Update README.md

Author: trrt-good

README.md

@@ -3,7 +3,7 @@
 This is the official code repository for PLAPT, a state-of-the-art 1D sequence-only protein-ligand binding affinity predictor, first introduced [here](https://community.wolfram.com/groups/-/m/t/3094670)
 
 ### Abstract
-This study, introduces the Protein Ligand Binding Affinity Prediction Using Pretrained Transformers (PLAPT) model, an innovative machine learning approach to predict protein-ligand binding affinities with high accuracy and generalizability, leveraging the wide knowledge of pretrained transformer models. By using ProtBERT and ChemBERTa for encoding protein and ligand sequences, respectively, we trained a two-branch dense neural network that effectively fuses these encodings to estimate binding affinity values. The PLAPT model not only achieves a high Pearson correlation coefficient of ~0.8, but also exhibits negligible overfitting, a remarkable feat in the context of computational affinity prediction. The robustness of PLAPT, attributed to its generalized transfer learning approach from pre-trained encoders, demonstrates the substantial potential of leveraging extant biochemical knowledge to enhance predictive models in drug discovery.
+Understanding protein-ligand binding affinity is crucial for drug discovery, enabling the identification of promising drug candidates efficiently. We introduce PLAPT, a novel model leveraging transfer learning from pre-trained transformers like ProtBERT and ChemBERTa to predict binding affinities with high accuracy. Our method processes one-dimensional protein and ligand sequences, leveraging a branching neural network architecture for feature integration and affinity estimation. We demonstrate PLAPT's superior performance through validation on multiple datasets, achieving state-of-the-art results while requiring significantly less computational resources for training compared to existing models. Our findings indicate that PLAPT offers a highly effective and accessible approach for accelerating drug discovery efforts.
 
 ![PLAPT Architecture](https://github.com/trrt-good/WELP-PLAPT/blob/main/Diagrams/PLAPT.png)