On the necessity to include multiple types of evidence when predicting molecular function of proteins

Machine learning-based platforms are currently revolutionizing many fields of molecular biology including structure prediction for monomers or complexes, predicting the consequences of mutations, or predicting the functions of proteins. However, these platforms use training sets based on currently available knowledge and, in essence, are not built to discover novelty. Hence, claims of discovering novel functions for protein families using artificial intelligence should be carefully dissected, as the dangers of overpredictions are real as we show in a detailed analysis of the prediction made by Kim et al 1 on the function of the YciO protein in the model organism Escherichia coli.