Add local module dshbio/fastatoparquet

conf/modules.config

@@ -10,6 +10,8 @@
 ----------------------------------------------------------------------------------------
 */
 
+nextflow.enable.moduleBinaries = true
+
 process {
 
     publishDir = [
@@ -30,4 +32,8 @@ process {
     withName: SEQKIT_STATS {
         ext.args = ' ' // turn off --all default argument
     }
+
+    withName: DSHBIO_FASTATOPARQUET {
+        ext.args = '--alphabet protein'
+    }
 }

modules/local/dshbio/fastatoparquet/environment.yml

@@ -0,0 +1,7 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - bioconda::dsh-bio=3.0

modules/local/dshbio/fastatoparquet/main.nf

@@ -0,0 +1,47 @@
+process DSHBIO_FASTATOPARQUET {
+    tag "${meta.id}"
+    label 'process_medium'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/dsh-bio:3.0--hdfd78af_0' :
+        'biocontainers/dsh-bio:3.0--hdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(fasta)
+
+    output:
+    tuple val(meta), path("*.sequences.parquet"), emit: parquet
+    path "versions.yml"                         , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    dsh-bio \\
+        fasta-to-parquet3 \\
+        $args \\
+        -i $fasta \\
+        -o ${prefix}.sequences.parquet
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        dshbio: \$(dsh-bio --version 2>&1 | grep -o 'dsh-bio-tools .*' | cut -f2 -d ' ')
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    mkdir -p ${prefix}.sequences.parquet
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        dshbio: \$(dsh-bio --version 2>&1 | grep -o 'dsh-bio-tools .*' | cut -f2 -d ' ')
+    END_VERSIONS
+    """
+}

modules/local/dshbio/fastatoparquet/meta.yml

@@ -0,0 +1,52 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "dshbio_fastatoparquet"
+description: Convert DNA or protein sequences in FASTA format to Parquet format
+keywords:
+  - fasta
+  - parquet
+  - sequence
+tools:
+  - dshbio:
+      description: |
+        Reads, features, variants, assemblies, alignments, genomic range trees, pangenome
+        graphs, and a bunch of random command line tools for bioinformatics. LGPL version 3
+        or later.
+      homepage: https://github.com/heuermh/dishevelled-bio
+      documentation: https://github.com/heuermh/dishevelled-bio
+      doi: "10.5281/zenodo.15027131"
+      licence: ["LGPL-3.0-or-later"]
+
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. [ id:'test', single_end:false ]
+    - fasta:
+        type: file
+        description: DNA or protein sequences in compressed FASTA format
+        pattern: "*.fasta.{gz|zst|bgz|bgzf|bzip2}"
+
+output:
+  - parquet:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+      - "*.sequences.parquet":
+          type: directory
+          description: |
+            Directory of DNA or protein sequences in Parquet format with zstd compression
+          pattern: "*.sequences.parquet"
+  - versions:
+      - versions.yml:
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
+
+authors:
+  - "@heuermh"
+maintainers:
+  - "@heuermh"

modules/local/duckdb/aminoacidhistogram/environment.yml

@@ -0,0 +1,7 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+channels:
+  - conda-forge
+
+dependencies:
+  - conda-forge::duckdb-cli=1.0.0

modules/local/duckdb/aminoacidhistogram/main.nf

@@ -0,0 +1,34 @@
+process DUCKDB_AMINOACIDHISTOGRAM {
+    tag "${meta.id}"
+    label 'process_medium'
+
+    conda "${moduleDir}/environment.yml"
+    container 'community.wave.seqera.io/library/duckdb-cli:1.1.3--c5d9961e3b49178e'
+    //container 'community.wave.seqera.io/library/duckdb-cli_pip_duckdb-extension-parquet:48635535d267c0b5'
+    //container 'community.wave.seqera.io/library/duckdb-cli_pip_duckdb-extension-parquet:be97269b25d3a5b6'
+    //container 'community.wave.seqera.io/library/pip_duckdb-extension-parquet_duckdb:8326cfa0a50bf9c9'
+
+    input:
+    tuple val(meta), path(parquet)
+
+    output:
+    tuple val(meta), path("*.histogram.tsv"), emit: histogram
+    path "versions.yml"                     , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def amino_acid_properties = file("${moduleDir}/assets/amino_acid_properties.tsv")
+    //template 'amino_acid_histogram.py'
+    def sql = "INSTALL parquet; LOAD parquet; COPY (WITH p AS (SELECT * FROM read_parquet('${parquet}/*.parquet')), s AS (SELECT unnest(string_to_array(sequence, '')) AS aa FROM p), h AS (SELECT unnest(map_entries(histogram(aa))) AS kv FROM s), e AS (SELECT * from read_csv_auto('${amino_acid_properties}')) SELECT '${prefix}' AS id, h.kv['value'] AS count, e.* FROM h JOIN e ON h.kv['key'] = e.one_letter_symbol) TO '${prefix}.histogram.tsv' (HEADER, DELIMITER '\t')"
+    """
+    duckdb :memory: "$sql"
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        duckdb: \$( duckdb --version | cut -f 1 -d " " )
+    END_VERSIONS
+    """
+}

modules/local/duckdb/aminoacidhistogram/resources/usr/bin/create_amino_acid_properties.sh

@@ -0,0 +1,34 @@
+#!/usr/bin/env bash
+
+#
+# See https://en.wikipedia.org/wiki/Amino_acid
+
+cat <<END_PROPERTIES > amino_acid_properties.tsv
+amino_acid	three_letter_symbol	one_letter_symbol	class	chemical_polarity	net_charge	hydropathy_index	molecular_mass	abundance_in_proteins	standard_genetic_coding	hydrophobic	aromatic	aliphatic	small	hydrophilic	positively_charged	negatively_charged
+Alanine	Ala	A	Aliphatic	Nonpolar	Neutral	1.8	89.094	8.76	GCN	FALSE	FALSE	FALSE	TRUE	FALSE	FALSE	FALSE
+Arginine	Arg	R	Fixed cation	Basic polar	Positive	−4.5	174.203	5.78	MGR, CGY	FALSE	FALSE	FALSE	FALSE	TRUE	TRUE	FALSE
+Asparagine	Asn	N	Amide	Polar	Neutral	−3.5	132.119	3.93	AAY	FALSE	FALSE	FALSE	FALSE	TRUE	FALSE	FALSE
+Aspartate	Asp	D	Anion	Brønsted base	Negative	−3.5	133.104	5.49	GAY	FALSE	FALSE	FALSE	FALSE	TRUE	FALSE	TRUE
+Cysteine	Cys	C	Thiol	Brønsted acid	Neutral	2.5	121.154	1.38	UGY	FALSE	FALSE	FALSE	FALSE	FALSE	FALSE	FALSE
+Glutamine	Gln	Q	Amide	Polar	Neutral	−3.5	146.146	3.9	CAR	FALSE	FALSE	FALSE	FALSE	TRUE	FALSE	FALSE
+Glutamate	Glu	E	Anion	Brønsted base	Negative	−3.5	147.131	6.32	GAR	FALSE	FALSE	FALSE	FALSE	TRUE	FALSE	TRUE
+Glycine	Gly	G	Aliphatic	Nonpolar	Neutral	−0.4	75.067	7.03	GGN	FALSE	FALSE	FALSE	TRUE	FALSE	FALSE	FALSE
+Histidine	His	H	Cationic	Brønsted acid and base	Positive, 10% Neutral, 90%	−3.2	155.156	2.26	CAY	FALSE	TRUE	FALSE	FALSE	TRUE	TRUE	FALSE
+Isoleucine	Ile	I	Aliphatic	Nonpolar	Neutral	4.5	131.175	5.49	AUH	TRUE	FALSE	TRUE	FALSE	FALSE	FALSE	FALSE
+Leucine	Leu	L	Aliphatic	Nonpolar	Neutral	3.8	131.175	9.68	YUR, CUY	TRUE	FALSE	TRUE	FALSE	FALSE	FALSE	FALSE
+Lysine	Lys	K	Cation	Brønsted acid	Positive	−3.9	146.189	5.19	AAR	FALSE	FALSE	FALSE	FALSE	TRUE	TRUE	FALSE
+Methionine	Met	M	Thioether	Nonpolar	Neutral	1.9	149.208	2.32	AUG	TRUE	FALSE	TRUE	FALSE	FALSE	FALSE	FALSE
+Phenylalanine	Phe	F	Aromatic	Nonpolar	Neutral	2.8	165.192	3.87	UUY	TRUE	TRUE	FALSE	FALSE	FALSE	FALSE	FALSE
+Proline	Pro	P	Cyclic	Nonpolar	Neutral	−1.6	115.132	5.02	CCN	FALSE	FALSE	FALSE	TRUE	FALSE	FALSE	FALSE
+Serine	Ser	S	Hydroxylic	Polar	Neutral	−0.8	105.093	7.14	UCN, AGY	FALSE	FALSE	FALSE	TRUE	TRUE	FALSE	FALSE
+Threonine	Thr	T	Hydroxylic	Polar	Neutral	−0.7	119.119	5.53	ACN	FALSE	FALSE	FALSE	FALSE	TRUE	FALSE	FALSE
+Tryptophan	Trp	W	Aromatic	Nonpolar	Neutral	−0.9	204.228	1.25	UGG	TRUE	TRUE	FALSE	FALSE	FALSE	FALSE	FALSE
+Tyrosine	Tyr	Y	Aromatic	Brønsted acid	Neutral	−1.3	181.191	2.91	UAY	TRUE	TRUE	FALSE	FALSE	FALSE	FALSE	FALSE
+Valine	Val	V	Aliphatic	Nonpolar	Neutral	4.2	117.148	6.73	GUN	TRUE	FALSE	TRUE	FALSE	FALSE	FALSE	FALSE
+Selenocysteine	Sec	U					168.064									
+Pyrrolysine	Pyl	O					255.313									
+Any/unknown	Xaa	X														
+Asparagine or aspartate	Asx	B														
+Glutamine or glutamate	Glx	Z														
+Leucine or isoleucine	Xle	J														
+END_PROPERTIES

modules/local/eider/aminoacidhistogram/assets/amino_acid_properties.tsv

@@ -0,0 +1,27 @@
+amino_acid	three_letter_symbol	one_letter_symbol	class	chemical_polarity	net_charge	hydropathy_index	molecular_mass	abundance_in_proteins	standard_genetic_coding	hydrophobic	aromatic	aliphatic	small	hydrophilic	positively_charged	negatively_charged
+Alanine	Ala	A	Aliphatic	Nonpolar	Neutral	1.8	89.094	8.76	GCN	FALSE	FALSE	FALSE	TRUE	FALSE	FALSE	FALSE
+Arginine	Arg	R	Fixed cation	Basic polar	Positive	−4.5	174.203	5.78	MGR, CGY	FALSE	FALSE	FALSE	FALSE	TRUE	TRUE	FALSE
+Asparagine	Asn	N	Amide	Polar	Neutral	−3.5	132.119	3.93	AAY	FALSE	FALSE	FALSE	FALSE	TRUE	FALSE	FALSE
+Aspartate	Asp	D	Anion	Brønsted base	Negative	−3.5	133.104	5.49	GAY	FALSE	FALSE	FALSE	FALSE	TRUE	FALSE	TRUE
+Cysteine	Cys	C	Thiol	Brønsted acid	Neutral	2.5	121.154	1.38	UGY	FALSE	FALSE	FALSE	FALSE	FALSE	FALSE	FALSE
+Glutamine	Gln	Q	Amide	Polar	Neutral	−3.5	146.146	3.9	CAR	FALSE	FALSE	FALSE	FALSE	TRUE	FALSE	FALSE
+Glutamate	Glu	E	Anion	Brønsted base	Negative	−3.5	147.131	6.32	GAR	FALSE	FALSE	FALSE	FALSE	TRUE	FALSE	TRUE
+Glycine	Gly	G	Aliphatic	Nonpolar	Neutral	−0.4	75.067	7.03	GGN	FALSE	FALSE	FALSE	TRUE	FALSE	FALSE	FALSE
+Histidine	His	H	Cationic	Brønsted acid and base	Positive, 10% Neutral, 90%	−3.2	155.156	2.26	CAY	FALSE	TRUE	FALSE	FALSE	TRUE	TRUE	FALSE
+Isoleucine	Ile	I	Aliphatic	Nonpolar	Neutral	4.5	131.175	5.49	AUH	TRUE	FALSE	TRUE	FALSE	FALSE	FALSE	FALSE
+Leucine	Leu	L	Aliphatic	Nonpolar	Neutral	3.8	131.175	9.68	YUR, CUY	TRUE	FALSE	TRUE	FALSE	FALSE	FALSE	FALSE
+Lysine	Lys	K	Cation	Brønsted acid	Positive	−3.9	146.189	5.19	AAR	FALSE	FALSE	FALSE	FALSE	TRUE	TRUE	FALSE
+Methionine	Met	M	Thioether	Nonpolar	Neutral	1.9	149.208	2.32	AUG	TRUE	FALSE	TRUE	FALSE	FALSE	FALSE	FALSE
+Phenylalanine	Phe	F	Aromatic	Nonpolar	Neutral	2.8	165.192	3.87	UUY	TRUE	TRUE	FALSE	FALSE	FALSE	FALSE	FALSE
+Proline	Pro	P	Cyclic	Nonpolar	Neutral	−1.6	115.132	5.02	CCN	FALSE	FALSE	FALSE	TRUE	FALSE	FALSE	FALSE
+Serine	Ser	S	Hydroxylic	Polar	Neutral	−0.8	105.093	7.14	UCN, AGY	FALSE	FALSE	FALSE	TRUE	TRUE	FALSE	FALSE
+Threonine	Thr	T	Hydroxylic	Polar	Neutral	−0.7	119.119	5.53	ACN	FALSE	FALSE	FALSE	FALSE	TRUE	FALSE	FALSE
+Tryptophan	Trp	W	Aromatic	Nonpolar	Neutral	−0.9	204.228	1.25	UGG	TRUE	TRUE	FALSE	FALSE	FALSE	FALSE	FALSE
+Tyrosine	Tyr	Y	Aromatic	Brønsted acid	Neutral	−1.3	181.191	2.91	UAY	TRUE	TRUE	FALSE	FALSE	FALSE	FALSE	FALSE
+Valine	Val	V	Aliphatic	Nonpolar	Neutral	4.2	117.148	6.73	GUN	TRUE	FALSE	TRUE	FALSE	FALSE	FALSE	FALSE
+Selenocysteine	Sec	U					168.064									
+Pyrrolysine	Pyl	O					255.313									
+Any/unknown	Xaa	X														
+Asparagine or aspartate	Asx	B														
+Glutamine or glutamate	Glx	Z														
+Leucine or isoleucine	Xle	J														

modules/local/eider/aminoacidhistogram/assets/query_template.sql

@@ -0,0 +1,41 @@
+COPY (
+  WITH p AS (
+    SELECT * FROM read_parquet('${parquet}/*.parquet')
+  ),
+  s AS (
+    SELECT unnest(string_to_array(sequence, '')) AS aa FROM p
+  ),
+  h AS (
+    SELECT unnest(map_entries(histogram(aa))) AS kv FROM s
+  ),
+  e AS (
+    SELECT * from read_csv_auto('${amino_acid_properties}')
+  )
+  SELECT
+    '${prefix}' AS id,
+    h.kv['value'] AS count,
+    e.amino_acid,
+    e.one_letter_symbol,
+    e.three_letter_symbol,
+    e.class,
+    e.chemical_polarity,
+    e.net_charge,
+    e.hydropathy_index,
+    e.molecular_mass,
+    e.abundance_in_proteins,
+    e.standard_genetic_coding,
+    e.hydrophobic,
+    e.aromatic,
+    e.aliphatic,
+    e.small,
+    e.hydrophilic,
+    e.positively_charged,
+    e.negatively_charged
+  FROM
+    h
+  JOIN
+    e
+  ON
+    h.kv['key'] = e.one_letter_symbol
+)
+TO '${prefix}.histogram.tsv' (HEADER, DELIMITER '\t')

modules/local/eider/aminoacidhistogram/environment.yml

@@ -0,0 +1,7 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - bioconda::eider=0.1

modules/local/eider/aminoacidhistogram/main.nf

@@ -0,0 +1,39 @@
+process EIDER_AMINOACIDHISTOGRAM {
+    tag "${meta.id}"
+    label 'process_medium'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/eider:0.1--hdfd78af_0' :
+        'biocontainers/eider:0.1--hdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(parquet)
+
+    output:
+    tuple val(meta), path("*.histogram.tsv"), emit: histogram
+    path "versions.yml"                     , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def amino_acid_properties = file("${moduleDir}/assets/amino_acid_properties.tsv")
+    def query_template = file("${moduleDir}/assets/query_template.sql")
+    """
+    eider \
+        $args \
+        --verbose \
+        --skip-history \
+        --parameters prefix=${prefix} \
+        --parameters amino_acid_properties=${amino_acid_properties} \
+        --query-path ${query_template}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        eider: \$(eider --version 2>&1 | grep -o 'eider .*' | cut -f2 -d ' ')
+    END_VERSIONS
+    """
+}

modules/local/eider/aminoacidhistogram/meta.yml

@@ -0,0 +1,47 @@
+name: eider_aminoacidhistogram
+description: Build amino acid histogram from protein sequences
+keywords:
+  - duckdb
+  - parquet
+  - sql
+  - query
+tools:
+  - eider:
+      description: |
+        Command line bioinformatics tools for DuckDB.
+      homepage: https://github.com/heuermh/eider
+      documentation: https://github.com/heuermh/eider
+      licence: ["Apache-2.0"]
+      identifier: ""
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. [ id:'test', single_end:false ]
+    - parquet:
+        type: directory
+        description: |
+          Directory of protein sequences in Parquet format
+        pattern: "*.parquet"
+output:
+  - histogram:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+      - "*.tsv":
+          type: file
+          description: |
+            Amino acid histogram in tab separated values (TSV) text format
+          pattern: "*.{tsv}"
+  - versions:
+      - versions.yml:
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
+authors:
+  - "@heuermh"
+maintainers:
+  - "@heuermh"