RESEARCH: PROTEIN-DYNAMICS-MODELING
FOLDING PROJECT #19503 PROFILE

This project uses AI to understand how proteins move and interact. This can help us predict how viruses change and design new drugs.

Summary The AI4Science Group at Freie Universität Berlin develops machine learning methods for physical sciences, with a focus on physics-constrained learning algorithms, complex dynamical systems analysis, efficient generative learning methods for statistical mechanics, and highly accurate machine learning methods for quantum mechanics.

They are an interdisciplinary team of mathematicians, chemists, physicists, and computer scientists. Details The primary objective of this project is to develop large-scale artificial intelligence (AI) models to efficiently sample protein dynamics and predict the stability of folded states and protein-protein interactions.

Being able to do this efficiently and accurately would be a game-changer for the prediction of virus mutants and the design of therapies for various diseases.

AI techniques have demonstrated exceptional performance on benchmark systems and have the potential to vastly speed up computations yet maintain comparable levels of accuracy as classical molecular dynamics simulations. The project aims to generate a comprehensive dataset of small protein systems that will provide the necessary information for creating the next generation of AI models for protein simulations.

We will collaborate with the Clementi Group at Freie Universität Berlin to achieve this goal.

artificial intelligence

A branch of computer science dealing with the creation of intelligent agents.

Artificial intelligence (AI) is a field of computer science focused on creating machines that can perform tasks that typically require human intelligence. This includes learning from data, recognizing patterns, making decisions, and solving problems.

machine learning

A type of AI that allows software applications to become more accurate at predicting outcomes without being explicitly programmed to do so.

Machine learning is a subset of AI where computer algorithms learn from data to make predictions or decisions. Instead of relying on explicit instructions, these algorithms identify patterns and relationships in data to improve their performance over time.

protein dynamics

The motion and flexibility of protein molecules.

Protein dynamics refers to the constant movement and flexibility of protein molecules. Understanding these movements is crucial for comprehending how proteins function in biological systems.

protein-protein interactions

The ways in which proteins bind to and interact with each other.

Protein-protein interactions are essential for many biological processes. Proteins often work together by binding to each other, forming complexes that carry out specific tasks.

virus mutants

Variants of a virus that have genetic changes.

Virus mutants are versions of a virus with altered genetic sequences. These changes can lead to differences in the virus's behavior, such as increased transmissibility or resistance to antiviral drugs.

therapies

Treatments for diseases or medical conditions.

Therapies are interventions aimed at treating or managing diseases. They can involve medications, surgery, lifestyle changes, or a combination of approaches.