MolLIBRA: Genetic Molecular Optimization with Multi-Fingerprint Surrogates and Text-Molecule Aligned Critic
Not on the map. Why?
Abstract (arXiv)
We study sample-efficient molecular optimization under a limited budget of oracle evaluations. We propose MolLIBRA (MultimOdaLity and Language Integrated Bayesian and evolutionaRy optimizAtion), a genetic algorithm based framework that pre-ranks candidate molecules using multiple critics before oracle calls: (i) an ensemble of Gaussian process (GP) surrogates defined over multiple molecular fingerprints and (ii) a pretrained text-molecule aligned encoder CLAMP. The GP ensemble enables adaptive selection of task-appropriate fingerprints, while CLAMP provides a zero-shot scoring signal from task descriptions by measuring the similarity between molecular and text embeddings. On the Practical Molecular Optimization (PMO) benchmark with a budget of 1,000 evaluations (PMO-1K), MolLIBRA-L, our variant with a language-model-based candidate generator, attains the best Top-10 AUC on 14/22 tasks and the highest overall sum of Top-10 AUC across tasks among prior methods.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 32 of its 50 references that are in the map. First posted on arXiv 29 Jan 2026.
Builds on
32 of 50 references.
References · 32
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
- 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 762
- 2021GFlowNet Foundationscited by 286
- 2017Molecular De Novo Design through Deep Reinforcement Learningcited by 264
- 2022Sample Efficiency Matters: A Benchmark for Practical Molecular Optimizationcited by 151
- 2021MARS: Markov Molecular Sampling for Multi-objective Drug Discoverycited by 125
- 2014Generalized Product of Experts for Automatic and Principled Fusion of Gaussian Process Predictionscited by 66
- 2024Efficient Evolutionary Search Over Chemical Space with Large Language Modelscited by 59
- 2025GenMol: A Drug Discovery Generalist with Discrete Diffusioncited by 47
- 2023Enhancing Activity Prediction Models in Drug Discovery with the Ability to Understand Human Languagecited by 44
- 2022GAUCHE: A Library for Gaussian Processes in Chemistrycited by 40
20 more
- 2024Genetic-guided GFlowNets for Sample Efficient Molecular Optimizationcited by 36
- 2021DOCKSTRING: easy molecular docking yields better benchmarks for ligand designcited by 33
- 2023Genetic algorithms are strong baselines for molecule generationcited by 31
- 2024LICO: Large Language Models for In-Context Molecular Optimizationcited by 26
- 2022Surrogate modeling for Bayesian optimization beyond a single Gaussian processcited by 22
- 2024A survey and benchmark of high-dimensional Bayesian optimization of discrete sequencescited by 22
- 2024Molecule Generation with Fragment Retrieval Augmentationcited by 22
- 2023Searching for High-Value Molecules Using Reinforcement Learning and Transformerscited by 18
- 2025LLINBO: Trustworthy LLM-in-the-Loop Bayesian Optimizationcited by 13
- 2025MT-Mol:Multi Agent System with Tool-based Reasoning for Molecular Optimizationcited by 13
- 2025Return of the Latent Space COWBOYS: Re-thinking the use of VAEs for Bayesian Optimisation of Structured Spacescited by 13
- 2024Diagnosing and fixing common problems in Bayesian optimization for molecule designcited by 9
- 2024Scikit-fingerprints: easy and efficient computation of molecular fingerprints in Pythoncited by 9
- 2025Graph Diffusion Transformers are In-Context Molecular Designerscited by 6
- 2025Gradient GA: Gradient Genetic Algorithm for Drug Molecular Designcited by 4
- 2025De Novo Molecular Design Enabled by Direct Preference Optimization and Curriculum Learningcited by 4
- 2025A Genetic Algorithm for Navigating Synthesizable Molecular Spacescited by 4
- 2025Leveraging Partial SMILES Validation Scheme for Enhanced Drug Design in Reinforcement Learning Frameworkscited by 3
- 2025GP-MoLFormer-Sim: Test Time Molecular Optimization through Contextual Similarity Guidancecited by 2
- 2024Conditional Latent Space Molecular Scaffold Optimization for Accelerated Molecular Designcited by 1
Built on by
Not cited yet.