A5063532782- Monoclonal and Polyclonal Antibodies Research
- Protein Structure and Dynamics
- Glycosylation and Glycoproteins Research
- RNA and protein synthesis mechanisms
- Methane Hydrates and Related Phenomena
- Biochemical and Structural Characterization
- Computational Drug Discovery Methods
- Spacecraft and Cryogenic Technologies
- Machine Learning in Bioinformatics
- Toxin Mechanisms and Immunotoxins
- Antimicrobial Peptides and Activities
- Peptidase Inhibition and Analysis
- Cell Adhesion Molecules Research
- vaccines and immunoinformatics approaches
- Atmospheric and Environmental Gas Dynamics
- Hydrocarbon exploration and reservoir analysis
- Bacterial Genetics and Biotechnology
- Force Microscopy Techniques and Applications
- CO2 Sequestration and Geologic Interactions
- Platelet Disorders and Treatments
- Enzyme Structure and Function
- Quantum, superfluid, helium dynamics
Johns Hopkins University
2022-2024
National Taiwan University
2018-2020
Abstract Antibodies have the capacity to bind a diverse set of antigens, and they become critical therapeutics diagnostic molecules. The binding antibodies is facilitated by six hypervariable loops that are diversified through genetic recombination mutation. Even with recent advances, accurate structural prediction these remains challenge. Here, we present IgFold, fast deep learning method for antibody structure prediction. IgFold consists pre-trained language model trained on 558 million...
Abstract We present the results for CAPRI Round 54, 5th joint CASP‐CAPRI protein assembly prediction challenge. The offered 37 targets, including 14 homodimers, 3 homo‐trimers, 13 heterodimers antibody–antigen complexes, and 7 large assemblies. On average ~70 CASP predictor groups, more than 20 automatics servers, submitted models each target. A total of 21 941 by these groups 15 scorer were evaluated using model quality measures DockQ score consolidating measures. performance was quantified...
Antibodies have the capacity to bind a diverse set of antigens, and they become critical therapeutics diagnostic molecules. The binding antibodies is facilitated by six hypervariable loops that are diversified through genetic recombination mutation. Even with recent advances, accurate structural prediction these remains challenge. Here, we present IgFold, fast deep learning method for antibody structure prediction. IgFold consists pre-trained language model trained on 558M natural sequences...
Conventional protein-protein docking algorithms usually rely on heavy candidate sampling and reranking, but these steps are time-consuming hinder applications that require high-throughput complex structure prediction, for example, structure-based virtual screening. Existing deep learning methods docking, despite being much faster, suffer from low success rates. In addition, they simplify the problem to assume no conformational changes within any protein upon binding (rigid docking). This...
Diffusion models have shown promise in addressing the protein docking problem. Traditionally, these are used solely for sampling docked poses, with a separate confidence model ranking. We introduce DFMDock (Denoising Force Matching Dock), diffusion that unifies and ranking within single framework. features two output heads: one predicting forces other energies. The trained using denoising force matching objective, while energy gradients to align forces. This design enables our sample...
We present the results for CAPRI Round 54, 5th joint CASP-CAPRI protein assembly prediction challenge. The offered 37 targets, including 14 homo-dimers, 3 homo-trimers, 13 hetero-dimers antibody-antigen complexes, and 7 large assemblies. On average ~70 CASP predictor groups, more than 20 automatics servers, submitted models each target. A total of 21941 by these groups 15 scorer were evaluated using model quality measures DockQ score consolidating measures. performance was quantified a...
Abstract Conventional protein-protein docking algorithms usually rely on heavy candidate sampling and re-ranking, but these steps are time-consuming hinder applications that require high-throughput complex structure prediction, e.g., structure-based virtual screening. Existing deep learning methods for docking, despite being much faster, suffer from low success rates. In addition, they simplify the problem to assume no conformational changes within any protein upon binding (rigid docking)....
Guest migration in clathrate hydrates is a slow but important process for reaching thermodynamic equilibrium. The transport of guest molecules hydrate lattice considered as series hopping events from an occupied cage to empty neighboring facilitated by water vacancies and without significant restructuring the bulk. In this work, we developed analytical model determining equilibrium distribution diffusivity gas cages sI based on their rate. Furthermore, kinetic Monte Carlo simulations were...
It is well understood that tetrahydrofuran (THF) molecules are able to stabilize the large cages (51264) of structure II form THF hydrate with empty small even at atmospheric pressure. This leaves store gas relatively lower pressures and higher temperatures. The dissociation enthalpy temperature strongly depend on size enclathrated in hydrate. A high-pressure microdifferential scanning calorimeter was applied measure enthalpies temperatures hydrates pressurized by helium methane under a...
Abstract Animal venoms, distinguished by their unique structural features and potent bioactivities, represent a vast relatively untapped reservoir of therapeutic molecules. However, limitations associated with extracting or expressing large numbers individual venoms venom-like molecules have precluded evaluation via high throughput screening. Here, we developed an innovative computational approach to design highly diverse library animal “metavenoms”. We employed programmable M13 hyperphage...