Quantum-Enhanced Multi-Task Learning with Learnable Weighting for Pharmacokinetic and Toxicity Prediction

2025-09-04

AI Summary

To address the limitations of single-task learning (STL) in ADMET prediction—particularly its inability to exploit task complementarity and its high computational cost—this paper proposes QW-MTL, a quantum-enhanced weighted multi-task learning framework. Methodologically: (1) it conducts standardized joint multi-task training across all 13 TDC classification benchmarks for the first time; (2) it augments the Chemprop-RDKit molecular backbone with quantum chemical descriptors to enhance representation fidelity; and (3) it introduces a dataset-prior-driven, learnable exponential weighting mechanism to achieve dynamic loss balancing. Experimental results demonstrate that QW-MTL significantly outperforms STL baselines on 12 of the 13 tasks, achieving superior predictive accuracy, reduced model complexity, and accelerated inference speed. Collectively, QW-MTL establishes an efficient, scalable, and principled paradigm for ADMET modeling.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Learning to Search
• Multiagent Systems: Adversarial Agents

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Prediction for ADMET (Absorption, Distribution, Metabolism, Excretion, and Toxicity) plays a crucial role in drug discovery and development, accelerating the screening and optimization of new drugs. Existing methods primarily rely on single-task learning (STL), which often fails to fully exploit the complementarities between tasks. Besides, it requires more computational resources while training and inference of each task independently. To address these issues, we propose a new unified Quantum-enhanced and task-Weighted Multi-Task Learning (QW-MTL) framework, specifically designed for ADMET classification tasks. Built upon the Chemprop-RDKit backbone, QW-MTL adopts quantum chemical descriptors to enrich molecular representations with additional information about the electronic structure and interactions. Meanwhile, it introduces a novel exponential task weighting scheme that combines dataset-scale priors with learnable parameters to achieve dynamic loss balancing across tasks. To the best of our knowledge, this is the first work to systematically conduct joint multi-task training across all 13 Therapeutics Data Commons (TDC) classification benchmarks, using leaderboard-style data splits to ensure a standardized and realistic evaluation setting. Extensive experimental results show that QW-MTL significantly outperforms single-task baselines on 12 out of 13 tasks, achieving high predictive performance with minimal model complexity and fast inference, demonstrating the effectiveness and efficiency of multi-task molecular learning enhanced by quantum-informed features and adaptive task weighting.

Problem

• Improving ADMET prediction accuracy in drug discovery
• Addressing limitations of single-task learning approaches
• Enhancing molecular representation with quantum chemical descriptors

Innovation

• Quantum-enhanced molecular descriptors for electronic structure
• Learnable exponential weighting for dynamic loss balancing
• Joint multi-task training across 13 TDC benchmarks