q2-unassigner replacement

.github/workflows/test.yml

@@ -0,0 +1,76 @@
+name: Test
+
+on:
+  push:
+    branches: [ main, master ]
+  pull_request:
+    branches: [ main, master ]
+
+jobs:
+    test:
+        runs-on: ubuntu-latest
+        steps:
+            - uses: actions/checkout@v4
+
+            - name: setup-conda
+              uses: s-weigand/setup-conda@v1.0.7
+              with:
+                # Additional channels like 'conda-forge' which can be used to install packages
+                conda-channels: '' # optional, default is 'defaults conda-forge'
+                # Additional packages which should be installed
+
+            - name: Install dependencies
+              run: |
+                conda create -n qiime2 --file environment.yml
+                conda run -n qiime2 pip install git+https://github.com/PennChopMicrobiomeProgram/dnabc.git
+                git clone https://github.com/Ulthran/q2-unassigner.git
+                cd q2-unassigner
+                conda run -n qiime2 make install
+
+            - name: Write configs
+              run: |
+                echo "cores: 4" > test/config.yaml
+                echo "printshellcmds: True" >> test/config.yaml
+                echo "nolock: True" >> test/config.yaml
+                echo "verbose: True" >> test/config.yaml
+                echo "configfile: ${PWD}/test/qiime2_config.yml" >> test/config.yaml
+
+                echo "all:" > test/qiime2_config.yml
+                echo "    project_dir: ${PWD}/test" >> test/qiime2_config.yml
+                echo "    mux_dir: 'multiplexed_fastq'" >> test/qiime2_config.yml
+                echo "    mapping: 'test_mapping_file.tsv'" >> test/qiime2_config.yml
+                echo "    admin_email: 'userid@email'" >> test/qiime2_config.yml
+                echo "demux:" >> test/qiime2_config.yml
+                echo "    mismatch: 0" >> test/qiime2_config.yml
+                echo "    revcomp: false" >> test/qiime2_config.yml
+                echo "denoise:" >> test/qiime2_config.yml
+                echo "    trim_left_f: 0" >> test/qiime2_config.yml
+                echo "    trunc_len_f: 240" >> test/qiime2_config.yml
+                echo "    trim_left_r: 0" >> test/qiime2_config.yml
+                echo "    trunc_len_r: 240" >> test/qiime2_config.yml
+                echo "taxonomy:" >> test/qiime2_config.yml
+                echo "    classifier_fp: ${PWD}/test/data/test_classifier_species.qza" >> test/qiime2_config.yml
+                echo "diversity:" >> test/qiime2_config.yml
+                echo "    sampling_depth: 100" >> test/qiime2_config.yml
+                echo "unassign:" >> test/qiime2_config.yml
+                echo "    unassigner_species_fp: ${PWD}/test/data/unassigner_species.fasta" >> test/qiime2_config.yml
+                echo "dada2:" >> test/qiime2_config.yml
+                echo "    rscript: ${PWD}/scripts/dada2.R" >> test/qiime2_config.yml
+                echo "    species_training_set: ''" >> test/qiime2_config.yml
+                echo "vsearch:" >> test/qiime2_config.yml
+                echo "    db: ''" >> test/qiime2_config.yml
+                echo "    min_id: 0.97" >> test/qiime2_config.yml
+                echo "    weak_id: 0.97" >> test/qiime2_config.yml
+                echo "    userfields: 'query+target+id2+alnlen+mism+gaps+qilo+qihi+tilo+tihi+qs+ts+qrow+trow'" >> test/qiime2_config.yml
+                echo "    iddef: 2" >> test/qiime2_config.yml
+                echo "    fasta_width: 0" >> test/qiime2_config.yml
+                echo "    maxaccepts: 1" >> test/qiime2_config.yml
+
+                cat test/qiime2_config.yml
+                cat test/config.yaml
+
+            - name: Dryrun
+              run: conda run -n qiime2 snakemake -n --profile test
+
+            - name: Run
+              run: conda run -n qiime2 snakemake --profile test

environment.yml

@@ -4,7 +4,7 @@
 @EXPLICIT
 https://conda.anaconda.org/conda-forge/linux-64/_libgcc_mutex-0.1-conda_forge.tar.bz2
 https://conda.anaconda.org/conda-forge/noarch/_r-mutex-1.0.1-anacondar_1.tar.bz2
-https://conda.anaconda.org/conda-forge/linux-64/ca-certificates-2022.12.7-ha878542_0.conda
+https://conda.anaconda.org/conda-forge/linux-64/ca-certificates-2025.1.31-hbcca054_0.conda
 https://conda.anaconda.org/conda-forge/noarch/font-ttf-dejavu-sans-mono-2.37-hab24e00_0.tar.bz2
 https://conda.anaconda.org/conda-forge/noarch/font-ttf-inconsolata-3.000-h77eed37_0.tar.bz2
 https://conda.anaconda.org/conda-forge/noarch/font-ttf-source-code-pro-2.038-h77eed37_0.tar.bz2
@@ -72,7 +72,7 @@ https://conda.anaconda.org/conda-forge/linux-64/mpg123-1.31.2-hcb278e6_0.conda
 https://conda.anaconda.org/conda-forge/linux-64/ncurses-6.3-h27087fc_1.tar.bz2
 https://conda.anaconda.org/conda-forge/linux-64/nspr-4.35-h27087fc_0.conda
 https://conda.anaconda.org/conda-forge/linux-64/oniguruma-6.9.8-h166bdaf_0.tar.bz2
-https://conda.anaconda.org/conda-forge/linux-64/openssl-1.1.1t-h0b41bf4_0.conda
+https://conda.anaconda.org/conda-forge/linux-64/openssl-1.1.1w-hd590300_0.conda
 https://conda.anaconda.org/conda-forge/linux-64/pcre-8.45-h9c3ff4c_0.tar.bz2
 https://conda.anaconda.org/conda-forge/linux-64/pixman-0.40.0-h36c2ea0_0.tar.bz2
 https://conda.anaconda.org/conda-forge/linux-64/pthread-stubs-0.4-h36c2ea0_1001.tar.bz2
@@ -177,7 +177,7 @@ https://conda.anaconda.org/conda-forge/noarch/backports-1.0-pyhd8ed1ab_3.conda
 https://conda.anaconda.org/conda-forge/linux-64/brotli-1.0.9-h166bdaf_8.tar.bz2
 https://conda.anaconda.org/conda-forge/noarch/cached_property-1.5.2-pyha770c72_1.tar.bz2
 https://conda.anaconda.org/conda-forge/noarch/cachetools-5.3.0-pyhd8ed1ab_0.conda
-https://conda.anaconda.org/conda-forge/noarch/certifi-2022.12.7-pyhd8ed1ab_0.conda
+https://conda.anaconda.org/conda-forge/noarch/certifi-2024.8.30-pyhd8ed1ab_0.conda
 https://conda.anaconda.org/conda-forge/noarch/charset-normalizer-2.1.1-pyhd8ed1ab_0.tar.bz2
 https://conda.anaconda.org/conda-forge/noarch/click-8.1.3-unix_pyhd8ed1ab_2.tar.bz2
 https://conda.anaconda.org/conda-forge/noarch/colorama-0.4.6-pyhd8ed1ab_0.tar.bz2
@@ -310,6 +310,7 @@ https://conda.anaconda.org/conda-forge/noarch/asttokens-2.2.1-pyhd8ed1ab_0.conda
 https://conda.anaconda.org/conda-forge/noarch/backports.functools_lru_cache-1.6.4-pyhd8ed1ab_0.tar.bz2
 https://conda.anaconda.org/conda-forge/noarch/beautifulsoup4-4.11.2-pyha770c72_0.conda
 https://conda.anaconda.org/conda-forge/noarch/bibtexparser-1.4.0-pyhd8ed1ab_0.tar.bz2
+https://conda.anaconda.org/conda-forge/linux-64/biopython-1.83-py38h01eb140_0.conda
 https://conda.anaconda.org/conda-forge/noarch/bleach-6.0.0-pyhd8ed1ab_0.conda
 https://conda.anaconda.org/bioconda/linux-64/bowtie2-2.5.1-py38h77f66f0_0.tar.bz2
 https://conda.anaconda.org/conda-forge/linux-64/cairo-1.16.0-ha61ee94_1014.tar.bz2
@@ -396,6 +397,7 @@ https://conda.anaconda.org/conda-forge/noarch/rich-13.3.1-pyhd8ed1ab_1.conda
 https://conda.anaconda.org/bioconda/linux-64/samtools-1.16.1-h6899075_1.tar.bz2
 https://conda.anaconda.org/conda-forge/linux-64/scikit-learn-0.24.1-py38h658cfdd_0.tar.bz2
 https://conda.anaconda.org/conda-forge/noarch/stack_data-0.6.2-pyhd8ed1ab_0.conda
+https://conda.anaconda.org/bioconda/noarch/unassigner-1.1.0-pyh7e72e81_0.tar.bz2
 https://conda.anaconda.org/bioconda/linux-64/unifrac-binaries-1.1.1-h15a0faf_4.tar.bz2
 https://conda.anaconda.org/conda-forge/noarch/veracitools-0.1.3-py_0.tar.bz2
 https://conda.anaconda.org/conda-forge/noarch/wcwidth-0.2.6-pyhd8ed1ab_0.conda

rules/demux/dnabc.rules

@@ -33,7 +33,7 @@ rule run_dnabc:
             shell("""
             mkdir -p {params.demux_dir}
             touch {output.demux_fastq}
-            dnabc.py \
+            dnabc \
             --revcomp \
             --output-dir {params.demux_dir} \
             --mismatches {params.mismatch} \
@@ -46,7 +46,7 @@ rule run_dnabc:
             shell("""
             mkdir -p {params.demux_dir}
             touch {output.demux_fastq}
-            dnabc.py \
+            dnabc \
             --output-dir {params.demux_dir} \
             --mismatches {params.mismatch} \
             --manifest-file {output.manifest_fp} \

rules/targets/targets.rules

@@ -39,7 +39,5 @@ TARGET_ALL = (
     TARGET_TAXONOMY +
     TARGET_TREE +
     TARGET_DIVERSITY +
-    TARGET_UNASSIGN +
-    TARGET_DADA2SP +
-    TARGET_VSEARCH
+    TARGET_UNASSIGN
 )

rules/unassign/unassign.rules

@@ -1,25 +1,41 @@
+
+
+
+
 rule all_unassign:
     input:
         TARGET_UNASSIGN
 
+
 rule run_unassign:
     input:
-        DENOISE_DIR + "/representative_seq_fasta/dna-sequences.fasta"
+        DENOISE_DIR + "/representative-seqs.qza"
     params:
-        unassigner_species_fp = config["unassign"]["unassigner_species_fp"],
-        outdir = DENOISE_DIR + "/representative_seq_fasta/unassigned"
+        unassigner_species_fp=config["unassign"]["unassigner_species_fp"],
     output:
-        DENOISE_DIR + "/representative_seq_fasta/unassigned/unassigner_output.tsv"
+        DENOISE_DIR + "/representative_seq_fasta/unassigned.qza"
     shell:
         """
         if [[ -f {params.unassigner_species_fp} ]]; then
-            unassign \
-            --type_strain_fasta {params.unassigner_species_fp} \
-            --output_dir {params.outdir} \
-            {input}
+            qiime unassigner unassign \
+            --p-type-strain-fasta {params.unassigner_species_fp} \
+            --o-unassigned {output} \
+            --i-seqs {input}
         else
-            unassign \
-            --output_dir {params.outdir} \
-            {input}
-        fi
+            qiime unassigner unassign \
+            --o-unassigned {output} \
+            --i-seqs {input}
+        fi   
+        """
+
+
+rule export_unassigner:
+    input:
+        DENOISE_DIR + "/representative_seq_fasta/unassigned.qza"
+    output:
+        DENOISE_DIR + "/representative_seq_fasta/unassigned/unassigner_output.tsv"
+    shell:
         """
+        qiime tools export \
+        --input-path {input} \
+        --output-path $(dirname {output})    """

test/config.yaml

@@ -0,0 +1,5 @@
+cores: 4
+printshellcmds: True
+nolock: True
+verbose: True
+configfile: "test/qiime2_config.yml"

test/qiime2_config.yml

@@ -0,0 +1,46 @@
+all:
+    project_dir: "/home/ctbus/Penn/16S_QIIME2/test"
+    mux_dir: "multiplexed_fastq"
+    mapping: "test_mapping_file.tsv"
+    admin_email: "userid@email"
+
+#try revcomp if you are getting 0 reads when demultiplexing
+demux:
+    mismatch: 0
+    revcomp: false
+
+#~240 for V1V2, ~280 for V3V4
+denoise:
+    trim_left_f: 0
+    trunc_len_f: 240
+    trim_left_r: 0
+    trunc_len_r: 240
+#threads are now specificed in config.yaml
+
+taxonomy:
+    classifier_fp: "/home/ctbus/Penn/16S_QIIME2/test/data/test_classifier_species.qza"
+
+diversity:
+    sampling_depth: 100
+#100 is just for testing, recommend change to 1000
+
+unassign:
+    unassigner_species_fp: "/home/ctbus/Penn/16S_QIIME2/test/data/unassigner_species.fasta"
+
+dada2:
+    rscript: "/mnt/isilon/microbiome/analysis/biodata/dada2/dada2.R"
+    species_training_set: "/mnt/isilon/microbiome/analysis/biodata/dada2/rdp_species_assignment_18.fa.gz"
+    #if you want to use SILVA:
+    #species_training_set: "/mnt/isilon/microbiome/analysis/biodata/dada2/silva_species_assignment_v138.1.fa.gz"
+
+vsearch:
+    db: "/mnt/isilon/microbiome/analysis/biodata/green_genes/current_gg16S.fasta"
+    min_id: 0.97 #minimum identity for query-target match
+    weak_id: 0.97 #set lower than min-id and you will get some weaker matches too
+    userfields: "query+target+id2+alnlen+mism+gaps+qilo+qihi+tilo+tihi+qs+ts+qrow+trow" #fields for results file, see vsearch documentation for details
+    iddef: 2 #the way "identity" is calculated, see vsearch docs for details (it's equal to (matching columns) / (alignment length) excluding terminal gaps)
+    fasta_width: 0 #Width of alignment lines in fasta output, set to 0 to eliminate wrapping
+    maxaccepts: 1 #Maximum number of hits to accept before stopping the search Default is 1
+
+# picrust:
+#     threads: 8