Artificial intelligence (AI) has proven to be incredibly versatile, aiding people with a myriad of mundane and important tasks. Now, scientists from the Pacific Northwest National Laboratory (PNNL) and Harvard Medical School (HMS) are utilizing this same technology to develop a knowledge base that guides decision-makers in vaccine development and distribution.
Through the Rapid Assessment of Platform Technologies to Expedite Response (RAPTER) project, researchers employ machine learning (ML) and AI to search scientific literature for information on creating effective vaccines against new infectious viruses and bacteria. Typically, vaccine development is a time-consuming and costly process, often taking years and millions of dollars. With RAPTER, scientists can determine the best strategy for combating a specific virus or bacteria, optimizing immune responses in the host. This tool aims to expedite vaccine production while reducing time and cost.
Under the RAPTER project, PNNL scientists can collaborate closely with HMS colleagues to extract information from scientific publications in a meaningful manner. The goal is to learn from past successes and failures in vaccine design through the scientific literature, ultimately constructing robust AI decision-making tools for vaccine development. By building upon existing know-how, researchers aim to extract crucial information from publications to enhance understanding of immune responses using different vaccine strategies. By understanding these strategies and relationships, scientists can predict the effectiveness of different vaccine strategies, enabling them to focus on those more likely to succeed.
Additionally, the COVID-19 pandemic demonstrated the significant threat pandemics pose to national security. In order to combat future pandemics, the Defense Threat Reduction Agency (DTRA) supports a research institute consortium led by Los Alamos National Laboratory in the development of the RAPTER tool. Unlike the efforts of PNNL and HMS, Los Alamos scientists collect and organize raw experimental data on viruses and vaccines, using AI to identify patterns that form a profile for each vaccine candidate. Once the initial computational tools are complete, these research institutes will collaborate to experimentally validate their results, and verify the computational outcomes for the mRNA platform, the same platform used in the SARS-CoV-2 vaccine. By pooling their efforts, scientists aim to create an automated pipeline that accelerates vaccine design.
The whytry.ai article you just read is a brief synopsis; the original article can be found here: Read the Full Article…
