?Structure-based prediction of the interactome? NIH R01GM081871-10 PI: Bonnie Berger We have designed and implemented a system for privacy-preserving and scalable sharing of drug-target interaction data (Aim 1, under review at Science), where we required GPUs to run our protocol, discover and experimentally validate novel drug-target interactions and will make our software publicly-available for academic and non-profit use (Aim 3). At the same time, we have presented a novel loss function for training classifiers from positive and unlabeled data and developed a software pipeline, Topaz, which uses convolutional neural networks trained with few positive examples for protein detection (Aim 2, RECOMB 2018). We are now developing new deep learning models for protein structure embedding and extending the Topaz framework to learn a general deep learning model of protein images from multiple cryo-EM micrograph datasets. Our continued progress on these projects is significantly jeopardized by our lack of GPU compute power. While in the last year we have purchased a compute node with four GPUs, we are continually frustrated by wait-times and inability to try different models and hyperparameters. Thus, we are requesting an additional node with eight GPUs to enable us to reach the broader goals of our grant.
The interactions of small molecules with proteins are omnipresent throughout cellular processes and of fundamental importance to drug design and disease treatment, yet the task of predicting these interactions brings major challenges because of the heterogeneity and proprietary nature of the data. Here, we develop new mathematical methods and software that can address not only interpreting the data itself, but also the collaborative and generative process through which researchers work: new cryptographic tools can enable unprecedented forms of secure sharing and collaboration between industry and the public, and deep learning can accelerate the drug discovery process.
| Cho, Hyunghoon; Berger, Bonnie; Peng, Jian (2018) Generalizable visualization of mega-scale single-cell data. Res Comput Mol Biol 10812:251-253 |
| Liu, Yang; Palmedo, Perry; Ye, Qing et al. (2018) Enhancing Evolutionary Couplings with Deep Convolutional Neural Networks. Cell Syst 6:65-74.e3 |
| Ordovas-Montanes, Jose; Dwyer, Daniel F; Nyquist, Sarah K et al. (2018) Allergic inflammatory memory in human respiratory epithelial progenitor cells. Nature 560:649-654 |
| Bepler, Tristan; Morin, Andrew; Noble, Alex J et al. (2018) Positive-unlabeled convolutional neural networks for particle picking in cryo-electron micrographs. Res Comput Mol Biol 10812:245-247 |
| Hie, Brian; Cho, Hyunghoon; Berger, Bonnie (2018) Realizing private and practical pharmacological collaboration. Science 362:347-350 |
| Cho, Hyunghoon; Berger, Bonnie; Peng, Jian (2018) Generalizable and Scalable Visualization of Single-Cell Data Using Neural Networks. Cell Syst 7:185-191.e4 |
| Orenstein, Yaron; Ohler, Uwe; Berger, Bonnie (2018) Finding RNA structure in the unstructured RBPome. BMC Genomics 19:154 |
| Orenstein, Yaron; Kim, Ryan; Fordyce, Polly et al. (2017) Joker de Bruijn: Sequence Libraries to Cover All k-mers Using Joker Characters. Res Comput Mol Biol 10229:389-390 |
| Orenstein, Yaron; Puccinelli, Robert; Kim, Ryan et al. (2017) Optimized Sequence Library Design for Efficient In Vitro Interaction Mapping. Cell Syst 5:230-236.e5 |
| Luo, Yunan; Zhao, Xinbin; Zhou, Jingtian et al. (2017) A network integration approach for drug-target interaction prediction and computational drug repositioning from heterogeneous information. Nat Commun 8:573 |
Showing the most recent 10 out of 50 publications
