Prot2Token: A Unified Framework for Protein Modeling via Next-Token Prediction

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Pourmirzaei, Mahdi, Esmaili, Farzaneh, Alqarghuli, Salhuldin, Pourmirzaei, Mohammadreza, Han, Ye, Chen, Kai, Rezaei, Mohsen, Wang, Duolin, Xu, Dong
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912754691997696
author Pourmirzaei, Mahdi
Esmaili, Farzaneh
Alqarghuli, Salhuldin
Pourmirzaei, Mohammadreza
Han, Ye
Chen, Kai
Rezaei, Mohsen
Wang, Duolin
Xu, Dong
author_facet Pourmirzaei, Mahdi
Esmaili, Farzaneh
Alqarghuli, Salhuldin
Pourmirzaei, Mohammadreza
Han, Ye
Chen, Kai
Rezaei, Mohsen
Wang, Duolin
Xu, Dong
contents The diverse nature of protein prediction tasks has traditionally necessitated specialized models, hindering the development of broadly applicable and computationally efficient Protein Language Models (PLMs). In this work, we introduce Prot2Token, a unified framework that overcomes these challenges by converting a wide spectrum of protein-related predictions-from sequence-level properties and residue-specific attributes to complex inter-protein interactions-into a standardized next-token prediction format. At its core, Prot2Token employs an autoregressive decoder, conditioned on embeddings from pre-trained protein encoders and guided by learnable task tokens, to perform diverse predictions. This architecture uniquely facilitates multi-task learning, enabling general-purpose decoders to generalize across five distinct categories. We present extensive experimental validation across a variety of benchmarks, demonstrating Prot2Token's predictive power in different types of protein-prediction tasks. In 3D structure prediction, Prot2Token delivers substantial speedups (up to 1000x faster than AlphaFold2 with MSA on the same hardware) while, across other numerous tasks, matching or surpassing specialized methods. Beyond that, we introduce an auxiliary self-supervised decoder pre-training approach to improve spatially sensitive task performance. Prot2Token thus offers a step towards standardizing biological prediction into a generative interface, promising to accelerate biological discovery and the development of novel therapeutics. The code is available at https://github.com/mahdip72/prot2token .
format Preprint
id arxiv_https___arxiv_org_abs_2505_20589
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Prot2Token: A Unified Framework for Protein Modeling via Next-Token Prediction
Pourmirzaei, Mahdi
Esmaili, Farzaneh
Alqarghuli, Salhuldin
Pourmirzaei, Mohammadreza
Han, Ye
Chen, Kai
Rezaei, Mohsen
Wang, Duolin
Xu, Dong
Machine Learning
Quantitative Methods
The diverse nature of protein prediction tasks has traditionally necessitated specialized models, hindering the development of broadly applicable and computationally efficient Protein Language Models (PLMs). In this work, we introduce Prot2Token, a unified framework that overcomes these challenges by converting a wide spectrum of protein-related predictions-from sequence-level properties and residue-specific attributes to complex inter-protein interactions-into a standardized next-token prediction format. At its core, Prot2Token employs an autoregressive decoder, conditioned on embeddings from pre-trained protein encoders and guided by learnable task tokens, to perform diverse predictions. This architecture uniquely facilitates multi-task learning, enabling general-purpose decoders to generalize across five distinct categories. We present extensive experimental validation across a variety of benchmarks, demonstrating Prot2Token's predictive power in different types of protein-prediction tasks. In 3D structure prediction, Prot2Token delivers substantial speedups (up to 1000x faster than AlphaFold2 with MSA on the same hardware) while, across other numerous tasks, matching or surpassing specialized methods. Beyond that, we introduce an auxiliary self-supervised decoder pre-training approach to improve spatially sensitive task performance. Prot2Token thus offers a step towards standardizing biological prediction into a generative interface, promising to accelerate biological discovery and the development of novel therapeutics. The code is available at https://github.com/mahdip72/prot2token .
title Prot2Token: A Unified Framework for Protein Modeling via Next-Token Prediction
topic Machine Learning
Quantitative Methods
url https://arxiv.org/abs/2505.20589