Blog
Scientists leverage machine learning and AI to guide vaccine development
Aug
From tackling homework challenges to drafting emails, persons are discovering an enormous array of applications for natural language processing tools like generative artificial intelligence (AI) engines. Now, researchers from Pacific Northwest National Laboratory (PNNL) and Harvard Medical School (HMS) are using this same form of technology to construct a knowledge base to be able to guide decision-makers on vaccine development. Through the Rapid Assessment of Platform Technologies to Expedite Response (RAPTER) project, the scientists leverage machine learning and AI to go looking the scientific literature for knowledge on methods to construct effective vaccines against recent infectious viruses and bacteria.
Historically, vaccine development is a lengthy and expensive process-;often taking multiple years and tens of millions of dollars to finish. Vaccines are typically made using one in every of several different strategies, or “platforms.” Nonetheless, different strategies can generate different immune responses. With RAPTER, researchers work out which strategy would work best for a selected virus or bacteria to maximise the worth of immune responses from the host. The tool goals to assist produce recent vaccines more rapidly and with a reduced timeline and price.
Speed-reading with AI
A part of being a scientist involves publishing research results in order that other scientists may learn from the experiments.
“There may be a variety of information already in existence in scientific literature-;an excessive amount of for any person to possibly read through,” said data scientist and PNNL RAPTER lead researcher Neeraj Kumar. “We’re constructing RAPTER to routinely comb through the literature and catalog results from different experiments on vaccine design strategies-;ultimately providing decision-makers with information to pick out the perfect strategy for the following pandemic.”
Under the RAPTER project, PNNL scientists work closely with colleagues from HMS to routinely extract information from scientific publications in a meaningful way. “For our a part of the RAPTER project, we aim to learn from existing successes and failures in vaccine design through the scientific literature and construct robust artificial intelligence decision-making tools for vaccine design,” said HMS’s Director of Machine-Assisted Modeling and Evaluation Benjamin Gyori.
HMS scientists have already built similar tools for small molecule design. Nonetheless, vaccines and immunology are way more complex. Together, we’re constructing upon those tools to routinely extract key information from publications to grasp more in regards to the immune responses using different vaccine strategies.”
Jeremy Zucker, PNNL computational scientist
PNNL and HMS scientists make this possible by defining the important thing terms that connect mechanisms of immunity to experimental measurements. Once the terms are defined, the RAPTER tool can discover the relationships between terms across different scientific publications. This information feeds into the Knowledge Extraction for Strategic Threat Response using Evidence from the Literature (KESTREL) database to construct an in depth graph of relationships within the immune response.
“Understanding these relationships within the immune response might help us predict how different vaccine strategies can provide protection,” said Kumar. “With this information, scientists can focus their efforts on strategies which are more prone to succeed.”
Defending against future threats
For a long time, the Department of Defense’s Defense Threat Reduction Agency (DTRA) has mitigated emerging threats-;from nuclear to biological-;with science, technology, and capability development investments. As evidenced by the consequences of COVID-19, pandemics pose a significant threat to national security. To assist protect us against future pandemics, DTRA supports a consortium of research institutes, led by Los Alamos National Laboratory (LANL), in the event of the RAPTER tool.
In contrast to PNNL and HMS’s efforts, scientists at LANL are collecting and curating raw experimental data on viruses and vaccines and using artificial intelligence to discover patterns throughout the data to construct a profile for every vaccine candidate. Researchers from Lawrence Livermore National Laboratory, Sandia National Laboratories, U.S. Army Medical Research Institute of Infectious Diseases, Northern Arizona University, Tulane University, University of California San Diego, University of Recent Mexico and University of Nevada at Reno also contribute to the project.
Once the initial computational tools are built, the research institutes will mix their efforts to experimentally validate their results. Researchers including PNNL’s biomedical scientist Zachary Stromberg will work to experimentally confirm the computational results for the mRNA platform-;the identical platform utilized in the vaccine against SARS-CoV-2.
“Together, we will construct an automatic pipeline to expedite scientists’ vaccine design efforts,” said Kumar.
