BioVDB: biological vector database for high-throughput gene expression meta-analysis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:38525301", "kind": "science-record", "revision": 1, "content_hash": "sha256:a663bafab9a04ea18a9632b12da034407fe91caf6aeadc083221eca9ec46a10e", "created_at": "2026-11-01T19:20:28Z", "updated_at": "2026-11-01T19:20:28Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "BioVDB: biological vector database for high-throughput gene expression meta-analysis.", "doi": "10.3389/frai.2024.1366273", "pmid": "38525301", "authors": ["Michał J Winnicki", "Chase A Brown", "Hunter L Porter", "Cory B Giles", "Jonathan D Wren"], "journal": "Frontiers in artificial intelligence", "year": 2024, "abstract": "High-throughput sequencing has created an exponential increase in the amount of gene expression data, much of which is freely, publicly available in repositories such as NCBI's Gene Expression Omnibus (GEO). Querying this data for patterns such as similarity and distance, however, becomes increasingly challenging as the total amount of data increases. Furthermore, vectorization of the data is commonly required in Artificial Intelligence and Machine Learning (AI/ML) approaches. We present BioVDB, a vector database for storage and analysis of gene expression data, which enhances the potential for integrating biological studies with AI/ML tools. We used a previously developed approach called Automatic Label Extraction (ALE) to extract sample labels from metadata, including age, sex, and tissue/cell-line. BioVDB stores 438,562 samples from eight microarray GEO platforms. We show that it allows for efficient querying of data using similarity search, which can also be useful for identifying and inferring missing labels of samples, and for rapid similarity analysis.", "claims": [{"id": "claim-data-access", "statement": "Publicly available datasets were analyzed in this study. This data can be found at: https://huggingface.co/collections/mwinn99/biovdb-658daf0c3ceccd00f3ad63a9. The BioVDB code can be found at: https://gitlab.com/wrenlab/biovdb.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38525301", "locator": "sections[19] \"Data availability statement\" paragraph 2", "quote": "Publicly available datasets were analyzed in this study. This data can be found at: https://huggingface.co/collections/mwinn99/biovdb-658daf0c3ceccd00f3ad63a9. The BioVDB code can be found at: https://gitlab.com/wrenlab/biovdb."}], "state": "complete"}, {"id": "claim-target-result", "statement": "BioVDB stores 438,562 gene-expression samples from eight microarray GEO platforms and supports efficient similarity search, label inference, and rapid similarity analysis.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:38525301", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "We present BioVDB, a vector database for storage and analysis of gene expression data, which enhances the potential for integrating biological studies with AI/ML tools."}, {"asset": "source:pmid:38525301", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "BioVDB stores 438,562 samples from eight microarray GEO platforms."}, {"asset": "source:pmid:38525301", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "We show that it allows for efficient querying of data using similarity search, which can also be useful for identifying and inferring missing labels of samples, and for rapid similarity analysis."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "BioVDB stores 438,562 gene-expression samples from eight microarray GEO platforms and supports efficient similarity search, label inference, and rapid similarity analysis.", "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:38525301"], "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:38525301", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/frai.2024.1366273", "sha256": "sha256:6c8fb8dd3fa83554fe81bb70d38a3c0404adb5583f4d7c82567ec25b94304660", "bytes": 23037, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/frai.2024.1366273", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10957786", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "operations"]}, "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 (not named), 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": ["Publicly available datasets were analyzed in this study. This data can be found at: https://huggingface.co/collections/mwinn99/biovdb-658daf0c3ceccd00f3ad63a9. The BioVDB code can be found at: https://gitlab.com/wrenlab/biovdb."], "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:38525301"], "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": "2026-11-01T19:13:13Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 6974, "completion_tokens": 1412, "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:38525301", "type": "paper", "label": "pmid:38525301"}, {"id": "source:pmid:38525301", "type": "manuscript", "label": "PMID 38525301 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:38525301", "type": "paper", "label": "pmid:38525301"}, {"id": "source:pmid:38525301", "type": "manuscript", "label": "PMID 38525301 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-38525301", "type": "extraction", "used": ["source:pmid:38525301"], "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": null, "parent_hash": null, "fork_of": null, "generation": 0}, "gaps": ["execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["ne. BioVDB stores 438,562 samples from eight microarray GEO platforms. We show that it allows for ef"], "order_basis": "paper_text_order:895", "id": "assay:1"}]}