From a351019d4a4b183d7c77cf59cebd66327c7df4e9 Mon Sep 17 00:00:00 2001 From: Glenn Hickey Date: Fri, 23 Feb 2024 09:32:15 -0500 Subject: [PATCH] prep release v2.7.2 --- BIN-INSTALL.md | 10 +++++----- ReleaseNotes.md | 10 ++++++++++ doc/progressive.md | 6 +++--- setup.py | 2 +- src/cactus/shared/common.py | 2 +- 5 files changed, 20 insertions(+), 10 deletions(-) diff --git a/BIN-INSTALL.md b/BIN-INSTALL.md index a4db76566..cb7447d6c 100644 --- a/BIN-INSTALL.md +++ b/BIN-INSTALL.md @@ -6,17 +6,17 @@ pre-compile binary, static linked distribution. ## Extracting If you have not already extract the distribution and cd into the cactus directory: ``` -tar -xzf cactus-bin-v2.7.1.tar.gz -cd cactus-bin-v2.7.1 +tar -xzf cactus-bin-v2.7.2.tar.gz +cd cactus-bin-v2.7.2 ``` ## Setup To build a python virtualenv and activate, do the following steps. This requires Python version >= 3.7 (so Ubuntu 18.04 users should use `-p python3.8` below): ``` -virtualenv -p python3 venv-cactus-v2.7.1 -printf "export PATH=$(pwd)/bin:\$PATH\nexport PYTHONPATH=$(pwd)/lib:\$PYTHONPATH\n" >> venv-cactus-v2.7.1/bin/activate -source venv-cactus-v2.7.1/bin/activate +virtualenv -p python3 venv-cactus-v2.7.2 +printf "export PATH=$(pwd)/bin:\$PATH\nexport PYTHONPATH=$(pwd)/lib:\$PYTHONPATH\n" >> venv-cactus-v2.7.2/bin/activate +source venv-cactus-v2.7.2/bin/activate python3 -m pip install -U setuptools pip wheel python3 -m pip install -U . python3 -m pip install -U -r ./toil-requirement.txt diff --git a/ReleaseNotes.md b/ReleaseNotes.md index fde3b0324..13237e7ca 100644 --- a/ReleaseNotes.md +++ b/ReleaseNotes.md @@ -1,3 +1,13 @@ +# Release 2.7.2 2023-02-23 + +This release improves MAF output, along with some other fixes + +- `--maxMemory` option given more teeth. It is now used to clamp most large Toil jobs. On single-machine it defaults to system memory. This should prevent errors where Toil requrests more memory than available, halting the pipeline in an un-resumable state. +- Update to latest `taffy` and use newer MAF normalization. This should result in larger blocks and fewer gaps. MAF rows will now be sorted phylogenetically rather than alphabetically +- Better handle `.` characters in genome names during MAF processing. Previously neither duplicate filtering nor bigmaf summary creation could handle dots, but that should be fixed now. +- Duplicating filtering now done automatically in `cactus-maf2bigmaf`. +- Disable support for multifurcations (aka polytomies or internal nodes with more than 2 children) in Progressive Cactus. I'm doing this because I got spooked by a drop in coverage I noticed recently in a 4-child alignment. This regression appears to be linked to the new PAF chaining logic that's been added over the past several months. Until that's resolved, Cactus will exit with an error if it sees degree > 2 in the tree. This behaviour can, however, be overridden in the XML configuration file. + # Release 2.7.1 2023-01-19 This release adds some options to tune outgroup selection, as well as updates many included dependencies and tools diff --git a/doc/progressive.md b/doc/progressive.md index 6e239608b..331bf9d7e 100644 --- a/doc/progressive.md +++ b/doc/progressive.md @@ -199,12 +199,12 @@ The Cactus Docker image contains everything you need to run Cactus (python envir ``` wget -q https://raw.githubusercontent.com/ComparativeGenomicsToolkit/cactus/master/examples/evolverMammals.txt -O evolverMammals.txt -docker run -v $(pwd):/data --rm -it quay.io/comparative-genomics-toolkit/cactus:v2.7.1 cactus /data/jobStore /data/evolverMammals.txt /data/evolverMammals.hal +docker run -v $(pwd):/data --rm -it quay.io/comparative-genomics-toolkit/cactus:v2.7.2 cactus /data/jobStore /data/evolverMammals.txt /data/evolverMammals.hal ``` Or you can proceed interactively by running ``` -docker run -v $(pwd):/data --rm -it quay.io/comparative-genomics-toolkit/cactus:v2.7.1 bash +docker run -v $(pwd):/data --rm -it quay.io/comparative-genomics-toolkit/cactus:v2.7.2 bash cactus /data/jobStore /data/evolverMammals.txt /data/evolverMammals.hal ``` @@ -250,7 +250,7 @@ You cannot run `cactus --batchSystem slurm` from *inside* the Cactus docker cont To run Progressive Cactus with CPU (default) lastz, you should increase the chunk size. This will divide the input assemblies into fewer pieces, resulting in fewer jobs on the cluster. ``` -cp cactus-bin-v2.7.1/src/cactus/cactus_progressive_config.xml ./config-slurm.xml +cp cactus-bin-v2.7.2/src/cactus/cactus_progressive_config.xml ./config-slurm.xml sed -i config-slurm.xml -e 's/blast chunkSize="30000000"/blast chunkSize="90000000"/g' sed -i config-slurm.xml -e 's/dechunkBatchSize="1000"/dechunkBatchSize="200"/g' ``` diff --git a/setup.py b/setup.py index 7b1684174..a275391f4 100644 --- a/setup.py +++ b/setup.py @@ -24,7 +24,7 @@ def run(self): setup( name = "Cactus", - version = "2.7.1", + version = "2.7.2", author = "Benedict Paten", package_dir = {'': 'src'}, packages = find_packages(where='src'), diff --git a/src/cactus/shared/common.py b/src/cactus/shared/common.py index e76100584..1e987c0aa 100644 --- a/src/cactus/shared/common.py +++ b/src/cactus/shared/common.py @@ -318,7 +318,7 @@ def getDockerTag(gpu=False): return "latest" else: # must be manually kept current with each release - return 'v2.7.1' + ('-gpu' if gpu else '') + return 'v2.7.2' + ('-gpu' if gpu else '') def getDockerImage(gpu=False): """Get fully specified Docker image name."""