ifyoungnet/chemsar

a web-based platform to realize the online pipelining of molecular SAR modelling

ChemSAR

A web-based platform to realize the online pipelining of molecular SAR modelling.
It is now availiable at http://chemsar.scbdd.com

Introduction

It is not easy for pharmaceutical chemist or medical researchers to perform a complete SAR modelling pipenining because of the requirements for programming skills when using package tools or software in most instances. Here, we developed a smart and easy-to-use platform, which can be used to work through the whole modelling process just by clicking mouse. ChemSAR is able to accomplish six model generation steps:

• (1) structure preprocessing
• (2) molecular descriptor calculation
• (3) data preprocessing
• (4) feature selection
• (5) model building and prediction
• (6) statistical analysis

These six steps together with several assistant tools are designed as five main modules:

• (1) User space
• (2) Structure preprocessing
• (3) Data preprocessing
• (4) Modelling process
• (5) Tools

Each of them not only could be utilized as one part of the whole pipelining, but also could be used alone.

Features

• (1) ChemSAR realized a whole online model building process, which enables medicinal chemists and biologists
• to obtain predictive models conveniently without requiring tedious deployment and programming skills.
• (2) ChemSAR provided a comprehensive modelling pipelining, which integrated six model generation steps into the current web platform and contributed to a unified workflow of modelling.
• (3) The modular design of the framework enables five sub-modules to run independently to accomplish specific functionalities.
• (4) The way of submission based on job task strategy could enable different users to query the calculation results at spare time. This creates an essential basis for the report system to generate a clear model report.
• (5) The modular design of the framework allows researchers to deal with not only small molecular analysis but also modelling problems in the biomedical field. For example, building a classification model based on the biochemical indicators of patients helps study the disease classification or stage.