diff --git a/README.md b/README.md
index 8e7a971..ab1c38f 100644
--- a/README.md
+++ b/README.md
@@ -1,6 +1,6 @@
-= decagon-pytorch
+# decagon-pytorch
 
-== Introduction
+## Introduction
 
 [Decagon](https://github.com/mims-harvard/decagon)
 is a method for learning node embeddings in multimodal graphs,
@@ -9,7 +9,7 @@ settings.
 
 Decagon-PyTorch is a PyTorch reimplementation of the algorithm.
 
-== References
+## References
 
 1. Zitnik, M., Agrawal, M., & Leskovec, J. (2018).
 [Modeling polypharmacy side effects with graph convolutional networks](https://academic.oup.com/bioinformatics/article/34/13/i457/5045770)