# Ligand-Conditioned Discrete Diffusion for Protein Sequence-Structure Co-Design

arXiv: https://arxiv.org/abs/2605.27413 · HTML: https://mlsanity.com/paper/2605.27413/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Flow matching, time series and science, one of 14 directions in Diffusion models.
- Builds on 19 of its 44 references that are in the map.
- First posted on arXiv 15 May 2026.

## Placed in

- Diffusion models / [Flow matching, time series and science](https://mlsanity.com/diffusion/flow-matching-time-series-and-science/)

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Large Language Diffusion Models](https://mlsanity.com/paper/2502.09992/) (2025)
- [Simple and Effective Masked Diffusion Language Models](https://mlsanity.com/paper/2406.07524/) (2024)
- [Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation](https://mlsanity.com/paper/2310.05737/) (2023)
- [Simplified and Generalized Masked Diffusion for Discrete Data](https://mlsanity.com/paper/2406.04329/) (2024)
- [Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models](https://mlsanity.com/paper/2503.09573/) (2025)
- [Learning from Protein Structure with Geometric Vector Perceptrons](https://mlsanity.com/paper/2009.01411/) (2020)
- [Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions](https://mlsanity.com/paper/2502.06768/) (2025)
- [Remasking Discrete Diffusion Models with Inference-Time Scaling](https://mlsanity.com/paper/2503.00307/) (2025)
- [A Reparameterized Discrete Diffusion Model for Text Generation](https://mlsanity.com/paper/2302.05737/) (2023)
- [MolCA: Molecular Graph-Language Modeling with Cross-Modal Projector and Uni-Modal Adapter](https://mlsanity.com/paper/2310.12798/) (2023)
- [Diffusion Language Models Are Versatile Protein Learners](https://mlsanity.com/paper/2402.18567/) (2024)
- [DPLM-2: A Multimodal Diffusion Protein Language Model](https://mlsanity.com/paper/2410.13782/) (2024)
- [La-Proteina: Atomistic Protein Generation via Partially Latent Flow Matching](https://mlsanity.com/paper/2507.09466/) (2025)
- [ProtT3: Protein-to-Text Generation for Text-based Protein Understanding](https://mlsanity.com/paper/2405.12564/) (2024)
- [NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generation](https://mlsanity.com/paper/2502.12638/) (2025)
- [Scaling Atomistic Protein Binder Design with Generative Pretraining and Test-Time Compute](https://mlsanity.com/paper/2603.27950/) (2026)
- [Towards Unified and Lossless Latent Space for 3D Molecular Latent Diffusion Modeling](https://mlsanity.com/paper/2503.15567/) (2025)
- [Elucidating the Design Space of Multimodal Protein Language Models](https://mlsanity.com/paper/2504.11454/) (2025)

## Abstract (arXiv)

Proteins perform their biological functions through three-dimensional structures encoded by amino acid sequences, and ligand-binding protein co-design requires models that generate sequence-structure compatible proteins under explicit ligand constraints. Although continuous diffusion and flow-based models support ligand-aware design in coordinate or latent spaces, existing discrete diffusion protein language models mainly operate over sequence or structure tokens without direct small-molecule conditioning. We introduce ProtLiD2, a Protein Ligand-conditioned Discrete Diffusion model for protein sequence-structure co-design. ProtLiD2 jointly generates amino-acid sequence and discrete structure tokens while incorporating ligand chemical and geometric information through geometry-aware cross-attention. Trained on over one million ligand-protein complexes, ProtLiD2 extends masked discrete diffusion to ligand-aware functional protein design. We further propose maximum confidence-margin guided ReMask decoding, an inference-time self-correction strategy that retains confident predictions and remasks uncertain tokens. ProtLiD2 improves global fold confidence over Complexa in whole-protein design, increasing TM-score from 0.672 to 0.802 and pLDDT from 64.55 to 73.00. In pocket co-design, ProtLiD2 reduces active-site BB-RMSD from 3.46/3.40AA for FAIR/PocketGen to 1.97AA, and improves ligand-aware pass rates over PocketGen from 14.86% to 59.73% and from 6.08% to 23.49% under stricter docking thresholds. These results support ligand-conditioned discrete diffusion as an effective token-space framework for functional protein co-design. Code will be available at https://github.com/auroua/ProtLiD.