make dask optional and update documentation for installation

Author: mschwoer

README.md

@@ -102,6 +102,18 @@ For those who are really adventurous, it is also possible to directly install an
 pip install "git+https://github.com/MannLabs/alphaquant.git@development#egg=alphaquant[stable,development-stable]"
 ```
 
+#### Optional extras
+
+For processing very large PTM files that don't fit in memory, install the optional dask extra:
+
+```bash
+pip install "alphaquant[dask]"
+```
+or the version with a pinned dependency (recommended)
+```bash
+pip install "alphaquant[dask-stable]"
+```
+
 ### Developer installation
 
 AlphaQuant can also be installed in editable (i.e. developer) mode with a few `bash` commands. This allows to fully customize the software and even modify the source code to your specific needs. When an editable Python package is installed, its source code is stored in a transparent location of your choice. While optional, it is advised to first (create and) navigate to e.g. a general software folder:

alphaquant/ptm/ptmsite_mapping.py

@@ -18,8 +18,16 @@
 # Cell
 
 import pandas as pd
-import dask.dataframe as dd
+import warnings
 
+try:
+    import dask.dataframe as dd
+    HAS_DASK = True
+except ModuleNotFoundError:
+    HAS_DASK = False
+    warnings.warn(
+        "Dependency 'dask' not installed. If you want to use its functionality, install alphaquant with the 'dask' extra. Falling back to non-dask based processing."
+    )
 
 
 def assign_dataset_chunkwise(input_file, results_dir, samplemap_df , modification_type = "[Phospho (STY)]", id_thresh = 0.6, excl_thresh =0.2 ,swissprot_file = None,
@@ -46,6 +54,12 @@ def assign_dataset_chunkwise(input_file, results_dir, samplemap_df , modificatio
         input_type (str): Type of input data ("Spectronaut" or "DIANN")
         organism (str): Organism name
     """
+    if not HAS_DASK:
+        raise ImportError(
+            "Dask is required for out-of-memory PTM site mapping. "
+            "Install it with: pip install \"alphaquant[dask]\""
+        )
+
     clean_up_previous_processings(results_dir)
 
     if input_type == 'Spectronaut':

pyproject.toml

@@ -53,6 +53,8 @@ optional-dependencies = { stable = { file = ["requirements/requirements.txt",
 ] }, gui-stable = { file = [ "requirements/requirements_gui.txt",
 ] }, tests = { file = [ "requirements/requirements_tests.txt",
 ] }, development = { file = ["requirements/requirements_development.txt", "requirements/requirements_tests.txt",
+] }, dask = { file = [ "requirements/requirements_dask_loose.txt",
+] }, dask-stable = { file = [ "requirements/requirements_dask.txt",
 ] }}
 
 version = {attr = "alphaquant.__version__"}

requirements/requirements.txt

@@ -9,7 +9,6 @@ anytree==2.12.1
 graphviz==0.20.3
 click==8.1.8
 lmfit==1.3.2
-dask==2025.1.0
 multiprocess==0.70.17
 pyfasta==0.5.2
 openpyxl==3.1.5

requirements/requirements_dask.txt

@@ -0,0 +1 @@
+dask==2025.1.0

requirements/requirements_dask_loose.txt

@@ -0,0 +1 @@
+dask

requirements/requirements_loose.txt

@@ -9,7 +9,6 @@ anytree
 graphviz
 click
 lmfit
-dask
 multiprocess
 pyfasta
 openpyxl