Overview

Molecular generation studies how to create new chemical structures or 3D conformations that meet goals such as binding a protein, having useful properties, or matching spectral evidence. Common approaches include autoregressive chemical language models, graph and 3D diffusion or flow-matching models, and fragment-based generators; reinforcement learning, search, and active learning can steer their outputs toward desired properties. Researchers compare methods on benchmarks such as QM9, ZINC, MOSES, CrossDocked, and MassSpecGym, evaluating validity, novelty, diversity, property performance, and structural fit. A central challenge is balancing goal-directed optimization with chemical plausibility, diversity, and synthesizability, while ensuring that gains on computational proxies hold up in independent or experimental tests.

Latest papers

CardsList

253 papers16 papers in the last four weeks, down 52% on the four weeks before. 0.1% of all new papers.

  1. SPID: Distilled Protein Backbone Generation

    Oct 3, 2025Liyang Xie, Haoran Zhang, Zhendong Wang +2Diffusion Model DistillationFew-Step Diffusion Sampling

  2. Why Pool When You Can Flow? Active Learning with GFlowNets

    Aug 31, 2025Renfei Zhang, Mohit Pandey, Artem Cherkasov +1Active LearningVirtual Screening

  3. Cross-Modality Controlled Molecule Generation with Diffusion Language Model

    Aug 20, 2025Yunzhe Zhang, Yifei Wang, Khanh Vinh Nguyen +1Diffusion Model GuidanceMultimodal Generation

  4. A Large Scale Investigation of Scaling Limits in Chemical Language Models

    Aug 19, 2025Roshan Balaji, Kamran Chitsaz, Quentin Fournier +2Chemical Language ModelsLanguage Model Scaling Laws

  5. ProteinZero: Self-Improving Protein Generation via Online Reinforcement Learning

    Jun 9, 2025Ziwen Wang, Jiajun Fan, Ruihan Guo +3Protein Language ModelsMolecular Generation

  6. PDFBench: A Benchmark for De novo Protein Design from Function

    May 25, 2025Jiahao Kuang, Nuowei Liu, Jie Wang +3Benchmark DesignMolecular Generation

  7. A Comprehensive Benchmark of Computational Models for Antibody--Antigen Binding Affinity

    May 23, 2025Xinyan Zhao, Yi-Ching Tang, Victor J Cantu +7antibody designProtein Design

  8. AbFlowNet: Optimizing Antibody-Antigen Binding Energy via Diffusion-GFlowNet Fusion

    May 18, 2025Abrar Rahman Abir, Haz Sameen Shahgir, Md Rownok Zahan Ratul +3antibody designMolecular Generation

  9. OmegAMP: Targeted AMP Discovery via Biologically Informed Generation

    Apr 24, 2025Diogo Soares, Leon Hetzel, Paulina Szymczak +6Molecular GenerationConditional Generative Modeling

  10. MolMiner: Toward Controllable, 3D-Aware, Fragment-Based Molecular Design

    Nov 10, 2024Raul Ortega-Ochoa, Tejs Vegge, Jes Frellsen3D Molecular GenerationAutoregressive Generation

  11. Small Molecule Optimization with Large Language Models

    Jul 26, 2024Philipp Guevorguian, Menua Bedrosian, Tigran Fahradyan +3Molecular OptimizationEvolutionary Optimization