Dorado

Dorado is a high-performance, easy-to-use, open source basecaller for Oxford Nanopore reads.

Features

One executable with sensible defaults, automatic hardware detection and configuration.
Runs on Apple silicon (M1/2 family) and Nvidia GPUs including multi-GPU with linear scaling.
Modified basecalling.
Duplex basecalling.
Support for aligned read output in SAM/BAM.
POD5 support for highest basecalling performance.
Based on libtorch, the C++ API for pytorch.
Multiple custom optimisations in CUDA and Metal for maximising inference performance.

If you encounter any problems building or running Dorado please report an issue.

Installation

Platforms

Dorado is heavily-optimised for Nvidia A100 and H100 GPUs and will deliver maximal performance on systems with these GPUs.

Dorado has been tested extensively and supported on the following systems:

Platform	GPU/CPU
Windows	(G)V100, A100, H100
Apple	M1, M1 Pro, M1 Max, M1 Ultra
Linux	(G)V100, A100, H100

Systems not listed above but which have Nvidia GPUs with >=8GB VRAM and architecture from Volta onwards have not been widely tested but are expected to work. If you encounter problems with running on your system please report an issue

Roadmap

Dorado is Oxford Nanopore's recommended basecaller for offline basecalling. We are working on a number of features which we expect to release soon:

DNA Barcode multiplexing
Adapter trimming
Python API
Statically linked binary

Performance tips

For optimal performance Dorado requires POD5 file input. Please convert your Fast5 files before basecalling.
Dorado will automatically detect your GPUs' free memory and select an appropriate batch size.
Dorado will automatically run in multi-GPU cuda:all mode. If you have a hetrogenous collection of GPUs select the faster GPUs using the --device flag (e.g --device cuda:0,2). Not doing this will have a detrimental impact on performance.

Running

Simplex basecalling

To run Dorado basecalling, download a model and point it to POD5 files (Fast5 files are supported but will not be as performant).

$ dorado download --model [email protected]
$ dorado basecaller [email protected] pod5s/ > calls.bam

Modified basecalling

To call modifications simply add --modified-bases to the basecaller command

$ dorado basecaller [email protected] pod5s/ --modified-bases 5mCG_5hmCG > calls.bam

Duplex

To run Duplex basecalling run the command:

$ dorado duplex [email protected] pod5s/ > duplex.bam

This command will output both simplex and duplex reads. Duplex reads will have the dx tag set to 1 in the output BAM, simplex reads will have the dx tag set to 0.

Dorado duplex previously required a separate tool to perform duplex pair detection and read splitting, but this is now integrated into Dorado.

Alignment

Dorado supports aligning existing basecalls or producing aligned output directly.

To align existing basecalls run:

$ dorado aligner <index> <reads>

where index is a reference to align to in (fastq/fasta/mmi) format and reads is a file in any HTS format.

to basecall with alignment with duplex or simplex run with the --reference option:

$ dorado basecaller <model> <reads> --reference <index>

Alignment uses minimap2 and by default uses the map-ont preset. This can be overridden with the -k and -w options to set kmer and window size respectively.

Available basecalling models

To download all available dorado models run:

$ dorado download --model all

Simplex models:

v4.1.0 models are recommended for our latest released condition (4kHz).

The following simplex models are also available:

RNA models:

rna003_120bps_sup@v3

Modified base models

[email protected]_5mCG@v0
[email protected]_5mCG@v0
[email protected]_5mCG@v0
[email protected]_5mCG@v2
[email protected]_5mCG@v2
[email protected]_5mCG@v2
[email protected]_5mCG@v2
[email protected]_5mCG@v2
[email protected]_5mCG@v2
[email protected]_5mCG_5hmCG@v2
[email protected]_5mCG_5hmCG@v2
[email protected]_5mCG_5hmCG@v2
[email protected]_5mCG_5hmCG@v2
[email protected]_5mCG_5hmCG@v2
[email protected]_5mCG_5hmCG@v2
[email protected]_5mCG_5hmCG@v2
[email protected]_5mCG_5hmCG@v2
[email protected]_5mCG_5hmCG@v2
[email protected]_5mCG_5hmCG@v2
[email protected]_5mCG_5hmCG@v2
[email protected]_5mCG_5hmCG@v2
[email protected]_5mCG_5hmCG@v2 (5kHz)
[email protected]_5mCG_5hmCG@v2 (5kHz)
[email protected]_5mCG_5hmCG@v2 (5kHz)
[email protected]_5mC@v2 (5kHz)
[email protected]_6mA@v2 (5kHz)

Developer quickstart

Linux dependencies

The following packages are necessary to build dorado in a barebones environment (e.g. the official ubuntu:jammy docker image)

$ apt-get update && apt-get install -y --no-install-recommends \
        curl \
        git \
        ca-certificates \
        build-essential \
        nvidia-cuda-toolkit \
        libhdf5-dev \
        libssl-dev \
        libzstd-dev \
        cmake \
        autoconf \
        automake

Clone and build

$ git clone https://github.com/nanoporetech/dorado.git dorado
$ cd dorado
$ cmake -S . -B cmake-build
$ cmake --build cmake-build --config Release -j
$ ctest --test-dir cmake-build

The -j flag will use all available threads to build dorado and usage is around 1-2GB per thread. If you are constrained by the amount of available memory on your system you can lower the number of threads i.e. -j 4.

After building you can run dorado from the build directory ./cmake-build/bin/dorado or install it somewhere else on your system i.e. /opt (note: you will need the relevant permissions for the target installation directory).

$ cmake --install cmake-build --prefix /opt

Pre commit

The project uses pre-commit to ensure code is consistently formatted, you can set this up using pip:

$ pip install pre-commit
$ pre-commit install

Licence and Copyright

Dorado is distributed under the terms of the Oxford Nanopore Technologies PLC. Public License, v. 1.0. If a copy of the License was not distributed with this file, You can obtain one at http://nanoporetech.com

mjfos2r / ont-dorado Goto Github PK

ont-dorado's Introduction