NVIDIA's collaboration with MMseqs2 enhances protein sequence alignment using GPU acceleration, promising significant advancements in AI-driven drug discovery and protein design.

Research team used ProteinMPNN to expand the sequence space of synthetic binding proteins (SBPs), improving their solubility and stability, and showed ProteinMPNN-designed proteins outperform ...

A phylogenetic tree (left) illustrates the major green plant lineages, from chlorophyte algae to angiosperms. Aligned amino acid sequences (right) show the insertion regions in VAMP72 and VAMP727 ...

The team experimentally quantified the aggregation of more than 100,000 protein sequences, and used this dataset to train the new AI tool for predicting aggregation from sequence.

Smith-Waterman (S-W) algorithm is an optimal sequence alignment method and is widely used for genetic databases. This paper presents a Graphics Processing Units (GPUs) accelerated S-W implementation ...

David Baker, Demis Hassabis and John Jumper shared the Nobel prize in chemistry for work that revolutionized our understanding of protein structure.

Abstract Protein structure prediction has been greatly improved by deep learning in the past few years. However, the most successful methods rely on multiple sequence alignment (MSA) of the sequence ...

The 2023 Lasker Award for Basic Medical Research underscores the value of an AI system that predicts the three-dimensional structure of proteins from the one-dimensional sequence of their amino acids.

Microsoft has open sourced EvoDiff, an AI system and framework that can generate proteins without needing a protein sequence.

Pyridoxal phosphate-dependent enzymes able to use oxygen as a co-substrate have emerged in multiple protein families. Here, we use crystallography to solve the 2.40 Å resolution crystal structure of ...