Life Sciences

PeSTo: a new AI tool for predicting protein interactions

Scientists at EPFL have developed PeSTo, an AI model for predicting protein binding interfaces with proteins, nucleic acids, lipids, ions, and small molecules with high confidence. The model's low computational cost enables the processing large amounts of structural data, opening up opportunities for discovering new biology.

Predict what a mouse sees by decoding brain signals

A research team from EPFL has developed a novel machine-learning algorithm that can reveal the hidden structure in data recorded from the brain, predicting complex information such as what mice see.

Engineering molecular interactions with machine learning

By using deep learning-generated ‘fingerprints’ to characterize millions of protein fragments, EPFL researchers have computationally designed novel protein binders that attach seamlessly to key targets, including the SARS-CoV-2 spike protein.

How to make self-folding surgical tools

For minimally invasive surgery, the instruments used must be small. ETH Zurich researchers have now developed a method to transport large devices through a narrow catheter. This expands the possibilities for designing minimally invasive surgical tools.

A new tool for protein sequence generation and design

EPFL researchers have developed a new technique that uses a protein language model for generating protein sequences with comparable properties to natural sequences. The method outperforms traditional models and offers promising potential for protein design.

Oral bacteria may increase heart disease risk

Researchers at EPFL have found that infection with a common bacterium that is linked to periodontal disease, oral cancers, and bad breath may cause a small increase in the risk of cardiovascular disease.

2 3 4

5

6 7 8 9...

Page 5 of 15