Protein function prediction has seen significant advancements over the last decade, coinciding with the rise of new machine learning and artificial intelligence computational methods. In this article, we speak with Iddo Friedberg, Ph.D., an expert in protein function prediction and the co-organizer of the Critical Assessment of Function Annotation (CAFA) experiment, about how accurately models are predicting protein function and where he believes the field is headed next.
CAS: How did you initially become interested in protein function prediction?
CAS: How has the field of automated protein function prediction evolved since you started?
CAS: Are some approaches to protein function prediction working better than others?
CAS: As molecular function predictions are improving, how well are we able to predict biological processes and cellular components?
CAS: What would you say are the main bottlenecks in the field?
CAS: One of the main bottlenecks is not computational at all then, but what wet lab work is being done and published?
CAS: Do you think that recent advances in natural language processing models (NLPs) can be used for biocuration?
CAS: What do you think the big opportunities are in protein function prediction right now?
CAS: If you had a magic wand to change anything in the drug discovery process, what would you change?
Iddo Friedberg, Ph.D., is an Associate Professor at Iowa State University, College of Veterinary Medicine. With a Ph.D. in Bioinformatics, Iddo has carved his career in computational metagenomics and protein function prediction. His research aims to make use of the vast quantity of omics data available to predict protein and gene function, and he works to bring like-minded scientists together to discuss automated protein function prediction. As a co-organizer of the Critical Assessment of Function Annotation (CAFA), an experiment designed to provide a large-scale assessment of computational methods dedicated to predicting protein function, Iddo is at the cutting edge of the future of protein function prediction.