From 57eef18b457ab37cf7b294fb15678b75bc8deca8 Mon Sep 17 00:00:00 2001
From: Julian Pollmann <julian.pollmann@hs-duesseldorf.de>
Date: Wed, 18 Feb 2026 17:28:42 +0100
Subject: [PATCH 1/2] Load Data from registry (Zenodo) and fix DF issue

---
 chemap/data_loader.py | 62 +++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 60 insertions(+), 2 deletions(-)

diff --git a/chemap/data_loader.py b/chemap/data_loader.py
index af95218..1453bc5 100644
--- a/chemap/data_loader.py
+++ b/chemap/data_loader.py
@@ -1,5 +1,6 @@
 import os
 import pathlib
+import re
 import pandas as pd
 import pooch
 
@@ -33,6 +34,30 @@ def load(self, source: str, **kwargs) -> list:
         else:
             raise ValueError(f"Source {source} unknown.")
 
+    def load_collection(self, source: str, **kwargs) -> list:
+        """
+        Loads a dataset collection from a DOI-based registry (e.g. Zenodo).
+
+        Parameters
+        -------------
+        source:
+            A DOI.
+
+        Returns
+        -------------
+        list of downloaded filenames from the registry.
+
+        Raises
+        -------------
+        ValueError if DOI not present.
+        """
+        doi_pattern = r'(10\.\d{4,9}/[-._;()/:a-zA-Z0-9]+)'
+
+        if not source.startswith("doi") or not bool(re.search(doi_pattern, source)):
+            ValueError(f"Could not detect DOI in source {source}.")
+
+        return self._from_registry(source, **kwargs)
+
     def _from_local_file(self, path, smiles_column: str = "smiles") -> list:
         """
         Loads a dataset from local file.
@@ -67,10 +92,13 @@ def _from_local_file(self, path, smiles_column: str = "smiles") -> list:
         else:
             raise ValueError(f"Fileformat {suffix} not supported.")
 
-        if smiles_column not in df.columns:
+        column_map = {col.lower(): col for col in df.columns}
+        target_col = column_map.get(smiles_column.lower())
+
+        if not target_col:
             raise ValueError(f"Smiles column {smiles_column} not in dataframe.")
 
-        return df[smiles_column].tolist()
+        return df[target_col].tolist()
 
     def _from_web(self, url: str, **kwargs) -> list:
         """
@@ -93,3 +121,33 @@ def _from_web(self, url: str, **kwargs) -> list:
         )
 
         return self._from_local_file(file_path, **kwargs)
+
+    def _from_registry(self, doi: str, **kwargs) -> list:
+        """
+        Loads a dataset collection from DOI-based registry (e.g., Zenodo).
+
+        Parameters
+        -------------
+        doi:
+            A valid DOI string.
+
+        Returns
+        -------------
+        list of strings with absolute path for all downloaded files.
+
+        Raises
+        -------------
+        ValueError if file type unsupported.
+        ValueError if smiles column not present.
+        """
+        if not doi.startswith("doi"):
+            doi = f"doi:{doi}"
+
+        client = pooch.create(
+            path=self.cache_dir,
+            base_url=f"{doi}/",
+            registry=None,
+        )
+        client.load_registry_from_doi()
+
+        return [client.fetch(f, progressbar=True) for f in client.registry]
\ No newline at end of file

From eca3832226eb5aa434877bea26e5ff53d37d821e Mon Sep 17 00:00:00 2001
From: Julian Pollmann <julian.pollmann@hs-duesseldorf.de>
Date: Wed, 18 Feb 2026 17:34:26 +0100
Subject: [PATCH 2/2] Update README

---
 README.md | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/README.md b/README.md
index 5226c55..e1ce203 100644
--- a/README.md
+++ b/README.md
@@ -50,7 +50,12 @@ from chemap import compute_fingerprints, DatasetLoader, FingerprintConfig
 
 
 ds_loader = DatasetLoader()
+# Load a single dataset from a local file
 smiles = ds_loader.load("tests/data/smiles.csv")
+# or load a dataset collection from a DOI based registry (e.g., Zenodo)
+files = ds_loader.load_collection("10.5281/zenodo.18682050")
+# pass one of the absolute file paths from files
+smiles = ds_loader.load(files[0])
 
 # ----------------------------
 # RDKit: Morgan (folded, dense)