A foundation model for clinician-centered drug repurposing

Abstract

Drug repurposing - identifying new therapeutic uses for approved drugs - is often serendipitous and opportunistic, expanding the use of drugs for new diseases. The clinical utility of drug repurposing AI models remains limited because the models focus narrowly on diseases for which some drugs already exist. Here, we introduce TXGNN, a graph foundation model for zero-shot drug repurposing, identifying therapeutic candidates even for diseases with limited treatment options or no existing drugs. Trained on a medical knowledge graph, TXGNN utilizes a graph neural network and metric-learning module to rank drugs as potential indications and contraindications across 17,080 diseases. When benchmarked against eight methods, TXGNN improves prediction accuracy for indications by 49.2% and contraindications by 35.1% under stringent zero-shot evaluation. To facilitate model interpretation, TXGNN's Explainer module offers transparent insights into multi-hop medical knowledge paths that form TXGNN's predictive rationales. Human evaluation of TXGNN's Explainer showed that TXGNN's predictions and explanations perform encouragingly on multiple axes of performance beyond accuracy. Many of TxGNN's novel predictions align with off-label prescriptions clinicians make in a large healthcare system. TXGNN's drug repurposing predictions are accurate, consistent with off-label drug use, and can be investigated by human experts through multi-hop interpretable rationales.

Figure 1:. TXGNN is a graph foundation model for drug repurposing, identifying candidate drugs for diseases with limited treatment options and limited molecular data.

a. Drug repurposing involves exploring new therapeutic applications for existing drugs to treat different diseases. Leveraging existing safety and efficacy data can dramatically cut costs and time to deliver life-saving therapeutics. b. Although computational drug repurposing has shown promise, it has been considered for diseases with already available treatments and well-understood molecular mechanisms. However, many diseases lack treatments and a complete understanding of disease mechanisms. These inherent constraints pose challenges for AI models. TXGNN addresses this challenge by formulating drug repurposing as a zero-shot prediction problem. c. TXGNN presents a novel AI framework that generates actionable predictions for zero-shot drug repurposing. TXGNN geometric deep learning model incorporates a vast and comprehensive biological knowledge graph to accurately predict the likelihood of indication or contraindication for any given disease-drug pair. Additionally, TXGNN generates explainable multi-hop paths, facilitating human understanding of how the prediction is grounded in medical knowledge. d. TXGNN model is trained on a medical knowledge graph of disease mechanisms across 17,080 diseases and drug mechanisms of action for 7,957 drugs.

Figure 2:. TXGNN accurately predicts drug indications and contraindications.

a. TXGNN is a deep learning model that learns to reason over a large-scale knowledge graph to predict the relationship between drugs and disease. In zero-shot repurposing, limited indication and mechanism information is available for the query disease. Our key insight revolves around the interconnectedness of biological systems. We recognize that diseases, despite their distinctiveness, can exhibit partial similarities and share multiple underlying mechanisms. Based on this motivation, we have developed a specialized module known as disease pooling, which harnesses the power of network medicine principles. This module identifies mechanistically similar diseases and employs them to enhance the information available for the query disease. The disease pooling module has significantly improved the prioritization of repurposing candidates within zero-shot settings. b. The TXGNN disease similarity score provides a nuanced and meaningful measure of the relationship between diseases. This metric empowers TXGNN to discover similar diseases that can inform and enrich the understanding of query diseases lacking treatment and mechanistic information. c. The conventional AI-based repurposing evaluates indication predictions on diseases where the model may have seen other approved drugs during training. In this scenario, we show that TXGNN achieves good performance along with existing methods. d. To provide a more realistic evaluation, we introduce a novel setup for assessing zero-shot repurposing, where the model is evaluated on diseases that have no approved drugs available during training. In this challenging setting, we observe a significant degradation in performance for baseline methods. In contrast, TXGNN consistently exhibits robust performance, surpassing the best baseline by up to 19% for indications and 23.9% for contraindications. These results highlight TxGNN’s reasoning capabilities when confronted with query diseases lacking treatment options. For both c and d, the evaluation uses the area under the precision-recall curve (AUPRC) and is conducted with five random data splits (N=5). Shown is the average performance; 95% confidence intervals are represented by error bars.

Figure 3:. TXGNN predicts drug indications and contraindications across challenging disease areas with small molecular datasets.

a. We construct nine ‘disease area’ splits to evaluate how well each model can generalize to new diseases when using only a limited amount of disease-associated molecular data and no information about its treatments. The diseases in the holdout set have (1) no approved drugs in training, (2) limited overlap with the training disease set because we exclude similar diseases, and (3) lack molecular data because we deliberately remove their biological neighbors from the training set. These data splits constitute challenging but realistic evaluation scenarios that mimic zero-shot drug repurposing settings. b-f. Holdout folds evaluate diseases related to adrenal glands, autoimmune diseases, neurodegenerative diseases, metabolic disorders, and cardiovascular diseases. Results for four disease areas, anemia, diabetes, cancer, and mental health, are provided in Figure S7. Raw scores are provided in Tables S1 and S2. TXGNN shows up to 59.3% improvement over the next best baseline in ranking therapeutic candidates, measured by AUPRC. Each method under each split is conducted with five random data splits (N=5). Shown is the average performance; 95% confidence intervals are represented by error bars.

Figure 4:. Development, visualization, and evaluation of multi-hop interpretable paths in TXGNN Explainer.

a. Prediction alone is often insufficient for trustworthy machine learning model deployment. We develop TXGNN Explainer to aid human experts using graph AI explainability techniques. TXGNN Explainer identifies a sparse, interpretable subgraph underlying the model’s predictions. For each drug candidate, it generates a multi-hop path of biomedical concepts linking the disease to the drug. A visualization module then transforms these subgraphs into multi-hop paths that align with human cognitive processes. b. We design an interactive tool to help experts explore TXGNN predictions and explanations. The ‘Control Panel’ lets users select a disease and view top-ranked predictions. The ‘Edge Threshold’ module adjusts the sparsity of explanations, controlling the density of displayed multi-hop paths. The ‘Drug Embedding’ panel compares a selected drug’s position to the entire repurposing candidate library. The ‘Path Explanation’ panel shows crucial biological relations for TXGNN’s therapeutic predictions. c. To evaluate the usefulness of TXGNN explanations, we conducted a user study involving five clinicians, five clinical researchers, and two pharmacists. These participants were shown 16 drug-disease pairs with TXGNN’s predictions, where 12 predictions were accurate. For each pairing, participants indicated whether they agreed or disagreed with TXGNN’s predictions using the explanations provided. d. We compared the performance of TXGNN Explainer with a no-explanation baseline regarding user answer accuracy, task completion time, and user confidence. The results are aggregated on 192 trials (12 participants × 16 tasks) and reveal a significant improvement in accuracy (P=0.044), confidence (P=0.004), and time to think (P=0.0013) when explanations were provided. Error bars represent 95% confidence intervals, and the center of the error bar is the average performance. The statistics are computed using a two-sided Tukey’s honest significance difference test without multiple test adjustments. e. After the user study, participants were asked qualitative usability questions. Human experts agreed that the explanations provided by TXGNN helped assess drug repurposing candidates and instilled greater trust in the TXGNN’s predictions than using predictions alone.

Figure 5:. Drug repurposing predictions and multi-hop interpretable paths produced by TXGNN align with medical evidence.

a. We assess the alignment of drug repurposing candidates identified by TXGNN with established medical reasoning across three rare diseases. The process begins with the TXGNN Predictor, which selects potential drugs for repurposing based on a disease query and continues with the TxGNN Explorer, which provides interpretable paths explaining the selection. Our case studies conclude with independent verification of the TXGNN ’s predictions against clinical knowledge, showcasing the congruence between the TXGNN’s recommendations and medical insights. b. TXGNN predicts Zolpidem, typically used as a sedative, as a repurposing candidate for Kleefstra syndrome, characterized by developmental delays and neurological symptoms. Despite Zolpidem’s conventional inhibitory effects on the brain, TXGNN Explainer suggests its potential to enhance prefrontal cortex activity and improve cognitive functions in those with Kleefstra syndrome. TXGNN’s counterintuitive recommendation aligns with emerging clinical evidence of Zolpidem’s ability to awaken dormant neurons, potentially aiding speech, motor skills, and alertness in patients with neurodevelopmental disorders. c. TXGNN identifies Tretinoin as the top candidate for treating Ehlers-Danlos syndrome. TXGNN’s predictive rationale is rooted in the drug’s interactions with albumin (ALB) and ALDH1A2, which aligns with medical insights about Ehlers-Danlos syndrome regarding collagen loss and inflammation mitigation. d. TXGNN identifies Amyl Nitrite as a therapeutic option for the nephrogenic syndrome of inappropriate antidiuresis (NSIAD). In NSIAD, an AVPR2 mutation leads to water and sodium imbalances. TXGNN Explorer points out the connection between NSIAD and Amyl Nitrite through congestive heart failure, a condition with similar fluid retention issues, by exploring gene interactions (AVPR2 and NPR1) that regulate electrolyte balance.

Figure 6:. Evaluating TXGNN’s novel predictions in a large healthcare system.

a. We illustrate the steps to evaluate TXGNN’s novel indication predictions using electronic medical records (EMRs). First, we matched the drugs and diseases in the TXGNN knowledge graph to the EMR database, resulting in a curated cohort of 1.27 million patients spanning 478 diseases and 1,290 drugs. Next, we calculated the log-odds ratio (log-OR) for each drug-disease pair to indicate drug usage for specific diseases. We validated the log-OR metric as a proxy for clinical usage by comparing drug-disease pairs against FDA-approved indications. Finally, we evaluated TXGNN’s novel predictions to determine if their log-ORs exhibited enrichment within the medical records. b. The racial diversity within the patient cohort. c. The sex distribution of the patient cohort. d. The medical records encompassed a diverse range of diseases spanning major disease areas. e. In validating log-ORs as a proxy metric for clinical prescription, we observed that while most drug-disease pairs exhibited low log-OR values, there was a significant enrichment of log-OR values for FDA-approved drugs. Additionally, we noted that contraindications displayed similar log-OR values to the general non-indicated drug-disease pairs, minimizing potential confounders such as adverse drug effects. f. We evaluated log-ORs for the novel indications proposed by TXGNN. The y-axis represents the log-OR of the disease-drug pairs, serving as a proxy for clinical usage. We ranked TXGNN’s predictions for each disease and extracted the average Log-OR values for the top-1 predicted drug (N = 470), top-5 predicted drugs (N = 2,314), top 5% predicted drugs (N = 27,618), and bottom-50% predicted drugs (N = 123,718). The red line represents the average log-OR for FDA-approved indications, while the green line represents the average log-OR for contraindications. Predicted drugs are consistent with off-label prescription decisions made by clinicians. The error bar is a 95% confidence interval. g. We provide a case study of TXGNN’s predicted scores plotted against the log-OR for Wilson’s disease. Each point on the plot represents a therapeutic candidate. The top-1 most likely drug identified by TXGNN is highlighted, indicating its associated TXGNN and log-OR scores.