The Computational Toxicology group functions to develop, refine, and bring awareness to in-silico methods that may help predict and understand safety and toxicology for small and large molecules. Team members will gain exposure to a wide range of safety-related datasets ranging from biology, pharmacology, toxicology, and chemistry to help with predictive modeling and data analysis. Using these datasets, the team hopes to apply data science and machine-learning methodology to better visualize the data and help identify novel and mechanistic associations.
- Collaborate with research and bioinformatics scientists to conceive informatics analysis strategy leveraging advanced machine learning/AI algorithms to support discovery and pre-clinical safety studies. Specific applications can be but not limited to transcriptomics, bioactivity, in vitro/vivo safety data and molecular data integration, etc.
- Identify and process relevant internal and external safety datasets and knowledge resources. Propose and execute computational research to identify associations across safety features by leveraging and harmonizing datasets
- Develop tools and user-interfaces that incorporate learnings from computational work to assist team members to evaluate and predict safety outcomes
- Communicate results and methods verbally and in writing for scientific and non-technical audiences
- Bachelor’s Degree with 4 years’ experience or Master’s Degree with experience in Statistics, Computer Science, or a related quantitative field. Background in life sciences or work experience in the pharmaceutical industry preferred.
- Experience with data science and a variety of coding languages and packages, such as R, Python etc. Expected proficiency in at least Python and R.
- Knowledge of data mining, cleaning and transformation techniques, such as dimensional reduction, normalization, standardization, imputation, aggregation, and performing exploratory analysis prior to statistical analysis or machine learning
- Familiarity with modern relational databases and/or distributed computing platforms Big Data, and their query interfaces, such as SQL, Impala, Spark, PySpark and Hive.
- Experience using visualization techniques for presenting data and analysis as dashboard in tools such as R/Shiny, ggplot, SpotFire, and Custom web-based solutions.
Significant Work Activities: Continuous sitting for prolonged periods (more than 2 consecutive hours in an 8 hour day)
Job Type: Recent Graduate