FATHMM-XF: accurate prediction of pathogenic point mutations via extended features.
Rogers MF, Shihab HA, Mort M, Cooper DN, Gaunt TR, Campbell C. · 2018
Read FATHMM-XF: accurate prediction of pathogenic point mutations via extended features. by Rogers MF, Shihab HA, Mort M, Cooper DN, Gaunt TR, Campbell C. (2018) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/europmc-pmc5860356.txt.
Description
Rogers and co-authors present FATHMM-XF, a method for judging point mutations. Their article appeared in Bioinformatics. The method predicts which single-letter DNA changes may cause disease. It draws on a wide set of features from genome databases. Training data came from a human mutation database and the 1000 Genomes Project. The method covers both coding and non-coding parts of the genome.
The authors report that it beats rival tools on benchmark tests. Gains were largest in non-coding regions, where most harmful changes may sit. Each prediction carries a confidence score for the user. Careful use of top scores pushed accuracy above 94 percent. A web server and genome browser tracks are provided. Predictions use the GRCh37 human genome build.
Catalog record
| CREATOR | Rogers MF, Shihab HA, Mort M, Cooper DN, Gaunt TR, Campbell C. |
|---|---|
| YEAR | 2018 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 13 KB |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |