LLNL’s biosecurity mission includes detecting pathogens and developing medical countermeasures for them. Thanks to decades-long investments in these areas, computational biologist Kevin McLoughlin and Computing’s Bioinformatics group pivoted quickly when the COVID-19 pandemic began. He notes, “Long before SARS-CoV-2 came along, it was clear that our country needed to be better prepared to deal with a major pandemic or a bioterrorism attack. Continuing this research is important preparation for the next biosecurity event in whatever form it takes.”
Kevin helped develop the Lawrence Livermore Microbial Detection Array (LLMDA) system and its commercial platform, which won an R&D 100 Award in 2017. With software that compares microbial DNA sequences, the technology can identify thousands of microbes and process nearly 100 samples simultaneously. LLMDA has been used aboard the International Space Station and now includes the SARS-CoV-2 genome. Kevin initially contributed to the software used to design probes for new organisms and wrote the software that determines which microbes are present in the samples. He rejoined the project in 2019 to add coronavirus probes to the array and help update the sequence database.
Since 2017, Kevin has participated in the Accelerating Therapeutics for Opportunities in Medicine (ATOM) consortium, which combines HPC and data science techniques to design drugs for cancer, pathogens, and other diseases. “I feel lucky to be part of the ATOM consortium. It’s challenging, enormously important, draws on my full skill set, and demands that I constantly learn new things. I also get to work with extremely smart people from LLNL and our partners,” he explains.
Building on ATOM’s progress, Kevin helped develop a COVID-19 antiviral drug design pipeline that combines a computational autoencoder framework with machine learning algorithms to propose molecular structures, identify those with desirable properties, and suggest new molecules based on the best results. The model was a finalist for the 2020 Gordon Bell Special Prize for High Performance Computing-Based COVID-19 Research, and the team received one of the Lab’s 2021 Excellence in Publication Awards.
The appeal for Kevin in these projects lies at the intersection of computing and biology. “I love finding ways to visualize data that reveal relationships to the underlying biology,” he says. And he knows that successfully applying computational and machine learning techniques to real-world problems depends on the quality of the data. “Finding enough quality data and cleaning it up before you can train models are big challenges,” Kevin explains. “The work isn’t glamorous, and doing it correctly requires domain knowledge.”
Kevin traces his domain experience back to graduate school in the 1980s, when he worked on early neural network simulations to understand the human brain. He recalls, “Computational biology as a field didn’t exist then, but that changed when the Human Genome Project launched.” He took a bioinformatics class from now-retired LLNL scientist Tom Slezak and, after a stint with the biotech startup Gene Logic, joined the Lab in 2004 to work on pathogen bioinformatics.
Kevin holds a Master’s in Physics from the University of California, Santa Cruz. In 2013, he earned a PhD in Biostatistics from UC Berkeley with help from the Lab’s Educational Assistance Program, which reimburses tuition for employees pursuing a degree in their field. Although returning to school while working full time was a significant challenge, Kevin recommends deferring graduate studies until a student has gained some work experience. “My education was much more valuable with this approach,” he states. “I focused on applying what I learned to problems encountered in my job. In fact, for my dissertation I developed new algorithms to analyze LLMDA data.”
He also mentors computer science undergrads, graduate students, and postdocs who work on computational drug design projects at ATOM, helping them gain biology and chemistry domain knowledge. “Working with bright, motivated students is especially rewarding because they ask the most challenging questions, often leading me to question my assumptions and perhaps discover something new,” Kevin says.