Company Summary:

The latest Flagship Pioneering company has been founded through its venture creation engine, where companies such as Moderna Therapeutics, Rubius Therapeutics, and Evelo Therapeutics were conceived and created. Since Flagship’s founding in 2000, the firm has originated and fostered the development of nearly 100 scientific ventures resulting in $19+ billion in aggregate value, 500+ issued patents, and more than 50 clinical trials for novel therapeutic agents.

The new company is dedicated to turning causal human genetics and biology into new, differentiated disease modifying therapies to improve the lives of patients across a broad range of complex diseases.

Position Summary:

To fulfill this mission the Computational Biology and Data Science team is searching for a highly collaborative and inquisitive scientist to join an inter-disciplinary team to transform human disease by turning human genetic and clinical discoveries into testable therapeutic hypotheses.  We are looking for a biomedical informaticist and data scientist with extensive experience with text analytics, biomedical ontologies and analyzing electronic health records (EHRs).  The position will involve collaboration with computational biologists, statistical geneticists and wet-lab biologists to mine clinical and phenotypic data sets to support genomic studies, association analyses and patient stratification.  The candidate will leverage publicly available data as well as proprietary data from partnerships.  The successful candidate will have a strong work ethic, ability to work independently as well as on highly collaborative teams, and a strong foundation in statistics including biostatistics, machine learning and graph theory.  This biomedical informatics and data science position with the Computational Biology & Data Science team provides a unique opportunity to harness the information from human genetics, genomics, and clinical data to support the development of novel therapeutics. 

Key Responsibilities:

  • Clean, organize and harmonize EHR data from multiple sources
  • Convert unstructured text into structured text and integrate with EHR
  • Generate patient cohorts from EHR data for genetic and genomic analysis
  • Develop patient stratification algorithms
  • Collaborate with statistical geneticist & computational biologist to integrate EHR with functional data
  • Collaborate and coordinate with external EHR resources and informaticians

Key Requirements:

  • PhD in a quantitative discipline (biomedical informatics, computer science, computational biology, biostatistics, statistics, statistical genetics, engineering, epidemiology) [2+ years post-PhD preferred]
  • Experience with experimental design and classical statistics
  • Experience with machine learning, exploratory data analysis, statistical modeling
  • Experience in novel classifier development and implementation
  • Scripting, Statistical and Visualization programming skills (R/RShiny/Python/etc.)
  • Experience with cloud computing (e.g. AWS, Google)
  • Experience with managing, cleaning and normalizing large, multi-dimensional datasets
  • Knowledge and experience with electronic health records (EHRs)
  • Knowledge of clinical data standards and ontologies including ICD, SNOMED, UMLS, etc.
  • Knowledge of text analytics and natural language processing
  • Excellent communication and presentation skills to both technical and non-technical colleagues
  • Experience collaborating with computational biologists and statistical geneticists

Apply for this Job

* Required