A5022146582- Protein Structure and Dynamics
- RNA and protein synthesis mechanisms
- Computational Drug Discovery Methods
- Enzyme Structure and Function
- Machine Learning in Bioinformatics
- Virology and Viral Diseases
- Receptor Mechanisms and Signaling
- Respiratory viral infections research
- Microbial Natural Products and Biosynthesis
- Monoclonal and Polyclonal Antibodies Research
- Advanced Electron Microscopy Techniques and Applications
- Transgenic Plants and Applications
- Genomics and Phylogenetic Studies
- Advanced Fluorescence Microscopy Techniques
- Parvovirus B19 Infection Studies
- Genetics, Bioinformatics, and Biomedical Research
- Cell Image Analysis Techniques
- Biochemical and Structural Characterization
- HIV Research and Treatment
École Polytechnique Fédérale de Lausanne
2022-2024
SIB Swiss Institute of Bioinformatics
2022-2024
Abstract Physical interactions between proteins are essential for most biological processes governing life 1 . However, the molecular determinants of such have been challenging to understand, even as genomic, proteomic and structural data increase. This knowledge gap has a major obstacle comprehensive understanding cellular protein–protein interaction networks de novo design protein binders that crucial synthetic biology translational applications 2–9 Here we use geometric deep-learning...
Protein structures are essential to understanding cellular processes in molecular detail. While advances artificial intelligence revealed the tertiary structure of proteins at scale, their quaternary remains mostly unknown. We devise a scalable strategy based on AlphaFold2 predict homo-oligomeric assemblies across four proteomes spanning tree life. Our results suggest that approximately 45% an archaeal proteome and bacterial 20% two eukaryotic form homomers. predictions accurately capture...
De novo protein design enhances our understanding of the principles that govern folding and interactions, has potential to revolutionize biotechnology through engineering novel functionalities. Despite recent progress in computational strategies, de structures remains challenging, given vast size sequence-structure space. AlphaFold2 (AF2), a state-of-the-art neural network architecture, achieved remarkable accuracy predicting from amino acid sequences. This raises question whether AF2...
Abstract De novo design of complex protein folds using solely computational means remains a substantial challenge 1 . Here we use robust deep learning pipeline to and soluble analogues integral membrane proteins. Unique topologies, such as those from G-protein-coupled receptors 2 , are not found in the proteome, demonstrate that their structural features can be recapitulated solution. Biophysical analyses high thermal stability designs, experimental structures show remarkable accuracy. The...
Protein-protein interactions (PPIs) are at the core of all key biological processes. However, complexity structural features that determine PPIs makes their design challenging. We present BindCraft, an open-source and automated pipeline for
design of complex protein folds using solely computational means remains a significant challenge. Here, we use robust deep learning pipeline to and soluble analogues integral membrane proteins. Unique topologies, such as those from GPCRs, are not found in the proteome demonstrate that their structural features can be recapitulated solution. Biophysical analyses reveal high thermal stability designs experimental structures show remarkable accuracy. The were functionalized with native motifs,...
Abstract Protein structures are essential to understand cellular processes in molecular detail. While advances AI revealed the tertiary structure of proteins at scale, their quaternary remains mostly unknown. Here, we describe a scalable strategy based on AlphaFold2 predict homo-oligomeric assemblies across four proteomes spanning tree life. We find that 50% archaeal, 45% bacterial, and 20% eukaryotic form homomers. Our predictions accurately capture protein homo-oligomerization,...
Abstract Predicting ligand-binding sites, particularly in the absence of previously resolved homologous structures, presents a significant challenge structural biology. Here, we leverage internal pairwise representation AlphaFold2 (AF2) to train model, AF2BIND, accurately predict small-molecule-binding residues given only target protein. AF2BIND uses 20 “bait” amino acids optimally extract binding signal small-molecule ligand. We find that AF2 pair outperforms other neural-network...
De novo protein design explores uncharted sequence and structure space to generate novel proteins not sampled by evolution. A main challenge in de involves crafting "designable" structural templates guide the searches toward adopting target structures. We present a convolutional variational autoencoder that learns patterns of structure, dubbed Genesis. coupled Genesis with trRosetta sequences for set folds found is capable reconstructing native-like distance angle distributions five native...
Abstract De novo protein design enhances our understanding of the principles that govern folding and interactions, has potential to revolutionize biotechnology through engineering novel functionalities. Despite recent progress in computational strategies, de structures remains challenging, given vast size sequence-structure space. AlphaFold2 (AF2), a state-of-the-art neural network architecture, achieved remarkable accuracy predicting from amino acid sequences. This raises question whether...
Abstract Foamy viruses (FVs) constitute a subfamily of retroviruses. Their envelope glycoprotein (Env) drives the merger viral and cellular membranes during entry into cells. The only available structures retroviral Envs are those from human simian immunodeficiency orthoretroviruses, which distantly related to FVs. We report here cryo-EM FV Env ectodomain in pre- post-fusion states, demonstrate structural similarity with fusion protein (F) paramyxo- pneumoviruses, implying an evolutionary...
Foamy viruses (FVs) constitute a subfamily of retroviruses. Their envelope (Env) glycoprotein drives the merger viral and cellular membranes during entry into cells. The only available structures retroviral Envs are those from human simian immunodeficiency orthoretroviruses, which distantly related to FVs. We report cryo–electron microscopy FV Env ectodomain in pre- post-fusion states, unexpectedly demonstrate structural similarity with fusion protein (F) paramyxo- pneumoviruses, implying an...
Abstract Physical interactions between proteins are essential for most biological processes governing life. However, the molecular determinants of such have been challenging to understand, even as genomic, proteomic, and structural data grows. This knowledge gap has a major obstacle comprehensive understanding cellular protein-protein interaction (PPI) networks de novo design protein binders that crucial synthetic biology translational applications. We exploit geometric deep learning...
Abstract De novo protein design aims to explore uncharted sequence-and structure areas generate novel proteins that have not been sampled by evolution. One of the main challenges in de involves crafting “designable” structural templates can guide sequence search towards adopting target structures. Here, we present an approach learn patterns based on a convolutional variational autoencoder, dubbed Genesis. We coupled Genesis with trRosetta sequences for set folds and found is capable...
De novo protein design aims to explore uncharted sequence- and structure areas generate novel proteins that have not been sampled by evolution. One of the main challenges in de involves crafting “designable” structural templates can guide sequence search towards adopting target structures. Here, we present an approach learn patterns based on a convolutional variational autoencoder, dubbed Genesis. We coupled Genesis with trRosetta sequences for set folds found is capable reconstructing...