A5082484924- Machine Learning in Materials Science
- Computational Drug Discovery Methods
- Protein Degradation and Inhibitors
- Metabolomics and Mass Spectrometry Studies
- Machine Learning in Bioinformatics
- RNA and protein synthesis mechanisms
- Protein Structure and Dynamics
- Genetics, Bioinformatics, and Biomedical Research
Nvidia (United States)
2023
Carnegie Mellon University
2021-2022
Deep learning models have demonstrated outstanding results in many data-rich areas of research, such as computer vision and natural language processing. Currently, there is a rise deep computational chemistry materials informatics, where could be effectively applied modeling the relationship between chemical structures their properties. With immense growth data, can begin to outperform conventional machine techniques random forest, support vector machines, nearest neighbor. Herein, we...
Deep generative neural networks have been used increasingly in computational chemistry for de novo design of molecules with desired properties. Many deep learning approaches employ reinforcement optimizing the target properties generated molecules. However, success this approach is often hampered by problem sparse rewards as majority are expectedly predicted inactives. We propose several technical innovations to address and improve balance between exploration exploitation modes learning. In...
Abstract The data-driven design of protein sequences with desired function is challenged by the absence good theoretical models for sequence-function mapping and vast size sequence space. Deep generative have demonstrated success in learning to relationship over natural training data sampling from this distribution synthetic engineered functionality. We introduce a deep model termed Protein Transformer Variational AutoEncoder (ProT-VAE) that furnishes an accurate, generative, fast,...
Artificial Intelligence models encoding biology and chemistry are opening new routes to high-throughput high-quality in-silico drug development. However, their training increasingly relies on computational scale, with recent protein language (pLM) hundreds of graphical processing units (GPUs). We introduce the BioNeMo Framework facilitate AI across GPUs. Its modular design allows integration individual components, such as data loaders, into existing workflows is open community contributions....