Developing new, innovative drugs takes a very long time, and so it becomes imperative to improve predictability and efficiency along the critical path from laboratory concept to a commercial medical product.
Roopal Bhatnagar, our next pathbreaker, Data Analyst at the Critical Path Institute (Tucson, Arizona) works with diverse stakeholders to identify specific barriers to developing a safe and effective therapy for a given disease, in order to develop solutions that help drug developers overcome those barriers.
Roopal talks to Shyam Krishnamurthy from The Interview Portal about how her exposure to the field of bioinformatics helped her make a switch from experimental lab-work to computational modeling and data science.
For students, clinical data science in the domain of drug discovery is undergoing an exciting period of transformation with the advent of digital technologies such as smartphones or any other forms of wearable sensors.
Roopal, Your background?
I come from the beautiful city of Udaipur. My father worked as a bank manager and my mother was a mathematics and economics teacher and later a homemaker. My family has always put emphasis on my education. I was a competent student throughout my schooling. My observant and hard-working nature coupled with my curiosity to understand nature and natural systems led me to be inherently interested in science. I chose PCM after my 10th board exams to pursue engineering. I started preparing for engineering entrance exams as well. Chemistry and Physics were my strongest suits. Apart from studies, I used to participate in dance and creative writing competitions. In college, I started hiking and swimming, and have been doing those ever since.
What did you do for graduation/post graduation?
I did BTech in Chemical Engineering from IIT Roorkee. This was followed with an MS in Chemical and Biomolecular Engineering from University of Pennsylvania.
My research assistantship was enough to cover my living expenses.
How did you end up in such an offbeat, unconventional and interesting career?
My journey from a chemical engineer to a clinical data analyst has been everything but linear. I was interested in applying chemical engineering principles to life science problems to understand drug mechanisms better. My undergrad research internship experience was a turning point in my academic life as it motivated me to pursue graduate studies where I could get a better perspective on research. During my masters, I got interested in working in the pharmaceutical industry. My programming courses in grad school and training in the bioinformatics lab helped me make my switch from experimental lab-work to computational modeling and data science.
How did you plan the steps to get into the career you wanted? Or how did you make a transition to a new career? Tell us about your career path
During my undergrad, I was interested in applying chemical engineering techniques that I was learning in my undergrad to life sciences. This led to my internship at the Institute of Chemical Process Fundamentals at the Czech Academy of Sciences in Prague, Czech Republic. I got to work hands-on in a lab designing, conducting and analyzing data from mass spectrometry and NMR spectroscopy of compounds with anti-tumor properties. I got interested in the process of drug action in the human body and how it can be manipulated by making changes on a molecular level.
During my graduate studies, I got to work in different labs as a research assistant. My first assistantship was in the Translational Bioinformatics lab. I got an opportunity to be a part of projects which aimed at a better understanding of drug action and leveraging treatments through advanced informatics tools to unravel the role of genetics in drug action. The experience exposed me to the fundamentals of machine learning and data science and their applications in the life science domain. I got a chance to further develop my programming skills by getting hands-on experience in pipeline building with tools and libraries.
In my second research assistantship at Penn Institute for Computational Science, my work involved analyzing molecular level data of protein molecules to investigate protein-water and protein-protein interactions using machine learning tools. To gain a broader outlook of real-world applications of technologies in life science, I started working as a fellow at Penn Center for Innovation. It was an experiential internship where I got the opportunity to evaluate the novelty of a plethora of cutting-edge technologies developed at the University of Pennsylvania. The challenging task exposed me to the far-reaching impact of modern-day science and its scope. Analyzing patent applications for technologies specifically in the pharmaceutical and life science domains made me realize the challenges still needed to be addressed in the journey of a drug from a molecule to patients. The commercialization aspect of technology transfer helped me gain insights into the potential of a technology in the market for varied applications.
I was working in other verticals of life science as well with applications of biochemistry. The goal was to explore as much as possible until I decided to narrow down into drug discovery and development in my later projects.
I also joined Penn Biotech Group Healthcare Consulting in Fall 2018 to gain a new perspective of technology commercialization for an early start-up company by finding funding solutions for them.
How did you get your first break?
While presenting my research at the American Conference on Clinical Pharmacology and Therapeutics (ASCPT), I got the opportunity to meet my now-colleagues from the Critical Path Institute. I got to know about the impactful work the company does and was very impressed by it. Later, when an opening came up in the company, I reached out to the same colleagues who encouraged me to apply as they saw me as a good fit for the role. I interviewed for the position and got the job. I have been at C-Path since then working on some very exciting projects.
What were some of the challenges you faced? How did you address them?
Challenge 1: Learning new skills
Transitioning from Chemical Engineering to computational modeling and data science required me to learn many new skills along the way. I sought out internships, courses and projects that have helped me learn new skills in clinical data science that have been very useful in my career. I also focused on implementing those skills in my work and presenting or publishing it.
Challenge 2: Finding innovative solutions to open ended problems
This can be the best part as well as the most challenging aspect of research. It provides an exciting opportunity to push the boundaries of knowledge and discover novel solutions, but it also demands creative thinking and perseverance to navigate uncharted territory and find answers to questions that have yet to be addressed.
Challenge 3: Keeping up to date with new advancements in field
My work being at an intersection of data science and biochemistry requires me to keep abreast of all the latest developments in both the fields. In addition to that, it is crucial to be able to implement these data science technologies to biomedical data for advancing drug development.
Where do you work now? What problems do you solve?
I work at the Critical Path Institute (C-Path) in Tucson, Arizona. C-Path forms collaborative work groups of diverse stakeholders such as industry and academic research groups to identify specific barriers to developing a safe and effective therapy for a given disease, and then creates tools and solutions that help drug developers overcome those barriers. These tools and solutions are primarily data driven. We acquire data from clinical trials conducted by our collaborators. My work as a data analyst is to curate and analyze this clinical data to gain insights from it and assist in the formulation of drug development solutions.
Examples of such tools and solutions can include disease progression models, clinical trial simulators, new biomarkers, or analytics pipeline to aid research in a disease area.
Our collaborators include academic institutions as well as Pharma companies (like Merck, Novartis etc.) for whom C-Path aims to address unmet needs in various disease areas. We come in the picture in the pre-competitive stage in which we share and standardize data from trials and develop clinical outcome assessments and tools that can be utilized by the industry to accelerate their trials.
What skills are needed for your role? How did you acquire the skills?
The job requires strong programming skills along with knowledge about the drug development process. Keeping updated with new developments in the field helps with honing these skills for the job. My job role includes python programming, writing and testing data processing and analysis pipelines, testing new natural language processing methods for Electronics Health Record data mining and publishing and presenting my research results to internal and external collaborators. The part of my job that I love the most is how impactful the work is and my co-workers’ passion keeps me motivated.
How does your work benefit society?
Clinical trials and therapies are crucial for patients because they offer access to safe and effective treatments. Trials help determine the best interventions, leading to improved health outcomes and potential cures. Patients benefit from cutting-edge treatments, through better quality of life, and hope for managing or overcoming their medical conditions. However, it takes too long and costs too much to take a new compound discovered in the laboratory through the drug development process and achieve a regulatory-approved safe and effective therapy. C-Path creates new medical product development toolkits — containing powerful new scientific and technical methods such as computer-based predictive models, biomarkers for safety and effectiveness, and new clinical evaluation techniques. These improve predictability and efficiency along the critical path from laboratory concept to commercial medical product. The work I do aides in accelerating the drug development process.
Tell us an example of a specific memorable work you did that is very close to you!
A work that is very close to me is my project on advancing the use of digital health technologies in clinical trials for Parkinson’s disease. Some examples of such technologies include smartwatches, smartphones or any other forms of wearable sensors. These technologies have potential to bring several significant improvements to clinical trials, enabling real-world data collection outside of the traditional clinical setting and through more patient-centered approaches. The urgent need of such technologies in trials for therapies to improve the lives of people living with this debilitating neurodegenerative disease, adds to the impact of the work. Through this project, I am trying my best to hopefully make a small difference in their lives.
Your advice to students based on your experience?
If you have real passion for solving a problem, you can achieve it by putting the right amount of effort into it. The key is to be curious and always keep learning and exploring – even when you reach your goal. One should keep updated with the advancements in the field of interest.
Future Plans?
I plan to continue my work in clinical data science in the domain of drug discovery and development. I also want to learn more about the regulatory side of the process. This is something I am working on.