Opportunity at National Institute of Standards and Technology (NIST)
Automated Functional Genomics: Active Learning of Promoter Architecture via Probabilistic Deep Networks
Information Technology Laboratory, Statistical Engineering Division
Please note: This Agency only participates in the February and August reviews.
|Samarov, Daniel Victor
1. Our project group is working to design and build a machine learning-driven autonomous system for genetic engineering of novel functionality into microbial systems. The postdoc will develop machine learning algorithms to analyze phenotype and sequence data, as well as active learning algorithms to optimize and control experiments in directed evolution. This position requires expertise in Computer Science, Statistics, or a similar field. Experience with machine learning, genetics, and/or bio-informatics is strongly preferred. The postdoc will work together and within a collaborative, interdisciplinary team to enable innovative methods for the predictive engineering of genetic sensors and other living measurement systems in bacteria and yeast. Facilities available for this project include state-of-the-art automation for microbial engineering, culture, and measurement.
i. Haoyang Zeng et al. “Convolutional neural network architectures for predicting DNA–protein binding”. In: Bioinformatics 32.12 (June 15, 2016).
ii. Taking the Human Out of the Loop: A Review of Bayesian Optimization”. In: Proceedings of the IEEE 104.1 (Jan. 2016).
iii. Andreas C. Damianou and Neil D. Lawrence. “Deep Gaussian Processes”. In: 16thInternational Conference on Artificial Intelligence and Statistics (AISTATS) (2013)
Gaussian processes; Deep learning; Active learning; Uncertainty quantification; Bayesian optimization; Genomics; Next generation sequencing; Model interpretability
Open to U.S. citizens
Open to Postdoctoral applicants