MutaFrame

***You can refer to ...... text book for more info on amino acid biochemistry

DEOGEN2 is an amino acid sequence-based variant effect predictor which improves the DEOGEN1. It aims at the multi-level contextualization of the variant residue and protein by integrating information related to molecular, domain, gene and pathway aspects. These heterogeneous sources of information are then encoded and fed to a random forest algorithm, from which the deleterious predictions are obtained More Info
REFERENCE DEOGEN1: Raimondi D, Gazzo AM, Rooman M, Lenaerts T, Vranken WF. Multilevel biological characterization of exomic variants at the protein level significantly improves the identification of their deleterious effects. Bioinformatics. 2016 Jun 15;32(12):1797-804.
REFERENCE DEOGEN2: Raimondi D, Tanyalcin I, Ferté J, Gazzo A, Orlando G, Lenaerts T, Rooman M, Vranken W. DEOGEN2: prediction and interactive visualization of single amino acid variant deleteriousness in human proteins. Nucleic Acids Res. 2017 Jul 3;45(W1):W201-W206.

DynaMine is a fast predictor of protein backbone dynamics using only sequence information as input.
REFERENCE: Elisa Cilia, Rita Pancsa, Peter Tompa, Tom Lenaerts, and Wim Vranken. From protein sequence to dynamics and disorder with DynaMine. Nature Communications 4:2741 doi: 10.1038/ncomms3741 (2013)

SNPMuSiC is a protein structure-based variant effect classifier that uses solvent accessibility-dependent combinations of statistical potentials, evolutionary amino acid conservation and artificial neural networks to predict whether variants are deleterious or neutral. SNPMuSiC has the advantage to predict with high accuracy variants that are deleterious for stability reasons, but miss variants that are deleterious for other reasons.
REFERENCE: Ancien F, Pucci F, Godfroid M, Rooman M. Prediction and interpretation of deleterious coding variants in terms of protein structural stability. Sci Rep. 2018 Mar 14;8(1):4480.