Large Language Models for Controllable Multi-property Multi-objective Molecule Optimization
In real-world drug design, molecule optimization requires selectively improving multiple molecular properties up to pharmaceutically relevant levels, while maintaining others that already meet such criteria. However, existing computational approaches and instruction-tuned LLMs fail to capture such nuanced property-specific objectives, limiting their practical applicability. To address this, we introduce C-MuMOInstruct, the first instruction-tuning dataset focused on multi-property optimization with explicit, property-specific objectives. Leveraging C-MuMOInstruct, we develop GeLLMO-Cs, a series of instruction-tuned LLMs that can perform targeted property-specific optimization. Our experiments across 5 in-distribution and 5 out-of-distribution tasks show that GeLLMO-Cs consistently outperform strong baselines, achieving up to 126% higher success rate. Notably, GeLLMO-Cs exhibit impressive 0-shot generalization to novel optimization tasks and unseen instructions. This offers a step toward a foundational LLM to support realistic, diverse optimizations with property-specific objectives. C-MuMOInstruct and code are accessible through https://github.com/ninglab/GeLLMO-C.
Code (1)
Tasks
Drug DesignSimilar Papers 제목 키워드 기반
M^4olGen: Multi-Agent, Multi-Stage Molecular Generation under Precise Multi-Property Constraints
Generating molecules that satisfy precise numeric constraints over multiple physicochemical properties is critical and challenging. Although large language models (LLMs) are expressive, they struggle with precise multi-o…
Scaffold-Conditioned Preference Triplets for Controllable Molecular Optimization with Large Language Models
Molecular property optimization is central to drug discovery, yet many deep learning methods rely on black-box scoring and offer limited control over scaffold preservation, often producing unstable or biologically implau…
Drug DiscoveryInterpretable Multi-Headed Attention for Abstractive Summarization at Controllable Lengths
Abstractive summarization at controllable lengths is a challenging task in natural language processing. It is even more challenging for domains where limited training data is available or scenarios in which the length of…
Abstractive Text SummarizationTransfer LearningUser-Controllable Multi-Texture Synthesis with Generative Adversarial Networks
We propose a novel multi-texture synthesis model based on generative adversarial networks (GANs) with a user-controllable mechanism. The user control ability allows to explicitly specify the texture which should be gener…
DescriptiveTexture SynthesisC-MORAL: Controllable Multi-Objective Molecular Optimization with Reinforcement Alignment for LLMs
Large language models (LLMs) show promise for molecular optimization, but aligning them with selective and competing drug-design constraints remains challenging. We propose C-Moral, a reinforcement learning post-training…
Reinforcement Learning