pythonflex 0.1.1__tar.gz

pythonflex-0.1.1/.gitignore

@@ -0,0 +1,17 @@
+# Python-generated files
+__pycache__/
+*.py[oc]
+build/
+dist/
+wheels/
+*.egg-info
+
+
+bfg-*.jar
+
+# Virtual environments
+.venv
+**/result.pkl
+examples/output/
+src/benchmarkcr/examples/output/
+.aider*

pythonflex-0.1.1/.python-version

@@ -0,0 +1 @@
+3.12

pythonflex-0.1.1/PKG-INFO

@@ -0,0 +1,163 @@
+Metadata-Version: 2.4
+Name: pythonflex
+Version: 0.1.1
+Summary: pythonFLEX is a benchmarking toolkit for evaluating CRISPR screen results against biological gold standards. The toolkit computes gene-level and complex-level performance metrics, helping researchers systematically assess the biological relevance and resolution of their CRISPR screening data.
+Author-email: Yasir Demirtaş <tyasird@hotmail.com>
+Requires-Python: >=3.9
+Requires-Dist: adjusttext
+Requires-Dist: art
+Requires-Dist: bitarray
+Requires-Dist: emoji
+Requires-Dist: importlib-resources
+Requires-Dist: ipython
+Requires-Dist: joblib
+Requires-Dist: loguru
+Requires-Dist: matplotlib
+Requires-Dist: numba
+Requires-Dist: numpy
+Requires-Dist: pandas
+Requires-Dist: pyarrow
+Requires-Dist: python-slugify
+Requires-Dist: scikit-learn
+Requires-Dist: scipy
+Requires-Dist: tqdm
+Description-Content-Type: text/markdown
+
+# pythonFLEX
+
+🧬 **pythonFLEX** is a benchmarking toolkit for evaluating CRISPR screen results against biological gold standards. It provides precision-recall analysis using reference gene sets from CORUM protein complexes, Gene Ontology Biological Processes (GO-BP), KEGG pathways, and other curated resources. The toolkit computes gene-level and complex-level performance metrics, helping researchers systematically assess the biological relevance and resolution of their CRISPR screening data.
+
+
+---
+
+## 🔧 Features
+
+- Precision-recall curve generation for ranked gene lists
+
+- Evaluation using CORUM complexes, GO terms, pathways
+
+- Complex-level resolution analysis and visualization
+
+- Easy integration into CRISPR screen workflows
+
+---
+
+## 📦 Installation
+
+Suggested to use Python version `3.10` with `virtual env`.
+
+Create `venv`
+
+```bash
+conda create -n p310 python=3.10
+conda activate p310
+pip install uv
+```
+
+Install pythonFLEX via pip
+
+``` bash
+uv pip install pythonflex
+```
+
+or 
+
+```bash
+pip install pythonflex
+```
+
+or Install pythonFLEX via git (to develop package in local)
+
+```bash
+git clone https://github.com/tyasird/pythonFLEX.git
+cd pythonFLEX
+uv pip install -e .
+```
+
+
+
+---
+
+## 🚀 Quickstart
+
+```python
+
+import pythonflex as flex
+
+inputs = {
+    "Melanoma (63 Screens)": {
+        "path": flex.get_example_data_path("melanoma_cell_lines_500_genes.csv"), 
+        "sort": "high"
+    },
+    "Liver (24 Screens)": {
+        "path": flex.get_example_data_path("liver_cell_lines_500_genes.csv"), 
+        "sort": "high"
+    },
+    "Neuroblastoma (37 Screens)": {
+        "path": flex.get_example_data_path("neuroblastoma_cell_lines_500_genes.csv"), 
+        "sort": "high"
+    },
+}
+
+
+
+default_config = {
+    "min_genes_in_complex": 2,
+    "min_genes_per_complex_analysis": 2,
+    "output_folder": "output",
+    "gold_standard": "GOBP",
+    "color_map": "RdYlBu",
+    "jaccard": True,
+    "plotting": {
+        "save_plot": True,
+        "output_type": "png",
+    },
+    "preprocessing": {
+        "fill_na": True,
+        "normalize": False,
+    },
+    "corr_function": "numpy",
+    "logging": {  
+        "visible_levels": ["DONE","STARTED"]  # "PROGRESS", "STARTED", ,"INFO","WARNING"
+    }
+}
+
+
+# Initialize logger, config, and output folder
+flex.initialize(default_config)
+
+# Load datasets and gold standard terms
+data, _ = flex.load_datasets(inputs)
+terms, genes_in_terms = flex.load_gold_standard()
+
+# Run analysis
+for name, dataset in data.items():
+    df, pr_auc = flex.pra(name, dataset)
+    fpc = flex.pra_percomplex(name, dataset, is_corr=False) 
+    cc = flex.complex_contributions(name)
+
+# Generate plots
+flex.plot_auc_scores()
+flex.plot_precision_recall_curve()
+flex.plot_percomplex_scatter()
+flex.plot_percomplex_scatter_bysize()
+flex.plot_significant_complexes()
+flex.plot_complex_contributions()
+
+# Save Result CSVspyflex.save_results_to_csv()
+flex.save_results_to_csv()
+
+
+```
+
+---
+
+## 📂 Examples
+
+- [src/pythonflex/examples/basic_usage.py](src/pythonflex/examples/basic_usage.py)
+
+---
+
+## 📃 License
+
+MIT

pythonflex-0.1.1/README.md

@@ -0,0 +1,138 @@
+# pythonFLEX
+
+🧬 **pythonFLEX** is a benchmarking toolkit for evaluating CRISPR screen results against biological gold standards. It provides precision-recall analysis using reference gene sets from CORUM protein complexes, Gene Ontology Biological Processes (GO-BP), KEGG pathways, and other curated resources. The toolkit computes gene-level and complex-level performance metrics, helping researchers systematically assess the biological relevance and resolution of their CRISPR screening data.
+
+
+---
+
+## 🔧 Features
+
+- Precision-recall curve generation for ranked gene lists
+
+- Evaluation using CORUM complexes, GO terms, pathways
+
+- Complex-level resolution analysis and visualization
+
+- Easy integration into CRISPR screen workflows
+
+---
+
+## 📦 Installation
+
+Suggested to use Python version `3.10` with `virtual env`.
+
+Create `venv`
+
+```bash
+conda create -n p310 python=3.10
+conda activate p310
+pip install uv
+```
+
+Install pythonFLEX via pip
+
+``` bash
+uv pip install pythonflex
+```
+
+or 
+
+```bash
+pip install pythonflex
+```
+
+or Install pythonFLEX via git (to develop package in local)
+
+```bash
+git clone https://github.com/tyasird/pythonFLEX.git
+cd pythonFLEX
+uv pip install -e .
+```
+
+
+
+---
+
+## 🚀 Quickstart
+
+```python
+
+import pythonflex as flex
+
+inputs = {
+    "Melanoma (63 Screens)": {
+        "path": flex.get_example_data_path("melanoma_cell_lines_500_genes.csv"), 
+        "sort": "high"
+    },
+    "Liver (24 Screens)": {
+        "path": flex.get_example_data_path("liver_cell_lines_500_genes.csv"), 
+        "sort": "high"
+    },
+    "Neuroblastoma (37 Screens)": {
+        "path": flex.get_example_data_path("neuroblastoma_cell_lines_500_genes.csv"), 
+        "sort": "high"
+    },
+}
+
+
+
+default_config = {
+    "min_genes_in_complex": 2,
+    "min_genes_per_complex_analysis": 2,
+    "output_folder": "output",
+    "gold_standard": "GOBP",
+    "color_map": "RdYlBu",
+    "jaccard": True,
+    "plotting": {
+        "save_plot": True,
+        "output_type": "png",
+    },
+    "preprocessing": {
+        "fill_na": True,
+        "normalize": False,
+    },
+    "corr_function": "numpy",
+    "logging": {  
+        "visible_levels": ["DONE","STARTED"]  # "PROGRESS", "STARTED", ,"INFO","WARNING"
+    }
+}
+
+
+# Initialize logger, config, and output folder
+flex.initialize(default_config)
+
+# Load datasets and gold standard terms
+data, _ = flex.load_datasets(inputs)
+terms, genes_in_terms = flex.load_gold_standard()
+
+# Run analysis
+for name, dataset in data.items():
+    df, pr_auc = flex.pra(name, dataset)
+    fpc = flex.pra_percomplex(name, dataset, is_corr=False) 
+    cc = flex.complex_contributions(name)
+
+# Generate plots
+flex.plot_auc_scores()
+flex.plot_precision_recall_curve()
+flex.plot_percomplex_scatter()
+flex.plot_percomplex_scatter_bysize()
+flex.plot_significant_complexes()
+flex.plot_complex_contributions()
+
+# Save Result CSVspyflex.save_results_to_csv()
+flex.save_results_to_csv()
+
+
+```
+
+---
+
+## 📂 Examples
+
+- [src/pythonflex/examples/basic_usage.py](src/pythonflex/examples/basic_usage.py)
+
+---
+
+## 📃 License
+
+MIT

pythonflex-0.1.1/pyproject.toml

@@ -0,0 +1,63 @@
+[project]
+name = "pythonflex"
+version = "0.1.1"
+description = "pythonFLEX is a benchmarking toolkit for evaluating CRISPR screen results against biological gold standards. The toolkit computes gene-level and complex-level performance metrics, helping researchers systematically assess the biological relevance and resolution of their CRISPR screening data."
+readme = "README.md"
+authors = [
+    { name = "Yasir Demirtaş", email = "tyasird@hotmail.com" }
+]
+requires-python = ">=3.9"
+
+
+# Exclude the input folder
+exclude = ["src/pythonflex/input/*", "src/pythonflex/output/*", "src/pythonflex/examples/output/*", 
+ "src/pythonflex/examples/.tmp/*"]
+
+
+dependencies = [
+    "adjustText",
+    "art",
+    "bitarray",
+    "emoji",
+    "ipython",
+    "joblib",
+    "loguru",
+    "matplotlib",
+    "numba",
+    "numpy",
+    "pandas",
+    "pyarrow",
+    "python-slugify",
+    "scikit-learn",
+    "scipy",
+    "tqdm",
+    "importlib-resources"  # <- Only needed for Python < 3.9
+]
+
+[project.scripts]
+pythonflex = "pythonflex:main"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+
+[tool.ruff]
+ignore = ["F541"]
+
+[tool.setuptools.package-data]
+pythonflex = ["data/**/*.parquet", "data/**/*.csv", "data/**/*.tsv", "data/**/*.json", "data/**/*.txt", "data/**/*.xlsx", "data/**/*.xls", "data/**/*.h5", "data/**/*.hdf5"]
+
+[tool.hatch.build]
+exclude = ["**/result.pkl", "examples/output"]
+
+[tool.hatch.build.targets.wheel]
+packages = ["pythonFLEX"]
+
+[tool.uv.sources]
+pythonflex = { workspace = true }
+
+[dependency-groups]
+dev = [
+    "pythonflex",
+]

pythonflex-0.1.1/src/pythonflex/__init__.py

@@ -0,0 +1,18 @@
+
+from .logging_config import log
+from .utils import dsave, dload
+from .preprocessing import get_example_data_path, load_datasets,  get_common_genes, filter_matrix_by_genes, load_gold_standard, filter_duplicate_terms
+from .analysis import initialize, pra, pra_percomplex, fast_corr, perform_corr, is_symmetric, binary, has_mirror_of_first_pair, convert_full_to_half_matrix, drop_mirror_pairs, quick_sort, complex_contributions, save_results_to_csv
+from .plotting import (
+    adjust_text_positions, plot_precision_recall_curve, plot_percomplex_scatter,
+    plot_percomplex_scatter_bysize, plot_complex_contributions, plot_significant_complexes, plot_auc_scores
+)
+
+__all__ = [ "log", "get_example_data_path", "fast_corr",
+    "initialize", "dsave", "dload", "load_datasets", "get_common_genes",
+    "filter_matrix_by_genes", "load_gold_standard", "filter_duplicate_terms", "pra", "pra_percomplex",
+    "perform_corr", "is_symmetric", "binary", "has_mirror_of_first_pair", "convert_full_to_half_matrix",
+    "drop_mirror_pairs", "quick_sort", "complex_contributions", "adjust_text_positions", "plot_precision_recall_curve",
+    "plot_percomplex_scatter", "plot_percomplex_scatter_bysize", "plot_complex_contributions",
+    "plot_significant_complexes", "plot_auc_scores", "save_results_to_csv"
+]