NIH/NLM T15 Training Grant
Background. Novel computational and statistical techniques are essential for enabling the translation of recent scientific discoveries across the widening spectrum of observations from both conventional information sources (e.g., electronic health records) and emergent methods (e.g., genomics, mHealth, etc.). Indeed, biomedical informatics and data science are now foundational to both clinical care as well as in the advancement of scientific knowledge related to human health and disease. These methods are empowering more individually-tailored insights that can better guide healthcare delivery – the mainstay of precision health. Still, there remains an effective translational gap that must be overcome, as today’s biomedical informaticians and data scientists need to better understand how to develop algorithms and tools for equitable precision medicine across the wide diversity spectrum of individuals.
The UCLA Biomedical Data Science Training Program for Precision Health Equity is aimed directly at this purpose, fostering a new type of scientist trained at the intersection of contemporary computational approaches, biomedical informatics, public health, and precision medicine. Our trainees are equipped with a technical depth that embraces these areas alongside an ability to translate such approaches to affect the transform of healthcare policy and practice with a goal for equitable medicine for all patients. This T15 brings together leading scientists and clinicians from across our institution and key areas to provide training in a comprehensive, interdisciplinary manner that offers students a core curriculum in topics in clinical informatics, translational bioinformatics, clinical research informatics, and public health informatics. It will afford trainees opportunities to see the pragmatic issues surrounding precision health and to learn how to address these barriers through innovative research and engagement. Didactic coursework and hands-on research experiences are shaped to reinforce technical and communication skills, team science, and a deep appreciation for the socio-technological concerns increasingly intertwined with precision health. As biomedical informatics and data science evolves, this T15 sees to an important area of growth that must be tackled to better serve the larger populous. Our program also makes a further commitment to diversity and equity through our broad inclusion efforts – a fundamental consideration if precision health is to ultimately be representative of everyone. Our trainees are instilled with the critical ability to be forward-thinking, independent scientists who effectively contribute to transformation, working to improve every individual’s well-being through improve computational methods. Building on our faculty’s extensive experience in mentorship and establishment of groundbreaking scientific directions, this T15 is helping to create new scientific leaders who will drive needed change to enable precision health paradigms.
Eligibility and application process. This T15 funds both PhD predoctoral students and postdoctoral fellows. You must be a US citizens or permanent residents (i.e., NRSA-eligible). Applications will require:
- Personal statement, including a description of research training goals and career goals
- Curriculum vitae (CV);
- One letters of recommendation familiar with the applicant; and
- Academic transcripts
Prerequisites. All applicants are expected to have a baccalaureate or advanced degree from an accredited institution in a discipline related to computer science, biological/health science, information sciences, mathematics, statistics, or other area of relevance to the targeted PhD program. Regardless of the PhD program, prospective T15 students are expected to have strong quantitative and computational skills including upper division mathematics and basic computer science courses. In addition, the students should have some relevant research experience and related background.
Predoctoral Requirements and Core Curriculum
T15 predoctoral trainees are required:
- To complete a core curriculum, comprising four key classes;
- To select an additional two elective courses in a specific focus area;
- To conduct a mentored research project in relation to precision health;
- To complete a course in responsible conduct of research (RCR) and training in scientific reproducibility; and
- To participate in at least three workshops.
Please note that per PhD student, we consider tailoring of these requirements to suit the needs of the individual.
Core curriculum. Four classes have been selected to provide foundational training across the affiliated PhD programs. Critically, these core courses are also core classes in the respective PhD programs, thus effectively providing the students a background in each area and introducing seminal concepts and methods, as well an initial foundation to understanding precision health:
- Bioinformatics CM221 (Introduction to Bioinformatics). This class introduces bioinformatics and methodologies, with emphasis on concepts and inventing new computational and statistical techniques to analyze biological data. An introduction is given on sequence analysis and alignment algorithms, and the computational challenges involved with omics analyses. Topics related to precision medicine are described to contextualize the use of these computational methods.
- Computer Science M226 (Machine Learning in Bioinformatics). Biology has become a data-intensive science. The bottleneck in being able to make sense of biological processes has shifted from data generation to statistical models and inference algorithms that can analyze these datasets. Statistical machine learning provides important toolkit in this endeavor. This course examines the statistical and computational underpinnings of ML techniques and their application to key biological questions.
- Bioengineering/Medical Informatics M227 (Medical Information Infrastructures and Internet Technologies). This course introduces the design and communication/data standards behind current architectures used in EHRs and other information systems (e.g., PACS) more advanced frameworks used in biomedical research and clinical care. Concepts around mHealth, cloud computing, and emergent technologies are covered. Socio-technological issues are presented with respect to adoption. Current challenges in the use of EHR datasets and translational problems are described.
- Epidemiology/Biostatistics 203B (Introduction to Data Science). This class provides covers pragmatic computing skills and software tools for dealing with big public health data. Topics include database design and management, visualization of longitudinal data, ML and deep learning methods, cloud/high performance computing, and reproducible research. These topics are presented in the context of biostatistics and computational epidemiological concerns. Elective courses. Students in the program must choose two additional electives to provide a deeper understanding of a specific area of interest within precision health. Focus areas may include statistical genetics, algorithmic bias detection, radio-genomics, health equity and societal genetics, population health, and genomic risk prediction. The ACC and trainee’s faculty mentor will advise the student in choosing appropriate courses, which are drawn from across the UCLA campus.
We are presently accepting applications for both pre- and postdoctoral candidates in this T15! Please use the Biosciences Application Portal to submit an application. For additional inquiries, please email biosciencephd@mednet.ucla.edu.