Data Scientist
About the role
The Protein Homeostasis (PH) IPS team is part of the Informatics and Predictive Sciences division at client, with a strong focus on supporting early-stage pharmaceutical programs. This position will provide cross-portfolio support by enabling scientists to readily interrogate available molecular and meta-data across a diverse spectrum of pre-clinical, patient derived models (organoids, xenographs). The successful candidate will be responsible for QCing, harmonizing, and ingesting omics and other datasets programmatically, developing code to facilitate the principles of reproducible research. In addition this role will involve managing the incorporation of newly curated data into a proprietary interface to facilitate accessibility and visibility of patient derived models to scientists across client.
Responsibilities
- Compile and harmonize de-identified patient meta-data from multiple internal and external resources (includes clinical treatment history, clinical characteristics, patient demographics, model growth parameters, etc)
- Compile and format omics datasets from multiple internal and external resources including RNASeq, DNASeq, Copy Number and scRNASeq datasets
- Develop automated scripts to help harmonize datasets from multiple data sources
- Load formatted datasets into a proprietary interface to enable access by all client employees
- This role may extend to providing some high-level QC assessment of data sets based on a defined set of parameters
Requirements
- Strong coding skills in either R (preferred) and/or python. Experience in Java desired but not mandatory
- Background in bioinformatics, experience working with RNA-Seq and other NGS data
- Bachelors degree in bioinformatics, biology, computer science, or a related field, with 3+ years of hands-on bioinformatics experience after graduation, in industry or academia
- Preferred: experience in cancer