Michael Bronstein outlines his vision for the new Aithyra Institute, which aims to transform biological sciences using AI, with a focus on developing novel approaches to data collection, model training, and hypothesis generation to advance research and improve human health. [Image: see text]
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11549334 | PMC |
| http://dx.doi.org/10.1038/s44319-024-00268-6 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Targeting protein-ligand neosurfaces with a generalizable deep learning tool.
Nature
January 2025
Laboratory of Protein Design and Immunoengineering, Institute of Bioengineering, Ecole polytechnique fédérale de Lausanne, Lausanne, Switzerland.
Molecular recognition events between proteins drive biological processes in living systems. However, higher levels of mechanistic regulation have emerged, in which protein-protein interactions are conditioned to small molecules. Despite recent advances, computational tools for the design of new chemically induced protein interactions have remained a challenging task for the field.
View Article and Find Full Text PDFStructure-based drug design with equivariant diffusion models.
Nat Comput Sci
December 2024
École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland.
Article Synopsis
- - Structure-based drug design (SBDD) focuses on creating small molecules that accurately target specific proteins, using structural data to help propose new drug candidates.
- - Current methods typically require extensive dataset preparation and retraining for different tasks, while our approach introduces a single pretrained model that can handle multiple design challenges.
- - We introduce DiffSBDD, a diffusion model that generates new ligands based on protein structures, and demonstrate how it can be enhanced with constraints for better drug candidate quality.
Exploring "dark-matter" protein folds using deep learning.
Cell Syst
October 2024
École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland; Swiss Institute of Bioinformatics (SIB), Lausanne, Switzerland. Electronic address:
Article Synopsis
- De novo protein design aims to create new proteins that evolution hasn't explored, with challenges in developing structural templates to guide the design process.* -
- Researchers introduced "Genesis," a convolutional variational autoencoder, which effectively learns protein structure patterns and collaborates with trRosetta to design sequences for various protein folds.* -
- The team demonstrated Genesis's ability to replicate native-like structural features in both known and novel protein folds, showcasing its potential for rapid protein design while addressing designability issues effectively.*
Message-Passing Monte Carlo: Generating low-discrepancy point sets via graph neural networks.
Proc Natl Acad Sci U S A
October 2024
Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139.
Discrepancy is a well-known measure for the irregularity of the distribution of a point set. Point sets with small discrepancy are called low discrepancy and are known to efficiently fill the space in a uniform manner. Low-discrepancy points play a central role in many problems in science and engineering, including numerical integration, computer vision, machine perception, computer graphics, machine learning, and simulation.
View Article and Find Full Text PDFIdentifying psychological predictors of SARS-CoV-2 vaccination: A machine learning study.
Vaccine
August 2024
Department of Psychiatry and Behavioral Sciences, University of Minnesota, MN, USA.
Background: Major barriers to addressing SARS-CoV-2 vaccine hesitancy include limited knowledge of what causes delay/refusal of SARS-CoV-2 vaccination and limited ability to predict who will remain unvaccinated over significant time periods despite vaccine availability. The present study begins to address these barriers by developing a machine learning model that prospectively predicts who will persist in not vaccinating against SARS-CoV-2.
Method: Unvaccinated individuals (n = 325) who completed a baseline survey were followed over the six-month period when vaccines against SARS-CoV-2 were first widely available (April-October 2021).
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!