Merge pull request #20 from pinellolab/doc

Move documentation and add support for the survival screens

.github/workflows/CI.yml

@@ -23,11 +23,11 @@ jobs:
     - name: Set up Python
       uses: actions/setup-python@v3
       with:
-        python-version: '3.8'
+        python-version: '3.x'
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        pip install torch==1.12.1+cpu torchvision==0.13.1+cpu torchaudio==0.12.1 --extra-index-url https://download.pytorch.org/whl/cpu
+        pip install torch torchvision torchaudio
         pip install -r requirements.txt
         pip install -e .
     - name: Test with pytest

.github/workflows/documentation.yml

@@ -0,0 +1,41 @@
+name: "Sphinx: Render docs"
+
+on: push
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python
+      uses: actions/setup-python@v3
+      with:
+        python-version: '3.x'
+
+    - name: Install Sphinx & Dependencies
+      run: |
+        pip install sphinx sphinx_markdown_builder sphinx_rtd_theme sphinx-argparse m2r pandas bio
+        sudo apt-get install python3-distutils
+    - name: Build Documentation
+      working-directory: docs
+      run: sphinx-build . _build
+    - name: copy image files
+      run: cp -r docs/assets docs/_build/
+    - uses: actions/upload-pages-artifact@v3
+      with:
+        name: github-pages
+        path: docs/_build/
+
+  deploy:
+    needs: build
+    permissions:
+      id-token: write
+      pages: write
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    runs-on: ubuntu-latest
+    steps:
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v4

.gitignore

@@ -1 +1,2 @@
 *.pyc
+*.fastq

bean/annotate/utils.py

@@ -218,22 +218,12 @@ def get_cds_seq_pos_from_gene_name(gene_name: str, ref_version: str = "GRCh38"):
     return cds_chrom, cds_seq, cds_pos, strand
 
 
-def parse_args():
-    """Get the input arguments"""
-    print(
-        r"""
-    _ _         
-  /  \ '\       __ _ _ _           
-  |   \  \     / _(_) | |_ ___ _ _ 
-   \   \  |   |  _| | |  _/ -_) '_|
-    `.__|/    |_| |_|_|\__\___|_|  
-    """
-    )
-    print("bean-filter: filter alleles")
-    parser = argparse.ArgumentParser(
-        prog="allele_filter",
-        description="Filter alleles based on edit position in spacer and frequency across samples.",
-    )
+def parse_args(parser=None):
+    if parser is None:
+        parser = argparse.ArgumentParser(
+            prog="allele_filter",
+            description="Filter alleles based on edit position in spacer and frequency across samples.",
+        )
     parser.add_argument(
         "bdata_path",
         type=str,
@@ -349,7 +339,7 @@ def parse_args():
         action="store_true",
         help="Load temporary file and work from there.",
     )
-    return parser.parse_args()
+    return parser
 
 
 def check_args(args):

bin/bean-count → bean/cli/count.py

@@ -1,105 +1,90 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-"""Count guides, optionally with reporter and alleles of a single sequencing sample."""
-
-import logging
-import os
-import sys
-
-import bean
-from bean.mapping.utils import (
-    _check_arguments,
-    _get_input_parser,
-    _check_file,
-    _get_first_read_length,
-    _check_read_length,
-)
-
-logging.basicConfig(
-    level=logging.INFO,
-    format="%(levelname)-5s @ %(asctime)s:\n\t %(message)s \n",
-    datefmt="%a, %d %b %Y %H:%M:%S",
-    stream=sys.stderr,
-    filemode="w",
-)
-error = logging.critical
-warn = logging.warning
-debug = logging.debug
-info = logging.info
-
-
-_ROOT = os.path.abspath(os.path.dirname(__file__))
-
-
-def get_input_parser():
-    """Get single-sample specific argument parser."""
-    parser = _get_input_parser()
-    parser.add_argument(
-        "--R1",
-        type=str,
-        help="fastq file for read 1",
-        required=True,
-        default="Fastq filename",
-    )
-    parser.add_argument(
-        "--R2",
-        type=str,
-        help="fastq file for read 2, sorted as the same name order as in --R1 file.",
-        required=True,
-        default="Fastq filename",
-    )
-    return parser
-
-
-def check_arguments(args, info_logger, warn_logger, error_logger):
-    args = _check_arguments(
-        args, info_logger=info, warn_logger=warn, error_logger=error
-    )
-    _check_file(args.R1)
-    _check_file(args.R2)
-    read_length = _get_first_read_length(args.R1)
-    _check_read_length(args, read_length, warn)
-    return args
-
-
-def main():
-    parser = get_input_parser()
-    args = parser.parse_args()
-
-    args = check_arguments(args, info_logger=info, warn_logger=warn, error_logger=error)
-    args_dict = vars(args)
-
-    edited_from = args_dict["edited_base"]
-    match_target_pos = args_dict["match_target_pos"]
-
-    counter = bean.mp.GuideEditCounter(**args_dict)
-    counter.check_filter_fastq()
-
-    counter.get_counts()
-    if counter.count_reporter_edits:
-        counter.screen.uns["allele_counts"] = counter.screen.uns["allele_counts"].loc[
-            counter.screen.uns["allele_counts"].allele.map(str) != "", :
-        ]
-        if match_target_pos:
-            base_editing_map = {"A": "G", "C": "T"}
-            edited_to = base_editing_map[edited_from]
-            counter.screen.get_edit_mat_from_uns(
-                edited_from, edited_to, match_target_pos
-            )
-    counter.screen.write(f"{counter.output_dir}.h5ad")
-    counter.screen.to_Excel(f"{counter.output_dir}.xlsx")
-    info(f"Output written at:\n {counter.output_dir}.h5ad,\n {counter.output_dir}.xlsx")
-    info("All Done!")
-    print(
-        r"""
-    _ _       
-  /  \ '\                       _   
-  |   \  \      __ ___ _  _ _ _| |_ 
-   \   \  |    / _/ _ \ || | ' \  _|
-    `.__|/     \__\___/\_,_|_||_\__|
-    """
-    )
-
-
-if __name__ == "__main__":
-    main()
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+"""Count guides, optionally with reporter and alleles of a single sequencing sample."""
+
+import logging
+import os
+import sys
+
+import bean
+from bean.mapping.utils import (
+    _check_arguments,
+    _check_file,
+    _get_first_read_length,
+    _check_read_length,
+)
+
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(levelname)-5s @ %(asctime)s:\n\t %(message)s \n",
+    datefmt="%a, %d %b %Y %H:%M:%S",
+    stream=sys.stderr,
+    filemode="w",
+)
+error = logging.critical
+warn = logging.warning
+debug = logging.debug
+info = logging.info
+
+
+_ROOT = os.path.abspath(os.path.dirname(__file__))
+
+
+
+
+
+def check_arguments(args, info_logger, warn_logger, error_logger):
+    args = _check_arguments(
+        args, info_logger=info, warn_logger=warn, error_logger=error
+    )
+    _check_file(args.R1)
+    _check_file(args.R2)
+    read_length = _get_first_read_length(args.R1)
+    _check_read_length(args, read_length, warn)
+    return args
+
+
+def main(args):
+    """Get the input data"""
+    print(
+        r"""
+    _ _       
+  /  \ '\                       _   
+  |   \  \      __ ___ _  _ _ _| |_ 
+   \   \  |    / _/ _ \ || | ' \  _|
+    `.__|/     \__\___/\_,_|_||_\__|
+    """
+    )
+    args = check_arguments(args, info_logger=info, warn_logger=warn, error_logger=error)
+    args_dict = vars(args)
+
+    edited_from = args_dict["edited_base"]
+    match_target_pos = args_dict["match_target_pos"]
+
+    counter = bean.mp.GuideEditCounter(**args_dict)
+    counter.check_filter_fastq()
+
+    counter.get_counts()
+    if counter.count_reporter_edits:
+        counter.screen.uns["allele_counts"] = counter.screen.uns["allele_counts"].loc[
+            counter.screen.uns["allele_counts"].allele.map(str) != "", :
+        ]
+        if match_target_pos:
+            base_editing_map = {"A": "G", "C": "T"}
+            edited_to = base_editing_map[edited_from]
+            counter.screen.get_edit_mat_from_uns(
+                edited_from, edited_to, match_target_pos
+            )
+    counter.screen.write(f"{counter.output_dir}.h5ad")
+    counter.screen.to_Excel(f"{counter.output_dir}.xlsx")
+    info(f"Output written at:\n {counter.output_dir}.h5ad,\n {counter.output_dir}.xlsx")
+    info("All Done!")
+    print(
+        r"""
+    _ _       
+  /  \ '\                       _   
+  |   \  \      __ ___ _  _ _ _| |_ 
+   \   \  |    / _/ _ \ || | ' \  _|
+    `.__|/     \__\___/\_,_|_||_\__|
+    """
+    )