“There's a wonderful opportunity for computational biologists and people with computer science backgrounds to have an impact on experimental immunology."
Emily Miraldi, PhD, of Cincinnati Children’s Hospital, believes that rapid developments in immunology have created new opportunities for collaboration, and have opened the door for machine learning to help inform experiments.
“I think there's been a lot more emphasis on team science,” she said, speaking to Healthcare Analytics News™ at IDWeek this October in San Diego.
Advances in proteomics and animal modelling, for example, open new doors for immunologists to explore disease predispositions and outcomes. They also result in large amounts of data.
“Experimental immunology takes incredible training, and it's hard to expect that someone who is able to do very intricate experiments…is also going to know what to do with a high dimensional data set.”
Also, according to Miraldi, machine learning can help experimental immunologists derive more relatable information from those animal models. While they might not be able to do experiments on a human intestine, applying a multitask learning approach to a mouse intestine can allow them to reverse engineer how a human organ may respond a disease.
“There's a wonderful opportunity for computational biologists and people with computer science backgrounds to have an impact on experimental immunology,” Miraldi said.