diff --git a/CHANGELOG.md b/CHANGELOG.md index 7dd167c..7b47149 100755 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -3,14 +3,56 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). -## v1.0dev - [date] +## [[1.0.0](https://github.com/sanger-tol/curationpretext/releases/tag/1.0.0)] - UNSC Infinity - [2023-10-02] Initial release of sanger-tol/curationpretext, created with the [sager-tol](https://nf-co.re/) template. -### `Added` +### Added -### `Fixed` +- Subworkflow to generate tracks containing telomeric sites. +- Subworkflow to generate Pretext maps and images +- Subworkflow to generate repeat density tracks. +- Subworkflow to generate longread coverage tracks from pacbio data. +- Subworkflow to generate gap tracks. -### `Dependencies` +### Parameters -### `Deprecated` +| Old Version | New Versions | +| ----------- | ------------ | +| | --input | +| | --cram | +| | --pacbio | +| | --sample | +| | --teloseq | +| | -entry | + +### Software Dependencies + +Note, since the pipeline is using Nextflow DSL2, each process will be run with its own Biocontainer. This means that on occasion it is entirely possible for the pipeline to be using different versions of the same tool. However, the overall software dependency changes compared to the last release have been listed below for reference. + +| Module | Old Version | New Versions | +| -------------------------------------- | ----------- | -------------- | +| bamtobed_sort ( bedtools + samtools ) | - | 2.31.0 + 1.17 | +| bedtools | - | 2.31.0 | +| cram_filter_align_bwamem2_fixmate_sort | - | | +| ^ ( samtools + bwamem2 ) ^ | - | 1.16.1 + 2.2.1 | +| extract_cov_id ( coreutils ) | - | 9.1 | +| extract_repeat ( perl ) | - | 5.26.2 | +| extract_telo ( coreutils ) | - | 9.1 | +| find_telomere_regions ( gcc ) | - | 7.1.0 | +| find_telomere_windows ( java-jdk ) | - | 8.0.112 | +| gap_length ( coreutils ) | - | 9.1 | +| generate_cram_csv ( samtools ) | - | 1.17 | +| get_largest_scaff ( coreutils ) | - | 9.1 | +| gnu-sort | - | 8.25 | +| pretextmap + samtools | - | 0.1.9 + 1.17 | +| seqtk | - | 1.4 | +| tabix | - | 1.11 | +| ucsc | - | 377 | +| windowmasker (blast) | - | 2.14.0 | + +### Fixed + +### Dependencies + +### Deprecated diff --git a/conf/base.config b/conf/base.config index b25f0e7..891e2fe 100755 --- a/conf/base.config +++ b/conf/base.config @@ -21,12 +21,12 @@ process { withName: '.*:.*:LONGREAD_COVERAGE:(MINIMAP2_ALIGN|MINIMAP2_ALIGN_SPLIT)' { cpus = { check_max( 16 * 1, 'cpus' ) } - memory = { check_max( 100.GB * task.attempt, 'memory' ) } + memory = { check_max( 25.GB * task.attempt, 'memory' ) } } withName: CRAM_FILTER_ALIGN_BWAMEM2_FIXMATE_SORT { cpus = { check_max( 16 * 1, 'cpus' ) } - memory = { check_max( 80.GB * task.attempt, 'memory' ) } + memory = { check_max( 25.GB * task.attempt, 'memory' ) } } withName: PRETEXTMAP_STANDRD{ @@ -45,7 +45,7 @@ process { } withName: BWAMEM2_INDEX { - memory = { check_max( 100.GB * task.attempt, 'memory' ) } + memory = { check_max( 25.GB * task.attempt, 'memory' ) } } // Process-specific resource requirements diff --git a/docs/usage.md b/docs/usage.md index 289bf12..f0cb0c3 100755 --- a/docs/usage.md +++ b/docs/usage.md @@ -19,6 +19,32 @@ The `--pacbio` should point to the folder containing `.fasta.gz` files. If you do not have these file formats we have also included instructions on converting from common formats to our preferred format. If there is a popular public preference for a particular format, we can modify the pipeline to utilise those formats. Just submit an issue. +## Prior to running CurationPretext + +
+ Details + +We provide a complete set of data that can be used to test the pipeline locally. + +By default the test.config file is set up to run on GitHub, however, should you want to test this locally you can follow the below instructions. + +First, choose a download location `${PRETEXT_TEST_DATA}` and run this command (this assumes you are inside the curationpretext directory): + +``` +PRETEXT_TEST_DATA=$(pwd) +curl https://tolit.cog.sanger.ac.uk/test-data/resources/treeval/TreeValTinyData.tar.gz | tar xzf - + +sed -i'' -e "s|/home/runner/work/curationpretext/curationpretext|${PRETEXT_TEST_DATA}|" conf/test.config +``` + +Then, you should be able to run the pipeline with: + +``` +nextflow run . -profile test,singularity +``` + +
+ ### HiC data Preparation