A5088091669- Machine Learning in Materials Science
- Protein Structure and Dynamics
- Computational Drug Discovery Methods
- RNA and protein synthesis mechanisms
- Machine Learning in Bioinformatics
- RNA modifications and cancer
- Genomics and Chromatin Dynamics
- Bioinformatics and Genomic Networks
- Scientific Computing and Data Management
- Receptor Mechanisms and Signaling
- RNA Research and Splicing
- Enzyme Structure and Function
- Genetics, Bioinformatics, and Biomedical Research
- Forensic and Genetic Research
- Mass Spectrometry Techniques and Applications
- Robotics and Sensor-Based Localization
- Machine Learning and Data Classification
- Neuropeptides and Animal Physiology
- Biomedical Text Mining and Ontologies
- Advanced Proteomics Techniques and Applications
- Advanced Image and Video Retrieval Techniques
- Cancer-related molecular mechanisms research
- Adversarial Robustness in Machine Learning
- Signaling Pathways in Disease
- Advanced Vision and Imaging
Stanford University
2016-2024
Stanford Medicine
2018-2019
University of California, Berkeley
2013
Machine learning solves RNA puzzles molecules fold into complex three-dimensional shapes that are difficult to determine experimentally or predict computationally. Understanding these structures may aid in the discovery of drugs for currently untreatable diseases. Townshend et al . introduced a machine-learning method significantly improves prediction (see Perspective by Weeks). Most other recent advances deep have required tremendous amount data training. The fact this succeeds given very...
Gene activator proteins comprise distinct DNA-binding and transcriptional activation domains (ADs). Because few ADs have been described, we tested tiling all yeast transcription factors for in vivo identified 150 ADs. By mRNA display, showed that 73% of bound the Med15 subunit Mediator, binding strength was correlated with activation. AD-Mediator interaction vitro unaffected by a large excess free protein, pointing to dynamic mechanism interaction. Structural modeling interact without shape...
Learning on 3D structures of large biomolecules is emerging as a distinct area in machine learning, but there has yet to emerge unifying network architecture that simultaneously leverages the graph-structured and geometric aspects problem domain. To address this gap, we introduce vector perceptrons, which extend standard dense layers operate collections Euclidean vectors. Graph neural networks equipped with such are able perform both relational reasoning efficient natural representations...
Predicting the structure of multi-protein complexes is a grand challenge in biochemistry, with major implications for basic science and drug discovery. Computational prediction methods generally leverage pre-defined structural features to distinguish accurate models from less ones. This raises question whether it possible learn characteristics directly atomic coordinates protein complexes, no prior assumptions. Here we introduce machine learning method that learns 3D positions all atoms...
RNA-Puzzles is a collective endeavor dedicated to the advancement and improvement of RNA three-dimensional structure prediction. With agreement from structural biologists, structures are predicted by modeling groups before publication experimental structures. We report large-scale set predictions 18 for 23 RNA-Puzzles: 4 elements, 2 Aptamers, Viral 5 Ribozymes 8 Riboswitches. describe automatic assessment protocols comparisons between prediction experiment. Our analyses reveal some critical...
Abstract RNA-based medicines and RNA-targeting drugs are emerging as promising new approaches for treating disease. Optimizing these therapeutics by naive experimental screening is a time-consuming expensive process, while rational design requires an accurate understanding of the structure function RNA. To address this challenge, we present ATOM-1, first RNA foundation model trained on chemical mapping data, enabled data collection strategies purposely developed machine learning training....
We propose a system for user-aided visual localization of desert imagery without the use any metadata such as GPS readings, camera focal length, or field-of-view. The makes only publicly available digital elevation models (DEMs) to rapidly and accurately locate photographs in non-urban environments deserts. Our generates synthetic skyline views from DEM extracts stable concavity-based features these skylines form database. To localize queries, user manually traces on an input photograph. is...
Despite an explosion in the number of experimentally determined, atomically detailed structures biomolecules, many critical tasks structural biology remain data-limited. Whether performance such can be improved by using large repositories tangentially related data remains open question. To address this question, we focused on a central problem biology: predicting how proteins interact with one another---that is, which surfaces protein bind to those another protein. We built training dataset,...
Computational methods that operate on three-dimensional molecular structure have the potential to solve important questions in biology and chemistry. In particular, deep neural networks gained significant attention, but their widespread adoption biomolecular domain has been limited by a lack of either systematic performance benchmarks or unified toolkit for interacting with data. To address this, we present ATOM3D, collection both novel existing benchmark datasets spanning several key...
SUMMARY Gene activator proteins comprise distinct DNA-binding and transcriptional activation domains (ADs). Because few ADs have been described, we tested tiling all yeast transcription factors for in vivo identified 150 ADs. By mRNA display, showed that 73% of bound the Med15 subunit Mediator, binding strength was correlated with activation. AD-Mediator interaction vitro unaffected by a large excess free protein, pointing to dynamic mechanism interaction. Structural modeling interact...
Many quantities we are interested in predicting geometric tensors; refer to this class of problems as prediction. Attempts perform prediction real-world scenarios have been limited approximating them through scalar predictions, leading losses data efficiency. In work, demonstrate that equivariant networks the capability predict tensors without need for such approximations. We show applicability method force fields and then propose a novel formulation an important task, biomolecular structure...
<h3>Background</h3> Targeting RNA with small molecules is emerging as a new paradigm in drug discovery. Altered regulation of translation, mRNA stability, pre-mRNA splicing are key mechanisms that drive various diseases, which amenable to molecule intervention. A significant gap RNA-targeted discovery has been the lack clear structure-function relationship RNA. Alternative implicated including cancer and neurological disorders. Specifically, evidence on role aberrant cancer, can lead loss...
Abstract Machine learning research concerning protein structure has seen a surge in popularity over the last years with promising advances for basic science and drug discovery. Working macromolecular machine context requires an adequate numerical representation, researchers have extensively studied representations such as graphs, discretized 3D grids, distance maps. As part of CASP14, we explored new conceptually simple representation blind experiment: atoms points 3D, each associated...
Proteins are miniature machines whose function depends on their three-dimensional (3D) structure. Determining this structure computationally remains an unsolved grand challenge. A major bottleneck involves selecting the most accurate structural model among a large pool of candidates, task addressed in quality assessment. Here, we present novel deep learning approach to assess protein model. Our network builds point-based representation atomic and rotation-equivariant convolutions at...
Gene activator proteins comprise distinct DNA-binding and transcriptional activation domains (ADs). Because few ADs have been described, we tested tiling all yeast transcription factors for in vivo identified 150 ADs. By mRNA display, showed that 73% of bound the Med15 subunit Mediator, binding strength was correlated with activation. AD-Mediator interaction vitro unaffected by a large excess free protein, pointing to dynamic mechanism interaction. Structural modeling interact without shape...