Large language models generate functional protein sequences across diverse families

By Ali Madani, Ben Krause, E. Greene, Subu Subramanian, Benjamin P. Mohr, J. Holton, J. L. Olmos, Caiming Xiong, Zachary Z. Sun, Richard Socher and 2 more. Nature Biotechnology, 2023

1,084 citations recorded by the source corpus.

A generative deep-learning model designs artificial proteins with desired enzymatic activities. Deep-learning language models have shown promise in various biotechnological applications, including protein design and engineering. Here we describe ProGen, a language model that can generate protein sequences with a predictable function across large protein families, akin to generating grammatically and semantically correct natural language sentences on diverse topics. The model was trained on 280 million protein sequences from >19,000 families and is augmented with control tags specifying protein properties. ProGen can be further fine-tuned to curated sequences and tags to improve controllable generation performance of proteins from families with sufficient homologous samples. Artificial proteins fine-tuned to five distinct lysozyme families showed similar catalytic efficiencies as natural lysozymes, with sequence identity to natural proteins as low as 31.4%. ProGen is readily adapted to diverse protein families, as we demonstrate with chorismate mutase and malate dehydrogenase.

Subfields: Molecular Biology

View Paper: https://www.semanticscholar.org/paper/835c305e52769a8433f8383e91d33ba6c66ad55b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

1. Pushmeet Kohli
2. Sebastian Nowozin
3. Yaron Lipman
4. Ricky T. Q. Chen

Citations in the corpus

• Discrete Flow Matching (2024, background): “…to other domains such as, code (Roziere et al., 2023; Li et al., 2023; Chen et al., 2021), biology (Zhang et al., 2024; Ferruz and Höcker, 2022; Madani et al., 2023), math (Romera-Paredes et al., 2024; Imani et al., 2023; Ahn et al., 2024), audio (Kreuk et al., 2022; Copet et al., 2024; Hassid…”
• Large language models in medicine (2023, background): “So-called ‘hallucinations’ have been widely reported, where inaccurate information is invented (as it is not represented in the training dataset) and espoused lucidly; an alternative term such as ‘fact fabrication’ is preferred to avoid inappropriate anthropomorphism 81,82 .”
• HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution (2023, neutral): “In contrast to protein sequences, which have had successes in protein language models [29, 31, 32, 17, 5, 41, 14], DNA sequences are orders of magnitudes longer (e.g. the human genome is 3.2B nucleotides) with long-range dependencies and interactions that span over 100k+ nucleotides in length [1].”
• AlphaEvolve: A coding agent for scientific and algorithmic discovery (2025, positive): “In particular, there are numerous recent LLM-based methods that target scientific problems in multiple disciplines, such as materials science [45, 71, 94, 119], chemistry [12, 64], bioinformatics [67, 85], geoscience [79], and quantum physics [30, 78] (for surveys on the topic, see [36, 65, 81]).”
• Multimodal Large Language Models in Health Care: Applications, Challenges, and Future Outlook (2024, neutral): “…proteomics, protein language models are used for secondary structure and contact prediction (ProtTrans [127]), protein sequence generation (ProGen [128]), protein function prediction (ProtST [129]), major posttranslational modification prediction (ProteinBERT [130]), biophysical property…”