From decoding plant genomes to modeling microbial behavior, computational biologist Priya Ranjan builds computational tools that turn extensive biological datasets into real-world insights. These tools transform the way scientists ask and answer complex biological questions that advance biotechnology breakthroughs and support cultivation of better crops for energy and food security.
As part of the Computational and Predictive Biology group at the Department of Energy’s Oak Ridge National Laboratory, Ranjan works with large datasets generated from genome sequencing and other high-throughput biological experiments. He builds AI-enabled predictive tools and models to interpret data. His tools allow researchers to test hypotheses, design experiments and predict outcomes, accelerating discovery and innovation.
Curiosity and a passion for bridging disciplines
Ranjan’s scientific journey spans both disciplines and continents. Originally from India, he trained first in chemistry, then followed his growing fascination with biomolecules to a master’s degree in biotechnology from the Indian Institute of Technology. It was there, during an internship exploring protein structure and mutations, that he turned to forest genetics and bioinformatics, leveraging computing and mathematics to analyze patterns in biological information. His interest was sparked by the hands-on discovery process that allowed scientists to design experiments, make small changes in molecules and observe the effects. That interest culminated in a doctorate in bioinformatics from Michigan Technological University.
During his graduate studies, he connected with Jerry Tuskan, now director of the Center for Bioenergy Innovation, or CBI, at ORNL. Tuskan was leading efforts to match genes to traits in the newly sequenced genome of the poplar tree, an energy crop that can be converted into fuels, chemicals and materials. Having spent several years working with poplar, Ranjan found a natural fit in ORNL’s Plant Systems Biology group.
Since then, Ranjan’s work has continued to span disciplines, from plant biology to data science, and his systems-level approach helps him address complex biological questions.
“Chemistry to biotech to bioinformatics — that’s been the journey,” he said. “Very interdisciplinary, which gives me a unique perspective because each of these fields comes with a different approach to problems and how to solve them.”
Harnessing computing for biological discovery
Ranjan’s early work centered on using computational models to identify the genetic drivers of key plant traits, especially those related to cell wall composition. The goal was to identify genes that, when modified, could make it easier to break down and convert plant materials into biofuels and other valuable products. Ranjan analyzed data from past experiments, pinpointing promising candidate genes and passing these predictions along to experimental biologists, who tested them in the lab to validate real-world effects on plant performance.
“We were working in a big, collaborative group where everyone was bringing their different perspectives,” Ranjan said. “There were biologists, there were chemists — and I was bringing my computational expertise to the table. There was an amazing amount of data coming from the project, and it became this beautiful pipeline where computation and experimentation worked hand in hand.”
Ranjan’s focus evolved from there, moving from data analysis to data infrastructure when he joined the multi-lab team building DOE’s Systems Biology Knowledgebase, or KBase. KBase is an open platform for biological data analysis and sharing, designed to make it easier for researchers without programming expertise to gain insights from complex datasets.
Ranjan is developing plant-specific workflows and tools for functional genomics, building a knowledge base with reproducible processes so that scientists will be able to upload their data, generate meaningful insights and see how their results compare or connect with data already in the system. He’s also helping to build a standardized data hub within KBase to streamline research across DOE’s Biological and Environmental Research, or BER, programs.
“I collect data, I organize it, I build models and I work with experimental biologists to test and refine them,” Ranjan said. “And we make it all available in KBase so others can benefit. That’s the goal: building tools that don’t just advance one project but empower a whole community of researchers.”
More recently, he has helped lead the integration of KBase with ORNL’s Plant-Microbe Interfaces, or PMI, Science Focus Area. Here, his efforts are aimed at understanding and designing beneficial synthetic microbial communities — or lab-created batches of what Ranjan describes as “probiotics for plants.” These microbial blends are designed to enhance plant growth, improve nutrient uptake, enable biomining of critical materials and increase resilience to environmental stress.
“But you can’t just throw microbes together and hope they cooperate,” Ranjan said. “Some will compete; others may even inhibit each other. We want to build a tool to assess these potential interactions based on their genomic profiles.”
To tackle this, Ranjan and colleagues are using machine learning and metabolic modeling to calculate scores that predict how microbes will behave individually and in communities — and how these combinations will ultimately impact plant growth. These models help experimentalists design and test microbes and microbial combinations that could improve crop resilience, reduce dependence on synthetic fertilizers and naturally capture critical materials to drive economic prosperity.
These tools are already available in KBase, with more features under development.
Design, build, test and learn
Ranjan’s work is underpinned by a cycle of design, build, test and learn. Whether he’s developing predictive models or contributing to open, scalable platforms that empower the global research community to interpret data, he relies on this iterative process to refine both the tools and the science behind them. His computational predictions are tested by experimentalists, and the results refine those models further, continually improving accuracy and expanding their utility.
What’s most exciting is that we’re building models that aren’t just theoretical — they’re tested in the lab, refined and made better. That’s where real impact happens.
But working with data isn’t always straightforward. One of the biggest challenges Ranjan faces is data standardization. Experimental protocols can vary widely across labs, from different growth media to different data recording methods. These discrepancies can make it difficult to compare results or integrate datasets, so a big part of Ranjan’s role involves formatting and organizing inconsistent public data to make it usable for modeling and compatible with the database.
Collaborating with teams like PMI helps develop standardized, reproducible datasets that improve the accuracy and reliability of computational models. He’s also working more broadly to develop a standardized data architecture within KBase that can streamline how information flows in from various sources, including large-scale research initiatives. Ranjan hopes that this centralized, AI-ready data hub will support broader sharing and analysis across BER research efforts by enabling seamless integration of genome-based predictions, experimental results and machine learning insights.
For Ranjan, ORNL’s collaborative culture and mission-driven science make it the ideal research environment. With hundreds of researchers working together in CBI, PMI and KBase, he’s part of a powerful system dedicated to solving some of the world’s toughest energy and environmental challenges.
UT-Battelle manages ORNL for DOE’s Office of Science, the single largest supporter of basic research in the physical sciences in the United States. The Office of Science is working to address some of the most pressing challenges of our time. For more information, visit https://energy.gov/science. — Michaela Bluedorn
