DAMpred is a method to predict what gene mutations can cause human diseases
and what mutations do not do so.
Starting with a protein sequence and specified
non-synonymous single nucleotide polymorphisms (nsSNPs), DAMpred
calculates the probability of the mutations to be deleterious or neutral
to human health. The calculation is built on a deep-learning model that
integrates three sources of information from
sequence profiles, biological assembly and 3D structure model
(by
I-TASSER),
which is trained through
a novel Bayes-guided artificial neural network (BANN) algorithm
(>>
more about DAMpred ...).
DAMpred On-line (View an example of output)
DAMpred Downloads
References
-
Lijun Quan, Hongjie Wu, Qiang Lyu, Yang Zhang.
DAMpred: Recognizing disease-associated nsSNPs through Bayes-guided neural-network model built on low-resolution structure prediction of proteins and protein-protein interactions.
J Mol Biol, in press (2019).