P
Pablo Gainza
Researcher at École Polytechnique Fédérale de Lausanne
Publications - 25
Citations - 1182
Pablo Gainza is an academic researcher from École Polytechnique Fédérale de Lausanne. The author has contributed to research in topics: Protein design & Computer science. The author has an hindex of 14, co-authored 22 publications receiving 679 citations. Previous affiliations of Pablo Gainza include Swiss Institute of Bioinformatics & Duke University.
Papers
More filters
Journal ArticleDOI
Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning.
Pablo Gainza,Freyr Sverrisson,Federico Monti,Emanuele Rodolà,Davide Boscaini,Michael M. Bronstein,Michael M. Bronstein,Bruno E. Correia +7 more
TL;DR: MaSIF (molecular surface interaction fingerprinting) is presented, a conceptual framework based on a geometric deep learning method to capture fingerprints that are important for specific biomolecular interactions that will lead to improvements in the understanding of protein function and design.
Book ChapterDOI
OSPREY: protein design with ensembles, flexibility, and provable algorithms.
Pablo Gainza,Kyle E. Roberts,Ivelin S. Georgiev,Ryan H. Lilien,Daniel A. Keedy,Cheng-Yu Chen,Faisal Reza,Amy C. Anderson,David S. Richardson,Jane S. Richardson,Bruce R. Donald +10 more
TL;DR: It is shown in detail how OSPREY has been used to predict resistance mutations and explained why improved flexibility, ensembles, and provability are essential for this application.
Journal ArticleDOI
Protein Design Using Continuous Rotamers
TL;DR: It is shown that allowing continuous side-chain flexibility (which is called continuous rotamers) greatly improves protein flexibility modeling and presents a new protein design algorithm based on the dead-end elimination (DEE) algorithm, which is called iMinDEE, that makes the use of continuousRotamers feasible in larger systems.
Journal ArticleDOI
Optimization of therapeutic antibodies by predicting antigen specificity from antibody sequence via deep learning.
Derek M Mason,Simon Friedensohn,Cédric R. Weber,Christian Jordi,Bastian Wagner,Simon M Meng,Roy A. Ehling,Lucia Bonati,Jan Dahinden,Pablo Gainza,Bruno E. Correia,Sai T. Reddy +11 more
TL;DR: In this article, the authors used deep learning models trained on antibody-mutagenesis libraries to generate antibody variants and predict their antigen specificity, which can then be filtered for viscosity, clearance, solubility and immunogenicity.
Journal ArticleDOI
A computationally designed chimeric antigen receptor provides a small-molecule safety switch for T-cell therapy.
Greta Giordano-Attianese,Greta Giordano-Attianese,Pablo Gainza,Pablo Gainza,Elise Gray-Gaillard,Elise Gray-Gaillard,Elisabetta Cribioli,Elisabetta Cribioli,Sailan Shui,Sailan Shui,Seong Hoon Kim,Mi Jeong Kwak,Sabrina Vollers,Sabrina Vollers,Angel De Jesus Corria Osorio,Angel De Jesus Corria Osorio,Patrick Reichenbach,Patrick Reichenbach,Jaume Bonet,Jaume Bonet,Byung-Ha Oh,Melita Irving,Melita Irving,George Coukos,George Coukos,Bruno E. Correia,Bruno E. Correia +26 more
TL;DR: A chemically disruptable heterodimer (CDH) based on the binding of two human proteins that self-assembles, can be disrupted by a small-molecule drug and has a high-affinity protein interface with minimal amino acid deviation from wild-type human proteins is designed.