AI Insight
Researchers developed TRACE, an automated computational pipeline that uses a fine-tuned biomedical language model to identify drug repurposing opportunities from transcriptome-wide association studies (TWAS). The system analyzes FDA-approved drugs, reviews published literature, and classifies drug-gene relationships to match drugs with diseases based on gene expression patterns and mechanism of action directionality. When validated against manually curated datasets for endometriosis, metabolic dysfunction-associated steatotic liver disease, and type 2 diabetes, TRACE recovered approximately 90% of known drug-gene pairs and successfully identified established therapies like leuprolide acetate for endometriosis.
Why it matters
This tool addresses a major bottleneck in translating genetic discoveries into therapeutic opportunities by automating the time-consuming process of manually reviewing literature and databases. By making drug repurposing more systematic and scalable, TRACE could accelerate the identification of new uses for existing FDA-approved medications, potentially reducing drug development costs and time to treatment for patients with various diseases.
Understand the Science
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
Transcriptome-wide association studies (TWAS) can identify genes where genetically predicted gene expression is associated with disease risk, but translating those signals into therapeutic opportunities remains time-consuming, manual, and difficult to reproduce. We developed TRACE (TWAS-driven Repurposing through AI-assisted Curation of Evidence), a gene- and phenotype-agnostic computational pipeline that accepts a TWAS gene and effect-size direction, normalizes the gene symbol, retrieves FDA-approved drug-gene candidates from four online resources, collects related peer-reviewed literature from PubMed, and uses a fine-tuned biomedical language model to classify whether the literature supports a direct drug-gene relationship, the mechanism of action, and the direction of effect. The pipeline then compares the drug-derived direction with the direction implied by the TWAS effect estimate to rank candidate therapeutic pairs and flag potential drug safety concerns. The local classifier, built on BiomedBERT, was trained using pipeline-derived labels, BioCreative VI ChemProt gold-standard chemical-protein relation examples, and author-reviewed active-learning cases, reaching a held-out macro F1 of 0.809 across three simultaneous classification tasks. We validated the pipeline against a manually curated endometriosis gold standard of 43 drug-gene pairs spanning six TWAS-identified genes, developed through S-PrediXcan analysis of endometriosis GWAS summary statistics, manual querying of four drug-gene interaction databases for each gene, literature review of drug-gene mechanistic evidence, and Mendelian randomization validation of candidate pairs. External validation used two independently published genetically informed drug-repurposing studies in metabolic dysfunction-associated steatotic liver disease (MASLD) and type 2 diabetes (T2D). The pipeline recovered 90.7% of endometriosis pairs, 88.2% of MASLD pairs, and 92.9% of T2D pairs that were present in at least one queried database. Applied to 99 endometriosis-associated TWAS genes, the pipeline identified 1,089 FDA-approved drug-gene pairs, 32 candidate therapeutic pairs, and 77 potential safety concerns, including independent recovery of leuprolide acetate, an established endometriosis therapy. This framework provides a scalable, literature-grounded bridge from TWAS discovery to prioritized therapeutic hypotheses, while preserving uncertainty through manual-review flags and requiring downstream Mendelian randomization, electronic health record-based validation, and experimental follow-up before clinical interpretation.