A production-ready suite of tools for single-sample variant filtration

After training on a massive amount of data, the neural network models at the heart of CNNvariant have learned enough to be released from beta.

This suite of tools for single-sample variant filtration uses machine learning to differentiate between good variants and artifacts of the sequencing process, a fairly new approach that is especially effective at correctly calling indels. To enable the models to accurately filter and score variants from VCF files, we trained on validated VCFs (from truth models including SynDip, Genomes in a bottle, and Platinum Genomes) with unvalidated VCFs aligned to different reference builds (HG19, HG38), sequenced on different machines, using different protocols. The result is a single-sample tool that complements, rather than replaces, VQSR (our "traditional" cohort based variant filtering algorithm).

What’s in the CNN toolbox? Pre-trained and train-your-own CNNScoreVariant is a pre-trained Convolutional Neural Network ready to score variants. After scoring, you can filter your VCF by applying a sensitivity threshold with the tool FilterVariantTranches. Or you can train your own models with the tools CNNVariantWriteTensors and CNNVariantTrain, as long as you have validated VCFs to use as training data.

While the current release is only recommended for single sample variant filtration, in the future we hope to explore ways a similar model could be applied to joint-called VCFs.

Under the hood For details on how our deep learning tool works and how it stacks up to other variant filtering tools (both Deep Learning and traditional), as well as a bit of history on Deep Learning in genomics, see our other blog post.

Weichi on 12 Feb 2019

It's great to hear that! Thanks! Just remind you there is an error on [CNNScoreVariants documentation ](https://software.broadinstitute.org/gatk/documentation/tooldocs/current/org_broadinstitute_hellbender_tools_walkers_vqsr_CNNScoreVariants.php "CNNScoreVariants documentation "). The value in -tensor-type should be _read_tensor_ not _read-tensor_. Because I got the below error: >! A USER ERROR has occurred: Argument tensor-type has a bad value: read-tensor. 'read-tensor' is not a valid value for TensorType. Possible values: { >! reference ( 1 Hot encoding of a reference sequence. ) >! read_tensor (Read tensor are 3D tensors spanning aligned reads, sites and channels. The maximum number of reads is a hyper-parameter typically set to 128. There are 15 channels in the read tensor. They correspond to the reference sequence data (4), read sequence data (4), insertions and deletions (2) read flags (4) and mapping quality (1).) >! } Regards Weichi

- Recent posts

- Upcoming events

See Events calendar for full list and dates

- Recent events

See Events calendar for full list and dates

- Follow us on Twitter

GATK Dev Team


Getting expert help developing new #GATK workshop materials— priceless https://t.co/y3NHDnptiI
16 Mar 19
RT @RyanLCollins13: It's been years in the making, but 500k structural variants (SVs) from 15k genomes in #gnomAD are out 🎉today🎉! Preprin…
16 Mar 19
@liuym5 If you experience a technical issue please report your problem in our support forum at https://t.co/aoQ0eBmExP
10 Mar 19
@liuym5 @kaptenkvast We are working with several cloud providers including @awscloud and @alibaba_cloud to expand accessibility
10 Mar 19
@liuym5 @kaptenkvast You can download them from the cloud bundle, see the bundle docs
10 Mar 19

- Our favorite tweets from others

Working #bioinformatics https://t.co/KLyjJYpBaz
16 Mar 19
Best part of all: gnomAD SVs are completely #OpenAccess, with literally *no restrictions* on use:… https://t.co/tEEBtMcxjL
15 Mar 19
very excited to announce that GATK did not run out of memory overnight
14 Mar 19
if structural variants are so important why are they not snps
11 Mar 19
@nilshomer @fdmts @notSoJunkDNA Get in the Queue
8 Mar 19

See more of our favorite tweets...