Merge pull request #1 from uzh-dqbm-cmi/attn_siamese_paper_review

Attn siamese paper review

.gitignore

@@ -1,2 +1,57 @@
 *.p
 *.pickle
+
+.DS_Store
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Vs code
+.vscode
+
+# orisenbazuru
+explore.py
+notebooks/orisenbazuru/*
+notebooks/archive/*
+ideas.txt.rtf
+trained_models
+data/processed

README.md

@@ -1 +1,16 @@
-# side-effects
+# 📣 AttentionDDI 💊
+
+This repository contains the code for the AttentionDDI model implementation with PyTorch. 
+
+AttentionDDI is a Siamese multi-head self-Attention multi-modal neural network model used for drug-drug interaction (DDI) predictions.
+
+## Installation
+
+* `git clone` the repo and `cd` into it.
+* Run `pip install -e .` to install the repo's python package.
+
+## Running 🏃
+
+1. use `notebooks/jupyter/AttnWSiamese_data_generation.ipynb` to generate DataTensors from the drug similarity matrices.
+2. use `notebooks/jupyter/AttnWSiamese_hyperparam.ipynb` to find the best performing model hyperparameters.
+3. use `notebooks/jupyter/AttnWSiamese_train_eval.ipynb` to train / test on the best hyperparameters.