download phrogs

Author: telatin

Makefile

@@ -0,0 +1,57 @@
+.PHONY: help install install-dev test lint format clean docs
+
+# Default target
+help:
+	@echo "Available commands:"
+	@echo "  make install      - Install package"
+	@echo "  make install-dev  - Install package with development dependencies"
+	@echo "  make test         - Run tests"
+	@echo "  make lint         - Run linters"
+	@echo "  make format       - Format code"
+	@echo "  make docs         - Generate documentation"
+	@echo "  make clean        - Remove build artifacts"
+
+# Install package
+install:
+	pip install -e .
+
+# Install with development dependencies
+install-dev:
+	pip install -e ".[dev]"
+
+# Run tests
+test:
+	pytest tests/ -v
+
+# Run linters
+lint:
+	ruff check src/
+	mypy src/
+
+# Format code
+format:
+	ruff format src/
+	ruff check --fix src/
+
+# Generate documentation
+docs:
+	@echo "📚 Generating documentation..."
+	@if command -v pdoc > /dev/null; then \
+		pdoc -o docs src/votuderep && \
+		echo "✅ Documentation generated in docs/"; \
+	else \
+		echo "❌ Error: pdoc is not installed"; \
+		echo "   Install with: pip install pdoc"; \
+		exit 1; \
+	fi
+
+# Clean build artifacts
+clean:
+	@echo "🧹 Cleaning build artifacts..."
+	rm -rf build/
+	rm -rf dist/
+	rm -rf *.egg-info
+	rm -rf src/*.egg-info
+	find . -type d -name __pycache__ -exec rm -rf {} + 2>/dev/null || true
+	find . -type f -name "*.pyc" -delete
+	@echo "✅ Clean complete"

docs/votuderep.html

@@ -260,7 +260,7 @@ <h2 id="version-information">Version Information</h2>
 </span><span id="L-91"><a href="#L-91"><span class="linenos">91</span></a><span class="sd">-------------------</span>
 </span><span id="L-92"><a href="#L-92"><span class="linenos">92</span></a><span class="sd">&quot;&quot;&quot;</span>
 </span><span id="L-93"><a href="#L-93"><span class="linenos">93</span></a>
-</span><span id="L-94"><a href="#L-94"><span class="linenos">94</span></a><span class="n">__version__</span> <span class="o">=</span> <span class="s2">&quot;0.5.0&quot;</span>
+</span><span id="L-94"><a href="#L-94"><span class="linenos">94</span></a><span class="n">__version__</span> <span class="o">=</span> <span class="s2">&quot;0.6.0&quot;</span>
 </span><span id="L-95"><a href="#L-95"><span class="linenos">95</span></a><span class="n">__author__</span> <span class="o">=</span> <span class="s2">&quot;Andrea Telatin&quot;</span>
 </span><span id="L-96"><a href="#L-96"><span class="linenos">96</span></a><span class="n">__license__</span> <span class="o">=</span> <span class="s2">&quot;MIT&quot;</span>
 </span><span id="L-97"><a href="#L-97"><span class="linenos">97</span></a>
@@ -272,7 +272,7 @@ <h2 id="version-information">Version Information</h2>
                 <section id="__version__">
                     <div class="attr variable">
             <span class="name">__version__</span>        =
-<span class="default_value">&#39;0.5.0&#39;</span>
+<span class="default_value">&#39;0.6.0&#39;</span>
 
 
     </div>

src/votuderep.egg-info/PKG-INFO

@@ -54,7 +54,8 @@ A small toolkit developed for the [EBAME](https://maignienlab.gitlab.io/ebame/)
 - **filter**: Filter viral contigs based on quality, completeness, and other metrics from CheckV tsv output
 - **tabulate**: Generate CSV tables from paired-end sequencing read directories (for nextflow)
 - **trainingdata**: Fetch viral assembly datasets for training purposes
-- **getdbs**: Download Genomad and CheckV databases 
+- **getdbs**: Download Genomad and CheckV databases
+- **splitcoverm**: Split a CoverM TSV by metric into separate TSVs, one per metric.
 
 ## Requirements
 
@@ -95,7 +96,8 @@ brew install blast
 
 ## Usage
 
-votuderep provides subcommands: `derep`, `filter`, `tabulate`, and `trainingdata`...
+votuderep provides subcommands: `derep`, `filter`, `tabulate`, `trainingdata`, and `splitcoverm`.
+
 
 ### Dereplicate vOTUs
 
@@ -265,6 +267,31 @@ votuderep trainingdata
 votuderep trainingdata -o ./training_data/
 ```
 
+### Split CoverM TSV
+
+Split a CoverM TSV by metric into separate TSVs, one per metric.
+Reads a CoverM output table containing multiple metrics across samples and splits it into individual TSV files, one for each metric. Each output file will have the format: `<basename>_<metric>.tsv`
+The input TSV is expected to have columns formatted as: "Contig", "<sample1> <metric1>", "<sample1> <metric2>", ...
+
+```bash
+votuderep splitcoverm -i coverage.tsv -o output/cov
+```
+
+**Options:**
+
+- `-i, --input`: Input CoverM TSV (optionally gzipped: .gz) [required]
+- `-o, --output-basename`: Output basename/prefix for generated files [required]
+
+**Examples:**
+
+```bash
+# Basic usage
+votuderep splitcoverm -i coverage.tsv -o output/cov
+
+# With gzipped input
+votuderep splitcoverm -i coverage.tsv.gz -o results/sample
+```
+
 ## Global Options
 
 - `-v, --verbose`: Enable verbose logging

src/votuderep/__init__.py

@@ -91,7 +91,7 @@
 -------------------
 """
 
-__version__ = "0.5.0"
+__version__ = "0.6.0"
 __author__ = "Andrea Telatin"
 __license__ = "MIT"