edentity 1.4.3__py3-none-any.whl

edentity/__main__.py

@@ -0,0 +1,114 @@
+# identity/__main__.py
+from importlib.resources import files
+import argparse
+import subprocess
+from pathlib import Path
+from edentity.utils.configs import dump_config, dump_multiqc_config, dump_profile_config
+import os
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="eDentity Metabarcoding Pipeline",
+    )
+
+    # Project-specific
+    parser.add_argument("--raw_data_dir", help="Path to the raw input data directory", required=True, )
+    parser.add_argument("--work_dir", required=True, help="Working directory for outputs and temporary files")
+    parser.add_argument("--profile", help="Snakemake profile to use (e.g., 'slurm', 'galaxy', 'default')",
+                        default=None)
+    parser.add_argument("--make_json_reports", help="Generate an extended JSON report (default: False)", action="store_true")
+    
+    # if params are given through config file
+    parser.add_argument("--config_file", help="Path to the config file", default = None)
+    
+    # Fastp params
+    parser.add_argument("--average_qual", help="Minimum average quality score (default: 25)", default=25)
+    parser.add_argument("--length_required", help="Minimum read length after trimming (default: 100)", default=100)
+    parser.add_argument("--n_base_limit", help="Max N bases allowed per read (default: 0)", default=0)
+
+    # PE merging
+    parser.add_argument("--maxdiffpct", help="Max percentage difference in overlaps (default: 100)", default=100)
+    parser.add_argument("--maxdiffs", help="Max differences in overlap (default: 5)", default=5)
+    parser.add_argument("--minovlen", help="Minimum overlap length (default: 10)", default=10)
+
+    # Primer trimming
+    parser.add_argument("--forward_primer", help="Forward primer sequence", required=True)
+    parser.add_argument("--reverse_primer", help="Reverse primer sequence", required=True)
+    parser.add_argument("--anchoring", action="store_true", help="Use anchoring for primer matching")
+    parser.add_argument("--discard_untrimmed", action="store_true", help="Discard reads without primer match")
+
+    # Quality filtering
+    parser.add_argument("--min_length", help="Minimum read length after filtering (default: 100)", default=100)
+    parser.add_argument("--max_length", help="Maximum read length after filtering (default: 600)", default=600)
+    parser.add_argument("--maxEE", help="Maximum expected errors (default: 1)", default=1)
+
+    # Dereplication
+    parser.add_argument("--fasta_width", help="FASTA output line width (default: 0 for single-line)", default=0)
+
+    # Denoising
+    parser.add_argument("--alpha", help="Alpha value for chimera detection (default: 2)", default=2)
+    parser.add_argument("--minsize", help="Minimum size to retain sequences (default: 4)", default=4)
+
+    # Pipeline settings
+    parser.add_argument("--dataType", choices=["Illumina", "AVITI"], help="Sequencing data type", default="Illumina")
+    parser.add_argument("--cpu_cores", help="Number of CPU cores to use (default: 10)", default=12)
+    parser.add_argument("--log_level", help="Logging level (default: INFO)", default="INFO")
+
+    # Fixed paths
+    parser.add_argument("--license_file", help="Path to LICENSE file (default: LICENSE)", default="LICENSE")
+    parser.add_argument("--changelog_file", help="Path to CHANGELOG file (default: CHANGELOG)", default="CHANGELOG")
+    parser.add_argument("--conda", help="Path to conda env YAML for main tools (default: envs/vsearch.yaml)")
+    parser.add_argument("--bbtoolsConda", help="Path to conda env YAML for BBTools (default: envs/bbtools.yml)")
+
+    # snakemkae extra options
+    parser.add_argument("--dry-run", action="store_true", help="Dry run mode (equivalent to -n in snakemake)")
+
+    # add common snakemake options e.g -n, -cores e.t.c
+
+    config = vars(parser.parse_args())
+    
+    
+    # writeout a temp config file.
+    # the confile file has params from both the default config and the command line args
+    # pass this config file to snakemake
+  
+    # dump temp profile config
+    work_dir = Path(config['work_dir'])
+    profile_dir = work_dir / "edentity_pipeline_settings" / f"{os.path.basename(work_dir)}_snakemake_profile"
+    profile_dir.mkdir(parents=True, exist_ok=True)
+    profile_path = profile_dir / "config.yaml"
+    dump_profile_config(profile_path)
+    profile_path = profile_path.resolve()
+
+    # dump snakemake config file (if the user provides a config file, it will be used to override the default params)
+    work_dir.mkdir(parents=True, exist_ok=True)
+    snakemake_config_path = work_dir /"edentity_pipeline_settings" / f"{os.path.basename(work_dir)}_snakemake_config.yml"
+    dump_config(config, snakemake_config_path)
+    snakemake_config_path = snakemake_config_path.resolve()
+
+    # create temp multiqc config.
+    multiqc_config_dir = work_dir / "edentity_pipeline_settings" / "multiqc_config"
+    multiqc_config_dir.mkdir(parents=True, exist_ok=True)
+    multiqc_config_path = multiqc_config_dir / "config.yaml"
+    dump_multiqc_config(multiqc_config_path)
+    multiqc_config_path = multiqc_config_path.resolve()
+    
+
+    # prepare the command to run snakemake
+    cmd = [
+        "snakemake",
+        "--snakefile", str(files("edentity").joinpath("workflow/Snakefile").resolve()),
+        "--workflow-profile", profile_dir if config['profile'] is None else os.path.abspath(config['profile']),
+        "--configfile", snakemake_config_path if config['config_file'] is None else os.path.abspath(config['config_file']),
+    ]
+    
+    # add snakemake extra options
+    if config['dry_run']:
+        cmd.append("--dry-run")
+
+    # run snakemake 
+    subprocess.run(cmd, check=True)
+
+if __name__ == "__main__":
+    main()

edentity/_version.py

@@ -0,0 +1,21 @@
+# file generated by setuptools-scm
+# don't change, don't track in version control
+
+__all__ = ["__version__", "__version_tuple__", "version", "version_tuple"]
+
+TYPE_CHECKING = False
+if TYPE_CHECKING:
+    from typing import Tuple
+    from typing import Union
+
+    VERSION_TUPLE = Tuple[Union[int, str], ...]
+else:
+    VERSION_TUPLE = object
+
+version: str
+__version__: str
+__version_tuple__: VERSION_TUPLE
+version_tuple: VERSION_TUPLE
+
+__version__ = version = '1.4.3'
+__version_tuple__ = version_tuple = (1, 4, 3)

edentity/configs/multiQC_config.yaml

@@ -0,0 +1,43 @@
+# # This configuration file is used to control the behavior of the MultiQC report
+skip_generalstats: true
+show_analysis_paths: false
+fn_clean_exts:
+  - ".gz"
+  - ".fastq"
+  - "_R1"
+  - "_R2"
+  - "_merged"
+# # General formatting settings for numbers
+# formatting:
+#   numbers:
+#     human_readable: false  # Ensure all numbers are human-readable (e.g., 1M, 1K)
+
+# handle custom data
+custom_data:
+  edentity_summary:
+    file_format: 'tsv'
+    section_name: 'eDentity Pipeline Summary'
+    plot_type: 'table'
+
+# Update module order to include custom_content
+module_order:
+  - edentity_summary
+  - fastp
+  - cutadapt
+  # - custom_content
+
+# Configure table display
+table_columns_visible:
+  edentity_summary:
+    Sample: true
+    read_pairs: true
+    merged_percent: true
+    primer_trimmed_reads: true
+    passed_quality_filtering: true
+    dereplicated_reads: true
+    reads_passed_denoising: true
+    n_esv: true
+    # chimeric_reads: false
+    # borderline_reads: false 
+    
+    

edentity/configs/params.yml

@@ -0,0 +1,46 @@
+
+#project specific
+raw_data_dir: 
+work_dir: 
+make_json_reports: False
+
+# tool params
+
+# Fastp params (general quality control)
+average_qual: 25
+length_required: 100
+n_base_limit: 0
+# 3_PE_merging (these are set to vsearch default values)
+maxdiffpct: 100
+maxdiffs: 10
+minovlen: 10
+
+#4_primer_trimming
+forward_primer: 
+reverse_primer: 
+anchoring: False
+discard_untrimmed: True
+
+#5_quality_filtering (vsearch)
+min_length: 100
+max_length: 600
+maxEE: 1
+# dereplication params
+fasta_width: 0
+# 6_denoising (set to default vsearch values)
+alpha: 2
+minsize: 4
+
+
+#DO not change this ones :)
+conda: "../envs/vsearch.yaml" # strict channel can cause conda creation errors: disable this with: conda config --set channel_priority disabled
+bbtoolsConda: "../envs/bbtools.yml"
+
+# Pipeline settings
+dataType: "Illumina" # [Illumina, AVITI], one of the two
+
+# nbitk settings
+license_file: LICENSE
+changelog_file: CHANGELOG
+cpu_cores: 20
+log_level: INFO

edentity/resources/schemas/config_schema.yaml

@@ -0,0 +1,99 @@
+$schema: "https://json-schema.org/draft/2020-12/schema"
+description: Configuration of apscale tool settings
+properties:  
+  raw_data_dir: 
+    type: string
+    description: Path to the raw data directory, raw  fastq file are expected in this directory
+  
+  dataType:
+    type: string
+    description: "Type of data, either Illumina or AVITI"
+    enum:
+      - Illumina
+      - AVITI
+    default: "Illumina"
+  
+  work_dir:
+    type: string
+    description: Path to the project directory; this will be set as results directory
+    
+
+# 3_PE_merging (these are set to vsearch default values)
+  maxdiffpct:
+    type: integer
+    description: "maximum percentage diff. bases in overlap; default is 100"
+    default: 100
+
+  maxdiffs:
+    type: integer
+    description: "maximum number of different bases in overlap; default is 10"
+    default: 10
+
+  minovlen:
+    type: integer
+    description: "minimum length of overlap between reads, default is 10"
+    default: 10
+
+# 4_primer_trimming
+
+  forward_primer:
+    type: string
+    description: "Sequence of the forward primer"
+  
+  reverse_primer:
+    type: string
+    description: "Sequence of the reverse primer"
+
+  anchoring:
+    type: boolean
+    description: "the primer is only found if it is a suffix/prefix of the read"
+    default: False
+
+# 5_quality_filtering
+
+  min_length:
+    type: integer
+    description: "discard if length of sequence is shorter than min_length"
+    default: 100
+
+  max_length:
+    type: integer
+    description: "discard if length of sequence is longer than max_length"
+    default: 600
+
+  maxEE:
+    type: integer
+    description: "maximum expected error value for merged sequence"
+    default: 1
+
+ # 6_denoising (set to default vsearch values)
+
+  alpha:
+    type: integer
+    description: "cluster unoise alpha parameter"
+    default: 2
+
+  minsize:
+    type: integer
+    description: "minimum abundance; drop ESVs if they are less than minsize"
+    default: 5
+
+# 0_general_settings
+  
+  cores:
+    type: integer
+    description: "Cores used for parallelism in apscale"
+    default: 4
+
+  compression_level:
+    type: integer
+    description: "gzip compression level"
+    default: 6
+
+
+required:
+  - raw_data_dir
+  - work_dir
+  - forward_primer
+  - reverse_primer
+  

edentity/utils/configs.py

@@ -0,0 +1,75 @@
+import yaml
+
+def load_config(confile_path):
+    with open(confile_path, "r") as f:
+        return yaml.safe_load(f)
+
+# dump dicts to yaml at a given path
+def dump_config(config, path):
+    with open(path, "w") as f:
+        yaml.dump(config, f, sort_keys=False, default_flow_style=False)
+    
+
+# extratct the config file from the package
+def extract_package_yaml(package_file_path, target_path):
+    # config_path = files("edentity").joinpath("workflow/profiles/default/config.yaml")
+    with open(target_path, "w") as f:
+            f.write(package_file_path.read_text())
+
+
+def get_multiqc_config():
+    return {
+        "skip_generalstats": True,
+        "show_analysis_paths": False,
+        "fn_clean_exts": [
+            ".gz",
+            ".fastq",
+            "_R1",
+            "_R2",
+            "_merged"
+        ],
+        "custom_data": {
+            "edentity_summary": {
+                "file_format": "tsv",
+                "section_name": "eDentity Pipeline Summary",
+                "plot_type": "table"
+            }
+        },
+        "module_order": [
+            "edentity_summary",
+            "fastp",
+            "cutadapt"
+        ],
+        "table_columns_visible": {
+            "edentity_summary": {
+                "Sample": True,
+                "read_pairs": True,
+                "merged_percent": True,
+                "primer_trimmed_reads": True,
+                "passed_quality_filtering": True,
+                "dereplicated_reads": True,
+                "reads_passed_denoising": True,
+                "n_esv": True
+            }
+        }
+    }
+
+def get_default_profile():
+    return {
+        "jobs": "30",
+        "latency-wait": "30",
+        "use-conda": "False",
+        "printshellcmds": "True",
+        "rerun-incomplete": "True",
+        "keep-incomplete": "True",
+        
+    }
+
+def dump_multiqc_config(target_path):
+    default_config = get_multiqc_config()
+    dump_config(default_config, target_path)
+
+
+def dump_profile_config(target_path): # this should be flexible to handle different profiles, e.g slurm, galaxy, default.
+    default_profile = get_default_profile()
+    dump_config(default_profile, target_path)

edentity/workflow/Dockerfile

@@ -0,0 +1,30 @@
+FROM condaforge/mambaforge:latest
+
+# Step 2: Retrieve conda environments
+
+# Conda environment:
+#   source: workflow/envs/vsearch.yaml
+#   prefix: /conda-envs/163dd44b50c96433c482eacfda446195
+#   priority: strict
+#   name: vsearch
+#   channels:
+#     - conda-forge
+#     - bioconda
+#     - nodefaults
+#   dependencies:
+#     - vsearch=2.28.1
+#     - pip
+#     - biopython=1.84
+#     - multiqc
+#     - fastp
+#     - cutadapt=4.9
+#     - pip:
+#       - nbitk==0.3.2
+#       
+RUN mkdir -p /conda-envs/163dd44b50c96433c482eacfda446195
+COPY workflow/envs/vsearch.yaml /conda-envs/163dd44b50c96433c482eacfda446195/environment.yaml
+
+# Step 3: Generate conda environments
+
+RUN conda env create --prefix /conda-envs/163dd44b50c96433c482eacfda446195 --file /conda-envs/163dd44b50c96433c482eacfda446195/environment.yaml && \
+    conda clean --all -y

edentity/workflow/Snakefile

@@ -0,0 +1,120 @@
+from snakemake.logging import logger
+from snakemake.utils import validate, min_version, update_config
+import re, yaml, json, pandas as pd
+import glob, os
+from datetime import datetime
+import numpy as np
+import shutil
+import sys
+import secrets
+min_version("8.16.0") # declare the the lowest version of snakemake that can run this script
+
+# configfile: "configs/params.yml"
+
+
+# validate the parameter settings
+# validate(config, "../resources/schemas/config_schema.yaml")
+
+
+# docker [image]
+container: "docker://condaforge/mambaforge:latest"
+"""
+Organize fastq file names to fit the expected naming format
+the idea is to make a copy of the fastq files to a new folder with the expected naming format
+this will be removed on the sucess of the pipeline
+"""
+GZ =  True  # will be set to True if the fastq files are gzipped
+fastq_files = os.path.join(config['work_dir'], "input_fastq_files")
+os.makedirs(fastq_files, exist_ok=True)
+for file in os.listdir(config['raw_data_dir']):    
+    if ".fastq" not in file:
+        logger.error(f"{file} is not a valid fastq file: skipping")
+        continue
+    base_name, extension = re.split(r'_R[12]', file)
+    
+    # detect if the file is gzipped 
+    GZ = True if file.endswith(".gz") else False
+
+    if "R1" in file:
+        new_file_name = f"{base_name}{extension.split('.fastq')[0]}_R1.fastq.gz"  if GZ else f"{base_name}{extension.split('.fastq')[0]}_R1.fastq"      
+        # copy file if it doesn't already exist
+        if not os.path.islink(os.path.abspath(os.path.join(fastq_files, new_file_name))) or not os.path.isfile(os.path.abspath(os.path.join(fastq_files, new_file_name))):
+            os.symlink(os.path.abspath(os.path.join(config['raw_data_dir'], file)), os.path.abspath(os.path.join(fastq_files, new_file_name)))
+    elif "R2" in file:
+        new_file_name = f"{base_name}{extension.split('.fastq')[0]}_R2.fastq.gz" if GZ else f"{base_name}{extension.split('.fastq')[0]}_R2.fastq"
+        if not os.path.islink(os.path.abspath(os.path.join(fastq_files, new_file_name))):           
+            os.symlink(os.path.abspath(os.path.join(config['raw_data_dir'], file)), os.path.abspath(os.path.join(fastq_files, new_file_name)))
+    else:
+        logger.error(f"Missing file(s) for sample {base_name}: {r1_path} or {r2_path}")
+
+"""
+Loop through each sample in the SAMPLES list.
+For each sample, determine the base name by removing the "_R1" or "_R2" suffix if present.
+Construct the file paths for the R1 and R2 fastq.gz files using the base name.
+Check if both R1 and R2 files exist in the specified raw data directory.
+If both files exist, append the base name to the SAMPLE_NAMES list.
+If either file is missing, log an error message indicating the missing file(s) for the sample.
+
+"""
+SAMPLES,  EXTENSION = glob_wildcards(os.path.join(fastq_files, '{sample}_{extension}'))
+SAMPLE_NAMES = []
+
+for sample in SAMPLES:
+    base_name = "_".join(sample.split("_")[:-1]) if sample.endswith(("_R1", "_R2")) else sample
+    r1_path = os.path.join(fastq_files, f'{base_name}_R1.fastq.gz') if GZ else os.path.join(fastq_files, f'{base_name}_R1.fastq')
+    r2_path = os.path.join(fastq_files, f'{base_name}_R2.fastq.gz') if GZ else os.path.join(fastq_files, f'{base_name}_R2.fastq')
+    
+    if (os.path.isfile(r1_path) or os.path.islink(r1_path)) and (os.path.isfile(r2_path) or os.path.islink(r2_path)) is True:
+        SAMPLE_NAMES.append(base_name)
+    else:
+        logger.error(f"Missing file(s) for sample {base_name}: {r1_path} or {r2_path}")
+
+onstart:
+    print("Starting the pipeline")
+    update_config(config,
+        { "runID": f"MBR_{secrets.token_hex(8)}",
+        "start_time": datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
+        "snakemake_version": snakemake.__version__,
+        "command_line_args": sys.argv})  
+# flow of execution
+ruleorder: merge > trimming > filter > dereplication > denoise > removeChimera > searchExact 
+
+rule all:           
+    input:
+        # Exact sequence search (this is where the magic of making ESVs happen)
+        expand(os.path.join(config["work_dir"], "Results", "ESV_tables",f'{{sample}}_ESV_table.tsv'), sample=SAMPLE_NAMES),  
+
+        # MultiQC report
+        os.path.join(config["work_dir"], "Results", "report",
+            f"{os.path.basename(config['work_dir'])}_multiqc_reports",
+            f"{os.path.basename(config['work_dir'])}_multiqc_report.html"), 
+        # custom multiqc data
+        os.path.join(config["work_dir"], "Results", "report",
+        f"{os.path.basename(config['work_dir'])}_custom_multiqc_data_mqc.txt"),     
+        
+        # ESV table
+        os.path.join(config["work_dir"], "Results",
+            "report", f"{os.path.basename(config['work_dir'])}_ESV_table.tsv"),
+        
+
+        # summary report
+        os.path.join(config["work_dir"], "Results",
+            "report", f"{os.path.basename(config['work_dir'])}_summary_report.tsv")
+
+onsuccess:
+    # remove the copy of fastq files (to reduce memory footprint)
+    # this currently is a symlink; thus no memory is used; still, it is a good idea to remove it
+    shutil.rmtree(fastq_files)
+    # remove sample ESV tables
+    ESV_tables = os.path.join(config["work_dir"], "Results", "ESV_tables")
+    if os.path.exists(ESV_tables):
+        logger.info(f"Removing ESV tables directory: {ESV_tables}") 
+        shutil.rmtree(os.path.join(config["work_dir"], "Results", "ESV_tables"))
+
+include: "rules/merge.smk"
+include: "rules/trimming.smk"
+include: "rules/filter.smk"
+include: "rules/dereplication.smk"
+include: "rules/denoise.smk"
+include: "rules/chimera.smk"
+include: "rules/search_exact.smk"

edentity/workflow/profiles/default/config.yaml

@@ -0,0 +1,14 @@
+jobs: "30"
+max-jobs-per-second: "10"
+max-status-checks-per-second: "10"
+local-cores: 10
+latency-wait: "30"
+use-conda: "False"
+printshellcmds: "True"
+rerun-incomplete: "False"
+keep-incomplete: "True"
+
+default-resources:
+  - runtime=100
+  - mem_mb=6000
+  - disk_mb=1000000

edentity/workflow/profiles/galaxy/config.yaml

@@ -0,0 +1,14 @@
+jobs: "30"
+max-jobs-per-second: "10"
+max-status-checks-per-second: "10"
+local-cores: 44
+latency-wait: "30"
+# use-conda: "True"
+printshellcmds: "True"
+rerun-incomplete: "False"
+keep-incomplete: "True"
+
+# default-resources:
+#   - runtime=100
+#   - mem_mb=6000
+#   - disk_mb=1000000

edentity/workflow/profiles/slurm/config.yaml

@@ -0,0 +1,15 @@
+executor: "slurm"
+jobs: "30"
+max-jobs-per-second: "10"
+max-status-checks-per-second: "10"
+local-cores: 44
+latency-wait: "30"
+use-conda: "True"
+printshellcmds: "True"
+rerun-incomplete: "False"
+keep-incomplete: "True"
+
+default-resources:
+  - runtime=100
+  - mem_mb=6000
+  - disk_mb=1000000

edentity/workflow/rules/chimera.smk

@@ -0,0 +1,14 @@
+import os
+
+rule removeChimera:
+    input:        
+        denoised = os.path.join(config["work_dir"], "Results", "denoise", f'{{sample}}_merged_trimmed_filtered_derep_denoised.fasta'),
+        denoise_report = os.path.join(config["work_dir"], "Results", "report", f'{{sample}}_denoise_report.tsv')
+    output:
+        ESV_fasta = os.path.join(config["work_dir"],  "Results", "ESVs_fasta", f'{{sample}}_ESV.fasta'),
+        summary_report = temp(os.path.join(config["work_dir"], "Results", "report", f'{{sample}}_remove_chimera_report.tsv'))
+    log:
+        log = os.path.join(config["work_dir"], "logs", "chimera", f'{{sample}}_chimera.log')
+    conda: config['conda']
+    script:
+        "../scripts/chimera.py"

edentity/workflow/rules/denoise.smk

@@ -0,0 +1,15 @@
+import os
+
+rule denoise:
+    input:        
+        derep = os.path.join(config["work_dir"], "Results", "dereplication",  f'{{sample}}_merged_trimmed_filtered_derep.fasta'),
+        derep_report = os.path.join(config["work_dir"], "Results", "report", f'{{sample}}_derep_report.tsv')        
+    output:
+        denoised = temp(os.path.join(config["work_dir"], "Results", "denoise", f'{{sample}}_merged_trimmed_filtered_derep_denoised.fasta')),
+        summary_report = temp(os.path.join(config["work_dir"], "Results", "report", f'{{sample}}_denoise_report.tsv'))
+
+    log:
+        log = os.path.join(config["work_dir"], "logs", "denoise",  f'{{sample}}_denoising.log')
+    conda: config['conda']
+    script:
+        "../scripts/denoise.py"

edentity/workflow/rules/dereplication.smk

@@ -0,0 +1,14 @@
+import os
+
+rule dereplication:
+    input:        
+        filtered = os.path.join(config["work_dir"],  "Results", "filter", f'{{sample}}_merged_trimmed_filtered.fasta'), 
+        filter_report = os.path.join(config["work_dir"], "Results", "report", f'{{sample}}_filter_report.tsv')       
+    output:
+        derep = temp(os.path.join(config["work_dir"], "Results", "dereplication",  f'{{sample}}_merged_trimmed_filtered_derep.fasta')),
+        summary_report = temp(os.path.join(config["work_dir"], "Results", "report", f'{{sample}}_derep_report.tsv'))
+    log:
+        log = os.path.join(config["work_dir"], "logs", "dereplication",  f'{{sample}}_dereplication.log')
+    conda: config['conda']
+    script:
+        "../scripts/dereplication.py"

edentity/workflow/rules/filter.smk

@@ -0,0 +1,14 @@
+import os
+
+rule filter:
+    input:
+        trimmed = os.path.join(config["work_dir"], "Results","trimming", "trimmed_seqs", f'{{sample}}_merged_trimmed.fastq'), 
+        trimming_report = os.path.join(config["work_dir"], "Results", "report", f'{{sample}}_trimming_report.tsv')       
+    output:
+        filtered = temp(os.path.join(config["work_dir"],  "Results", "filter", f'{{sample}}_merged_trimmed_filtered.fasta')),
+        summary_report = temp(os.path.join(config["work_dir"], "Results", "report", f'{{sample}}_filter_report.tsv'))
+    log:
+        log = os.path.join(config["work_dir"], "logs", "filter",  f'{{sample}}_filter.log')
+    conda: config['conda']
+    script:
+        "../scripts/filter.py"