- Machine Learning
The Dana-Farber Cancer Institute seeks an Associate Computational Biologist who will work jointly under the Aguirre laboratory and the Wolpin laboratory within the Hale Center For Pancreatic Cancer Research (http://halecenter.dfci.harvard.edu) and the Broad Institute of Harvard and MIT. The successful candidate will work as a data scientist on the analysis of datasets generated from pancreatic cancer genome sequencing, bulk and single-cell RNA-sequencing and small molecule drug sensitivity testing in order to help advance efforts for precision cancer medicine.
The qualified candidate will develop and support data processing and analysis tools, create new algorithms for emerging clinically focused needs, maintain datasets and databases, integrate tools and databases into existing high-throughput pipelines, and facilitate the display and the distribution of processed data. The candidate will become part of an integrated team including laboratory, computational and clinical scientists. This group will include graduate students, post-doctoral scholars, clinical oncologists, surgeons, pathologists, geneticists and doctoral and entry level computational biologists and data scientists.
Related projects and responsibilities will include:
Prospective clinical sequencing to guide the care of cancer patients
Studies of drug sensitivity and resistance to existing and emerging cancer therapies using data from genomic and functional analysis of patient-derived samples
Studies of patient samples for tumor behavior and clinical outcomes
Studies of cancer immunotherapies to develop predictors of response
These projects are collaborative efforts between the Dana-Farber Cancer Institute and the Broad Institute. The goals of this initiative consist of analyzing sequencing data to determine the effects of genomic alterations and expression changes on clinical behavior, both retrospectively and prospectively.
These new data could help identify novel approaches for personalized care in pancreatic cancer treatment. In addition, this data may provide support for new methods in clinical decision-making, biomarkers for rational drug development, and new insights into tumor biology through innovative analyses.
The person hired for this position will join the team in this effort, and will participate in the design and implementation of algorithms to analyze the data and integrate with other data sets including clinical outcomes data.
This person will also help with the generation of tools needed for manipulating and preparing data for display; transferring data to external collaborators and data repositories; and will also help maintain, support, and document shared tools, code base, and data sets. As the software infrastructure evolves, this position is likely to present diverse and flexible opportunities - from deeper and more complex software design problems, to becoming more involved in the bioinformatic and analytic aspects of predictive modeling.
MINIMUM JOB QUALIFICATIONS:
A B.S. or M.S. in bioinformatics, mathematical, physical, or computer science, or comparable research experience, together with significant experience in computer programming and computational biological applications.
A strong background in statistics and biology. Experience managing and curating large datasets and with machine learning techniques desired.
Excellent oral and written communication skills and the ability to perform both self-directed and guided research are required.
Must demonstrate outstanding personal initiative and the ability to work effectively as part of a team.
Ability to meet deadlines and efficiently multitask is a must.
KNOWLEDGE, SKILLS, AND ABILITIES REQUIRED:
Excellent oral and written communication skills with the ability to effectively collaborate across a range of knowledge (e.g. effective communication with software developers and physicians)
Ability to seek out mentorship and assistance as needed, while also being a mentor to other members of the community.
Experience in R and/or Python is preferred, with willingness to learn new languages and tools as the field grows (e.g. Github, Docker, WDL, and other emerging algorithms)
This position will involve comentoring of students joining the group as described above, with opportunities for growth in developing multi-disciplinary teams that are project oriented.