VariantSpark

VariantSpark copied to clipboard

VariantSpark Hail Interface

1

When using VariantSpark interface for Hail to run important analysis, VariantSpark expect to have exactly one allele in REF and ALT field. If there was any issue (some dataset have...

ArashBayatDev

Built-in support for FDR (False Discovery Rate) calculation

1

An option to request calculation for FDR (False Discovery Rate) for importance on permutated labels. (It should be possible to build the permutated forests in parallel)

piotrszul

Create an automated way to spin up a Spark cluster on AWS with VariantSpark installed so researchers can get started easily. This extends the work done by Lynn Langit as...

BauerLab

Output trees in JSON format

1

Implement a readable output e.g. JSON for the trained trees. This will help evaluate the resulting interactions and visualise them.

BauerLab

scala randomForest classifier

1

Hi, I just started to try out VariantSpark with Scala using its featureImportance function on my own vcf file. Which worked perfectly as I followed the example code from the...

fifdick

Add support for continuous variables

1

Add support for continuous variables for trees.

piotrszul

Generate importances for random permutations of labels

10

Add functionality to generate variable importances for a selected number of random permutations of labels. Output variable variable importance for each permutation.

piotrszul

piotrszul

Could VariantSpark be used for multiple labels, instead of just binary? Thanks

rajputakhil

Add functionality to simulate sequencing errors to a phase and unphased genotypes (vcf files). Types of errors and other parameters to be defined.

piotrszul