Postdoctoral Associate

Stony Brook University
Biomedical Informatics
United States NY Stony Brook


The Department of Biomedical Informatics is seeking highly motivated postdoctoral fellows in bioinformatics methods development and research applied to translation and clinical biomedical research. The successful candidate will do significant open source algorithm and bioinformatics pipeline development as well as computational biology research, which is motivated by and will support several cutting-edge projects.

The projects, funded by the National Library of Medicine, are carried out with multidisciplinary teams. Our projects are developing novel informatics methods to identify differential alternative splicing/promoter events in heterogeneous cancer samples and normal tissues, and to predict transcriptional networks at isoform-level by application of recent machine learning methods. Work in these projects encompasses Statistical Analyses, Machine Learning, Database Integration and Web Development and requires reliable and efficient data science methods that can automate data analysis and management without close human supervision and that can work with a variety of input data. The end results will be innovative bioinformatics algorithms and pipelines that can perform specific sequence prediction tasks, based on a new breed of deep-learning algorithms. These algorithms will optimize the specific sequence prediction tasks and interpretation of non-coding DNA variants, improving the functional characterization of non-coding DNA in the human genome. These projects also span cancer genomics and precision medicine to predict molecular subgroups and response to treatment towards –omics based companion diagnostics. The new bioinformatics tools will be used by national or international researchers to process large -omics datasets to study individual aspects of cis-regulatory landscapes, including DNA-protein interactions that are disrupted in cancer.

The algorithm development and bioinformatics research will focus on data science and machine learning methods, -omics databases, computer programming and testing. You must be able to work and contribute in an environment that weaves genomics, molecular biology, genetics and clinical data, with statistical analysis and machine learning. Your work will have direct impact on cancer research and will be widely known nationally and internationally through collaborative participation in large-scale projects and open source software efforts. We collaborate extensively with well-known research groups from prominent institutions and draw upon the first rate technical and scientific resources available at Stony Brook University and our collaborating institutions.

Develop advanced bioinformatics methods and pipelines that will support multi –omics data analyses. Possess knowledge of relevant development environments and protocols for software development and methodologies.

Adapt Machine Learning, database integration and web development technologies to be used for big data analysis. Research and develop machine learning algorithms for use in data science applications. Maintain up to date knowledge of current machine learning methods and data science practices. Identify and suggest latest deep-learning methods to improve performance of the predictive algorithms.

Manuscript writing for journal and conference publications. Oral presentation during lab meetings. May attend conferences and seminars.

Serve as bioinformatics experts in collaborative projects with biomedical researchers.

Other duties as assigned.


Required Qualifications (as evidenced by an attached resume):

Doctoral Degree (or foreign equivalent). Training in the application of machine learning and statistical pattern recognition methods. Software development experience on Linux. Programming experience in R and at least one of the following languages: C/C++, Python and Perl.

Preferred Qualifications:

Doctoral Degree (or foreign equivalent) in biomedical informatics, bioinformatics, computational biology, computer science or applied statistics. Algorithm development and/or research experience with deep learning methods. Software development and/or research experience with relational and noSQL database technologies. Experience with open source software development and deployment.

Start date

As soon as possible

How to Apply

Submit the application online at URL: