416387", "locator": "sections[3] \"Website interface\" paragraph 5", "quote": "the enrichment scores, the p- and q- values for ChIP-seq peaks called by Model-based Analysis for ChIP-Seq (MACS2) 15, 16;"}], "state": "complete"}, {"id": "claim-data-access", "statement": "TFmapper is freely accessible at http://www.tfmapper.org/. The complete source code for TFmapper is freely available at GITHUB (https://github.com/jmzeng1314/TF_map) under a GPLv3 license.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30416387", "locator": "sections[12] \"ack\" paragraph 1", "quote": "TFmapper is freely accessible at http://www.tfmapper.org/. The complete source code for TFmapper is freely available at GITHUB (https://github.com/jmzeng1314/TF_map) under a GPLv3 license."}], "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:30416387"], "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:30416387", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.7150/ijbs.28850", "sha256": "sha256:358ab34a85d288cd61f1d84bc6e68cac75694f2d3a10f26cae263766622bce4f", "bytes": 20945, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.7150/ijbs.28850", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6216026", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Model-based Analysis for ChIP-Seq (MACS2)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "the enrichment scores, the p- and q- values for ChIP-seq peaks called by Model-based Analysis for ChIP-Seq (MACS2) 15, 16;"}}], "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 (Model-based Analysis for ChIP-Seq (MACS2)), 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": [], "resolved_accessions": [], "statements": ["TFmapper is freely accessible at http://www.tfmapper.org/. The complete source code for TFmapper is freely available at GITHUB (https://github.com/jmzeng1314/TF_map) under a GPLv3 license."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:30416387"], "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": "2026-10-31T18:12:56Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 15515, "completion_tokens": 1941, "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:30416387", "type": "paper", "label": "pmid:30416387"}, {"id": "source:pmid:30416387", "type": "manuscript", "label": "PMID 30416387 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30416387", "type": "paper", "label": "pmid:30416387"}, {"id": "source:pmid:30416387", "type": "manuscript", "label": "PMID 30416387 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30416387", "type": "extraction", "used": ["source:pmid:30416387"], "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:30416387", "parent_hash": "sha256:c749d91c6a0bba5ad4921021f2f31fb3534732698d5d46c00def03fee78d9c1e", "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": "amplicon_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["Background: Next-generation sequencing coupled to chromatin immunoprecipitation (Ch"], "order_basis": "paper_text_order:96", "id": "assay:1"}, {"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.69, "evidence": ["e, GRCh38/hg38 for human and GRCm38/mm10 for mouse respectively. HOMER assigns each peak to the"], "order_basis": "paper_text_order:1765", "id": "assay:2"}]}