What is the theory behind MemDis?
MemDis uses machine learning to predict disordered segments in membrane proteins. We used x-ray crystallography data to train convolutional neural networks and a bidirection long short term memory network. In addition to physico-chemical properties often incorporated in disorder prediction tools, we used features specific to membrane proteins, such as topology. You can find more information in the Description menu and in the manuscript.
Publication
How can I cite MemDis?
Please cite Laszlo Dobson and Gábor Tusnády MEMDIS: Predicting disordered regions in transmembrane proteins Int. J. Mol. Sci. 2021, 22(22), 12270
Server usage
What is MemDis?
MemDis is a novel prediction method, utilizing convolutional neural network and long short-term memory networks for predicting disordered regions in TMPs. MemDis achieved the highest prediction accuracy on TMP specific dataset among other popular IDR prediction methods.
In what format can sequences be submitted to MemDis?
Sequences can be submitted with one letter amino acid format in FASTA format. Optionally, sequences can be uploaded in FASTA formatted file.
All: #jobs: 2145 (21036 seqs) .:|:.
Last week: #jobs: 0 (0 seqs) .:|:.
Current load: #jobs 0 (0 seqs)