diff --git a/README.md b/README.md
index d0dc887..036da05 100644
--- a/README.md
+++ b/README.md
@@ -1,3 +1,5 @@
+[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.8150601.svg)](https://doi.org/10.5281/zenodo.8150601)
+
 # Train and evaluate espaloma
 This repository includes scripts to retrain and generate `espaloma-0.3.0` forcefield.
 `espaloma-0.3.0` force field is a `Class I` force field where the valence parameters are assigned and optimized via machine learning framework.
@@ -51,4 +53,7 @@ Please refer [here](https://github.com/choderalab/download-qca-datasets) to find
 [Espaloma ver. 0.3.0](https://github.com/choderalab/espaloma/tree/0.3.0) was used to create the DGL graphs in `01-create-dataset/`.
 Note that version 0.3.0 is no longer compatible with the 0.2.x models, and vice versa.
 A fixed version of 0.3.0 (commit hash:[4c6155b72d00ce0190b3cb551e7e59f0adc33a56](https://github.com/choderalab/espaloma/tree/4c6155b72d00ce0190b3cb551e7e59f0adc33a56)) 
-was used for the refitting experinment and model evaluation which allows improper torsions to be fit to n=1,2 phase multiplicity.
\ No newline at end of file
+was used for the refitting experinment and model evaluation which allows improper torsions to be fit to n=1,2 phase multiplicity.
+
+## Note
+For a quick start, the preprocessed data in `openff-default/02-train/merge-data/` is available [here](https://doi.org/10.5281/zenodo.8150601) on Zenodo for training `espaloma-0.3.0`.
\ No newline at end of file
diff --git a/openff-default/02-train/merge-data/README.md b/openff-default/02-train/merge-data/README.md
index b749131..3afa62e 100644
--- a/openff-default/02-train/merge-data/README.md
+++ b/openff-default/02-train/merge-data/README.md
@@ -6,6 +6,8 @@ This repository contains scripts to prepare the input DGL graphs used in trainin
 - Seperating duplicated isomeric smiles within different datasets into a new dataset
 - Merge duplicated isomeric smiles from different datasets into a single DGL graph
 
+The preprocessed data in `openff-default/02-train/merge-data/` is available [here](https://doi.org/10.5281/zenodo.8150601) on Zenodo for training `espaloma-0.3.0`.
+
 ## Manifest
 - `script`: Stores main scripts to filter and prepare input DGL graphs in training espaloma
     - `calc_ff.py`: Compute baseline energies and forces using `gaff-1.81`, `gaff-2.11`, `openff-1.2.1`, `openff-2.0.0`, and `Amber ff14SB (RNA.OL3)`