Update README.md

README.md

@@ -13,24 +13,22 @@ tags:
 
 <!-- Provide a quick summary of what the model is/does. -->
 
+
+CLASPP is a ESM2-150m protein lanuguage model that can pred PTM envents occuring on the substrate based 
+off primary protein sequence. This is done on multiple differnt PTM types (12) as a form of multi-label
+classifcation. The encoder is training on a supervised Contrastive learing task then the classifcation
+head is finetunted on the multi-label classifcation. 
+
 Post-Translational Modifications (PTMs) are a fundamental mechanism for regulating cellular functions and 
 increasing the functional diversity of the proteome. Despite the identification of hundreds of unique PTMs 
 through mass-spectrometry (MS) studies, accurately predicting many PTM types based on sequence data alone 
-remains a significant challenge. Existing PTM prediction models predominantly focus on either single PTM 
-types or employ ensemble methods that combine multiple models to predict different PTM types. This fragmentation 
-is largely driven by the vast imbalance in data availability across PTM types making it difficult to predict 
-multiple PTM types with a single model. To address this limitation, we present the Contrastively Learned 
-Attention-Based Stratified PTM Predictor (CLASPP), a unified PTM prediction model. CLASPP overcomes 
-data imbalance challenges by leveraging unsupervised clustering-based under-sampling and incorporating a novel 
-contrastive learning framework tailored to PTM data. Drawing inspiration from advancements in image and 
-natural language processing, the CLASPP model employs a multi-stage training strategy and utilizes a 
-high-quality curated training dataset to improve PTM prediction accuracy compared to existing multi-PTM prediction 
-models. Existing PTM prediction models predominantly focus on either single PTM types or employ ensemble methods 
+remains a significant challenge. 
+
+Existing PTM prediction models predominantly focus on either single PTM types or employ ensemble methods 
 that combine multiple models to predict different PTM types. This fragmentation is largely driven by the 
 vast imbalance in data availability across PTM types making it difficult to predict multiple PTM types 
-with a single model. To address this limitation, we present the 
-Contrastively Learned Attention-Based Stratified PTM Predictor (CLASPP), a unified PTM prediction model. 
-
+with a single model. To address this limitation, we present the Contrastively Learned Attention-Based 
+Stratified PTM Predictor (CLASPP), a unified PTM prediction model.
 
 
 <p align="center">