Update README.md

README.md

@@ -7,7 +7,6 @@ datasets:
 pipeline_tag: text-classification
 tags:
 - protein language model
-- chemistry
 - biology
 widget:
 - text: >-
@@ -77,7 +76,7 @@ prediction = probability.argmax(dim=-1) # 0 for no interaction, 1 for interactio
 We define a protein-protein interaction as physical contact that mediates chemical or conformational change, especially with non-generic function. However, due to SYNTERACTS propensity to predict false positives we believe that it identifies plausible conformational changes caused by interactions without relevance to function. Therefore, predictions by SYNTERACT should always be taken with a grain of salt and used as a means of hypothesis generation or secondary validation. 
 
 ## Our lab
-The [Gleghorn lab](https://www.gleghornlab.com/) is an interdiciplinary research group out of the University of Delaware that focuses on translational problems around biomedicine. Recently we have begun exploration into machine learning for image segmentation and protein language model based projects like this one.
+The [Gleghorn lab](https://www.gleghornlab.com/) is an interdiciplinary research group out of the University of Delaware that focuses on translational problems around biomedicine. Recently we have begun exploration into protein language models and are passionate about excellent protein design and annotation.
 
 ## Please cite
 @article {Hallee2023.06.07.544109,