SVM-Prot 2016: a web-server for machine learning prediction of protein functional families from sequence irrespective of similarity

Predicting protein function is critical for biological and medical research. Our SVM-Prot web-server uses a machine learning approach to predict protein functional families from sequences, which is particularly useful for distantly-related proteins or homologous proteins with different functions. Since its initial release, we have made significant improvements, including: expanding coverage from 54 to 192 functional families, incorporating more diverse protein descriptors, improving predictive performance, and adding BLAST analysis and batch submission options. The server now also includes K-nearest neighbor and probabilistic neural network methods to facilitate a collective assessment of protein function.

Recommended citation: Li, Y. H., Xu, J. Y., Tao, L., Li, X. F., Li, S., Zeng, X., Chen, S. Y., Zhang, P., Qin, C., Zhang, C., Chen, Z., Zhu, F., & Chen, Y. Z. (2016). "SVM-Prot 2016: a web-server for machine learning prediction of protein functional families from sequence irrespective of similarity." PLoS ONE. 11(8):e0155290.
Download Paper