/pepper

P.E.P.P.E.R.: Program for Evaluating Patterns in Pileups of Erroneous Reads

Primary LanguagePythonMIT LicenseMIT

P.E.P.P.E.R.

Build Status

PEPPER is a genome inference module based on recurrent neural networks that enables long-read variant calling and nanopore assembly polishing in the PEPPER-Margin-DeepVariant pipeline. This pipeline enables nanopore-based variant calling with DeepVariant.

PEPPER-Margin-DeepVariant Variant Calling Workflow

Methods and results

A detailed description of PEPPER-Margin-DeepVariant methods and results are discussed in the following manuscript:

bioRxiv: Haplotype-aware variant calling enables high accuracy in nanopore long-reads using deep neural networks. Authors: Kishwar Shafin, Trevor Pesout, Pi-Chuan Chang, Maria Nattestad, Alexey Kolesnikov, Sidharth Goel,
Gunjan Baid, Jordan M Eizenga, Karen H Miga, Paolo Carnevali, Miten Jain, Andrew Carroll, Benedict Paten.

Quickstart

Please follow the quickstart guides to assess your setup. Please follow case-study documentations for detailed instructions.

Case studies

The variant calling and assembly polishing pipelines can be run on Docker or Singularity. The case studies are designed on chr20 of HG002 sample.

Please pick the case-study of your pipeline of interest and the associated container runtime Docker or Singularity. The case-studies include input data and benchmarking of the run:

Pipeline Docker Singularity NVIDIA-docker
(GPU)
Nanopore
variant calling		 Link Link Link
PacBio HiFi
variant calling		 Link Link Link
Nanopore assembly polishing
with nanopore data		 Link Link Link
Nanopore assembly polishing
with PacBio HiFi data		 Link Link Link

Use PEPPER or Margin independently

  • If you want to run PEPPER or Margin independent of the pipeline, please follow this documentation.
  • If you want to install PEPPER locally for development, please follow this documentation

License

PEPPER license, Margin License and DeepVariant License extend to the trained models (PEPPER, Margin and DeepVariant) and container environment (Docker and Singularity).

Why use PEPPER-Margin-DeepVariant?

  • Accuracy: Our pipeline won the precisionFDA truth challenge v2 for all benchmarking region and difficult to map region in the Oxford Nanopore category.
  • Speed: PEPPER-Margin-DeepVariant provides a cheaper and faster solution to PacBio HiFi haplotype-aware variant calling.
  • Phased output: PEPPER-Margin-DeepVariant can produce high-quality phasing of variants without trio information with nanopore and PacBio HiFi reads.

Acknowledgement

We are thankful to the developers of these packages:

Authors

PEPPER-Margin-DeepVariant pipeline is developed in a collaboration between UC Santa Cruz genomics institute and the Genomics team in Google Health.

Fun Fact

guppy235

The name "P.E.P.P.E.R." is inspired from an A.I. created by Tony Stark in the Marvel Comics (Earth-616).

PEPPER is named after Tony Stark's then friend and the CEO of Resilient, Pepper Potts.