diff --git a/build_docs.py b/build_docs.py index cff6b4ce..0ee15709 100755 --- a/build_docs.py +++ b/build_docs.py @@ -52,7 +52,7 @@ def get_version(relpath): logging.info("Done updating [RELEASE_TAG] in Installation.md to {}".format(version)) subdir_and_commands = [ - ['tools', ['data','pipe','appraise','summarise','renew','supplement','read_fraction']], + ['tools', ['data','pipe','appraise','summarise','renew','supplement','microbial_fraction']], ['advanced', ['makedb','query','condense','seqs','create','metapackage']] ] @@ -66,7 +66,7 @@ def get_version(relpath): # Remove everything before the options section splitters = { 'pipe': 'COMMON OPTIONS', - 'read_fraction': 'OPTIONS', + 'microbial_fraction': 'OPTIONS', 'data': 'OPTIONS', 'summarise': 'INPUT', 'makedb': 'REQUIRED ARGUMENTS', diff --git a/docs/Installation.md b/docs/Installation.md index fe56831e..2aee4b52 100644 --- a/docs/Installation.md +++ b/docs/Installation.md @@ -20,45 +20,45 @@ After this, you'll also need to procure the reference data (the "metapackage"). ## Installation via DockerHub A docker image generated from the conda package is [available](https://hub.docker.com/r/wwood/singlem) on DockerHub. After installing Docker, run the following: ``` -docker pull wwood/singlem:0.15.1 +docker pull wwood/singlem:0.16.0 ``` Test if it works by running ``` -docker run wwood/singlem:0.15.1 -h +docker run wwood/singlem:0.16.0 -h ``` If the sequence data to be analyzed is in the current working directory, SingleM `pipe` can be used like so: ``` -docker run -v `pwd`:`pwd` wwood/singlem:0.15.1 pipe --sequences \ +docker run -v `pwd`:`pwd` wwood/singlem:0.16.0 pipe --sequences \ `pwd`/my.fastq.gz -p `pwd`/my.profile.csv --threads 4 ``` Two things to note: 1. The default SingleM reference data is included in the docker image, so running [singlem data](/tools/data) is not necessary for this installation method - you can jump straight to using `pipe`. -2. You should not specify `singlem` in the command line, as this is automatic. Simply use e.g. `docker run wwood/singlem:0.15.1 pipe -h`. +2. You should not specify `singlem` in the command line, as this is automatic. Simply use e.g. `docker run wwood/singlem:0.16.0 pipe -h`. ## Installation via Singularity / Apptainer SingleM can be installed via [Singularity](https://sylabs.io/singularity/) or [Apptainer](https://apptainer.org). After installing Singularity or Apptainer, run the following: ``` -singularity pull docker://wwood/singlem:0.15.1 +singularity pull docker://wwood/singlem:0.16.0 ``` Test if it works by running ``` -singularity run singlem_0.15.1.sif -h +singularity run singlem_0.16.0.sif -h ``` If the sequence data to be analyzed is in the current working directory, SingleM `pipe` can be used like so: ``` -singularity run -B `pwd`:`pwd` singlem_0.15.1.sif pipe --sequences \ +singularity run -B `pwd`:`pwd` singlem_0.16.0.sif pipe --sequences \ `pwd`/my.fastq.gz -p `pwd`/my.profile.csv --threads 4 ``` Two things to note: 1. The default SingleM reference data is included in the docker image, so running [singlem data](/tools/data) is not necessary for this installation method - you can jump straight to using `pipe`. -2. You should not specify `singlem` in the command line, as this is automatic. Simply use e.g. `singularity run singlem_0.15.1.sif pipe -h`. +2. You should not specify `singlem` in the command line, as this is automatic. Simply use e.g. `singularity run singlem_0.16.0.sif pipe -h`. ## Installation via PyPI diff --git a/docs/preludes/read_fraction_prelude.md b/docs/preludes/microbial_fraction_prelude.md similarity index 100% rename from docs/preludes/read_fraction_prelude.md rename to docs/preludes/microbial_fraction_prelude.md diff --git a/docs/tools/appraise.md b/docs/tools/appraise.md index fee39509..753e2c09 100644 --- a/docs/tools/appraise.md +++ b/docs/tools/appraise.md @@ -87,7 +87,7 @@ INEXACT APPRAISAL OPTIONS **\--sequence-identity** *SEQUENCE_IDENTITY* sequence identity cutoff to use if \--imperfect is specified - [default: \~species level divergence i.e. 0.95] + [default: \~species level divergence i.e. 0.9666666666666667] PLOTTING-RELATED OPTIONS ======================== diff --git a/docs/tools/read_fraction.md b/docs/tools/microbial_fraction.md similarity index 96% rename from docs/tools/read_fraction.md rename to docs/tools/microbial_fraction.md index 1108cd1d..83195571 100644 --- a/docs/tools/read_fraction.md +++ b/docs/tools/microbial_fraction.md @@ -1,8 +1,8 @@ --- -title: SingleM read_fraction +title: SingleM microbial_fraction --- -# singlem read_fraction -The 'read_fraction' subcommand can be used to estimate the fraction of reads +# singlem microbial_fraction +The 'microbial_fraction' subcommand can be used to estimate the fraction of reads from a metagenome that are assigned to Bacteria and Archaea compared to e.g. phages or eukaryotes. diff --git a/docs/tools/pipe.md b/docs/tools/pipe.md index d803db01..acd488ac 100644 --- a/docs/tools/pipe.md +++ b/docs/tools/pipe.md @@ -152,6 +152,12 @@ LESS COMMON OPTIONS Ignore reads aligning in less than this many positions to each protein HMM when using \--no-diamond-prefilter [default: 24] +**\--max-species-divergence** INT + + Maximum number of different bases acids to allow between a sequence + and the best hit in the database so that it is assigned to the + species level. [default: 2] + **\--exclude-off-target-hits** Exclude hits that are not in the target domain of each SingleM diff --git a/docs/tools/renew.md b/docs/tools/renew.md index 7d3d04e9..4a9d314d 100644 --- a/docs/tools/renew.md +++ b/docs/tools/renew.md @@ -128,6 +128,12 @@ LESS COMMON ARGUMENTS SHARED WITH \'PIPE\' Ignore reads aligning in less than this many positions to each protein HMM when using \--no-diamond-prefilter [default: 24] +**\--max-species-divergence** INT + + Maximum number of different bases acids to allow between a sequence + and the best hit in the database so that it is assigned to the + species level. [default: 2] + **\--exclude-off-target-hits** Exclude hits that are not in the target domain of each SingleM diff --git a/docs/tools/summarise.md b/docs/tools/summarise.md index e28d018f..c220b4d0 100644 --- a/docs/tools/summarise.md +++ b/docs/tools/summarise.md @@ -94,7 +94,7 @@ TRANSFORMATION **\--cluster-id** *CLUSTER_ID* Sequence clustering identity cutoff if \--cluster is used [default: - 0.95 i.e. 95.0%] + 0.9666666666666667 i.e. 96.66666666666667%] **\--taxonomy** *TAXONOMY* diff --git a/docs/tools/supplement.md b/docs/tools/supplement.md index 036f6281..5bfd90dd 100644 --- a/docs/tools/supplement.md +++ b/docs/tools/supplement.md @@ -15,6 +15,10 @@ OPTIONS FASTA files of new genomes +**\--new-genome-fasta-files-list** *NEW_GENOME_FASTA_FILES_LIST* [*NEW_GENOME_FASTA_FILES_LIST* \...] + + File containing FASTA file paths of new genomes + **\--new-taxonomies** *NEW_TAXONOMIES* newline separated file containing taxonomies of new genomes @@ -45,7 +49,12 @@ OPTIONS **\--gtdbtk-output-directory** *GTDBTK_OUTPUT_DIRECTORY* use this GTDBtk result. Not used if \--new-taxonomies is used - [default: run GTDBtk] + [default: not set, run GTDBtk] + +**\--taxonomy-file** *TAXONOMY_FILE* + + A 2 column tab-separated file containing each genome\'s taxonomy as + output by GTDBtk [default: not set, run GTDBtk] **\--output-taxonomies** *OUTPUT_TAXONOMIES* diff --git a/doctave.yml b/doctave.yml index 4040f806..96fc6e73 100644 --- a/doctave.yml +++ b/doctave.yml @@ -15,7 +15,7 @@ navigation: - path: docs/tools/summarise.md - path: docs/tools/renew.md - path: docs/tools/supplement.md - - path: docs/tools/read_fraction.md + - path: docs/tools/microbial_fraction.md - path: docs/tools/appraise.md - path: docs/advanced children: diff --git a/singlem/version.py b/singlem/version.py index 903e77ce..5a313cc7 100644 --- a/singlem/version.py +++ b/singlem/version.py @@ -1 +1 @@ -__version__ = "0.15.1" +__version__ = "0.16.0"