Guest post by Virginia Meyer, PhD, Training Director for the Intramural Research Program, National Library of Medicine, National Institutes of Health.
Every year, NLM’s Intramural Research Program (IRP) hosts its Data Science and Informatics (DSI) Scholars Program, which is open to undergraduate and graduate students from diverse backgrounds and underrepresented groups who are pursuing biomedical informatics training and research opportunities in computer science and related fields. I invite you to meet six of this year’s interns and learn about the innovative research they are doing in the NLM IRP!
Editor’s Note: Check out our intern slideshow below! To learn more about each intern and their experience with the DSI program, roll your cursor over their image to pause the slideshow.
Mukshud Ahamed
“I am from Westbrook, Connecticut. I attend Stony Brook University in New York and am co-mentored by NLM Principal Investigator (PI) Dr. Aravind Iyer and Dr. Jessica Seeliger at Stony Brook. My research areas are evolutionary genomics and biomolecular structure.”
Learn more about Mukshud!
Can you describe what interested you most about the program?
I am interested in the use of sequencing data to predict the functions of uncharacterized proteins. As such, the DSI Scholars program was an appropriate fit for me to pursue my interest within Dr. Iyer’s lab.
What research project are you working on and why?
I am studying the evolution and comparative genomics of bacterial lipid binding lipoproteins. As a trainee in Dr. Seeliger’s lab, I became profoundly interested in the mycobacterial cell envelope, specifically how it is made and what molecular machines are involved. I worked on the identification of surface proteins and realized that such knowledge would be greatly complemented by approaches to predict the function and evolution of mycobacterial cell envelope proteins.
What is next for you after you complete your internship?
I plan to continue my dissertation research at NLM in the fall through the NIH Graduate Partnerships Program.
Asmaa Awan
“I’m from Village Subedar Ahmad Khan Awan in Sindh, Pakistan. I’m an international student studying for my Master of Science degree in Bioinformatics at Morgan State University. My PI at NLM is Dr. Lauren Porter. My research areas are evolutionary genomics and biomolecular structure.”
Learn more about Asmaa!
Can you describe what interested you most about the program?
The program is exciting because you’re learning about new things all the time. NLM makes it special by the speed at which things get done here. I’ve never been able to learn so much in such a short time and there’s no pressure either. You learn to automatically go with the flow.
What research project are you working on and why?
I’m working on judging the ability of protein prediction models such as AlphaFold2 to predict alternate conformations for fold-switching proteins. This is important because the functions of proteins depend on their structures. Most proteins perform their designated functions by undergoing structural changes. Study of these changes not only helps us understand the mechanism of action of different proteins, but also enables us to detect abnormalities associated with disease conditions.
Why might someone want to apply to the DSI program in the future?
This program sharpens the experience of participants by providing them the opportunity to work with great PIs and PhDs who mentor them throughout the length of the program. The program helps you to polish your article reading, writing, and presentation skills through journal clubs and poster presentations. The program also conducts graduate and professional school fairs to help create connections and make you aware of the wide range of opportunities available. Apart from all these, career counselling is available.
What is next for you after you complete your internship?
I’ll return to Morgan State University to complete my degree in Bioinformatics and then plan on pursuing a PhD.
Smitha Edakalavan
“I’m a PhD student in Biomedical Informatics at the University of Pittsburgh. My PI is Dr. Jeremy Weiss, and my research area is clinical informatics.”
Learn more about Smitha!
What interested you most about the DSI program?
I became highly interested by the broad scope and profound social impact of the projects carried out at NIH. A summer internship is a great way to learn more about these projects and better understand the working environment at NIH.
What research project are you working on and why?
I am working with Dr. Weiss to assess the data sparsity in clinical notes and the tabular data in electronic health records at the time of patient admission. Our focus is on leveraging multimodal data, combining these diverse modalities to glean more insightful information about a patient’s condition. We then developed a machine learning model to predict any post-admission events for a patient using this multimodal data. It provides several advantages including early intervention and timely care, personalized treatment plans, resource allocation, and planning.
Why might someone want to apply to the DSI program in the future?
I perceive this as an excellent chance to engage with real-world challenges and make meaningful contributions to research and knowledge. Working with the latest technologies alongside a mentor will deepen your understanding of the field. You get a feel for the collaborative environment, working alongside people from diverse backgrounds. Being a part of NIH, the steward of medical research in the United States, is truly an achievement to take pride in. The supportive and friendly atmosphere fosters a valuable networking experience that can significantly benefit your career.
What is next for you after you complete your internship?
I will be going back to complete my PhD in Biomedical Informatics at the University of Pittsburgh. I definitely plan to come back to NIH after that!
Emily Guan
“I’m from Ocean, NJ, and I’m an undergrad at Johns Hopkins University. My PI is Dr. Zhiyong Lu, and my research area is image processing.”
Learn more about Emily!
Can you describe what interested you most about the program?
I’m very interested in computational methods for disease diagnosis and treatment. This program is an opportunity to conduct research in areas that I was interested in, but that were very different from my previous experiences. I wanted to contribute to ongoing research at NLM and learn from experts in the field.
What research project are you working on and why?
My project is on using machine learning to diagnose age-related macular degeneration through color fundus images. Early diagnosis of this disease is important and improving its diagnosis can lead to better quality of life for many patients. I’m interested in machine learning applications that directly improve patient care, so I’m excited to work on this project.
Why might someone want to apply to the DSI program in the future?
Learning about fields in computational medicine through research is very different from doing so through classes, and it’s an invaluable experience. You’re also surrounded by talented scientists and can gain a broader understanding of the projects they work on. The NIH also offers professional development and other opportunities—my favorite is the journal club program, where I get to learn about a field (in my case, large language models) through discussion of interesting papers.
What is next for you after you complete your internship?
I’m going into my junior year, where I’m pursing degrees in biomedical engineering and computer science. Because of this experience, I’m very interested in finding new research opportunities in machine learning and continuing to explore the field.
Radiah Islam
“I was born in Texas but have lived in Maryland over the past six years. I am a rising senior at the University of Maryland, and my PI is Dr. Ivan Ovcharenko. My research areas are networks, gene regulation, and chromatin.”
Learn more about Radiah!
Can you describe what interested you most about the program?
What interested about me in this program is that the program relies on both computer science and biological knowledge to help understand more about DNA.
What research project are you working on and why?
My research project is about quantifying enhancer strength and I am working on this project because mutations in enhancers play a large role in many diseases.
Why might someone want to apply to the DSI program in the future?
Someone might want to apply to the DSI program in the future if they want to learn about DNA and its effect on phenotype while also gaining computer science skills.
What is next for you after you complete your internship?
After I complete my internship, I will either complete my master’s degree in computer science or head to medical school.
Shreyash Singh
“My hometown is New Orleans. My university affiliation is Vanderbilt University, and my PI is Dr. Zhiyong Lu. My research areas are natural language processing and computational biology.”
Learn more about Shreyash!
Can you describe what interested you most about the program?
The DSI Scholars Program represents a unique combination between artificial intelligence and medical knowledge. It allows me to utilize and apply my computational knowledge towards novel biomedical research and delve deeper into natural language processing as well as the diverse clinical applications of such research. I am also continuing to expand my knowledge within large language models, which I have been deeply interested in learning more about this summer.
What research project are you working on and why?
Currently, my project concerns the upcoming BioCreative Challenge, where participants are tasked to develop algorithms to identify biomedical entities (genes, diseases, chemicals, etc.) and their combined relations within medical literature. For such a task, a testing dataset must be curated that should contain certain similarities to the Biomedical Relation Extraction (BioRED) dataset (training data). My project deals with the identification of these data trends in both databases through data visualization and text mining, so I can identify these similarities as well certain differences between them. Additionally, I’ve run a benchmark machine learning model to assess if both datasets achieve similar scores.
Why might someone want to apply to the DSI program in the future?
This program incorporates a comprehensive focus upon computational thinking towards biomedical research. One can engage in a practical research project while still growing and connecting through their peers and mentors. Additionally, outside of the research project, interns can be involved in numerous opportunities to advance and prepare for their careers, whether that be through graduate school or elsewhere.
What is next for you after you complete your internship?
After my internship, I will return to Vanderbilt as a second-year student where I am studying both cognitive studies as well as data science. I also aim to attend medical school after my undergraduate career as well as pursue separate opportunities within computational biology.
Virginia Meyer, PhD
Training Director, Intramural Research Program, NLMDr. Meyer received her PhD in Physical Chemistry from the University of Denver and completed postdoctoral training at the National Institute of Diabetes and Digestive and Kidney Diseases, National Institutes of Health. She transitioned to a training role at NIH in 2015 and worked as the Director of Student Services for the Undergraduate Scholarship Program until 2020 when she became the Training Coordinator at the National Library of Medicine. Dr. Meyer now oversees and advises postdoctoral, postbaccalaureate, and student researchers in the NLM Intramural Research Program.