{"id":296,"date":"2020-09-29T13:04:19","date_gmt":"2020-09-29T13:04:19","guid":{"rendered":"https:\/\/machine-learning.webcloning.com\/2020\/09\/29\/drug-discovery-in-the-age-of-covid-19\/"},"modified":"2020-09-29T13:04:19","modified_gmt":"2020-09-29T13:04:19","slug":"drug-discovery-in-the-age-of-covid-19","status":"publish","type":"post","link":"https:\/\/salarydistribution.com\/machine-learning\/2020\/09\/29\/drug-discovery-in-the-age-of-covid-19\/","title":{"rendered":"Drug Discovery in the Age of COVID-19"},"content":{"rendered":"
\n

Drug discovery is like searching for the right jigsaw tile \u2014 in a puzzle box with 1060 molecular-size pieces<\/a>. AI and HPC tools help researchers more quickly narrow down the options, like picking out a subset of correctly shaped and colored puzzle pieces to experiment with.<\/p>\n

An effective small-molecule drug will bind to a target enzyme, receptor or other critical protein along the disease pathway. Like the perfect puzzle piece, a successful drug will be the ideal fit, possessing the right shape, flexibility and interaction energy to attach to its target.<\/p>\n

But it\u2019s not enough just to interact strongly with the target. An effective therapeutic must modify the function of the protein in just the right way, and also possess favorable absorption, distribution, metabolism, excretion and toxicity properties \u2014 creating a complex optimization problem for scientists.<\/p>\n

Researchers worldwide are racing to find effective vaccine and drug candidates to inhibit infection with and replication of SARS-CoV-2, the virus that causes COVID-19. Using NVIDIA GPUs, they\u2019re accelerating this lengthy discovery process \u2014 whether for structure-based drug design, molecular docking, generative AI models, virtual screening or high-throughput screening.<\/p>\n

Identifying Protein Targets with Genomics<\/b><\/h2>\n

To develop an effective drug, researchers have to know where to start. A disease pathway \u2014 a chain of signals between molecules that trigger different cell functions \u2014 may involve thousands of interacting proteins. Genomic analyses can provide invaluable insights for researchers, helping them identify promising proteins to target with a specific drug.<\/p>\n

With the NVIDIA Clara Parabricks<\/a> genome analysis toolkit, researchers can sequence and analyze genomes up to 50x faster. Given the unprecedented spread of the COVID pandemic, getting results in hours versus days can have an extraordinary impact on understanding the virus and developing treatments.<\/p>\n

To date, hundreds of institutions, including hospitals, universities and supercomputing centers, in 88 countries have downloaded the software to accelerate their work \u2014 to sequence the viral genome itself, as well as to sequence the DNA of COVID patients and investigate why some are more severely affected by the virus than others.<\/p>\n

Another method, cryo-EM<\/a>, uses electron microscopes to directly observe flash-frozen proteins \u2014 and can harness GPUs to shorten processing time for the complex, massive datasets involved.<\/p>\n

Using CryoSPARC, a GPU-accelerated software built by Toronto startup Structura Biotechnology, researchers at the National Institutes of Health and the University of Texas at Austin created the first 3D, atomic-scale map of the coronavirus<\/a>, providing a detailed view into the virus\u2019 spike proteins, a key target for vaccines, therapeutic antibodies and diagnostics.<\/p>\n

GPU-Accelerated Compound Screening<\/b><\/h2>\n

\"\"
\nOnce a target protein has been identified, researchers search for candidate compounds that have the right properties to bind with it. To evaluate how effective drug candidates will be, researchers can screen drug candidates virtually, as well as in real-world labs.<\/p>\n

New York-based Schr\u00f6dinger<\/a> creates drug discovery software that can model the properties of potential drug molecules. Used by the world\u2019s biggest biopharma companies, the Schr\u00f6dinger platform allows its users to determine the binding affinity of a candidate molecule on NVIDIA Tensor Core GPUs<\/a> in under an hour and with just a few dollars of compute cost \u2014 instead of many days and thousands of dollars using traditional methods.<\/p>\n

Generative AI Models for Drug Discovery<\/b><\/h2>\n

Rather than evaluating a dataset of known drug candidates, a generative AI model starts from scratch. Tokyo-based startup Elix, Inc., a member of the NVIDIA Inception<\/a> virtual accelerator program, uses generative models trained on NVIDIA DGX Station<\/a> systems to come up with promising molecular structures. Some of the AI\u2019s proposed molecules may be unstable or difficult to synthesize, so additional neural networks are used to determine the feasibility for these candidates to be tested in the lab.<\/p>\n

With DGX Station, Elix achieves up to a 6x speedup<\/a> on training the generative models, which would otherwise take a week or more to converge, or to reach the lowest possible error rate.<\/p>\n

Molecular Docking for COVID-19 Research<\/b><\/h2>\n

With the inconceivable size of the chemical space, researchers couldn\u2019t possibly test every possible molecule to figure out which will be effective to combat a specific disease. But based on what\u2019s known about the target protein, GPU-accelerated molecular dynamics applications<\/a> can be used to approximate molecular behavior and simulate target proteins at the atomic level.<\/p>\n<\/p>\n

Software like AutoDock-GPU, developed by the Center for Computational Structural Biology at the Scripps Research Institute, enables researchers to calculate the interaction energy between a candidate molecule and the protein target. Known as molecular docking, this computationally complex process simulates millions of different configurations to find the most favorable arrangement of each molecule for binding. Using the more than 27,000 NVIDIA GPUs on Oak Ridge National Laboratory\u2019s Summit supercomputer, scientists were able to screen 1 billion drug candidates for COVID-19 in just 12 hours<\/a>. Even using a single NVIDIA GPU provides more than 230x speedup over using a single CPU.<\/p>\n

\"\"
Argonne deployed one of the first DGX-A100 systems. Courtesy of Argonne National Laboratory.<\/figcaption><\/figure>\n

In Illinois, Argonne National Laboratory<\/a> is accelerating COVID-19 research using an NVIDIA A100 GPU<\/a>-powered system based on the DGX SuperPOD reference architecture<\/a>. Argonne researchers are combining AI and advanced molecular modelling methods to perform accelerated simulations of the viral proteins, and to screen billions of potential drug candidates, determining the most promising molecules to pursue for clinical trials.<\/p>\n

Accelerating Biological Image Analysis<\/b><\/h2>\n

The drug discovery process involves significant high-throughput lab experiments as well. Phenotypic screening is one method of testing, in which a diseased cell is exposed to a candidate drug. With microscopes, researchers can observe and record subtle changes in the cell to determine if it starts to more closely resemble a healthy cell. Using AI to automate the process, thousands of possible drugs can be screened.<\/p>\n

Digital biology company Recursion<\/a>, based in Salt Lake City, uses AI and NVIDIA GPUs to observe these subtle changes in cell images, analyzing terabytes of data each week. The company has released an open-source COVID dataset<\/a>, sharing human cellular morphological data with researchers working to create therapies for the virus.<\/p>\n

Future Directions in AI for Drug Discovery<\/b><\/h2>\n

As AI and accelerated computing continue to accelerate genomics and drug discovery pipelines, precision medicine \u2014 personalizing individual patients\u2019 treatment plans based on insights about their genome and their phenotype \u2014 will become more attainable.<\/p>\n

Increasingly powerful NLP models will be applied to organize and understand massive datasets of scientific literature, helping connect the dots between independent investigations. Generative models will learn the fundamental equations of quantum mechanics and be able to suggest the optimal molecular therapy for a given target.<\/p>\n

To learn more about how NVIDIA GPUs are being used to accelerate drug discovery, check out talks by Schr\u00f6dinger<\/a>, Oak Ridge National Laboratory<\/a> and Atomwise<\/a> at the GPU Technology Conference<\/a> next week.<\/p>\n

For more on how AI and GPUs are advancing COVID research, read our <\/i>blog stories<\/i><\/a> and visit the <\/i>COVID-19 research hub<\/i><\/a>.<\/i><\/p>\n

Subscribe to <\/i>NVIDIA healthcare news here<\/i><\/a>.\u00a0<\/i><\/p>\n<\/div>\n","protected":false},"excerpt":{"rendered":"

http:\/\/feedproxy.google.com\/~r\/nvidiablog\/~3\/bzgiOv7qZk8\/<\/p>\n","protected":false},"author":0,"featured_media":297,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[3],"tags":[],"_links":{"self":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/posts\/296"}],"collection":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/comments?post=296"}],"version-history":[{"count":0,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/posts\/296\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/media\/297"}],"wp:attachment":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/media?parent=296"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/categories?post=296"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/tags?post=296"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}