update main to show latest docs

.editorconfig

@@ -0,0 +1,4 @@
+[*]
+max_line_length = 120
+trim_trailing_whitespace = true
+insert_final_newline = true

.flake8

@@ -0,0 +1,15 @@
+[flake8]
+max-line-length = 120
+
+# F405 - ignore error if class is imported in `*` import.
+# W293 - blank line contains whitespace
+# W503 - line break before binary operator
+ignore = F405,W293,W503
+
+exclude =
+    .git,
+    __pycache__,
+    docs/conf.py,
+    build,
+    dist,
+    venv,

.github/workflows/pages.yml

@@ -32,8 +32,8 @@ jobs:
         touch gh-pages/.nojekyll
 
         function build_docs {
-          # The function will checkout a branch and build the Javadoc & documentation 
-          # into provided documentation directory.
+          # The function will checkout a branch and build the API docs & documentation 
+          # into provided directory.
           BRANCH=${1}
           DOCDIR=${2}
 
@@ -50,8 +50,8 @@ jobs:
           printf "Building the %s documentation\n" ${DOCDIR}
 
           cd docs
-          sphinx-apidoc --separate --module-first -d 2 -H "API reference" --follow-links -o apidocs ../src/genophenocorr
-          make html
+          sphinx-apidoc --separate --module-first -d 2 -H "API reference" --follow-links -o apidocs ../src/gpsea
+          make clean html
 
           mv _build/html/* ../gh-pages/${DOCDIR}
           cd ..

.github/workflows/python_ci.yml

@@ -7,23 +7,23 @@ on:
       branches: [ main, develop ]
 
 jobs:
-    build:
+    run-ci:
       runs-on: ubuntu-latest
+      strategy:
+        matrix:
+          python-version: ['3.10', '3.11', '3.12']
 
       steps:
         - uses: actions/checkout@v4
-        - name: Initialize Python 3.11
+        - name: Initialize Python
           uses: actions/[email protected]
           with:
-            python-version: "3.11"
+            python-version: ${{ matrix.python-version }}
         - name: Install package
           run: |
-            python3 -m pip install .[test,docs]
+            python3 -m pip install --editable .[test]
         - name: Run pytest tests
           run: |
+            export MPLBACKEND=Agg
+            export GPSEA_CACHEDIR=.gpsea_ci_cachedir
             pytest
-        - name: Run documentation tests
-          run: |
-            cd docs
-            sphinx-apidoc --separate --module-first -d 2 -H "API reference" -o apidocs ../src/genophenocorr
-            make doctest

.gitignore

@@ -1,3 +1,6 @@
+# Cache with transcript/protein pickle files
+.gpsea_cache
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]
@@ -29,7 +32,6 @@ share/python-wheels/
 *.egg-info/
 .installed.cfg
 *.egg
-phenopackets
 notebooks/KBG/Backup/
 notebooks/KBG/phenopackets_extraHPO/
 notebooks/KBG/pickledVariants/
@@ -131,6 +133,10 @@ venv.bak/
 # PyCharm
 .idea/
 
+# VsCode
+*.code-workspace
+.vscode
+
 # mkdocs documentation
 /site
 

HOW_TO_RELEASE.md

@@ -1,6 +1,6 @@
 # How to release
 
-The document describes how to release `genophenocorr` to *PyPi*.
+The document describes how to release `gpsea` to *PyPi*.
 
 ## Release checklist
 
@@ -9,7 +9,7 @@ The document describes how to release `genophenocorr` to *PyPi*.
 - remove deprecated methods targeted for removal in this version. The `TODO` markers are labeled using 
   the target version (e.g. `TODO[v0.3.0]`)
 - bump versions to a release:
-  - `src/genophenocorr/__init__.py`
+  - `src/gpsea/__init__.py`
   - `docs/conf.py`
 - ensure the CI passes
 - deploy to PyPi (described below)
@@ -52,11 +52,11 @@ Store the token into `$HOME/.pypirc` file with `-rw-------` permissions. The fil
 Now we're ready to publish packages!
 
 ### Deploy
-Run the following to deploy `genophenocorr` to PyPi:  
+Run the following to deploy `gpsea` to PyPi:  
 
 ```bash
 # Ensure you're on the release branch
-cd genophenocorr
+cd gpsea
 
 # Build the package
 python3 -m build

MANIFEST.in

@@ -0,0 +1,2 @@
+include src/gpsea/model/genome/GCF_*.tsv
+include src/gpsea/view/templates/*.html

README.md

@@ -1,41 +1,50 @@
-[![Build status](https://github.com/monarch-initiative/genophenocorr/workflows/CI/badge.svg)](https://github.com/monarch-initiative/genophenocorr/actions/workflows/python_ci.yml)
-![PyPi downloads](https://img.shields.io/pypi/dm/genophenocorr.svg?label=Pypi%20downloads)
-![PyPI - Python Version](https://img.shields.io/pypi/pyversions/genophenocorr)
+[![Build status](https://github.com/monarch-initiative/gpsea/workflows/CI/badge.svg)](https://github.com/monarch-initiative/gpsea/actions/workflows/python_ci.yml)
+[![GitHub release](https://img.shields.io/github/release/monarch-initiative/gpsea.svg)](https://github.com/monarch-initiative/gpsea/releases)
+![PyPi downloads](https://img.shields.io/pypi/dm/gpsea.svg?label=Pypi%20downloads)
+![PyPI - Python Version](https://img.shields.io/pypi/pyversions/gpsea)
 
-Genophenocorr is a Python library for genotype-phenotype association analysis. 
+GPSEA is a Python library for discovery of genotype-phenotype associations.
 
 An example of simple genotype-phenotype association analysis
+
 ```python
 # Load HPO
 import hpotk
-hpo = hpotk.load_minimal_ontology('http://purl.obolibrary.org/obo/hp.json')
 
-# Load a cohort of phenopackets 
-from genophenocorr.data import get_toy_cohort
+store = hpotk.configure_ontology_store()
+hpo = store.load_minimal_hpo()
+
+# Load a cohort of phenopackets
+from gpsea.data import get_toy_cohort
+
 cohort = get_toy_cohort()
 
-# Analyze genotype-phenotype associations 
-from genophenocorr.analysis import CohortAnalysis
-from genophenocorr.constants import VariantEffect
+# Analyze genotype-phenotype associations
+from gpsea.analysis import configure_cohort_analysis
+from gpsea.analysis.predicate import PatientCategories
+
+from gpsea.model import VariantEffect
+
+cohort_analysis = configure_cohort_analysis(cohort, hpo)
+frameshift = cohort_analysis.compare_by_variant_effect(VariantEffect.FRAMESHIFT_VARIANT, tx_id='NM_1234.5')
 
-cohort_analysis = CohortAnalysis(cohort, 'NM_1234.5', hpo)
-frameshift = cohort_analysis.compare_by_variant_type(VariantEffect.FRAMESHIFT_VARIANT)
-print(frameshift)
+frameshift.summarize(hpo, category=PatientCategories.YES)
 ```
 
-prints a table with genotype-phenotype correlations:
+provides a pandas data frame with genotype-phenotype correlations:
 
 ```text
-                            With frameshift_variant         Without frameshift_variant
-                                              Count Percent                      Count Percent  p-value
-HP:0001166 (Arachnodactyly)                       4  30.77%                         10  76.92%  0.04718
-HP:0001250 (Seizure)                             11  84.62%                          9  69.23%  0.64472
-HP:0001257 (Spasticity)                           8  61.54%                          9  69.23%  1.00000
+FRAMESHIFT_VARIANT on NM_1234.5                                    No                Yes
+                                                                Count   Percent    Count   Percent    p value    Corrected p value
+    Arachnodactyly [HP:0001166]                                  1/10       10%    13/16       81%   0.000781             0.020299
+    Abnormality of the musculature [HP:0003011]                   6/6      100%    11/11      100%   1.000000             1.000000
+    Abnormal nervous system physiology [HP:0012638]               9/9      100%    15/15      100%   1.000000             1.000000
+    ...                                                           ...       ...      ...       ...        ...                  ...
 ```
 
 ## Documentation
 
 Check out the User guide and the API reference for more info:
 
-- [Stable documentation](https://monarch-initiative.github.io/genophenocorr/stable/) (last release on `main` branch)
-- [Latest documentation](https://monarch-initiative.github.io/genophenocorr/latest) (bleeding edge, latest commit on `development` branch)
+- [Stable documentation](https://monarch-initiative.github.io/gpsea/stable/) (last release on `main` branch)
+- [Latest documentation](https://monarch-initiative.github.io/gpsea/latest) (bleeding edge, latest commit on `develop` branch)