April 18, 2018 — When the students in Pierre Neuenschwander’s master’s level “Proteins and Nucleic Acids” class prepared for their midterm in March, they were actually following a path that their professor had begun nearly a decade ago.
A lab scientist by training, Neuenschwander, an associate professor of biochemistry at The University of Texas Health Science Center at Tyler (UTHSCT), began to experiment in the mid-2000s with computational drug docking, then in its early days.
The idea of discovering and testing how new drugs bind to proteins in silico (or on a computer) had been around for a while, but it was only around that time that computers were getting powerful enough to simulate the physics and chemistry involved in molecules interacting.
Neuenschwander used newly-available software to perform virtual experiments on clotting factor IXa, a blood clotting enzyme that was the subject of his research at that time.
He began the computations and day after day would return to his office to jiggle the mouse to make sure the computer was still processing. After several months, his computer finally spit out an answer. He was astounded to find it had deduced the location where a drug would bind.
“Eventually it gave an answer — nice different structural configurations of the small molecule — and one was just right,” Neuenschwander said. “I had given the computer no clue and told it to search the entire surface and it narrowed down to one spot on factor IXa.”
The story might have ended there had not a staff member from the Texas Advanced Computing Center (TACC) visited UTHSCT in 2009 and mentioned to Neuenschwander that, as part of the University of Texas Cyberinfrastructure (UTRC) program, researchers at all 14 of the University of Texas System institutions had free access to TACC’s supercomputers.
Neuenschwander re-ran his simulation on TACC’s Ranger supercomputer — one of the most powerful in the world at the time — and, lo and behold, he was able to solve the same problem that took months on his laptop in 15 minutes.
“I realized this is doable. Now we can start teaching students how to do this so when they go out and work for drug companies they can come armed with the knowledge of what’s pushing the limits and what’s possible,” he said.
Neuenschwander has offered the Proteins and Nucleic Acids course every year since 2014. Access to TACC allows him to expose students to computational modeling and design in a way that makes molecular and atomic reactions more concrete for students.
“In lectures, they learn about interactions between proteins, lipids and nucleic acids, but it’s really hard to do a lab on that,” he explained. “You can do experiments for binding but you can’t really see the interactions; you can’t get a good feel for all that’s happening. But with computer modeling on the other hand, you can, because you can visualize the process when you’re done. So I developed the lab portion of that course as a computing lab.”
Most of his students have no Linux or programming experience. In the class, they learn how to access TACC supercomputers and run virtual experiments. Neuenschwander sets up the projects in advance so students can focus on the scientific research rather than the computer programming. Nonetheless, they get a hands-on experience logging in to TACC’s systems, adjusting parameters, and running simulations.
For their mid-term exams, Neuenschwander has students download the crystal structure of docked molecules from a protein database and use TACC supercomputers to pull the molecules apart and predict how they will bind.
“The students learn that if they allow the computer to vary wildly from what’s known, they may not get the right results,” he said. “But if they make judicious choices that they can justify scientifically, the computer gets it right fairly often.”
For their finals, students are asked to take a sequence of RNA, fold it to make 1,000 three-dimensional structures, and then screen each to see if they will bind to a molecule – a process that forms the basis of a biotechnology tool called siRNA, which uses an RNA molecule to shut down a specific gene.
The exam is actually a bit of a trick though.
“What they will find out when they do the RNA modeling is that the computer can’t really find a good solution because it’s much too complicated,” Neuenschwander revealed. “So, it shows that even with the supercomputers that we have now, we need even more computing power to predict those structures with any accuracy.”
Several students who have taken Neuenschwander’s class have gone on to use advanced computing for their theses. Others end up using the skills they were first introduced to in his class in their careers and further education.
This was the case for Juan Macias, a PhD candidate in the computational and systems biology program at Washington University in Saint Louis, where he uses supercomputers to study epigenetic regulation in metabolic disease like obesity and diabetes. He says Neuenschwander’s class helped “demystify” the process of using advanced computing.
“Exposure to the TACC resources was very useful in getting me used to working on those sorts of systems,” Macias said. “Having someone guide you through the process of working with these sorts of resources, as was done in that class, is invaluable.”
Drug docking is not the only problem that advanced computing can be used for. Molecular dynamics — a method for studying the physical movements of atoms and molecules computationally — is another area that Neuenschwander is exploring. Using molecular dynamics, researchers can understand how bonds form between molecules and how their shape changes when molecules interact. He hopes to develop a new class teaching molecular dynamics to students in the biochemistry program in the near future.
Meanwhile, the number of problems that use computation is growing. Neuenschwander is particularly excited about proteomics and efforts to develop virtual human test subjects.
“Wouldn’t it be great instead of going into human trials and risking getting someone sick first, you have a computer tell you what the potential problems might be?” he asked. “The more we learn about how these molecules interact, the closer to reality that becomes.”
It may take decades to reach that goal, but by training the next-generation of computational biochemists, Neuenschwander is helping to make it a reality.
Source: Aaron Dubrow, TACC