snakemake · fgvieira · Apr 4, 2025 · Apr 4, 2025 · Apr 9, 2025 · Apr 9, 2025
diff --git a/bio/mmseqs2/db/environment.linux-64.pin.txt b/bio/mmseqs2/db/environment.linux-64.pin.txt
@@ -0,0 +1,32 @@
+# This file may be used to create an environment using:
+# $ conda create --name <env> --file <this file>
+# platform: linux-64
+# created-by: conda 25.3.0
+@EXPLICIT
+https://conda.anaconda.org/conda-forge/linux-64/_libgcc_mutex-0.1-conda_forge.tar.bz2#d7c89558ba9fa0495403155b64376d81
+https://conda.anaconda.org/conda-forge/linux-64/ca-certificates-2025.1.31-hbcca054_0.conda#19f3a56f68d2fd06c516076bff482c52
+https://conda.anaconda.org/conda-forge/linux-64/libgomp-14.2.0-h767d61c_2.conda#06d02030237f4d5b3d9a7e7d348fe3c6
+https://conda.anaconda.org/conda-forge/linux-64/_openmp_mutex-4.5-2_gnu.tar.bz2#73aaf86a425cc6e73fcf236a5a46396d
+https://conda.anaconda.org/conda-forge/linux-64/libgcc-14.2.0-h767d61c_2.conda#ef504d1acbd74b7cc6849ef8af47dd03
+https://conda.anaconda.org/conda-forge/linux-64/c-ares-1.34.4-hb9d3cd8_0.conda#e2775acf57efd5af15b8e3d1d74d72d3
+https://conda.anaconda.org/conda-forge/linux-64/libgcc-ng-14.2.0-h69a702a_2.conda#a2222a6ada71fb478682efe483ce0f92
+https://conda.anaconda.org/conda-forge/linux-64/libgettextpo-0.23.1-h5888daf_0.conda#a09ce5decdef385bcce78c32809fa794
+https://conda.anaconda.org/conda-forge/linux-64/libiconv-1.18-h4ce23a2_1.conda#e796ff8ddc598affdf7c173d6145f087
+https://conda.anaconda.org/conda-forge/linux-64/liblzma-5.6.4-hb9d3cd8_0.conda#42d5b6a0f30d3c10cd88cb8584fda1cb
+https://conda.anaconda.org/conda-forge/linux-64/libstdcxx-14.2.0-h8f9b012_2.conda#a78c856b6dc6bf4ea8daeb9beaaa3fb0
+https://conda.anaconda.org/conda-forge/linux-64/libzlib-1.3.1-hb9d3cd8_2.conda#edb0dca6bc32e4f4789199455a1dbeb8
+https://conda.anaconda.org/conda-forge/linux-64/ncurses-6.5-h2d0b736_3.conda#47e340acb35de30501a76c7c799c41d7
+https://conda.anaconda.org/conda-forge/linux-64/openssl-3.4.1-h7b32b05_0.conda#41adf927e746dc75ecf0ef841c454e48
+https://conda.anaconda.org/conda-forge/linux-64/bzip2-1.0.8-h4bc722e_7.conda#62ee74e96c5ebb0af99386de58cf9553
+https://conda.anaconda.org/conda-forge/linux-64/libasprintf-0.23.1-h8e693c7_0.conda#988f4937281a66ca19d1adb3b5e3f859
+https://conda.anaconda.org/conda-forge/linux-64/libsqlite-3.49.1-hee588c1_2.conda#962d6ac93c30b1dfc54c9cccafd1003e
+https://conda.anaconda.org/conda-forge/linux-64/libssh2-1.11.1-hf672d98_0.conda#be2de152d8073ef1c01b7728475f2fe7
+https://conda.anaconda.org/conda-forge/linux-64/libstdcxx-ng-14.2.0-h4852527_2.conda#c75da67f045c2627f59e6fcb5f4e3a9b
+https://conda.anaconda.org/conda-forge/linux-64/libxml2-2.13.7-h0d44e9d_0.conda#3ac6daa5c1210293a6deaec0c345b230
+https://conda.anaconda.org/conda-forge/linux-64/readline-8.2-h8c095d6_2.conda#283b96675859b20a825f8fa30f311446
+https://conda.anaconda.org/conda-forge/linux-64/zlib-1.3.1-hb9d3cd8_2.conda#c9f075ab2f33b3bbee9e62d4ad0a6cd8
+https://conda.anaconda.org/conda-forge/linux-64/aria2-1.37.0-hbc8128a_2.conda#03b8874fa70df577f3eee53085d025cf
+https://conda.anaconda.org/conda-forge/linux-64/gmp-6.3.0-hac33072_2.conda#c94a5994ef49749880a8139cf9afcbe1
+https://conda.anaconda.org/conda-forge/linux-64/mpfr-4.2.1-h90cbb55_3.conda#2eeb50cab6652538eee8fc0bc3340c81
+https://conda.anaconda.org/conda-forge/linux-64/gawk-5.3.1-hcd3d067_0.conda#91d4414ab699180b2b0b10b8112c5a2f
+https://conda.anaconda.org/bioconda/linux-64/mmseqs2-17.b804f-hd6d6fdc_1.tar.bz2#561fb589d37cff61ec6b887fc2976498
diff --git a/bio/mmseqs2/db/environment.yaml b/bio/mmseqs2/db/environment.yaml
@@ -0,0 +1,6 @@
+channels:
+  - conda-forge
+  - bioconda
+  - nodefaults
+dependencies:
+  - mmseqs2 =17.b804f
diff --git a/bio/mmseqs2/db/meta.yaml b/bio/mmseqs2/db/meta.yaml
@@ -0,0 +1,13 @@
+name: MMseqs2 db
+url: https://github.com/soedinglab/mmseqs2
+description: |
+  ultra fast and sensitive sequence search and clustering suite
+authors:
+  - Filipe G. Vieira
+input:
+  - input FAS file
+output:
+  - output: DB files
+params:
+  - module: workflow to use
+  - extra: additional program arguments
diff --git a/bio/mmseqs2/db/test/Snakefile b/bio/mmseqs2/db/test/Snakefile
@@ -0,0 +1,49 @@
+rule mmseqs2_databases:
+    output:
+        db=multiext(
+            "out/databases/{sample}",
+            "",
+            ".dbtype",
+            ".index",
+            ".lookup",
+            ".source",
+            ".version",
+            "_h",
+            "_h.dbtype",
+            "_h.index",
+            "_mapping",
+            "_taxonomy",
+        ),
+    log:
+        "logs/databases/{sample}.log",
+    params:
+        module="databases SILVA",
+        extra="-v 3",
+    threads: 1
+    wrapper:
+        "master/bio/mmseqs2/db"
+
+
+rule mmseqs2_createdb:
+    input:
+        fas="seqs/{sample}.fasta",
+    output:
+        db=multiext(
+            "out/createdb/{sample}",
+            "",
+            ".dbtype",
+            ".index",
+            ".lookup",
+            ".source",
+            "_h",
+            "_h.dbtype",
+            "_h.index",
+        ),
+    log:
+        "logs/createdb/{sample}.log",
+    params:
+        module="createdb",
+        extra="-v 3",
+    threads: 1
+    wrapper:
+        "master/bio/mmseqs2/db"
diff --git a/bio/mmseqs2/db/test/expected/createdb/a b/bio/mmseqs2/db/test/expected/createdb/a
diff --git a/bio/mmseqs2/db/test/expected/createdb/a.dbtype b/bio/mmseqs2/db/test/expected/createdb/a.dbtype
diff --git a/bio/mmseqs2/db/test/expected/createdb/a.index b/bio/mmseqs2/db/test/expected/createdb/a.index
@@ -0,0 +1,4 @@
+0	0	9
+1	9	9
+2	18	8
+3	26	8
diff --git a/bio/mmseqs2/db/test/expected/createdb/a.lookup b/bio/mmseqs2/db/test/expected/createdb/a.lookup
@@ -0,0 +1,4 @@
+0	1	0
+1	2	0
+2	1	0
+3	3	0
diff --git a/bio/mmseqs2/db/test/expected/createdb/a.source b/bio/mmseqs2/db/test/expected/createdb/a.source
@@ -0,0 +1 @@
+0	a.fasta
diff --git a/bio/mmseqs2/db/test/expected/createdb/a_h b/bio/mmseqs2/db/test/expected/createdb/a_h
diff --git a/bio/mmseqs2/db/test/expected/createdb/a_h.dbtype b/bio/mmseqs2/db/test/expected/createdb/a_h.dbtype
diff --git a/bio/mmseqs2/db/test/expected/createdb/a_h.index b/bio/mmseqs2/db/test/expected/createdb/a_h.index
@@ -0,0 +1,4 @@
+0	0	3
+1	3	3
+2	6	3
+3	9	3
diff --git a/bio/mmseqs2/db/test/expected/databases/a.dbtype b/bio/mmseqs2/db/test/expected/databases/a.dbtype
diff --git a/bio/mmseqs2/db/test/expected/databases/a.source b/bio/mmseqs2/db/test/expected/databases/a.source
@@ -0,0 +1 @@
+0	silva.fasta.gz
diff --git a/bio/mmseqs2/db/test/expected/databases/a.version b/bio/mmseqs2/db/test/expected/databases/a.version
@@ -0,0 +1,164 @@
+README for SILVA 138 export files
+
+RAST FILES:
+===========
+
+Specific export files for the MG-RAST server (Argonne National Lab)
+
+TAXONOMY FILES:
+===============
+
+tax_slv_[ls]su_VERSION.txt
+-------------------------
+These files contain taxonomic rank designations for all taxonomic paths
+used in the SILVA taxonomies. Additionally, a unique numeric identifier is 
+assigned to each taxon (path). These identifiers will be mostly stable in 
+upcoming SILVA releases. 
+
+IDs used in the SSU and LSU files do not match.
+
+Field description:
+path:
+    The full taxonomic path including the name of the group itself.
+    Segments are separated with ";"
+taxid:
+    numerical identifier
+rank:
+    The rank designation. 
+remark:
+    Can be empty ('') or a or w.
+    a: Marks taxa of environmental origin. That is, taxa containing no 
+       sequence coming from a cultivated organism.
+    w: Marks taxa scheduled for revision in the next release.
+release:
+    The SILVA release version
+
+tax_slv_[ls]su_VERSION.diff
+---------------------------
+Difference between the current version of the SILVA taxonomy and the previous
+release.
+
+Field description:
+status:
+    the status of the taxono (+ added, - removed)
+taxid:
+    numerical identifier
+path:
+    the full path of the added/removed taxon
+
+taxmap_TAXNAME_[ls]su_VERSION.txt
+----------------------------
+mapping of each entry in the SILVA database to a taxonomic path. Different
+rRNA regions of the same INSDC entry (genome) may be assigned to multiple
+paths (contaminations or micro diversity among the rRNA sequences).
+
+The taxmap_embl* files contain the taxonomic path assigned by the original
+submitter of the sequence. The last column in this file contains the numerical
+ID of the NCBI taxonomy project assigned to this entry. This ID is extracted
+from the source feature of an EMBL entry during the import of the sequence.
+
+Field description:
+pacc:
+    INSDC primary accession
+start
+    start position of the rRNA region within the INSDC sequence entry
+stop:
+    stop position of the rRNA region within the INSDC sequence entry
+path:
+    taxonomic path assigned to the region
+name
+    the organism name assigned to the sequence
+taxid:
+    optional field containing the numerical ID of the taxonomic path
+
+
+tax_TAXNAME_[ls]su_VERSION.{map,tre}
+----------------------------
+SILVA taxonomy in the Newick tree format and the corespoding numerical id to
+taxonomic path mapping file (MEGAN compatible).
+
+tax_TAXNAME_[ls]su_VERSION.acc_taxid
+----------------------------
+Mapping of 'SILVA' sequence IDs (<INSDC primary accession>.<start>.<stop>)
+used in FASTA files to the numeric SILVA taxid (MEGAN compatible).
+
+
+
+
+SEQUENCE FILES:
+===============
+
+*_tax_silva.fasta.gz
+-----------------
+Multi FASTA files of the SSU/LSU databases including the SILVA taxonomy for
+Bacteria, Archaea and Eukaryotes in the header.
+
+REMARK: The sequences in the files are NOT truncated to the effective LSU or
+SSU genes. They contain the full entries as they have been deposited in the
+public repositories (ENA/GenBank/DDBJ). 
+
+Fasta header:
+>accession_number.start_position.stop_position taxonomic path organism name
+
+*_tax_silva_full_align_trunc.fasta.gz
+-----------------------
+Multi FASTA files of the SSU/LSU databases including the SILVA taxonomy for
+Bacteria, Archaea and Eukaryotes in the header (including the FULL alignment).
+
+REMARK: Sequences in these files haven been truncated. This means that all
+nucleotides that have not been aligned were removed from the sequence.
+
+*_tax_silva_trunc.fasta.gz
+-----------------------
+Multi FASTA files of the SSU/LSU database including the SILVA taxonomy for 
+Bacteria, Archaea and Eukaryotes in the header.
+
+REMARK: Sequences in these files haven been truncated. This means that all
+nucleotides that have not been aligned were removed from the sequence.
+
+
+
+CUSTOMISED FILES:
+=================
+
+*.acs
+-----
+Lists with all accession numbers in LSUParc and SSUParc
+
+*.clstr
+-------
+Mapping of 'ref' sequences to 'nr' sequences. The file uses the CD-Hit file
+format.
+
+*quality*.csv
+-------------
+complete quality values for all SILVA Parc sequences Datasets.
+Header: Primary Accession,Start,Stop,Region Length,Annotation Source,Sequence Quality,
+% Ambiguities,% Homopolymers,% Vector Contamination,Alignment Quality, Base Pair Score,
+# Aligned Bases,Pintail Quality
+
+
+
+Directory 'User'
+User specific exports done on request
+
+Abbreviations:
+
+LSU: Large subunit (23S/28S ribosomal RNAs)
+SSU: Small subunit (16S/18S ribosomal RNAs)
+
+
+
+
+Questions: [email protected]
+
+December 2019
+
+If you are using SILVA please cite:
+Quast C, Pruesse E, Yilmaz P, Gerken J, Schweer T, Yarza P, Peplies J,
+Glockner FO (2013) The SILVA ribosomal RNA gene database project: improved
+data processing and web-based tools. Nucleic Acids Research 41:D590-D596
+
+Yilmaz P, Parfrey LW, Yarza P, Gerken J, Pruesse E, Quast C, Schweer T,
+Peplies J, Ludwig W, Glockner FO (2014) The SILVA and "All-species Living
+Tree Project (LTP)" taxonomic frameworks. Nucleic Acid Res. 42:D643-D648
diff --git a/bio/mmseqs2/db/test/expected/databases/a_h.dbtype b/bio/mmseqs2/db/test/expected/databases/a_h.dbtype
diff --git a/bio/mmseqs2/db/test/seqs/a.fasta b/bio/mmseqs2/db/test/seqs/a.fasta
@@ -0,0 +1,8 @@
+>1
+ACGGCAT
+>2
+ATGGCAT
+>1
+CGGCAT
+>3
+ATGGCA
diff --git a/bio/mmseqs2/db/wrapper.py b/bio/mmseqs2/db/wrapper.py
@@ -0,0 +1,31 @@
+__author__ = "Filipe G. Vieira"
+__copyright__ = "Copyright 2024, Filipe G. Vieira"
+__license__ = "MIT"
+
+import os
+import tempfile
+from snakemake.shell import shell
+
+extra = snakemake.params.get("extra", "")
+log = snakemake.log_fmt_shell(stdout=True, stderr=True)
+
+
+input = snakemake.input
+if isinstance(input, list):
+    input = os.path.commonprefix(input)
+
+# TODO: arbitrary output file names
+out = snakemake.output
+if isinstance(out, list):
+    out = os.path.commonprefix(out).rstrip("_")
+
+
+with tempfile.TemporaryDirectory() as tmpdir:
+    # Modules with threads
+    if snakemake.params.module in ["databases"]:
+        extra = f"--threads {snakemake.threads} {extra}"
+    # Modules with no temp folder
+    if snakemake.params.module in ["createdb"]:
+        tmpdir = ""
+
+    shell("mmseqs {snakemake.params.module} {input} {out} {tmpdir} {extra} {log}")
diff --git a/bio/mmseqs2/workflows/environment.linux-64.pin.txt b/bio/mmseqs2/workflows/environment.linux-64.pin.txt
@@ -0,0 +1,43 @@
+# This file may be used to create an environment using:
+# $ conda create --name <env> --file <this file>
+# platform: linux-64
+# created-by: conda 25.7.0
+@EXPLICIT
+https://conda.anaconda.org/conda-forge/linux-64/_libgcc_mutex-0.1-conda_forge.tar.bz2#d7c89558ba9fa0495403155b64376d81
+https://conda.anaconda.org/conda-forge/noarch/ca-certificates-2025.8.3-hbd8a1cb_0.conda#74784ee3d225fc3dca89edb635b4e5cc
+https://conda.anaconda.org/conda-forge/linux-64/ld_impl_linux-64-2.44-h1423503_1.conda#0be7c6e070c19105f966d3758448d018
+https://conda.anaconda.org/conda-forge/linux-64/libgomp-15.1.0-h767d61c_5.conda#dcd5ff1940cd38f6df777cac86819d60
+https://conda.anaconda.org/conda-forge/noarch/python_abi-3.13-8_cp313.conda#94305520c52a4aa3f6c2b1ff6008d9f8
+https://conda.anaconda.org/conda-forge/noarch/tzdata-2025b-h78e105d_0.conda#4222072737ccff51314b5ece9c7d6f5a
+https://conda.anaconda.org/conda-forge/linux-64/_openmp_mutex-4.5-2_gnu.tar.bz2#73aaf86a425cc6e73fcf236a5a46396d
+https://conda.anaconda.org/conda-forge/linux-64/libgcc-15.1.0-h767d61c_5.conda#264fbfba7fb20acf3b29cde153e345ce
+https://conda.anaconda.org/conda-forge/linux-64/bzip2-1.0.8-hda65f42_8.conda#51a19bba1b8ebfb60df25cde030b7ebc
+https://conda.anaconda.org/conda-forge/linux-64/c-ares-1.34.5-hb9d3cd8_0.conda#f7f0d6cc2dc986d42ac2689ec88192be
+https://conda.anaconda.org/conda-forge/linux-64/libexpat-2.7.1-hecca717_0.conda#4211416ecba1866fab0c6470986c22d6
+https://conda.anaconda.org/conda-forge/linux-64/libffi-3.4.6-h2dba641_1.conda#ede4673863426c0883c0063d853bbd85
+https://conda.anaconda.org/conda-forge/linux-64/libgcc-ng-15.1.0-h69a702a_5.conda#069afdf8ea72504e48d23ae1171d951c
+https://conda.anaconda.org/conda-forge/linux-64/libiconv-1.18-h3b78370_2.conda#915f5995e94f60e9a4826e0b0920ee88
+https://conda.anaconda.org/conda-forge/linux-64/liblzma-5.8.1-hb9d3cd8_2.conda#1a580f7796c7bf6393fddb8bbbde58dc
+https://conda.anaconda.org/conda-forge/linux-64/libmpdec-4.0.0-hb9d3cd8_0.conda#c7e925f37e3b40d893459e625f6a53f1
+https://conda.anaconda.org/conda-forge/linux-64/libstdcxx-15.1.0-h8f9b012_5.conda#4e02a49aaa9d5190cb630fa43528fbe6
+https://conda.anaconda.org/conda-forge/linux-64/libuuid-2.41.2-he9a06e4_0.conda#80c07c68d2f6870250959dcc95b209d1
+https://conda.anaconda.org/conda-forge/linux-64/libzlib-1.3.1-hb9d3cd8_2.conda#edb0dca6bc32e4f4789199455a1dbeb8
+https://conda.anaconda.org/conda-forge/linux-64/ncurses-6.5-h2d0b736_3.conda#47e340acb35de30501a76c7c799c41d7
+https://conda.anaconda.org/conda-forge/linux-64/openssl-3.5.3-h26f9b46_1.conda#4fc6c4c88da64c0219c0c6c0408cedd4
+https://conda.anaconda.org/conda-forge/linux-64/libasprintf-0.25.1-h3f43e3d_1.conda#3b0d184bc9404516d418d4509e418bdc
+https://conda.anaconda.org/conda-forge/linux-64/libgettextpo-0.25.1-h3f43e3d_1.conda#2f4de899028319b27eb7a4023be5dfd2
+https://conda.anaconda.org/conda-forge/linux-64/libsqlite-3.50.4-h0c1763c_0.conda#0b367fad34931cb79e0d6b7e5c06bb1c
+https://conda.anaconda.org/conda-forge/linux-64/libssh2-1.11.1-hcf80075_0.conda#eecce068c7e4eddeb169591baac20ac4
+https://conda.anaconda.org/conda-forge/linux-64/libstdcxx-ng-15.1.0-h4852527_5.conda#8bba50c7f4679f08c861b597ad2bda6b
+https://conda.anaconda.org/conda-forge/linux-64/libxml2-2.13.8-h2cb61b6_1.conda#42a8e4b54e322b4cd1dbfb30a8a7ce9e
+https://conda.anaconda.org/conda-forge/linux-64/readline-8.2-h8c095d6_2.conda#283b96675859b20a825f8fa30f311446
+https://conda.anaconda.org/conda-forge/linux-64/tk-8.6.13-noxft_hd72426e_102.conda#a0116df4f4ed05c303811a837d5b39d8
+https://conda.anaconda.org/conda-forge/linux-64/zlib-1.3.1-hb9d3cd8_2.conda#c9f075ab2f33b3bbee9e62d4ad0a6cd8
+https://conda.anaconda.org/conda-forge/linux-64/aria2-1.37.0-hbc8128a_2.conda#03b8874fa70df577f3eee53085d025cf
+https://conda.anaconda.org/conda-forge/linux-64/gmp-6.3.0-hac33072_2.conda#c94a5994ef49749880a8139cf9afcbe1
+https://conda.anaconda.org/conda-forge/linux-64/python-3.13.7-h2b335a9_100_cp313.conda#724dcf9960e933838247971da07fe5cf
+https://conda.anaconda.org/conda-forge/linux-64/mpfr-4.2.1-h90cbb55_3.conda#2eeb50cab6652538eee8fc0bc3340c81
+https://conda.anaconda.org/conda-forge/noarch/pip-25.2-pyh145f28c_0.conda#e7ab34d5a93e0819b62563c78635d937
+https://conda.anaconda.org/bioconda/noarch/snakemake-wrapper-utils-0.8.0-pyhdfd78af_0.conda#1650e521333852f45468d97b1b2fdcce
+https://conda.anaconda.org/conda-forge/linux-64/gawk-5.3.1-hcd3d067_0.conda#91d4414ab699180b2b0b10b8112c5a2f
+https://conda.anaconda.org/bioconda/linux-64/mmseqs2-17.b804f-hd6d6fdc_1.tar.bz2#561fb589d37cff61ec6b887fc2976498
diff --git a/bio/mmseqs2/workflows/environment.yaml b/bio/mmseqs2/workflows/environment.yaml
@@ -0,0 +1,7 @@
+channels:
+  - conda-forge
+  - bioconda
+  - nodefaults
+dependencies:
+  - mmseqs2 =17.b804f
+  - snakemake-wrapper-utils =0.8.0
diff --git a/bio/mmseqs2/workflows/meta.yaml b/bio/mmseqs2/workflows/meta.yaml
@@ -0,0 +1,14 @@
+name: MMseqs2 workflows
+url: https://github.com/soedinglab/mmseqs2
+description: |
+  ultra fast and sensitive sequence search and clustering suite
+authors:
+  - Filipe G. Vieira
+input:
+  - query: input query FAS file(s)
+  - target: input target FAS file(s) or DB
+output:
+  - output: FAS, cluster or DB file(s)
+params:
+  - module: workflow to use
+  - extra: additional program arguments
-Original file line number
+Diff line change
@@ -0,0 +1,4 @@
+	0	9
+	9	9
+	18	8
+	26	8