Seminar 2: Large language models generate functional protein sequences across diverse families

This week, please read the paper titled as “Large language models generate functional protein sequences across diverse families” by Madani et. al.


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.


  • Read the paper and using the Question Sheet which contains a set of questions designed to guide your reading and understanding.
  • Fill out your question sheet and submit here before the seminar.
  • Be ready to discuss in the seminar.

Join the Seminar

During the seminar, we will walk through the question sheet together. Everyone will be selected at random to answer one or more questions from the question sheet, and/or describe selected figures.