Skip to content

Fix #200: Populate Coefficients column with required CpG sites for mo… #217

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
hackergovind wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Fix #200: Populate Coefficients column with required CpG sites for mo… #217

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
23 changes: 22 additions & 1 deletion doc/generate.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,7 @@
import yaml
import csv
import os
import importlib

def generate_models_csv(models, output_file="generated/model_table.csv"):
header = ["Name", "Year", "Species", "Tissue", "Predicts", "Source", "Coefficients"]
Expand All @@ -23,6 +24,27 @@ def generate_models_csv(models, output_file="generated/model_table.csv"):
model_file = details.get('model', {}).get('file')
coefficients_link = f"`coefficients file <https://github.com/bio-learn/biolearn/blob/master/biolearn/data/{model_file}>`_" if model_file else "N/A"

# If there is no static coefficients file, try to obtain required CpG sites from the model class
if not model_file:
class_path = details.get('class')
if not class_path:
class_path = f"biolearn.model.{name}"
try:
module_path, class_name = class_path.rsplit(".", 1)
mod = importlib.import_module(module_path)
model_cls = getattr(mod, class_name)
if hasattr(model_cls, "methylation_sites"):
sites = model_cls.methylation_sites()
if isinstance(sites, (list, tuple)):
sites_str = ", ".join(map(str, sites))
if len(sites_str) > 200:
sites_str = sites_str[:197] + "..."
else:
sites_str = str(sites)
coefficients_link = sites_str if sites_str else "N/A"
except Exception:
pass

row = [
name,
details["year"],
Expand Down Expand Up @@ -122,7 +144,6 @@ def generate_model_usage_csv(models, output_file="generated/model_usage.csv"):
print(f"Model usage CSV generated at: {output_file}")



if __name__ == "__main__":
ensure_folder_exists("generated/")
generate_models_csv(model_definitions)
Expand Down