ESCOTT Missense Mutational Effect Predictions for Entire Human Proteome
This dataset contains ESCOTT single point mutation predictions of about ~19000 human proteins. Description of the data and file structure Data of each human protein is in a folder named after its uniprotID. Inside uniprotID folder, there is a subfolder called results that contain all input and output. An example results folder for uniprotID A0A0B4J245 will contain the following files: Raw escott predictions (output file): A0A0B4J245_normPred_evolCombi_escott.txt Ranksorted (between 0-1) escott predictions in csv format (output file): A0A0B4J245_normPred_evolCombiTransposedRanksorted_escott.csv Colabfold MSA file (input file): aliA0A0B4J245.fasta Bzipped pdb file (input file): AF-A0A0B4J245-F1-model_v4.pdb.tar.bz2 JET2 file containing JET, PC and CV scores for each amino acid (output file) : A0A0B4J245_jet_escott.res Configuration file containing default parameters (output file): default.conf Log file (output file): escott.log
This page was built for dataset: ESCOTT Missense Mutational Effect Predictions for Entire Human Proteome