Knowledge about the function of a protein is essential for understanding its role in both normal healthy and pathological conditions. Various computational methods have been applied to the challenging problem of predicting protein functions from the protein sequence alone and a handful of these are currently available as web services. Previously, we created FFANEprot—a deep convolutional neural network trained on a dataset of 81,267 proteins and 1,169 Gene Ontology (GO) terms of the molecular function (MF) from the Swiss-Prot database. This AI model achieved training and test Matthews correlation coefficients (accuracies) of 0.52 (98.84%) and 0.49 (98.67%), respectively.
Results: Here we present the ProtFunAI web service consisting of a database of MF predictions of 20,405 reviewed human proteins and a prediction service that can predict the MF of any supplied protein sequence within roughly a minute. All predictions are made by FFANEprot. Our database interface also shows the MF of each protein from Uniprot (
www.uniprot.org) with convenient linkage to look up additional information through a single click.
Conclusion: ProtFunAI (
protfunai.nordlinglab.org) provide convenient lookup or high accuracy prediction of GO MF terms from sequence alone.
Keywords: Deep learning; Convolutional neural network; Artificial intelligence; Protein function; Database; Web service