Multimodal AI predicts clinical outcomes of drug combinations from preclinical data

• URL: http://arxiv.org/abs/2503.02781v2
• Date: Wed, 24 Sep 2025 19:32:56 GMT
• Title: Multimodal AI predicts clinical outcomes of drug combinations from preclinical data
• Authors: Yepeng Huang, Xiaorui Su, Varun Ullanat, Intae Moon, Ivy Liang, Lindsay Clegg, Damilola Olabode, Ruthie Johnson, Nicholas Ho, Megan Gibbs, Megan Gibbs, Alexander Gusev, Bino John, Marinka Zitnik,
• Abstract summary: We introduce Madrigal, a multimodal AI model that learns from structural, pathway, cell viability, and transcriptomic data to predict drug-combination effects.<n>Madrigal uses an attention bottleneck module to unify preclinical drug data modalities.<n>It outperforms single-modality methods and state-of-the-art models in predicting adverse drug interactions.
• Score: 38.31103891121078
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Predicting clinical outcomes from preclinical data is essential for identifying safe and effective drug combinations, reducing late-stage clinical failures, and accelerating the development of precision therapies. Current AI models rely on structural or target-based features but 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 21,842 compounds, including combinations of approved drugs and novel compounds in development. Madrigal uses an attention 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, and ablations show both modality alignment and multimodality are necessary. It captures transporter-mediated interactions and aligns with head-to-head clinical trial differences for neutropenia, anemia, alopecia, and hypoglycemia. In type 2 diabetes and MASH, Madrigal supports polypharmacy decisions and prioritizes resmetirom among safer candidates. Extending to personalization, Madrigal improves patient-level adverse-event prediction in a longitudinal EHR cohort and an independent oncology cohort, and predicts ex vivo efficacy in primary acute myeloid leukemia samples and patient-derived xenograft models. Madrigal links preclinical multimodal readouts to safety risks of drug combinations and offers a generalizable foundation for safer combination design.

Related papers

• A Hybrid Computational Intelligence Framework with Metaheuristic Optimization for Drug-Drug Interaction Prediction [0.8602553195689512]
  Drug-drug interactions (DDIs) are a leading cause of preventable adverse events, often complicating treatment and increasing healthcare costs.<n>We propose an interpretable and efficient framework that blends modern machine learning with domain knowledge to improve DDI prediction.<n>Our approach combines two complementary embeddings - Mol2Vec, which captures fragment-level structural patterns, and SMILES-BERT, which learns contextual chemical features.
  arXiv  Detail & Related papers  (2025-10-08T09:55:18Z)
• impuTMAE: Multi-modal Transformer with Masked Pre-training for Missing Modalities Imputation in Cancer Survival Prediction [75.43342771863837]
  We introduce impuTMAE, a novel transformer-based end-to-end approach with an efficient multimodal pre-training strategy.<n>It learns inter- and intra-modal interactions while simultaneously imputing missing modalities by reconstructing masked patches.<n>Our model is pre-trained on heterogeneous, incomplete data and fine-tuned for glioma survival prediction using TCGA-GBM/LGG and BraTS datasets.
  arXiv  Detail & Related papers  (2025-08-08T10:01:16Z)
• Continually Evolved Multimodal Foundation Models for Cancer Prognosis [50.43145292874533]
  Cancer prognosis is a critical task that involves predicting patient outcomes and survival rates.<n>Previous studies have integrated diverse data modalities, such as clinical notes, medical images, and genomic data, leveraging their complementary information.<n>Existing approaches face two major limitations. First, they struggle to incorporate newly arrived data with varying distributions into training, such as patient records from different hospitals.<n>Second, most multimodal integration methods rely on simplistic concatenation or task-specific pipelines, which fail to capture the complex interdependencies across modalities.
  arXiv  Detail & Related papers  (2025-01-30T06:49:57Z)
• MD-Syn: Synergistic drug combination prediction based on the multidimensional feature fusion method and attention mechanisms [0.0]
  Drug combination therapies have shown promising therapeutic efficacy in complex diseases and have demonstrated the potential to reduce drug resistance. The huge number of possible drug combinations makes it difficult to screen them all in traditional experiments. In this study, we proposed MD-Syn, a computational framework, which is based on the multidimensional feature fusion method and multi-head attention mechanisms.
  arXiv  Detail & Related papers  (2025-01-14T06:50:56Z)
• MEXA-CTP: Mode Experts Cross-Attention for Clinical Trial Outcome Prediction [14.116060944536011]
  We propose a light-weight attention-based model, MEXA-CTP, to integrate readily-available multi-modal data and generate effective representations.<n>Our experiments on the Trial Outcome Prediction benchmark demonstrate that MEXA-CTP improves upon existing approaches by up to 11.3% in F1 score, 12.2% in PR-AUC, and 2.5% in ROC-AUC.
  arXiv  Detail & Related papers  (2025-01-12T14:35:31Z)
• KITE-DDI: A Knowledge graph Integrated Transformer Model for accurately predicting Drug-Drug Interaction Events from Drug SMILES and Biomedical Knowledge Graph [0.11049608786515838]
  Drug-Drug Interactions (DDI) can cause significant bodily injury and even death.<n>Most contemporary research for predicting DDI events relies on either information from Biomedical Knowledge graphs (KG) or drug SMILES.<n>In this study, we propose a KG-integrated Transformer architecture to generate an end-to-end fully automated Machine Learning pipeline.
  arXiv  Detail & Related papers  (2024-12-08T00:49:57Z)
• Causal machine learning for predicting treatment outcomes [75.13093479526151]
  Causal machine learning (ML) offers flexible, data-driven methods for predicting treatment outcomes. Key benefit of causal ML is that it allows for estimating individualized treatment effects.
  arXiv  Detail & Related papers  (2024-10-11T12:39:08Z)
• TCKAN:A Novel Integrated Network Model for Predicting Mortality Risk in Sepsis Patients [0.0]
  Sepsis poses a major global health threat, accounting for millions of deaths annually and significant economic costs. Current methods typically utilize only one type of data--either constant, temporal, or ICD codes. Time-Constant Kolmogorov-Arnold Network (TCKAN) uniquely integrates temporal data, constant data, and ICD codes within a single predictive model.
  arXiv  Detail & Related papers  (2024-07-09T05:37:50Z)
• A Cross-Field Fusion Strategy for Drug-Target Interaction Prediction [85.2792480737546]
  Existing methods fail to utilize global protein information during DTI prediction. Cross-field information fusion strategy is employed to acquire local and global protein information. Siamese drug-target interaction SiamDTI prediction method achieves higher accuracy levels than other state-of-the-art (SOTA) methods on novel drugs and targets.
  arXiv  Detail & Related papers  (2024-05-23T13:25:20Z)
• DrFuse: Learning Disentangled Representation for Clinical Multi-Modal Fusion with Missing Modality and Modal Inconsistency [18.291267748113142]
  We propose DrFuse to achieve effective clinical multi-modal fusion. We address the missing modality issue by disentangling the features shared across modalities and those unique within each modality. We validate the proposed method using real-world large-scale datasets, MIMIC-IV and MIMIC-CXR.
  arXiv  Detail & Related papers  (2024-03-10T12:41:34Z)
• XAI for In-hospital Mortality Prediction via Multimodal ICU Data [57.73357047856416]
  We propose an efficient, explainable AI solution for predicting in-hospital mortality via multimodal ICU data. We employ multimodal learning in our framework, which can receive heterogeneous inputs from clinical data and make decisions. Our framework can be easily transferred to other clinical tasks, which facilitates the discovery of crucial factors in healthcare research.
  arXiv  Detail & Related papers  (2023-12-29T14:28:04Z)
• Enhancing drug and cell line representations via contrastive learning for improved anti-cancer drug prioritization [0.7070726553564699]
  We propose the use of contrastive learning to improve learned drug and cell line representations. We find that our learned representations exhibit a more balances reliance on drug- and cell line-derived features when making predictions.
  arXiv  Detail & Related papers  (2023-10-20T04:18:47Z)
• Drug Interaction Vectors Neural Network: DrIVeNN [0.7624669864625037]
  Polypharmacy is the concurrent use of multiple drugs to treat a single condition. Many serious ADEs associated with polypharmacy only become known after the drugs are in use. It is impractical to test every possible drug combination during clinical trials.
  arXiv  Detail & Related papers  (2023-08-26T14:24:41Z)
• Cross-modality Attention-based Multimodal Fusion for Non-small Cell Lung Cancer (NSCLC) Patient Survival Prediction [0.6476298550949928]
  We propose a cross-modality attention-based multimodal fusion pipeline designed to integrate modality-specific knowledge for patient survival prediction in non-small cell lung cancer (NSCLC) Compared with single modality, which achieved c-index of 0.5772 and 0.5885 using solely tissue image data or RNA-seq data, respectively, the proposed fusion approach achieved c-index 0.6587 in our experiment.
  arXiv  Detail & Related papers  (2023-08-18T21:42:52Z)
• Drug Synergistic Combinations Predictions via Large-Scale Pre-Training and Graph Structure Learning [82.93806087715507]
  Drug combination therapy is a well-established strategy for disease treatment with better effectiveness and less safety degradation. Deep learning models have emerged as an efficient way to discover synergistic combinations. Our framework achieves state-of-the-art results in comparison with other deep learning-based methods.
  arXiv  Detail & Related papers  (2023-01-14T15:07:43Z)
• SSM-DTA: Breaking the Barriers of Data Scarcity in Drug-Target Affinity Prediction [127.43571146741984]
  Drug-Target Affinity (DTA) is of vital importance in early-stage drug discovery. wet experiments remain the most reliable method, but they are time-consuming and resource-intensive. Existing methods have primarily focused on developing techniques based on the available DTA data, without adequately addressing the data scarcity issue. We present the SSM-DTA framework, which incorporates three simple yet highly effective strategies.
  arXiv  Detail & Related papers  (2022-06-20T14:53:25Z)
• MIA-Prognosis: A Deep Learning Framework to Predict Therapy Response [58.0291320452122]
  This paper aims at a unified deep learning approach to predict patient prognosis and therapy response. We formalize the prognosis modeling as a multi-modal asynchronous time series classification task. Our predictive model could further stratify low-risk and high-risk patients in terms of long-term survival.
  arXiv  Detail & Related papers  (2020-10-08T15:30:17Z)
• Learning for Dose Allocation in Adaptive Clinical Trials with Safety Constraints [84.09488581365484]
  Phase I dose-finding trials are increasingly challenging as the relationship between efficacy and toxicity of new compounds becomes more complex. Most commonly used methods in practice focus on identifying a Maximum Tolerated Dose (MTD) by learning only from toxicity events. We present a novel adaptive clinical trial methodology that aims at maximizing the cumulative efficacies while satisfying the toxicity safety constraint with high probability.
  arXiv  Detail & Related papers  (2020-06-09T03:06:45Z)
• Reinforcement learning and Bayesian data assimilation for model-informed precision dosing in oncology [0.0]
  Current strategies comprise model-informed dosing tables or are based on maximum a-posteriori estimates. We propose three novel approaches for MIPD employing Bayesian data assimilation and/or reinforcement learning to control neutropenia. These approaches have the potential to substantially reduce the incidence of life-threatening grade 4 and subtherapeutic grade 0 neutropenia.
  arXiv  Detail & Related papers  (2020-06-01T16:38:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.