Vasor is a machine-learning based classification tool to predict the effect of single-site amino acid substitutions of MDR3 into the categories benign or pathogenic. Vasor was trained on an MDR3-specific dataset of known benign and pathogenic variants. Based on input from general protein predictors and other features (such as half-sphere exposure, post-translational modification (PTM) site influence, and secondary structure disruption), Vasor computes a probability of pathogenicity for a given single amino acid substitution within the MDR3 protein.
Vasor contains the precomputed results for every possible amino acid substitution within the MDR3 protein. The result for any possible substitution is a probability value, which can range from 0 to 1. This probability indicates the probability of pathogenicity, i.e. a higher value closer to 1 means a higher probability for the given substitution to be pathogenic. Vasor classifies variants with a probability of pathogenicity higher than 0.5 as pathogenic, while probability values lower than 0.5 are classified as benign.
One letter-code for the reference sequence amino acid, amino acid position, one letter-code for the substitution amino acid. The position refers to the longest isoform of MDR3, as depicted in the reference sequence P21439-1.
Vasor, as a prediction tool, cannot solely guide clinical and healthcare decision. Please refer to the AMCG-AMP guidelines for the usage of computational predictive programs. Vasor does not provide information about why a given variant might be benign or pathogenic.
If you have any questions or feedback, contact Behrendt@hhu.de.
If you want to contribute to Vasor by adding novel variants with a known and proven effect (benign or pathogenic), please get in contact!
Behrendt, A., Golchin, P., König, F., Mulnaes, D., Stalke, A., Dröge, C., Keitel, V., Gohlke, H.
Vasor: Accurate prediction of variant effects for amino acid substitutions in MDR3.
Hepatol. Commun., 2022, 6, 3098-3111.
This Server uses the NGL Viewer for visualization.
Rose, A. S., Bradley, A. R., Valasatava, Y., Duarte, J. M., Prlić, A., & Rose, P. W. (2016, July).
Web-based molecular graphics for large complexes.
In Proceedings of the 21st international conference on Web3D technology (pp. 185-186). ACM.
Rose, A. S., & Hildebrand, P. W. (2015). NGL Viewer: a web application for molecular visualization.
Nucleic acids research, 43(W1), W576-W579.