Benchmarking Large Protein Language Models

Analogous to natural language models, there are several large protein language models that models the protein sequences. In this project the students will benchmark a dozen of protein lanaguage models  in protein function related retrieval task.
** Interested students must have taken CS412-Machine Learning course or taking it this Spring semester. 
** The students must be proficient programmers in Python and be able to conduct large scale computational experiments.
** Interested students should send an email to otastan@sabanciuniv.edu with a title of the PURE project, indicating why they are interested in this project and their  skill set.