NCBI Home Page   NLM Intramural Research Program
  Research Group of Ivan Ovcharenko

Research Interests

  • Disease-causative noncoding mutations.
  • Sequence composition of gene regulatory elements.
  • Identification of cell-specific DNA sequence signatures of enhancers and silencers using Deep Learning.
  • Noncoding sequence evolution.

Open Staff Scientist Position

The National Library of Medicine (NLM), National Center for Biotechnology Information (NCBI) is recruiting for a Staff Scientist 1. The position supports interdisciplinary research in the Computational Biology Branch (CBB). NLM is one of the 27 Institutes at the National Institutes of Health (NIH), part of the Department of Health and Human Services (DHHS).

NLM is looking for an outstanding candidate to conduct research in computational analysis of human regulatory genomics. The candidate will develop state-of-the-art deep learning methods for the accurate prediction of enhancers and silencers, identification of disease-causative mutations, and reconstruction of cell-type specific regulatory architecture of the human genome. This position is responsible for:

  • developing machine learning methods, including deep learning methods;
  • performing statistical analyses, devising new computational methods, and creating analytic models;
  • analyzing large genomic and epigenetics datasets;
  • working in collaboration with other experimental and computational laboratories at the NIH;
  • publishing scientific manuscripts and presenting at conferences and meetings;
  • mentoring students and postdoctoral fellows; and,
  • staying abreast of bioinformatics and deep learning methods as well as genomic resources.


The ideal candidate may or may not be a United States citizen and must have a doctoral degree.

We are looking for an individual with several of these qualifications or talents:

  • a Ph.D. in a quantitative field, such as Computer Science, Mathematics, Computational Biology, or Bioinformatics;
  • at least two years of relevant postdoctoral experience;
  • a strong track record in research as evidenced by peer-reviewed publications;
  • research experience in regulatory genomics, statistics, evolutionary biology, gene regulation, epigenomics, computational disease genetics, and genomic and epigenomic architectures of cellular identity;
  • research experience and/or up-to-date understanding of the principles of eukaryotic gene regulation; hands-on experience on working with the Encyclopedia of DNA Elements (ENCODE), NIH Roadmap Epigenomics, Ensembl, and similar databases;
  • experience developing deep learning algorithms, methods, and tools;
  • fluency in Python, R, and MATLAB, including TensorFlow, PyTorch and/or Theano libraries;
  • experience working with GPU-based architectures;
  • proven ability to work on interdisciplinary projects;
  • mentoring experience;
  • ability to communicate effectively, both verbally and in writing; and
  • ability to work both independently and as a team member.

Salary is commensurate with research experience and accomplishments. A full package of benefits, including retirement, health, life, and long-term care insurance, Thrift Savings Plan participation, etc., is available. The successful candidate will serve in a non-competitive appointment in the excepted service.


Interested individuals should send a copy of their CV and Bibliography with the names of three references along with a cover letter detailing research interests, a brief summary of communication and organizational skills, and evidence of engagement in multi-disciplinary collaborative research to Please include the announcement number, NLM27-0015, in the cover letter. Applications will be accepted until the position is filled.

DHHS, NIH, and NLM are Equal Opportunity Employers

Gene Regulation: From Sequence to Function, to Disease.

The research of the Ovcharenko research group focuses on deciphering semantics and studying the evolution of the gene regulatory code in eukaryotes.

With less than 2% of the human genome sequence being coding, the search for noncoding functional DNA is a guileless treasure hunt. We currently lack a fundamental understanding of the genomic language that governs the temporal and spatial dynamics of gene expression regulation, native to every cell of a living creature. In an effort to bridge the gap between modern success in genome sequencing and sequencing data interpretation, we are developing pattern recognition AI methods to functionally characterize noncoding DNA. Our ultimate goal is to use these methods to translate the noncoding genome sequence into function.

Understanding the gene regulatory landscape of the human genome will open doors for studies of population variation in noncoding functional elements, promoting identification of disease-causative mutations residing outside of genes. As mutations in gene regulatory regions might be mainly linked to an increased susceptibility to disease, not necessarily resulting in a disease phenotype, our research has the potential for mapping key regulatory elements in the vicinity of disease-linked genes. Availability of computationally defined datasets of human regulatory elements tailored to specific common diseases (including heart disease, obesity, diabetes, and cancer) will permit designing novel disease susceptibility measurement methods, expressly targeting selected elements.

We utilize AI (including Deep Learning), comparative genomics, Bayesian statistics, multiple sequence alignments, libraries of transcription factor binding sites, gene expression data, population genetics, and transgenic animal experimentation (the latter through collaborations) -- all to infer the noncoding genome function through the analysis of sequence data and evolutionary trends. Our research relies on collaborative studies with several research and clinical groups within the NIH and from other research universities and institutions.

Disclaimer     Privacy statement