InterPro and Pfam: Protein domains and families for biomedical research

Molecular biology and by extension, the field of biomedical research have been revolutionised by our ability to read the genetic code. The string of ATGCs code for genes that in turn encode proteins, the essential molecular machines of life. Currently our ability to read the DNA of all species outstrips our capacity to understand the function of their encoded proteins considerably. Therefore, it is crucial to develop and apply existing and novel computational tools that facilitate transfer of functional information from characterised to uncharacterised proteins. InterPro, Pfam, and the HMMER web server are three resources that group similar protein sequences together, thereby allowing function to be attributed to previously uncharacterised proteins. In this project we will improve the scalability of these key resources and incorporate biomedically relevant data to enable Deep Learning artificial intelligence that will potentially revolutionise future developments.