Predictions of QAFI

QAFI predictions for all possible amino acid substitutions at all possible residue locations across a set of 3,460 proteins, encompassing a total of 45,165,679 variants. This dataset covers the majority of the Clinical Genome, defined as those proteins with at least one pathogenic variant listed in ClinVar.

Disclaimer: This prediction dataset is uniquely intended for research purposes. The authors are not responsible for neither its use nor misuse. The data provided are not intended as advice of any kind. The authors have worked with care in the development of this dataset, but assume no liability or responsibility for any error, weakness, incompleteness or temporariness of the data provided.

Note. The dataset published here corresponds to the work presented in our article, entitled  QAFI: A Novel Method for Quantitative Estimation of Missense Variant Impact Using Protein-Specific Predictors and Ensemble Learning, which is submitted for publication.