Update README.md

README.md

@@ -1,9 +1,17 @@
-# Model checkpoints for Madrigal
-
-GitHub repo: https://github.com/mims-harvard/Madrigal
-
-This repo contains first- (modality adapation) and second- (modality alignment) stage pretraining, and DDI finetuning (on DrugBank DDI dataset) checkpoints. See our GitHub for file organization after downloading.
-
----
-license: cc-by-4.0
----
+---
+tags:
+- biology
+---
+# Madrigal
+
+Madrigal is an open-source model for predicting drug combination outcomes from multimodal preclinical data. This repository provides the weights of the model as described in our [project page](https://zitniklab.hms.harvard.edu/projects/Madrigal/) and our paper. Specifically, weights of the model after the following two stages are provided:
+- Modality alignment: `pretrain/2024-02-06_18%3A12_helpful-field-81/checkpoint_1000.pt`
+- DDI finetuning (on DrugBank DDI dataset): `DrugBank/split_by_pairs/{run_name}/checkpoint_700.pt`
+
+Pretrained weights for individual modality encoders after modality adapation are provided in the [GitHub repo](https://github.com/mims-harvard/Madrigal).
+
+Please see our GitHub repo for file organization instructions after downloading. For more information on the model architecture, training, and evaluation, please see the [overview page](https://zitniklab.hms.harvard.edu/projects/Madrigal/) or the paper.
+
+---
+license: cc-by-4.0
+---