Changes for new wepp flow

Author: pgangwar-ucsd

README.md

@@ -79,9 +79,22 @@ All set to try the [examples](#example).
 ```
 git clone https://github.com/TurakhiaLab/metaWEPP.git
 cd metaWEPP
+chmod +x run-metawepp
 ```
 
-**Step 2:** Install Kraken.
+**Step 2:** Update `~/.bashrc` for linux or `~/.zshrc` for macOS.
+```
+echo "
+run-metawepp() {
+    snakemake -s $PWD/Snakefile \"\$@\"
+}
+export -f run-metawepp
+" >> ~/.bashrc
+
+source ~/.bashrc
+```
+
+**Step 3:** Install Kraken.
 The following commands install kraken and also update the `$PATH` variable for running the tool easily.
 ```
 git clone https://github.com/DerrickWood/kraken2.git
@@ -98,10 +111,12 @@ cd ..
 sudo apt-get install minimap2
 pip install viral_usher matplotlib snakemake
 ```
-**Step 4:** Install `WEPP`.
+**Step 5:** Install `WEPP`.
 
 ```
 git clone --recurse-submodules https://github.com/TurakhiaLab/WEPP.git
+cd WEPP
+chmod +x run-wepp
 ```
 View the WEPP installation guide starting from Option 3 in the [WEPP repository](https://github.com/TurakhiaLab/WEPP/tree/main?tab=readme-ov-file#-option-3-install-via-shell-commands-requires-sudo-access).
 
@@ -130,7 +145,7 @@ rm k2_viral_20251015.tar.gz
 Follow the command prompts to add the pathogens.
 
 ```
-snakemake --config KRAKEN_DB=viral_kraken_db DIR=simulated_metagenomic_sample MIN_PROP=0.05 PATHOGENS=default,respiratory_syncytial_virus_a,sars_cov_2 CLADE_LIST=,nextstrain,nextstrain:pango CLADE_IDX=-1,0,1 --cores 32
+run-metawepp --config KRAKEN_DB=viral_kraken_db DIR=simulated_metagenomic_sample MIN_PROP=0.05 PATHOGENS=default,respiratory_syncytial_virus_a,sars_cov_2 CLADE_LIST=,nextstrain,nextstrain:pango CLADE_IDX=-1,0,1 --cores 32
 ```
 
 For SARS-CoV-2:
@@ -215,7 +230,7 @@ rm k2_viral_20251015.tar.gz
 
 **Step 6:** Run the pipeline 
 ```
-snakemake --config KRAKEN_DB=viral_kraken_db DIR=real_metagenomic_sample MIN_PROP=0.05 PATHOGENS=default,respiratory_syncytial_virus_a CLADE_LIST=,nextstrain CLADE_IDX=-1,0 --cores 32
+run-metawepp --config KRAKEN_DB=viral_kraken_db DIR=real_metagenomic_sample MIN_PROP=0.05 PATHOGENS=default,respiratory_syncytial_virus_a CLADE_LIST=,nextstrain CLADE_IDX=-1,0 --cores 32
 ```
 
 On being prompted to add a new species for haplotype-level analysis, press `y`, and follow the steps below for RSV-A and Rhinovirus-A.
@@ -382,12 +397,12 @@ metaWEPP requires `KRAKEN_DB` and `DIR` to be specified as command-line argument
 Examples:
 1. Using all the parameters from the config file:
 ```
-snakemake --config KRAKEN_DB=viral_kraken_db DIR=simulated_metagenomic_sample --cores 32
+run-metawepp --config KRAKEN_DB=viral_kraken_db DIR=simulated_metagenomic_sample --cores 32
 ```
 
 2. Overriding MIN_Q and MIN_PROP_FOR_WEPP through command line:
 ```
-snakemake --config KRAKEN_DB=viral_kraken_db DIR=simulated_metagenomic_sample MIN_Q=25 MIN_PROP_FOR_WEPP=0.05 --cores 32
+run-metawepp --config KRAKEN_DB=viral_kraken_db DIR=simulated_metagenomic_sample MIN_Q=25 MIN_PROP_FOR_WEPP=0.05 --cores 32
 ```
 
 ### <a name="mat"> MAT for pathogen species

Snakefile

@@ -31,7 +31,7 @@ for arg in sys.argv[1:]:
 # 2. DEFINE PATHS FOR INTERNAL RESOURCES
 # ────────────────────────────────────────────────────────────────
 
-RUNNING_TEST  = "test" in requested_rules
+RUNNING_HELP  = "help" in requested_rules
 
 PATHOGEN_ROOT = Path("data/pathogens_for_wepp")
 ADDED_TAXONS  = PATHOGEN_ROOT / "added_taxons.csv"
@@ -47,7 +47,7 @@ if wepp_conda_path.exists():
     WEPP_DATA.mkdir(parents=True, exist_ok=True)
 else:
     WEPP_ROOT = WEPP_DATA
-    if not WEPP_ROOT.exists() and not RUNNING_TEST:
+    if not WEPP_ROOT.exists() and not RUNNING_HELP:
         print(f"Error: WEPP not installed at {WEPP_ROOT}", file=sys.stderr)
         sys.exit(1)
 
@@ -118,7 +118,7 @@ def check_input_files():
         fq2 = str(gzip_if_needed(r2_files[0]))
     return fq1, fq2
 
-if not RUNNING_TEST:
+if not RUNNING_HELP:
     FQ1, FQ2 = check_input_files()
 
 # ────────────────────────────────────────────────────────────────
@@ -381,8 +381,10 @@ rule prepare_for_wepp:
                 taxonium_files = list(dest_dir.glob("*.jsonl")) + list(dest_dir.glob("*.jsonl.gz"))
                 taxonium_arg = f"TAXONIUM_FILE={taxonium_files[0].name} " if taxonium_files else ""
 
+                wepp_executable = WEPP_ROOT / "run-wepp"
+                
                 cmd = (
-                    f"snakemake "
+                    f"{wepp_executable} "
                     f"-s {WEPP_SNAKEFILE} "
                     f"--directory {WEPP_DATA} "
                     f"--cores {workflow.cores} --use-conda "
@@ -407,10 +409,11 @@ rule run_wepp:
     output:
         "results/{DIR}/.wepp.done"
     run:
+
         for line in open(input[0]):
             cmd = line.strip()
             if cmd:
-                subprocess.check_call(cmd, shell=True)
+                subprocess.check_call(cmd, shell=True, executable="/bin/bash")
         Path(output[0]).touch()
 
 rule print_dashboard_instructions:
@@ -433,7 +436,7 @@ rule print_dashboard_instructions:
 
         Path(output[0]).touch()
 
-rule test:
+rule help:
     message: "Printing metaWEPP configuration help"
     params:
         script = BASE_DIR / "scripts/metawepp_help.py"

docker/Dockerfile

@@ -12,6 +12,8 @@ RUN apt-get update && apt-get install -y \
     sudo \
     pip \
     build-essential \
+    libopenmpi-dev \
+    libboost-all-dev \
     python3-pandas \
     pkg-config \
     zip \
@@ -58,6 +60,16 @@ RUN git clone https://github.com/DerrickWood/kraken2.git && \
     ./install_kraken2.sh . && \
     echo 'export PATH="/metaWEPP/kraken2:$PATH"' >> /root/.bashrc
 
+# Setting aliases for running WEPP and metaWEPP
+RUN echo 'run-wepp() {' >> /root/.bashrc && \
+    echo '    /root/miniforge3/bin/snakemake -s /metaWEPP/WEPP/workflow/Snakefile "$@"' >> /root/.bashrc && \
+    echo '}' >> /root/.bashrc && \
+    echo 'export -f run-wepp' >> /root/.bashrc
+
+RUN echo 'run-metawepp() {' >> /root/.bashrc && \
+    echo '    /root/miniforge3/bin/snakemake -s /metaWEPP/Snakefile "$@"' >> /root/.bashrc && \
+    echo '}' >> /root/.bashrc && \
+    echo 'export -f run-metawepp' >> /root/.bashrc
 
 # Default command: start an interactive login shell to source ~/.bashrc
 CMD [ "bash", "--login" ]

run-metawepp

@@ -0,0 +1,5 @@
+#!/bin/bash
+
+REPO_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+
+exec snakemake -s "$REPO_ROOT/workflow/Snakefile" "$@"

scripts/metawepp_help.py

@@ -10,44 +10,21 @@
 OPTIONS = [
     ("DIR", "Folder containing the metagenomic reads."),
     ("KRAKEN_DB", "Folder containing the Kraken2 database."),
-    (
-        "SEQUENCING_TYPE",
-        "Sequencing read type (s: Illumina single-ended, d: Illumina double-ended, n: ONT long reads).",
-    ),
+    ("SEQUENCING_TYPE", "Sequencing read type (s: Illumina single-ended, d: Illumina double-ended, n: ONT long reads)."),
     ("PRIMER_BED", "BED file for primers, expected under WEPP/primers."),
-    (
-        "MIN_AF",
-        "Alleles with an allele frequency below this threshold are masked (Illumina: 0.5%, Ion Torrent: 1.5%, ONT: 2%).",
-    ),
+    ("MIN_AF", "Alleles with an allele frequency below this threshold are masked (Illumina: 0.5%, Ion Torrent: 1.5%, ONT: 2%)."),
     ("MIN_DEPTH", "Sites with read depth below this threshold are masked by WEPP."),
     ("MIN_Q", "Alleles with a Phred score below this threshold are masked by WEPP."),
-    (
-        "MIN_PROP",
-        "Minimum proportion of haplotypes detected by WEPP (Wastewater samples: 0.5%, Clinical samples: 5%).",
-    ),
+    ("MIN_PROP", "Minimum proportion of haplotypes detected by WEPP (Wastewater samples: 0.5%, Clinical samples: 5%)."),
     ("MIN_LEN", "Minimum read length to consider after ivar trim (default: 80)."),
-    (
-        "MAX_READS",
-        "Maximum number of reads considered by WEPP from the sample (useful for reducing runtime).",
-    ),
+    ("MAX_READS", "Maximum number of reads considered by WEPP from the sample (useful for reducing runtime)."),
     ("DASHBOARD_ENABLED", "Enables the WEPP dashboard for visualizing haplotype results."),
-    (
-        "PATHOGENS",
-        "List of pathogens with custom WEPP settings; species not listed use default settings.",
-    ),
-    (
-        "CLADE_LIST",
-        "Comma-separated clade annotation schemes in the MAT file, ordered to match PATHOGENS; leave blank for species without clade annotations.",
-    ),
-    (
-        "CLADE_IDX",
-        "Comma-separated clade indices for each pathogen; use -1 for species without lineage annotations, ordered to match PATHOGENS.",
-    ),
+    ("ADD_SPECIES_RUNTIME", "Asks users to add pathogen species at runtime when enabled."),
+    ("PATHOGENS", "List of pathogens with custom WEPP settings; species not listed use default settings."),
+    ("CLADE_LIST", "Comma-separated clade annotation schemes in the MAT file, ordered to match PATHOGENS; leave blank for species without clade annotations."),
+    ("CLADE_IDX", "Comma-separated clade indices for each pathogen; use -1 for species without lineage annotations, ordered to match PATHOGENS."),
     ("MIN_DEPTH_FOR_WEPP", "Minimum read coverage required to run WEPP for any pathogen species."),
-    (
-        "MIN_PROP_FOR_WEPP",
-        "Minimum relative abundance before metaWEPP prompts adding a species for haplotype-level analysis.",
-    ),
+    ("MIN_PROP_FOR_WEPP", "Minimum relative abundance before metaWEPP prompts adding a species for haplotype-level analysis."),
 ]