DOSE-L1000-Viz: an interactive Shiny application for dose-response transcriptomic analysis, target-centric exploration, and signature search.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40608961", "kind": "science-record", "revision": 2, "content_hash": "sha256:508e73ed44af3175883da06e6b800effe5a035acdd230a02d62fb6b15447890d", "created_at": "2026-11-01T20:30:42Z", "updated_at": "2026-11-01T21:35:23Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "DOSE-L1000-Viz: an interactive Shiny application for dose-response transcriptomic analysis, target-centric exploration, and signature search.", "doi": "10.1093/bioinformatics/btaf353", "pmid": "40608961", "authors": ["Junmin Wang"], "journal": "Bioinformatics (Oxford, England)", "year": 2025, "abstract": "SUMMARY: Understanding how small molecules perturb gene expression is critical for guiding drug discovery. We present DOSE-L1000-Viz, a Shiny application that facilitates comprehensive exploration of compound-induced transcriptomic responses across doses, time points, and cell types. Powered by a dose-response database, DOSE-L1000-Viz features interactive visualization, target-centric compound ranking based on efficacy and potency, and a signature search module using reference gene sets derived from generalized additive models. We benchmarked signatures derived from generalized additive models against traditional methods and demonstrated the utility of DOSE-L1000-Viz through use cases in transcription factor modulation and drug repurposing.\nAVAILABILITY AND IMPLEMENTATION: DOSE-L1000-Viz and the backend data are publicly accessible at: https://dosel1000.com. All code is publicly hosted on GitHub (https://github.com/JmWangBio/DOSEL1000Viz) and archived via Zenodo (https://doi.org/10.5281/zenodo.15532392).", "claims": [{"id": "claim-method", "statement": "For each replicated condition defined by compound, cell line, time, and dose, we calculated the pairwise Jaccard index (i.e. overlap percentage) between batches to quantify overlap between gene signatures.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40608961", "locator": "sections[5] \"2.3 Signature similarity and statistical evaluation\" paragraph 3", "quote": "For each replicated condition defined by compound, cell line, time, and dose, we calculated the pairwise Jaccard index (i.e. overlap percentage) between batches to quantify overlap between gene signatures."}], "state": "complete"}, {"id": "claim-data-access", "statement": "DOSE-L1000-Viz and the backend data are publicly accessible at: https://dosel1000.com. All code and data are archived via Zenodo (https://doi.org/10.5281/zenodo.15532392).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40608961", "locator": "sections[16] \"Data availability\" paragraph 2", "quote": "DOSE-L1000-Viz and the backend data are publicly accessible at: https://dosel1000.com. All code and data are archived via Zenodo (https://doi.org/10.5281/zenodo.15532392)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "GAM-derived signatures demonstrated consistently higher reproducibility than CD-derived signatures across replicated perturbation conditions.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:40608961", "locator": "sections[9] \"3.3 GAM-derived signature search\" paragraph 2", "quote": "Across these conditions, signatures derived from GAMs demonstrated consistently higher reproducibility than those derived from the CD method."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "GAM-derived signatures demonstrated consistently higher reproducibility than CD-derived signatures across replicated perturbation conditions.", "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:40608961"], "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:GSE70138"], "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:GSE70138"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40608961", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btaf353", "sha256": "sha256:d6c05b664d1cbf8b3a9fbd9e4cb180a5890c95878bf9ee694090e413e89cd7ba", "bytes": 19325, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btaf353", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12237504", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE70138", "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=GSE70138", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE70138", "version": null, "note": "DOSE-L1000-Viz and the backend data are publicly accessible at: https://dosel1000.com. All code and data are archived via Zenodo (https://doi.org/10.5281/zenodo.15532392).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "DOSE-L1000-Viz and the backend data are publicly accessible at: https://dosel1000.com. All code and data are archived via Zenodo (https://doi.org/10.5281/zenodo.15532392).", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": 0, "group_sizes": null, "group_sizes_basis": null, "platform": "", "taxon": "Homo sapiens", "title": "L1000 Connectivity Map perturbational profiles from Broad Institute LINCS Center for Transcriptomics LINCS PHASE *II* (n=354,123; updated March 30, 2017)", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE92742", "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=GSE92742", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE92742", "version": null, "note": "DOSE-L1000-Viz and the backend data are publicly accessible at: https://dosel1000.com. All code and data are archived via Zenodo (https://doi.org/10.5281/zenodo.15532392).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "DOSE-L1000-Viz and the backend data are publicly accessible at: https://dosel1000.com. All code and data are archived via Zenodo (https://doi.org/10.5281/zenodo.15532392).", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": 0, "group_sizes": null, "group_sizes_basis": null, "platform": "", "taxon": "Homo sapiens", "title": "L1000 Connectivity Map perturbational profiles from Broad Institute LINCS Center for Transcriptomics LINCS Pilot PHASE I (n=1,319,138; updated March 03, 2017)", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE70138 not downloaded", "asset:data:geo:GSE70138 licence not read", "asset:data:geo:GSE92742 not downloaded", "asset:data:geo:GSE92742 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "pairwise Jaccard index", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "For each replicated condition defined by compound, cell line, time, and dose, we calculated the pairwise Jaccard index (i.e. overlap percentage) between batches to quantify overlap between gene signatures."}}], "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": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (pairwise Jaccard index), 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": "R1", "reachable": true, "accessions": ["GSE92742", "GSE70138"], "resolved_accessions": ["GSE92742", "GSE70138"], "statements": ["DOSE-L1000-Viz and the backend data are publicly accessible at: https://dosel1000.com. All code and data are archived via Zenodo (https://doi.org/10.5281/zenodo.15532392)."], "basis": "The paper names GSE92742, GSE70138 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:40608961", "data:geo:GSE70138"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE70138"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:55:56Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 6286, "completion_tokens": 2597, "cached_tokens": 264}}, "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:40608961", "type": "paper", "label": "pmid:40608961"}, {"id": "source:pmid:40608961", "type": "manuscript", "label": "PMID 40608961 full text"}, {"id": "data:geo:GSE70138", "type": "dataset", "label": "GEO GSE70138"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40608961", "type": "paper", "label": "pmid:40608961"}, {"id": "source:pmid:40608961", "type": "manuscript", "label": "PMID 40608961 full text"}, {"id": "data:geo:GSE70138", "type": "dataset", "label": "GEO GSE70138"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40608961", "type": "extraction", "used": ["source:pmid:40608961"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE70138", "type": "accession_resolution", "used": ["data:geo:GSE70138"], "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:40608961", "parent_hash": "sha256:4ba28e8ed79d25812a4fd932fce931a7c7889f0241ca8deee127462c507ced4d", "fork_of": null, "generation": 1}, "gaps": ["asset:data:geo:GSE70138 licence not read", "asset:data:geo:GSE70138 not downloaded", "asset:data:geo:GSE92742 licence not read", "asset:data:geo:GSE92742 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"]}