PON-mt-tRNA

PON-mt-tRNA is a posterior probability-based method for classification of mitochondrial tRNA variations. It integrates machine learning-based probability of pathogenicity and evidence-based likelihood of pathogenicity to predict the posterior probability of pathogenicity. In absence of evidence, it classifies the variations based on the machine learning-based probability of pathogenicity. It is trained and tested on variants classified as definitely pathogenic and definitely neutral by Yarham et al..
A manuscript describing PON-mt-tRNA has been published in Nucleic Acids Research.

'
Home About Disclaimer Datasets

Datasets used in PON-mt-tRNA manuscript

A manuscript describing PON-mt-tRNA has been submitted for publication. The datasets described in the manuscript are available for download.


Feature matrix for training and test data
This file contains the feature matrix used for developing PON-mt-tRNA. It contains 91 pathogenic and 55 neutral variations. 40 pathogenic and 40 neutral variations were selected by random sampling without replacement for training and the remaining variations were used for testing the method.
Download: PON-mt-tRNA feature matrix


Additional variation dataset
This file contains predictions of PON-mt-tRNA for additional variants obtained from MITOMAP, mtDB and mtSNP databases. The variations that were present in the PON-mt-tRNA training and test dataset were excluded from this dataset.
Download: Classification of additional mt-tRNA variations using PON-mt-tRNA

PON-mt-tRNA predictions for all possible single nucleotide subsitutions in human mt-tRNA
This file contains predictions of PON-mt-tRNA for all possible single nucleotide substitutions at each position in the 22 human mt-tRNA. The classification is based on ML predicted probability of pathogenicity.
Download: PON-mt-tRNA predictions for all possible variations