@article{sgarbossa_protmamba_2025,
	title = {{ProtMamba}: a homology-aware but alignment-free protein state space model},
	volume = {41},
	rights = {https://creativecommons.org/licenses/by/4.0/},
	issn = {1367-4811},
	url = {https://academic.oup.com/bioinformatics/article/doi/10.1093/bioinformatics/btaf348/8161314},
	doi = {10.1093/bioinformatics/btaf348},
	shorttitle = {{ProtMamba}},
	abstract = {Abstract 
             
              Motivation 
              Protein language models are enabling advances in elucidating the sequence-to-function mapping, and have important applications in protein design. Models based on multiple sequence alignments efficiently capture the evolutionary information in homologous protein sequences, but multiple sequence alignment construction is imperfect. 
             
             
              Results 
              We present {ProtMamba}, a homology-aware but alignment-free protein language model based on the Mamba architecture. In contrast with attention-based models, {ProtMamba} efficiently handles very long context, comprising hundreds of protein sequences. It is also computationally efficient. We train {ProtMamba} on a large dataset of concatenated homologous sequences, using two {GPUs}. We combine autoregressive modeling and masked language modeling through a fill-in-the-middle training objective. This makes the model adapted to various protein design applications. We demonstrate {ProtMamba}’s usefulness for sequence generation, motif inpainting, fitness prediction, and modeling intrinsically disordered regions. For homolog-conditioned sequence generation, {ProtMamba} outperforms state-of-the-art models. {ProtMamba}’s competitive performance, despite its relatively small size, sheds light on the importance of long-context conditioning. 
             
             
              Availability and implementation 
              A Python implementation of {ProtMamba} is freely available in our {GitHub} repository: https://github.com/Bitbol-Lab/{ProtMamba}-ssm and archived at https://doi.org/10.5281/zenodo.15584634.},
	pages = {btaf348},
	number = {6},
	journaltitle = {Bioinformatics},
	author = {Sgarbossa, Damiano and Malbranke, Cyril and Bitbol, Anne-Florence},
	editor = {Cheng, Jianlin},
	urldate = {2025-07-07},
	date = {2025-06-02},
	langid = {english},
}