265 citations · 619 across the 12 of their papers we have counts for
12 papers
Fast uncovering of protein sequence diversity from structure
Luca Alessandro Silva, Barthelemy Meynard-Piganeau, Carlo Lucibello +1
We present InvMSAFold, an inverse folding method for generating protein sequences that is optimized for diversity and speed. For a given structure, InvMSAFold generates the paramet…
The twin peaks of learning neural networks
Elizaveta Demyanenko, Christoph Feinauer, Enrico M. Malatesta +1
Recent works demonstrated the existence of a double-descent phenomenon for the generalization error of neural networks, where highly overparameterized models escape overfitting and…
The Mean Dimension of Neural Networks -- What causes the interaction effects?
Roman Hahn, Christoph Feinauer, Emanuele Borgonovo
Owen and Hoyt recently showed that the effective dimension offers key structural information about the input-output mapping underlying an artificial neural network. Along this line…
Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry
Fabrizio Pittorino, Antonio Ferraro, Gabriele Perugini +3
We systematize the approach to the investigation of deep neural network landscapes by basing it on the geometry of the space of implemented functions rather than the space of param…
Reconstruction of Pairwise Interactions using Energy-Based Models
Christoph Feinauer, Carlo Lucibello
Pairwise models like the Ising model or the generalized Potts model have found many successful applications in fields like physics, biology, and economics. Closely connected is the…
Entropic gradient descent algorithms and wide flat minima
Fabrizio Pittorino, Carlo Lucibello, Christoph Feinauer +4
The properties of flat minima in the empirical risk landscape of neural networks have been debated for some time. Increasing evidence suggests they possess better generalization ca…
Natural representation of composite data with replicated autoencoders
Matteo Negri, Davide Bergamini, Carlo Baldassi +2
Generative processes in biology and other fields often produce data that can be regarded as resulting from a composition of basic features. Here we present an unsupervised method b…
Inverse Statistical Physics of Protein Sequences: A Key Issues Review
Simona Cocco, Christoph Feinauer, Matteo Figliuzzi +2
In the course of evolution, proteins undergo important changes in their amino acid sequences, while their three-dimensional folded structure and their biological function remain re…
Context-Aware Prediction of Pathogenicity of Missense Mutations Involved in Human Disease
Christoph Feinauer, Martin Weigt
Amino-acid substitutions are implicated in a wide range of human diseases, many of which are lethal. Distinguishing such mutations from polymorphisms without significant effect on…
Inter-protein sequence co-evolution predicts known physical interactions in bacterial ribosomes and the trp operon
Christoph Feinauer, Hendrik Szurmant, Martin Weigt +1
Interaction between proteins is a fundamental mechanism that underlies virtually all biological processes. Many important interactions are conserved across a large variety of speci…
Fast and accurate multivariate Gaussian modeling of protein families: Predicting residue contacts and protein-interaction partners
Carlo Baldassi, Marco Zamparo, Christoph Feinauer +4
In the course of evolution, proteins show a remarkable conservation of their three-dimensional structure and their biological function, leading to strong evolutionary constraints o…
Improving contact prediction along three dimensions
Christoph Feinauer, Marcin J. Skwark, Andrea Pagnani +1
Correlation patterns in multiple sequence alignments of homologous proteins can be exploited to infer information on the three-dimensional structure of their members. The typical p…