DiGePred is a Random Forest algorithm which predicts the potential for any pair of genes to cause digenic disease in an individual, when carrying variants simultaneously. The scores for all human gene pairs are calculated.

Please find our manuscript here:
https://www.cell.com/ajhg/fulltext/S0002-9297(21)00318-9
https://pubmed.ncbi.nlm.nih.gov/34529933/

The DiGePred scores on all human gene pairs, for all models used for training, are available using the links below.
https://vanderbilt.box.com/s/n1nzdyj8i5fa55vultyq4xn6rsp792a7
https://vanderbilt.box.com/s/459ethsqv339nqiarhm0j227jdjb0whq
https://vanderbilt.box.com/s/acdqvjuihj3932c6msi5py82rvr5kam3
https://vanderbilt.box.com/s/kb3vzubfxjcjtxt8x0y1vytu59x8r8no

Please refer to the readme file for additional details regarding the method, model and input and output files and formats.

Please use HGNC gene symbols

input type: gene

Predicts digenic potential for all possible gene pairs from list of input genes

example:
TNF
MYH7
TTN
IL6

input type: pair

Predicts digenic potential for user input gene pairs

example:
TP53,TNF
EGFR,JAG1
MYH7,TTN
APOE,IL6

* please add newline after last entry

Note: log.txt is for debugging purposes only.

The data and code used to train and evaluate DiGePred and other models considered are available at https://github.com/CapraLab/DiGePred.git.

Files are limited to 4MB in size; if you are a Meiler-Lab member, please login to upload files up to 16MB