Skip to content

Postdoc: Statistical Modeling, Machine Learning, Biomarker Discovery [Peters Lab]

The Peters Lab is focused on discovery of novel therapeutic targets and identification of biomarkers for patients with immune mediated diseases. We generate in silico predictive models of disease from multi-omic profiling of patient tissue to inform on data driven insights and to generate and validate hypothesis on the functional implications of rare and common genetic variation in pathology.

This role will contribute significantly to our efforts to systematically study autoimmune, immunodeficient and inflammatory diseases through the integration of genetic, epigenetic, transcriptomic, proteomic and clinical phenotypic data into causal network models or machine learning models. The goal of this research is to identify and validate mechanisms underlying pathology using computational models such machine learning, deep learning, or other artificial intelligence techniques. Such models will be used to guide drug target and biomarker discovery and prioritization and to develop combination therapies for specific patient subsets.


  • Develop novel computational methods and/or application of existing methods for integrating diverse types of molecular multi-scale data.
  • Develop novel statistical models for comparing diverse datasets or network models.
  • Develop novel platforms and pipelines to identify novel therapeutic targets, and to discover biomarkers for drug response, patient stratification.
  • Analyze genomic data including whole genome, whole exome, long read sequencing, RNA-Seq (single cell and bulk), and epigenetic data.
  • Integrate analysis from large scale genotype-phenotype resources of structured and curated unstructured EHR and genomic data to develop predictive models for treatment response, risk and clinical outcome.


  • Expertise in statistical methodologies such as predictive modeling and inference, machine learning methods, mixed effects models, multivariate analysis, network construction, etc.
  • Expertise in integration of genetic, genomic, single cell and bulk expression, proteomics, metabolomic and microbiome data analysis, including raw data processing and modeling of processed/normalized data, and familiarity with state of the art pipelines.
  • Strong track record in methods development and/or application.
  • A track record of leading translational research projects using rigorous statistical and computational approaches.
  • Outstanding programming skills in R, Python; Perl, SQL, Matlab a plus.
  • Strong knowledge of Unix shell scripting.
  • Broad knowledge of biology and/or drug discovery preferred.
  • Experience in machine learning preferred.
  • Strong ability to collaborate with teams of research scientists, bioinformaticians, software developers, and external collaborators in biotech/pharma industry and academia.
  • Strong written and verbal communication skills.
  • Experience working in a high performance computing environment.
  • Experience working in an AWS Cloud computing environment is a plus.


  • D in quantitative sciences – Computer Science, Mathematics, Statistics, Data Science, Computational Biology or Bioinformatics.
  • 2+ years in analyzing large scale genetic and genomic data and statistical modeling.

How to Apply

Please send CV and cover letter to

The Icahn School of Medicine at Mount Sinai is an Equal Opportunity and Affirmative Action Educational Institution and Employer. Women and members of underrepresented minority groups are strongly encouraged to apply.