Explore projects

This project aims to offer a platform for sharing ideas, resources, tools & techniques, interesting publications, interviews and stories from all our community members. https://grp-bio-it.embl-community.io/blog/

This script implements a machine learning pipeline that integrates the ESM2 transformer-based protein model with a Logistic Regression classifier to predict the detectability of microprotein sequences by Mass Spectrometry. The script preprocesses data, extracts embeddings from sequences, performs feature selection, trains a logistic regression model, and evaluates its performance using multiple metrics.

Rendered at: https://grp-bio-it.embl-community.io/template-pages-workbench/