University of California, San Francisco Institute for Neurodegenerative Diseases
We are searching for a biostatistics research specialist to start in Summer 2021. This position is available to study machine learning and molecular datasets. The person in this position will work closely with our machine learning team members and established collaborators. This position will be part of a collaborative environment with access to state-of-the-art facilities in the new Sandler Neurosciences Building on the UCSF Mission Bay campus.
This specialist will work on the construction of a miRNA dataset, the technical preparation of the dataset for machine learning (ML), and the collection of human expert annotations on these data. This ML-ready molecular dataset is one deliverable. The work will progress to the use of the prepared dataset to train, optimize, and critically evaluate machine learning models to predict cancer vs benign lesions. Effective machine learning classifiers that can detect cancer vs benign lesions in the dataset is another deliverable. We will focus in particular on the detection of subtypes of cancer and on the inclusion of multiple expert annotators. Work may also extend to other datasets such as DNA and mRNA sequences, and/or other datasets currently under collection.
The person in this position will be responsible for successfully performing analyses including the following methods: mathematical modeling, statistical learning, multivariate analysis, bootstrapping, unsupervised learning, data augmentation, k-fold validation, PCA or other dimensionality reduction, machine learning such as random forests and/or SVM, ROC and precision-recall curves, and data visualization.
Required qualifications: • Specialists appointed at the Assistant rank must possess a master’s degree (or equivalent degree) or five years of experience in the relevant specialization. • Specialists appointed at the Associate rank must possess a master’s degree (or equivalent degree) or five to ten years of experience in the relevant specialization. • One-year time commitment, with possibility of extension. • Demonstrated experience in python programming. • Ability to work with pytorch, and related python libraries. • Background or work experience in mathematics, computer science, biology, physics, and/or statistics. • Candidates must meet the basic qualifications at the time of appointment. Candidate’s CV or cover letter must state qualifications (or if pending) upon submission.
Preferred qualifications: • Experience in cancer biology. • Experience with molecular datasets. • Experience with Linux, virtual machines, and cloud or cluster processing. • Experience with code versioning, management, tracking, and testing tools such as GitHub and continuous integration.
Appointees in the Specialist series will be expected to engage in specialized research, professional activities and do not have teaching responsibilities. Specialists are expected to use their professional expertise to make scientific and scholarly contributions and may participate in University and Public Service. Screening of applicants will begin immediately and will continue as needed throughout the recruitment period. Salary and rank will be commensurate with the applicants experience and training.
UC San Francisco seeks candidates whose experience, teaching, research, or community service that has prepared them to contribute to our commitment to diversity and excellence. The University of California is an Equal Opportunity/Affirmative Action Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, age or protected veteran status.
The University of California, San Francisco (UCSF) is a leading university dedicated to promoting health worldwide through advanced biomedical research, graduate-level education in the life sciences and health professions, and high-quality patient care. It is the only UC campus in the 10-campus system dedicated exclusively to the health sciences.