The CAFA6 Challenge: predicting protein function from sequence My strategy involves a dual towers network approach

Here is my approach to the CAFA6 challenge: predicting protein function from sequence. It is based on converting everything into numbers, using ESM2 for protein sequences, and an LLM for Gene Ontology terms.

gmdbioinformatics.substack.com/p/my-strateg...

#CAFA6 #ESM2 #deepLearning #bioinformatics

Understanding Representation Shapes in Protein Language Models

The study examined proteins from the SCOP database using ESM2 models of various sizes and found the richest structural encoding just before the final layer. Read more: getnews.me/understanding-representa... #proteinlanguage #esm2 #scop