On March 11, 2020, the World Health Organization declared the outbreak of COVID-19 a pandemic. Cases outside China had increased 13-fold and the virus spread rapidly.
Those first six months of the pandemic were challenging, he says Sam Scarpinodirector of AI+Life Sciences at the Institute for Experiential AI at Northeastern, because we didn't have great options for treating the disease.
By January of that year, scientists had identified the key spike protein of SARS-CoV-2, the virus that causes COVID-19, but antibody treatments for the disease were still a long way off. Just months later, scientists were able to extract antibodies from patients who had recovered from COVID-19 for the development of appropriate therapeutic methodsexplains Scarpino.
AI tools used for medical research could cut that time in half, he says.
“With artificial intelligence in the loop, we could have antibodies ready within three months of identifying the target, meaning we would have therapeutic or even potentially transmission-blocking antibodies ready in time for that first wave in Boston,” says. “This could have saved lives, kept schools open, protected healthcare workers, etc.”
At Northeastern, Scarpino is working closely with researchers in various fields across the university to use artificial intelligence tools to help accelerate the development of these kinds of treatments to prepare for future pandemics and other medical conditions.
The manufacture, Scarpino will host a webinar with Giulia Menichiettifaculty member of the Network Science Institute at Northeastern University, to talk about this project.
In medicine, AI tools are being used to help develop new drugs and medical treatments at the most fundamental part of the process, Scarpino says. Artificial intelligence is used to synthesize and analyze the chemical compounds used to make drugs, to derive the efficacy and safety of these compounds, to design clinical trials, and to identify patient populations that could benefit from these compounds. medicines.
“We have work in all these spaces at Northeastern, so my role as director of artificial intelligence and life sciences is to bring together faculty, researchers, undergraduates, Ph.D. students and graduate students to focus broadly on artificial intelligence and drug discovery.”
Scarpino is particularly invested in developing the design of antibody therapies using machine learning models.
Working with the university's network of researchers working in wet and dry labs, he hopes to use their data to train artificial intelligence models to help develop drugs to treat rare and unusual diseases.
As examples, he points to research being conducted by Northeastern chemistry professors Mike Pollastri and Lori Ferrins, who are working on drugs to treat neglected tropical diseases.
“They focus on pathogens like Trypanosoma cruzi (causes Chagas disease), malaria and leishmaniasis. One of our goals at EAI, and in particular the branch of life sciences research that I coordinate, is to identify expertise within NU that can have a global impact,” says Scarpino.
The models the university is working on will be trained on small curated data sets, Scarpino says. If you do not rely on large volumes of data, there will be less cost and development time. The institute will also leverage the expertise of Northeastern's Network Science Institute, which takes an interdisciplinary approach to understanding network systems in the technological, biological and informational domains.
“Instead of solving the problem by collecting ever larger datasets, which is partly what groups like OpenAI have done with GPT 4. We're trying to do this with intelligent datasets that are carefully curated and designed,” he says. “That's something we can do at a university uniquely well, working with researchers who have that wet lab experience and then bringing in AI models that can make the most of small data set techniques from network science.”
