Understanding protein function with a multimodal retrieval-augmented foundation model

• URL: http://arxiv.org/abs/2508.04724v1
• Date: Tue, 05 Aug 2025 15:11:25 GMT
• Title: Understanding protein function with a multimodal retrieval-augmented foundation model
• Authors: Timothy Fei Truong Jr, Tristan Bepler,
• Abstract summary: PoET-2 is a retrieval-augmented protein foundation model that incorporates in-context learning of family-specific evolutionary constraints.<n>PoET-2 achieves state-of-the-art performance on zero-shot variant effect prediction.
• Score: 4.281723404774888
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Protein language models (PLMs) learn probability distributions over natural protein sequences. By learning from hundreds of millions of natural protein sequences, protein understanding and design capabilities emerge. Recent works have shown that scaling these models improves structure prediction, but does not seem to improve mutation understanding and representation quality for protein function prediction. We introduce PoET-2, a multimodal, retrieval-augmented protein foundation model that incorporates in-context learning of family-specific evolutionary constraints with optional structure conditioning to learn generative distributions over protein sequences. PoET-2 uses a hierarchical transformer encoder that is equivariant to sequence context ordering and a dual decoder architecture with both causal and masked language modeling objectives, allowing PoET-2 to operate in both fully generative and bidirectional representation learning modes. PoET-2 achieves state-of-the-art performance on zero-shot variant effect prediction, excelling at scoring variants with multiple mutations and challenging indel mutations. In supervised settings, PoET-2 embeddings outperform previous methods for learning sequence-function relationships, especially with small datasets. This work highlights the benefits of combining retrieval augmentation with multimodal, family-centric modeling for advancing protein foundation models.

Related papers

• ProtCLIP: Function-Informed Protein Multi-Modal Learning [18.61302416993122]
  We develop ProtCLIP, a multi-modality foundation model that represents function-aware protein embeddings.<n>Our ProtCLIP consistently achieves SOTA performance, with remarkable improvements of 75% on average in five cross-modal transformation benchmarks.<n>The experimental results verify the extraordinary potential of ProtCLIP serving as the protein multi-modality foundation model.
  arXiv  Detail & Related papers  (2024-12-28T04:23:47Z)
• DPLM-2: A Multimodal Diffusion Protein Language Model [75.98083311705182]
  We introduce DPLM-2, a multimodal protein foundation model that extends discrete diffusion protein language model (DPLM) to accommodate both sequences and structures. DPLM-2 learns the joint distribution of sequence and structure, as well as their marginals and conditionals. Empirical evaluation shows that DPLM-2 can simultaneously generate highly compatible amino acid sequences and their corresponding 3D structures.
  arXiv  Detail & Related papers  (2024-10-17T17:20:24Z)
• Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Backbone Generation [55.93511121486321]
  We introduce FoldFlow-2, a novel sequence-conditioned flow matching model for protein structure generation.<n>We train FoldFlow-2 at scale on a new dataset that is an order of magnitude larger than PDB datasets of prior works.<n>We empirically observe that FoldFlow-2 outperforms previous state-of-the-art protein structure-based generative models.
  arXiv  Detail & Related papers  (2024-05-30T17:53:50Z)
• Learning to Predict Mutation Effects of Protein-Protein Interactions by Microenvironment-aware Hierarchical Prompt Learning [78.38442423223832]
  We develop a novel codebook pre-training task, namely masked microenvironment modeling. We demonstrate superior performance and training efficiency over state-of-the-art pre-training-based methods in mutation effect prediction.
  arXiv  Detail & Related papers  (2024-05-16T03:53:21Z)
• Diffusion Language Models Are Versatile Protein Learners [75.98083311705182]
  This paper introduces diffusion protein language model (DPLM), a versatile protein language model that demonstrates strong generative and predictive capabilities for protein sequences. We first pre-train scalable DPLMs from evolutionary-scale protein sequences within a generative self-supervised discrete diffusion probabilistic framework. After pre-training, DPLM exhibits the ability to generate structurally plausible, novel, and diverse protein sequences for unconditional generation.
  arXiv  Detail & Related papers  (2024-02-28T18:57:56Z)
• xTrimoPGLM: Unified 100B-Scale Pre-trained Transformer for Deciphering the Language of Protein [74.64101864289572]
  We propose a unified protein language model, xTrimoPGLM, to address protein understanding and generation tasks simultaneously.<n>xTrimoPGLM significantly outperforms other advanced baselines in 18 protein understanding benchmarks across four categories.<n>It can also generate de novo protein sequences following the principles of natural ones, and can perform programmable generation after supervised fine-tuning.
  arXiv  Detail & Related papers  (2024-01-11T15:03:17Z)
• Pairing interacting protein sequences using masked language modeling [0.3222802562733787]
  We develop a method to pair interacting protein sequences using protein language models trained on sequence alignments. We exploit the ability of MSA Transformer to fill in masked amino acids in multiple sequence alignments using the surrounding context. We show that it captures inter-chain coevolution while it was trained on single-chain data, which means that it can be used out-of-distribution.
  arXiv  Detail & Related papers  (2023-08-14T13:42:09Z)
• Prot2Text: Multimodal Protein's Function Generation with GNNs and Transformers [18.498779242323582]
  We propose a novel approach, Prot2Text, which predicts a protein's function in a free text style. By combining Graph Neural Networks(GNNs) and Large Language Models(LLMs), in an encoder-decoder framework, our model effectively integrates diverse data types.
  arXiv  Detail & Related papers  (2023-07-25T09:35:43Z)
• PoET: A generative model of protein families as sequences-of-sequences [5.05828899601167]
  We propose a generative model of whole protein families that learns to generate sets of related proteins as sequences-of-sequences. PoET can be used as a retrieval-augmented language model to generate and score arbitrary modifications conditioned on any protein family of interest. We show that PoET outperforms existing protein language models and evolutionary sequence models for variant function prediction across proteins of all depths.
  arXiv  Detail & Related papers  (2023-06-09T16:06:36Z)
• Retrieved Sequence Augmentation for Protein Representation Learning [40.13920287967866]
  We introduce Retrieved Sequence Augmentation for protein representation learning without additional alignment or pre-processing. We show that our model can transfer to new protein domains better and outperforms MSA Transformer on de novo protein prediction. Our study fills a much-encountered gap in protein prediction and brings us a step closer to demystifying the domain knowledge needed to understand protein sequences.
  arXiv  Detail & Related papers  (2023-02-24T10:31:45Z)
• Pre-training Co-evolutionary Protein Representation via A Pairwise Masked Language Model [93.9943278892735]
  Key problem in protein sequence representation learning is to capture the co-evolutionary information reflected by the inter-residue co-variation in the sequences. We propose a novel method to capture this information directly by pre-training via a dedicated language model, i.e., Pairwise Masked Language Model (PMLM) Our result shows that the proposed method can effectively capture the interresidue correlations and improves the performance of contact prediction by up to 9% compared to the baseline.
  arXiv  Detail & Related papers  (2021-10-29T04:01:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.