Researchers at India's International Institute of Information Technology Bangalore (IIIT Bangalore) have designed a deep learning method to help develop personalized cancer vaccines by better understanding the biological mechanisms of interaction between cancer cells and the human immune system.
The MHCAttnNet deep learning model uses bidirectional long short-term memories to predict Major Histocompatibility Complex allele (MHC)-peptide binding with greater accuracy than current methods.
The model also employs natural language processing to emphasize key subsequences from the amino-acid sequences of peptides and MHC alleles used to generate the prediction.
Shrisha Rao of IIIT Bangalore said the work was “an illustration of how artificial intelligence and machine learning research using cloud-based solutions can make a mark in different domains including medicine, in a much shorter time and at a fraction of the usual cost.”
View Full Article
Abstracts Copyright © 2020 SmithBucklin, Washington, DC, USA
No entries found