Usage:

1. Input a protein sequence with a fasta format.

2. Input your email to receive the predicted result.

Note:

(1) Please submit one sequence each time, with sequence length ranging from 20 to 3000 amino acids.

(2) Sequences with abnormal amino acid are not allowed.

(3) The results include four variables: identified class, as well as predicted probabilities for the three categories: p_llps, p_fiber and p_background, respectively.

(4) This web server is freely accessible to academic users. If you need to run it on your local computer, the source codes can be download click here

(5) For any question about using the model, please contact: biocomp-llpsdb@ucas.ac.cn.

Visits:

Citation:

Liao S, Zhang Y, Han X, Wang T, Wang X, Yan Q, et al. A sequence-based model for identifying proteins undergoing liquid–liquid phase separation/forming fibril aggregates via machine learning. Protein Science. 2024; 33(3):e4927. https://doi.org/10.1002/pro.4927