remove pythonpath explanation, add hints to pip install, -e

Author: sfluegel05

README.md

@@ -7,25 +7,41 @@ Graph-based models for molecular property prediction and ontology classification
 
 ## Installation
 
-Some dependencies, especially `torch-` libraries, may not install automatically. In case you are experiencing problems, please install them manually **with versions compatible with your installed PyTorch version**.
+To install this repository, download it and run 
+
+```bash
+pip install .
+```
+
+The dependencies `torch`, `torch_geometric` and `torch-sparse` cannot be installed automatically.
 
 Use the following command:
 
 ```bash
-pip install torch_scatter torch_geometric torch_sparse torch_cluster -f https://data.pyg.org/whl/torch-${TORCH}+${CUDA}.html
+pip install torch torch_scatter torch_geometric -f https://data.pyg.org/whl/torch-${TORCH}+${CUDA}.html
 ```
 
 Replace:
 - `${TORCH}` with your installed PyTorch version (e.g., `2.6.0`)
-- `${CUDA}` with: `cpu`, `cu118`, or `cu121` depending on your system and CUDA version
+- `${CUDA}` with e.g. `cpu`, `cu118`, or `cu121` depending on your system and CUDA version
 
-See also [PyTorch Geometric Documentation](https://pytorch-geometric.readthedocs.io/en/latest/install/installation.html)
+For a full list of currently available PyTorch versions and CUDA compatibility, please refer to libraries' official documentation:
+- [torch](https://pytorch.org/get-started/locally/)
+- [torch_geometric](https://pytorch-geometric.readthedocs.io/en/latest/notes/installation.html#installation)
+- [torch-scatter](https://github.com/rusty1s/pytorch_scatter)
+
+_Note for developers_: If you want to install the package in editable mode, use the following command instead:
+
+```bash
+pip install -e .
+```
 
 ## Recommended Folder Structure
 
 ChEB-AI Graph is not a standalone library. Instead, it provides additional models and datasets for [`python-chebai`](https://github.com/ChEB-AI/python-chebai).
+The training relies on config files that are located either in `python-chebai` or in this repository.
 
-Therefore, for training we recommend to clone both repositories into a common parent directory. For instance, your project can look like this:
+Therefore, for training, we recommend to clone both repositories into a common parent directory. For instance, your project can look like this:
 
 ```
 my_projects/
@@ -41,99 +57,14 @@ my_projects/
 
 ## Training & Pretraining
 
-### ⚠️ Important Setup Instructions
-
-Before running any training scripts, ensure your environment is correctly configured:
-
-* **Either**:
-
-    Install the `python-chebai` and `python-chebai-graph` repositories as packages in your environment. To do this, navigate to the root directory of each repository and run:
-    ```bash
-    pip install .
-    ```
-    
-* **OR**
-
-    Manually set the `PYTHONPATH` environment variable if working across multiple directories (`python-chebai` or `python-chebai-graph`):
-
-    If your **current working directory** is `python-chebai`, set:
+### Ontology Prediction
 
-    ```bash
-    export PYTHONPATH=path/to/python-chebai-graph
-    ```
-    
-    or **vice versa**.
 
-> 🔎 See the [PYTHONPATH Explained](#-pythonpath-explained) section below for more details.
-
-
-### 🧠 Pretraining (Atom/Bond Masking on PubChem)
-
-```bash
-python -m chebai fit --model=../python-chebai-graph/configs/model/gnn_resgated_pretrain.yml --data=../python-chebai-graph/configs/data/pubchem_graph.yml --trainer=configs/training/pretraining_trainer.yml
-```
-
-
-### 📊 Ontology Prediction (ChEBI50, v231, 200 epochs)
-
-This command trains a Residual Gated Graph Convolutional Network on the ChEBI50 dataset (see [wiki](https://github.com/ChEB-AI/python-chebai/wiki/Data-Management)). 
+This example command trains a Residual Gated Graph Convolutional Network on the ChEBI50 dataset (see [wiki](https://github.com/ChEB-AI/python-chebai/wiki/Data-Management)). 
 The dataset has a customizable list of properties for atoms, bonds and molecules that are added to the graph. 
-The list can be found in the `configs/data/chebi50_graph_properties.yml` file. 
+The list can be found in the `configs/data/chebi50_graph_properties.yml` file.
 
 ```bash
-python -m chebai fit --trainer=configs/training/default_trainer.yml --trainer.callbacks=configs/training/default_callbacks.yml --model=../python-chebai-graph/configs/model/gnn_res_gated.yml --model.train_metrics=configs/metrics/micro-macro-f1.yml --model.val_metrics=configs/metrics/micro-macro-f1.yml --model.test_metrics=configs/metrics/micro-macro-f1.yml --data=../python-chebai-graph/configs/data/chebi50_graph_properties.yml --model.criterion=configs/loss/bce.yml --data.init_args.batch_size=40 --data.init_args.num_workers=12 --data.init_args.chebi_version=231 --trainer.logger.init_args.name=chebi50_bce_unweighted_resgatedgraph --trainer.min_epochs=200 --trainer.max_epochs=200 --model.pass_loss_kwargs=false
-```
-
-
-
-## 🧭 PYTHONPATH Explained
-
-### What is `PYTHONPATH`?
-
-`PYTHONPATH` is an environment variable that tells Python where to search for modules that aren't installed via `pip` or not in your current working directory.
-
-### Why You Need It
-
-If your config refers to a custom module like:
-
-```yaml
-class_path: chebai_graph.preprocessing.datasets.chebi.ChEBI50GraphData
-```
-
-...and you're running the code from `python-chebai`, Python won't know where to find `chebai_graph` (from another repo like `python-chebai-graph/`) unless you add it to `PYTHONPATH`.
-
-
-### How Python Finds Modules
-
-Python looks for imports in this order:
-
-1. Current directory
-2. Standard library
-3. Paths in `PYTHONPATH`
-4. Installed packages (`site-packages`)
-
-You can inspect the full search paths:
-
-```bash
-python -c "import sys; print(sys.path)"
-```
-
-
-
-### ✅ Setting `PYTHONPATH`
-
-#### 🐧 Linux / macOS
-
-```bash
-export PYTHONPATH=/path/to/python-chebai-graph
-echo $PYTHONPATH
-```
-
-#### 🪟 Windows CMD
-
-```cmd
-set PYTHONPATH=C:\path\to\python-chebai-graph
-echo %PYTHONPATH%
+python -m chebai fit --trainer=configs/training/default_trainer.yml --trainer.logger=configs/training/csv_logger.yml --model=../python-chebai-graph/configs/model/gnn_res_gated.yml --model.train_metrics=configs/metrics/micro-macro-f1.yml --model.test_metrics=configs/metrics/micro-macro-f1.yml --model.val_metrics=configs/metrics/micro-macro-f1.yml --data=../python-chebai-graph/configs/data/chebi50_graph_properties.yml --data.init_args.batch_size=128 --trainer.accumulate_grad_batches=4 --data.init_args.num_workers=10 --model.pass_loss_kwargs=false --data.init_args.chebi_version=241 --trainer.min_epochs=200 --trainer.max_epochs=200 --model.criterion=configs/loss/bce.yml
 ```
 
-> 💡 **Note: This is temporary for your terminal session. To make it permanent, add it to your system environment variables.**