The tool, called ProtFus, was recently presented by Somnath Tagore the study's lead author and a previous postdoctoral researcher at the lab of Dr. Milana Frenkel-Morgenstern, head of the Cancer Genomics and BioComputing of Complex Diseases Lab at the Azrieli Faculty of Medicine. According to the spokesperson, the tool screens scientific literature to validate prediction about the activity of fusion proteins, which are encoded by the joining of two genes that previously encoded two separate proteins, the office said.
According to the press release, different kinds of fusion proteins can appear in the human body, sometimes leading to the development of cancer. By learning the interactions between fusion proteins and other proteins, researchers may improve personalized cancer treatment.
Using machine learning and text mining, ProtFus analyzes scientific literature from PubMed, an online search engine. ProtFus is able to identify fusion proteins that go by different names, making it easier for researchers to find the relevant literature.
"Our findings demonstrate the potential for text-mining of large-scale scientific articles using a novel big-data infrastructure, with real-time updating from articles published daily," said Frenkel-Mongenstern, the corresponding author of the study.
According to Tagore, "ProtFus can promote studying alterations of protein networks for individual cancer patients in a fully personalized manner."