Jesper Salomon

This paper investigates cross-species vs species-specific prediction of protein melting temperatures and finds that cross-species models perform no better than species-specific ones.

Kermut is a Gaussian process regression model for protein variant effect prediction that provides uncertainty estimates through its posterior.

The paper curates a benchmark dataset for exploring protein fitness landscapes using wildtype sequences and evaluates different representation paradigms for their predictive power.

This paper evaluates how different performance metrics and generalization definitions affect the assessment of protein regression models.

NetSolP predicts protein solubility in E. coli from sequence using transformers, achieving state-of-the-art performance with reduced dataset bias.

The paper develops a machine learning model to predict recombinant protein expression in Bacillus subtilis using deep protein representations, achieving moderate performance for prioritizing expression candidates.