Back

The geometry of hidden representations of protein language models

Valeriani, L.; Cuturello, F.; Ansuini, A.; Cazzaniga, A.

2022-10-26 bioinformatics
10.1101/2022.10.24.513504 bioRxiv
Show abstract

Protein language models (pLMs) transform their input into a sequence of hidden representations whose geometric behavior changes across layers. Looking at fundamental geometric properties such as the intrinsic dimension and the neighbor composition of these representations, we observe that these changes highlight a pattern characterized by three distinct phases. This phenomenon emerges across many models trained on diverse datasets, thus revealing a general computational strategy learned by pLMs to reconstruct missing parts of the data. These analyses show the existence of low-dimensional maps that encode evolutionary and biological properties such as remote homology and structural information. Our geometric approach sets the foundations for future systematic attempts to understand the space of protein sequences with representation learning techniques.

Matching journals

The top 8 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.