Multimodal AI predicts clinical outcomes of drug combinations from preclinical data

2025-03-04

AI Summary

Preclinical prediction of drug combination efficacy faces challenges of multimodal data incompleteness and cross-scale integration. This work introduces MADRIGAL—the first missingness-aware multimodal AI model—integrating molecular structures, pathway annotations, cellular viability profiles, and transcriptomic data to systematically predict the effects of 21,842 compounds (including approved and investigational drugs) in pairwise combinations on 953 clinical outcomes. Key contributions include: (1) a missingness-aware Transformer bottleneck architecture; (2) an LLM-augmented natural-language interface for interactive safety assessment; and (3) a personalized anticancer combination prediction framework incorporating patient genomic data and patient-derived xenograft (PDX) models. MADRIGAL significantly outperforms unimodal baselines and state-of-the-art methods across multiple benchmarks. It successfully recapitulates and mechanistically explains the clinical safety advantage of resmetirom in metabolic dysfunction–associated steatohepatitis (MASH), thereby enabling precision combinatorial therapy decisions for diabetes, MASH, and acute myeloid leukemia (AML).

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Predicting clinical outcomes from preclinical data is essential for identifying safe and effective drug combinations. Current models rely on structural or target-based features to identify high-efficacy, low-toxicity drug combinations. However, these approaches fail to incorporate the multimodal data necessary for accurate, clinically-relevant predictions. Here, we introduce MADRIGAL, a multimodal AI model that learns from structural, pathway, cell viability, and transcriptomic data to predict drug combination effects across 953 clinical outcomes and 21842 compounds, including combinations of approved drugs and novel compounds in development. MADRIGAL uses a transformer bottleneck module to unify preclinical drug data modalities while handling missing data during training and inference--a major challenge in multimodal learning. It outperforms single-modality methods and state-of-the-art models in predicting adverse drug interactions. MADRIGAL performs virtual screening of anticancer drug combinations and supports polypharmacy management for type II diabetes and metabolic dysfunction-associated steatohepatitis (MASH). It identifies transporter-mediated drug interactions. MADRIGAL predicts resmetirom, the first and only FDA-approved drug for MASH, among therapies with the most favorable safety profile. It supports personalized cancer therapy by integrating genomic profiles from cancer patients. Using primary acute myeloid leukemia samples and patient-derived xenograft models, it predicts the efficacy of personalized drug combinations. Integrating MADRIGAL with a large language model allows users to describe clinical outcomes in natural language, improving safety assessment by identifying potential adverse interactions and toxicity risks. MADRIGAL provides a multimodal approach for designing combination therapies with improved predictive accuracy and clinical relevance.

Problem

• Predicts clinical outcomes of drug combinations using multimodal AI.
• Improves accuracy by integrating structural, pathway, and transcriptomic data.
• Supports personalized therapy and identifies adverse drug interactions.

Innovation

• MADRIGAL integrates multimodal data for drug predictions.
• Transformer bottleneck unifies diverse preclinical drug data.
• Combines AI with large language models for safety.