papers

Publications (22)

q-bio.BM2026

Minimal-Action Discrete Schrödinger Bridge Matching for Peptide Sequence Design

Shrey Goel, Pranam Chatterjee

Generative modeling of peptide sequences requires navigating a discrete and highly constrained space in which many intermediate states are chemically implausible or unstable. Exist…

q-bio.BM2024

PepMLM: Target Sequence-Conditioned Generation of Therapeutic Peptide Binders via Span Masked Language Modeling

Tianlai Chen, Madeleine Dumas, Rio Watson +17

Target proteins that lack accessible binding pockets and conformational stability have posed increasing challenges for drug development. Induced proximity strategies, such as PROTA…

cs.LG2025

TR2-D2: Tree Search Guided Trajectory-Aware Fine-Tuning for Discrete Diffusion

Sophia Tang, Yuchen Zhu, Molei Tao +1

Reinforcement learning with stochastic optimal control offers a promising framework for diffusion fine-tuning, where a pre-trained diffusion model is optimized to generate paths th…

q-bio.BM2026

Rethinking Benchmarks and Models for Enzyme Specificity Prediction

Elizabeth H. Mahood, Natália Komorníková, Tomáš Pluskal +1

Artificial Intelligence has had a profound impact on the biological sciences, and in particular has accelerated research on protein form and function. Enzymes are no exception: a s…

cs.LG2026

Path Planning for Masked Diffusion Model Sampling

Fred Zhangzhi Peng, Zachary Bezemek, Sawan Patel +5

Any order generation of discrete data using masked diffusion models (MDMs) offers a compelling alternative to traditional autoregressive models, especially in domains that lack a n…

q-bio.BM2026

SF-Cluster: Frustration-Guided MSA Subsampling for Alternative Protein Conformation Recovery

Hanqun Cao, Zijun Gao, Chunbin Gu +3

Deep-learning structure predictors are sensitive to their multiple sequence alignment (MSA) input, making MSA subsampling a practical route to recovering alternative conformations.…