4 papers
Sparsity is All You Need: Rethinking Biological Pathway-Informed Approaches in Deep Learning
Isabella Caranzano, Corrado Pancotti, Cesare Rollo +4
Biologically-informed neural networks typically leverage pathway annotations to enhance performance in biomedical applications. We hypothesized that the benefits of pathway integra…
JanusDDG: A Thermodynamics-Compliant Model for Sequence-Based Protein Stability via Two-Fronts Multi-Head Attention
Guido Barducci, Ivan Rossi, Francesco Codicè +6
Understanding how residue variations affect protein stability is crucial for designing functional proteins and deciphering the molecular mechanisms underlying disease-related mutat…
Mass Balance Approximation of Unfolding Improves Potential-Like Methods for Protein Stability Predictions
Ivan Rossi, Guido Barducci, Tiziana Sanavia +3
The prediction of protein stability changes following single-point mutations plays a pivotal role in computational biology, particularly in areas like drug discovery, enzyme reengi…
How good Neural Networks interpretation methods really are? A quantitative benchmark
Antoine Passemiers, Pietro Folco, Daniele Raimondi +3
Saliency Maps (SMs) have been extensively used to interpret deep learning models decision by highlighting the features deemed relevant by the model. They are used on highly nonline…