Fix paper URL

README.md

@@ -5,7 +5,7 @@ inference: false
 
 # Enformer
 
-Enformer model. It was introduced in the paper [Effective gene expression prediction from sequence by integrating long-range interactions.](https://arxiv.org/abs/2010.11929) by Avsec et al. and first released in [this repository](https://github.com/deepmind/deepmind-research/tree/master/enformer). 
+Enformer model. It was introduced in the paper [Effective gene expression prediction from sequence by integrating long-range interactions.](https://www.nature.com/articles/s41592-021-01252-x) by Avsec et al. and first released in [this repository](https://github.com/deepmind/deepmind-research/tree/master/enformer). 
 
 This particular model was trained on sequences of 196,608 basepairs, target length 896, with shift augmentation but without reverse complement, on poisson loss objective. Final human pearson R of ~0.45.
 
@@ -17,7 +17,7 @@ Disclaimer: The team releasing Enformer did not write a model card for this mode
 
 Enformer is a neural network architecture based on the Transformer that led to greatly increased accuracy in predicting gene expression from DNA sequence.
 
-We refer to the [paper](https://www.nature.com/articles/s41592-021-01252-x#citeas) published in Nature for details.
+We refer to the [paper](https://www.nature.com/articles/s41592-021-01252-x) published in Nature for details.
 
 ### How to use