Junior Computational biologist / bioinformatician

Phenomic (https://phenomic.ai/) is a seed stage company using machine learning (ML), deep learning and bioinformatic approaches to identify new targets to disrupt tumor stroma, with an initial focus on cancer associated fibroblasts (CAFs). The main rationale behind this focus lies in the fact that stromal signatures are associated with poor response to current immunotherapy drugs in several indications including pancreatic, colorectal, lung, breast and other cancer types. As part of the company products, we are building single cell RNA-seq and spatial transcriptomic (scRNA) analysis tools for published and proprietary human and mouse stromal cell datasets. Our tools incorporate ML and bioinformatic methods to understand current targets of interest and identify new ones.

We are looking for a co-op computational biologist/bioinformatician to join the development of our ML and bioinformatic tools.

Specific activities include:

1. Interact with biologists/immunologists at Phenomic to mine public (e.g. TCGA, GEO, Broad Portal) and proprietary data sets, to help building or scale-up bioinformatic tools to analyze gene expression data relevant to human cancer and mouse models.
2. Provide informatics support for analysis of current targets under consideration, including identification of disease and cell type associations.
3. Potentially use available data sets to make predictions of logical combination therapies.
4. Collaborate with other ML/bioinformatic team members building Python and R code using version controlling systems.

Qualifications

1. Undergrad or Masters student in bioinformatics, computational biology, computer science or closely related field, preferably with experience in omic-scale analyzes.
2. Familiarity with high dimensional data at the molecular level, bulk and single cell analysis, and experience integrating multi-mode measurements.
3. Working knowledge of classes of machine learning to extract biological meaning and/or make drug target candidate predictions.
4. Experience coding in Python (preferred) or R.
5. Code contributions via version controlling tools (Github/Gitlab).
6. Experience in tumor immunology is a plus.