Developed for protein structures, ProTSPoM uses
a combination of Random Forest Regressors (RFR) and Gradient Boosted Regressors (GBR) along with residue properties,
fold level attributes, environmental compatibility, and evolutionary information to predict the change
in Gibbs free energy originating out of single point missense mutations. ProTSPoM outperforms all existing
state-of-the-art methods in both the Pearson correlation coefficient and root-mean-squared-error parameters
for the S2648, S350, S1925 and p53 databases (even if we do not include evolutionary information).
The ProTSPoM web service use the RFR and GBR models trained on the 2298 instances from the S2648 dataset
and tested on the most widely benchmarked S350 dataset to predict ΔΔG for new SPM instances.