Merge branch 'DOR-1440_v1.3.0-changelog' into 'master'

v1.3.0 changelog and readme updates

Closes DOR-1440

See merge request machine-learning/dorado!1768

Author: MarkBicknellONT

CHANGELOG.md

@@ -2,6 +2,28 @@
 
 All notable changes to Dorado will be documented in this file.
 
+# [1.3.0] (21 November 2025)
+
+This release of Dorado expands GPU compatibility with support for Nvidia DGX Spark* and Jetson Thor, and updates to Torch 2.9.0. Dorado 1.3.0 introduces an `--emit-summary` option in the basecaller and improved handling of modified base models, as well as several fixes to `summary`, `demux`, and `basecaller` and performance improvements to `polish` and `variant`.
+
+*Please note that in this release, Dorado `correct` is not yet compatible with DGX Spark. This will be addressed in a future release. 
+
+* 2f55740726ffbf20761a7780f212973e1bcc0934 - Add support for DGX Spark and Jetson Thor
+* bc4b95cf3c5907a9a81e8f825de6d319783e7d63 - Update Torch to 2.9.0 for CUDA 12 onwards
+* a65f9df4fc5dab4ea87de6a049e250d2ae9faf84 - Add `--emit-summary` option to Dorado `basecaller`
+* 47ccd2e00dec6c9e8365bd7db280351139b654f5 - Enable `--modified-bases-models` to use modified base model names in addition to paths; clean up .temp model directories
+* c91a872a705579ba8d1989afe7e9ce487cd5747d - Fix bug where Dorado `demux` with `--no-classify` fails to generate separate barcode files
+* 92758963942227353952d14aa67e85f43cc6bcf7 - Regenerate `RG` headers when running Dorado `demux` and fix `PG` header generation
+* a9d7d20cdf23bbe0bf8e5d81c3d18307ad3d4078 - Reinstate masking of modified base probabilities which fall below a minimum threshold of 5%
+* 13d47221985dbf38fd9f7b63f1983f5c4765148a - Ensure Dorado `summary` correctly calculates number of substitutions in the absence of an `MD` tag
+* 46be4fb19172e81f8c0e41a9a0d1500b49c80152 - Validate the input to Dorado `summary` and allow streaming input to match other commands
+* a52c1a0e255746f0b5a79cc68924aa1ef75649e0 - Fix bug causing `--chunksize` in Dorado `basecaller` to be set incorrectly when `--chunksize=10000` is passed at command line
+* 0c9f832d35c3d6613fe1039823293ce41e3866ef - Encoding parallelisation improvement for Dorado `polish` and `variant` from [pull request #1504](https://github.com/nanoporetech/dorado/pull/1504)
+* be473b1d2a4b80f59472c2a2e2b44f8a3cfc2b55 - Refactor local haplotagging in Dorado `variant`
+* 816bae64b1a5cf064194ec675fc1028c90424498 - Add RTX PRO 6000 Blackwell auto batch size benchmarks
+* 261a5b92892edc1fb1148b3e9bcd4eefc58edbd1 - Remove duplicated material from README.md and link to [Dorado Documentation](https://software-docs.nanoporetech.com/dorado/latest/)
+
+
 # [1.2.0] (21 October 2025)
 
 This release of Dorado delivers major improvements to short-read (<500 bp) basecalling speed with the HAC model, bringing performance in line with that for long reads. The Dorado basecaller now more closely follows the [Oxford Nanopore Output Specifications](https://nanoporetech.github.io/ont-output-specifications/latest/). CPU performance enhancements improve basecalling speed in cases where Dorado is not GPU-bound, such as on multi-GPU systems or when using faster models. The release also includes several other improvements and minor alignment-related bug fixes.

README.md

@@ -24,10 +24,11 @@ If you encounter any problems building or running Dorado, please [report an issu
 
 First, download the relevant installer for your platform:
 
-* [dorado-1.2.0-linux-x64](https://cdn.oxfordnanoportal.com/software/analysis/dorado-1.2.0-linux-x64.tar.gz)
-* [dorado-1.2.0-linux-arm64](https://cdn.oxfordnanoportal.com/software/analysis/dorado-1.2.0-linux-arm64.tar.gz)
-* [dorado-1.2.0-osx-arm64](https://cdn.oxfordnanoportal.com/software/analysis/dorado-1.2.0-osx-arm64.zip)
-* [dorado-1.2.0-win64](https://cdn.oxfordnanoportal.com/software/analysis/dorado-1.2.0-win64.zip)
+ - [dorado-1.3.0-linux-x64](https://cdn.oxfordnanoportal.com/software/analysis/dorado-1.3.0-linux-x64.tar.gz)
+ - [dorado-1.3.0-linux-arm64-cuda12 - Orin only](https://cdn.oxfordnanoportal.com/software/analysis/dorado-1.3.0-linux-arm64.tar.gz)
+ - [dorado-1.3.0-linux-arm64-cuda13 - Jetson Thor / DGX Spark](https://cdn.oxfordnanoportal.com/software/analysis/dorado-1.3.0-linux-arm64-cuda-13.0.tar.gz)
+ - [dorado-1.3.0-osx-arm64](https://cdn.oxfordnanoportal.com/software/analysis/dorado-1.3.0-osx-arm64.zip)
+ - [dorado-1.3.0-win64](https://cdn.oxfordnanoportal.com/software/analysis/dorado-1.3.0-win64.zip)
 
 Once the relevant `.tar.gz` or `.zip` archive is downloaded, extract the archive to your desired location.
 
@@ -56,10 +57,12 @@ Dorado has been tested extensively and supported on the following systems:
 | Platform | GPU/CPU | Minimum Software Requirements |
 | --- |---------|--------------|
 | Linux x86_64  | (G)V100, A100, H100 | CUDA Driver ≥525.105 |
-| Linux arm64 | Jetson Orin | Linux for Tegra ≥36.4.3 (JetPack ≥6.2) |
+| Linux arm64 | Jetson Orin, Jetson Thor, DGX Spark* | Linux for Tegra ≥36.4.3 (JetPack ≥6.2) |
 | Windows x86_64 | (G)V100, A100, H100 | CUDA Driver ≥529.19 |
 | Apple | Apple Silicon (M series) | macOS ≥14 |
 
+**DGX Spark supports all Dorado commands **except** Dorado `correct`. Support for Dorado `correct` will be added in a future release.*
+
 Linux x64 or Windows systems not listed above but which have Nvidia GPUs with ≥8 GB VRAM and architecture from Pascal onwards (except P100/GP100) have not been widely tested but are expected to work. When basecalling with Apple devices, we recommend systems with ≥16 GB of unified memory.
 
 If you encounter problems with running on your system, please [report an issue](https://github.com/nanoporetech/dorado/issues).
@@ -120,7 +123,7 @@ To run Duplex basecalling, run the command:
 dorado duplex sup pod5s/ > duplex.bam
 ```
 
-For more details please head to the the [dorado duplex basecalling documentation](https://software-docs.nanoporetech.com/dorado/latest/basecaller/duplex/).
+For more details please head to the [Dorado `duplex` basecalling documentation](https://software-docs.nanoporetech.com/dorado/latest/basecaller/duplex/).
 
 ### Alignment
 
@@ -140,19 +143,19 @@ To basecall with alignment with duplex or simplex, run with the `--reference` op
 dorado basecaller <model> <reads> --reference <index> > calls.bam
 ```
 
-For more details please check out the [dorado aligner documentation](https://software-docs.nanoporetech.com/dorado/latest/basecaller/alignment/).
+For more details please check out the [Dorado `aligner` documentation](https://software-docs.nanoporetech.com/dorado/latest/basecaller/alignment/).
 
 ### Sequencing Summary
 
-The `dorado summary` command outputs a tab-separated file with read level sequencing information from the BAM file generated during basecalling. To create a summary, run:
+The Dorado `summary` command outputs a tab-separated file with read level sequencing information from the BAM file generated during basecalling. To create a summary, run:
 
 ```bash
 dorado summary <bam> > summary.tsv
 ```
 
 ### Barcode Classification
 
-Dorado supports barcode classification for existing basecalls as well as producing classified basecalls directly. Further details can be found at the [dorado barcoding documentation](https://software-docs.nanoporetech.com/dorado/latest/barcoding/barcoding/).
+Dorado supports barcode classification for existing basecalls as well as producing classified basecalls directly. Further details can be found at the [Dorado `barcoding` documentation](https://software-docs.nanoporetech.com/dorado/latest/barcoding/barcoding/).
 
 ### Poly(A) tail estimation
 
@@ -162,13 +165,15 @@ Dorado has initial support for estimating poly(A) tail lengths for cDNA (PCS and
 
 Dorado supports single-read error correction with the integration of the [HERRO](https://github.com/lbcb-sci/herro) algorithm. HERRO uses all-vs-all alignment followed by haplotype-aware correction using a deep learning model to achieve higher single-read accuracies. The corrected reads are primarily useful for generating _de novo_ assemblies of diploid organisms.
 
+Dorado `correct` is available on all supported platforms *except* DGX Spark. Support for Dorado `correct` on DGX Spark will be added in a future release.
+
 To correct reads, run:
 
 ```bash
 dorado correct reads.fastq > corrected_reads.fasta
 ```
 
-Checkout the [doroado correct documentation](https://software-docs.nanoporetech.com/dorado/latest/assembly/correct/) for all the details.
+Checkout the [Dorado `correct` documentation](https://software-docs.nanoporetech.com/dorado/latest/assembly/correct/) for all the details.
 
 ### Polishing
 
@@ -180,12 +185,12 @@ Additionally, Dorado `polish` can output a VCF file containing records for all v
 
 Note that Dorado `polish` is a **haploid** polishing tool and does _not_ implement any sort of phasing internally. It will take input alignment data _as is_ and run it through the polishing model to produce the consensus sequences. For more information, please take a look at [this section](https://software-docs.nanoporetech.com/dorado/latest/assembly/polish/#polishing-diploidpolyploid-assemblies) of Dorado Docs.
 
-For more information on how to get started head to the [dorado polish documentation](https://software-docs.nanoporetech.com/dorado/latest/assembly/polish/).
+For more information on how to get started, head to the [Dorado `polish` documentation](https://software-docs.nanoporetech.com/dorado/latest/assembly/polish/).
 
 ### Variant Calling - Alpha preview release
 
 Dorado `variant` is an early-stage diploid small variant caller, released for experimental use and evaluation purposes.
-This version is intended for feedback and should not yet be considered production-ready. For more information check out the [dorado variant documentation](https://software-docs.nanoporetech.com/dorado/latest/assembly/variant/).
+This version is intended for feedback and should not yet be considered production-ready. For more information check out the [Dorado `variant` documentation](https://software-docs.nanoporetech.com/dorado/latest/assembly/variant/).
 
 ## Available basecalling models
 
@@ -199,11 +204,11 @@ To download all models instead of using the automatic download, run:
 dorado download --model all
 ```
 
-Click here for more information on [dorado downloader](https://software-docs.nanoporetech.com/dorado/latest/models/downloader/) and [dorado model selection](https://software-docs.nanoporetech.com/dorado/latest/models/selection/).
+Click here for more information on [Dorado `download`](https://software-docs.nanoporetech.com/dorado/latest/models/downloader/) and [Dorado model selection](https://software-docs.nanoporetech.com/dorado/latest/models/selection/).
 
 ## Troubleshooting Guide
 
-Click here for the [dorado troubleshooting documentation](https://software-docs.nanoporetech.com/dorado/latest/troubleshooting/troubleshooting/).
+Click here for the [Dorado troubleshooting documentation](https://software-docs.nanoporetech.com/dorado/latest/troubleshooting/troubleshooting/).
 
 ## Licence and Copyright