Improve introduction

README.md

@@ -9,9 +9,9 @@
 Cesaire J. K. Fouodo
 
 ### Introduction
-Recent technological advances have enabled the simultaneous targeting of multiple pathways to enhance therapies for complex diseases. This often results in the collection of numerous data entities across various layers of patient groups, posing a challenge in integrating all data into a single analysis. Ideally, patient data will overlap across layers, allowing for early or intermediate integrative techniques. However, when patient data does not overlap well, these techniques are difficult to apply. Late integration modeling addresses this by analyzing each data entity separately to obtain layer-specific results, which are then integrated using meta-analysis.
+Recent technological advances have enabled the simultaneous targeting of multiple pathways to enhance therapies for complex diseases. This often results in the collection of numerous data entities across various layers of patient groups, posing a challenge in integrating all data into a single analysis. Ideally, patient data will overlap across layers, allowing for early or intermediate integrative techniques. These techniques are challenging when patient data does not overlap well. Late integration modeling addresses this by analyzing each data entity separately to obtain layer-specific results, which are then integrated using meta-analysis. As data entities can differ by their internal architectures, it is commonly preferable to utilize layer-specific analysis methods instead of a single analysis method across all layers. 
 
-To address this need, we introduce the fuseMLR package for R, designed to facilitate late integration modeling. With fuseMLR, users can define a study with multiple layers and corresponding data entities, and train the entire study as a single task. The package is user-friendly, allowing for the training of different models across layers. Additionally, fuseMLR enables users to perform variable selection at the layer level and make predictions for new studies within a single task.
+We introduce the package fuseMLR for late integration modeling in R. The package allows users to define a study with multiple layers, data entities and layer-specific machine learning methods. After study definition user can train the entire study as a single task. The package is user-friendly, allowing for the training of different models across layers and conducts the meta analysis once layer-specific training is completed. Additionally, fuseMLR enables users to perform variable selection at the layer level and make predictions for new studies within a single task.
 
 ### Installation
 Installation from Github: