DeepPFP-CO webserver

Knowledge of protein functions plays an important role in biology and medicine. With the rapid development of highthroughput technologies, a huge number of proteins have been discovered. However, there are a great number of proteins without functional annotations. To reduce this huge gap, We propose a new deep learning model, named DeepPFP-CO, which uses Graph Convolutional Network (GCN) to explore and capture the co-occurrence of GO terms to improve the prediction performance. Experimental results show that DeepPFP-CO has good performance on protein function prediction.

Please follow the three steps below to make predictions:

1. Upload a file with protein sequences, or paste them into text area

Server accepts up to 50(FASTA formated) protein sequences at a time.

Choose a fileNo file chosen

2. Parameter setting

Release version (see changelog)

Version 1 Version 2

Please provide your email address to be notified when results are ready(optional).

3. Predict:

Click button to launch prediction.

Help

Server accepts up to 50 protein sequences at a time. The user should submit the protein sequence(s) in FASTA format.

The format of the input file is as follows (Here is an example of input file.)

Line1: >Entry
Line2: protein sequence (1-letter amino acid encoding)

Each protein requires two lines and multiple proteins should be placed in consecutive lines.

Changelog

Version 2

The current version release is 2. The model in the current release was trained using the Gene Ontology and the SwissProt data both released on 2021-01.

Version 1

The current version release is 1. The model in the current release was trained using the Gene Ontology and the SwissProt data both released on 2016-01.

References

Zhang F, Song H, Zeng M, et al. A deep learning framework for gene ontology annotation with sequence-and network-based information [J]. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2020.
Zhang F, Song H, Zeng M, et al. DeepFunc: a deep learning framework for accurate prediction of protein functions from protein sequences and interactions [J]. Proteomics, 2019, 19(12): 1900019.

Contact

DeepPFP-CO webserver is developed on a stable and flexible framework, which is easy to extend. If you have any questions or suggestions feel free to contact us. We look forward to hearing from you!

Telephone: +86-0731-88879560
Email: limin@mail.csu.edu.cn