PIPENN — Protein Interface Prediction from sequence with an Ensemble of Neural Nets

The recent major upgrade on our compute server, has lead to some configuration issues that turn out to be very hard to resolve. We are still working on this, and hope to have the server back online in the course of August. We apologise again for the inconvenience, and thank you for your continued patience.

The PIPENN server offers a simple interface to our ensemble-neural-net based methods for predicting protein-protein (PPI), epitope, protein-nucleic acids, or protein-small molecule interaction positions from a single input sequence (Stringer et al., 2022). You can input your sequence of interest, and obtain a table of predicted interface positions. Please note that runtimes are typically short, up to 15 minutes in the worst case. Depending on server load, you may be experiencing some queue waiting times as well. If you need more performance, or otherwise want more flexibility, you may instead rather get your own installation from the download page.	Paste in your input sequence:   or  upload your alignment: select PIPENN model trained on protein nucleic acids small molecule all dataset.
Please cite: Bas Stringer*, Hans de Ferrante, Sanne Abeln, Jaap Heringa, K. Anton Feenstra and Reza Haydarlou*. PIPENN: Protein Interface Prediction from sequence with an Ensemble of Neural Nets. Bioinformatics 38, 2111-2118, 2022. External prediction methods used: NetSurfP-2.0: Improved prediction of protein structural features by integrated deep learning. Klausen, M. S., Jespersen, M. C., Nielsen, H., Jensen, K. K., Jurtz, V. I., Sønderby, C. K., Sommer, M. O. A., Winther, O., Nielsen, M., Petersen, B., & Marcatili, P. (2019). Proteins: Structure, Function and Bioinformatics, 87(6), 520–527.
The PIPENN web server developed and Copyright (c) by K. Anton Feenstra and Reza Haydarlou.