Building a Knowledgebase for Molecular Tumor Board
ABOUT THE PROJECT
Project Description
UCSF has a molecular tumor board (MTB) that currently meets twice a month to discuss the results of genomic tests for oncology patients. The vast majority of clinicians who ask to discuss their patient at MTB want to know if there any therapeutically actionable variants in the patient's tumor. This requires the following information:
- Of the drugs that are approved for cancer, what are they approved for and what biomarkers do they target.
- What clinical trials are recruiting for patients with specific biomarkers.
- What is is the current scientific and/or clinical evidence to suggest treatment with a specific drug or drug class for a given variant.
Right now, our team that conducts these analyses, a group of 5 clinician scientists, have siloed environments. Reinventing the wheel is common and there is no common source of knowledge the team uses which introduces inconsistency and bias in the analysis. We need to build a knowledgbase to address these issues.
Funding
Definitely not
LOOKING FOR
Required Skills
- Python
- Natural Language Processing tools (NLTK, CTAKES, PyTorch-NLP, etc)
- Full stack engineer preferred
Acceptable Level of Education (eg. Undergrad, Grad Students, Post Docs, MD, PhD)
Undergraduate students, Graduate students, Postgraduates, Full-time workers who volunteer time
CONTACT
PI/Research group
Molecular Oncology Initiative
Contact
Michelle Turski, [email protected]