The Data (bio)Informatics Science and Engineering (DISE) team at Decipher Biosciences is a passionate group of scientists and software engineers striving to use the best science and engineering knowledge to develop data pipelines and software that make genomic data actionable to cancer patients and their doctors. We develop and deploy machine learning models based whole transcriptome gene expression data to reveal new insights in cancer biology. We also develop software/apps that facilitates better data visualization and interpretation for colleagues, physicians, and patients. We are responsible for maintaining and analyzing one of the largest proprietary transcriptomic data sets in oncology.
As a data scientist, you will work closely with a team of research and production professionals. You will be a key member in preparing, interpreting and analyzing business, genomic and clinical data, providing analysis support to our colleagues and our external partners. You will also participate in our data-related software design, development, and maintenance. This role requires a broad knowledge of cancer biology, oncology, bioinformatics, statistics, and programming, paired with effective communication skills, a strong sense of diligence, and timeliness.
Duties and Tasks
- Perform data analysis that contributes to the process improvement of Decipher products
- Contribute the design of experiments focused on assay improvement.
- Conduct data analysis in support of biopharma clinical trials and collaborations
- Support development of novel genomic signatures
- Design and implement data reports and dashboards
- Contribute to manuscript drafting for peer-reviewed journals and patent filings
- Support and assist colleagues and external collaborators in data preparation and analysis
- Understanding, maintaining, and improving various databases and schema
- Contribute to the maintenance and improvement of the data processing pipelines, automating common data analysis routines into software packages or applications.
- Contribute to the research and development of applying latest developments of AI technologies to the Decipher data.
- Graduate degree from a quantitative field with strong programming experience (data science, statistics, bioinformatics, or equivalent).
- Proven experience in analysis and interpretation of large-scale gene expression data (microarray, sequencing).
- 1 year + experience in data science and quantitative data analysis.
- 1 year + experience in working with cloud platform like GCP.
- Familiar with a Linux environment and shell scripting.Experience working with source control tools (Git) in a collaborative programming environment.
- Knowledge in cancer biology and genomics. Work/research experience with public genomic data platforms (GEO, CBioPortal, MSigDB, etc or equivalent) is a plus.
- Extensive experience of working with R or Python. Experience of building and testing customized R packages.
- Experience in performing complex data analysis on large volumes of data and present findings to collaborators.
- Experience in drafting and publishing scientific research papers and addressing comments and feedbacks from collaborators and reviewers.
- Strong interpersonal and communication skills (both written and verbal); ability to communicate with people in a wide variety of areas and at various levels from technical specialists to executives
- Ability to quickly and efficiently adapt to new concepts and collaborate with cross-function teams and business units.
- Critical thinking
- Curiosity and eager to learn.