MIT Mathematics (@mitmath.bsky.social)

By using a sparse autoencoder, Prof Berger and @bergerlab.bsky.social students uncover how protein language models make predictions."Identifying features that protein language models track has the potential to reveal novel biological insights from these representations." @mitscience.bsky.social

loading . . .

Researchers glimpse the inner workings of protein language models MIT researchers used sparse autoencoders to shed light on the inner workings of protein language models, an advance that could streamline the process of identifying new drugs or vaccine targets. https://news.mit.edu/2025/researchers-glimpse-inner-workings-protein-language-models-0818