To Download: Click Here 

MLR plus Validation 1.3 (Last updated on 12 June 2017) tool develops QSAR model using MLR technique and calculates internal, and external validation parameters of the developed model [1,2]. Further it judges the test set predictions based on the actual prediction errors as GOOD, MODERATE and BAD [3]. It also checks Golbarikh and Tropsha model acceptibillity criteria [4], and optionally can determine applicability domain (AD) employing two available methods i.e., Standardization Approach [5] and Euclidean-based Method [6]. User may also perform Y randomization.

To Download and Run the Program

Click on the download link above (it will direct you to google drive) and then press "ctrl + S (Windows) or cmd+S (Macs)" to save as zip file. Extract the .zip file and click on .jar file to run the program.

Note: The program folder will consist of three folders "Data", "Lib" and "Output". For user convenience, user may keep input files in "Data" folder and may save output file in "Output" folder."Lib" folder consists of library files required for running the program. Check the format of training and test sets input files (.xlsx/.xls/.csv) before using the program (sample files are provided in Data Folder). *Manual is provided in the program folder.

File Format: Compound number (first column), Descriptors (Subsequent Columns), Activity/Property (Last column)

       Reference Articles for MLR plus Validation Tool

1.   Roy, Kunal, and Indrani Mitra. "On various metrics used for validation of predictive QSAR models with applications in virtual screening and focused library design." Combinatorial chemistry & high throughput screening 14, no. 6 (2011): 450-474.

2.  Roy, Kunal, et al. "Some case studies on application of “rm2” metrics for judging quality of quantitative structure–activity relationship predictions: emphasis on scaling of response data." Journal of computational chemistry34.12 (2013): 1071-1082.

3. Roy K, Das RN, Ambure P, Aher RB, "Be aware of error measures. Further studies on validation of predictive QSAR models." Chemom. Intell. Lab. Sys.,(2016), 152, 18–33. doi:10.1016/j.chemolab.2016.01.008 (Click here).

4.  Golbraikh, Alexander, and Alexander Tropsha. "Beware of q 2!." Journal of Molecular Graphics and Modelling 20.4 (2002): 269-276.

5. Roy, Kunal, Supratik Kar, and Pravin Ambure. "On a simple approach for determining applicability domain of QSAR models." Chemometrics and Intelligent Laboratory Systems 145 (2015): 22-29.

6.   Golmohammadi, Hassan, Zahra Dashtbozorgi, and William E. Acree. "Quantitative structure–activity relationship prediction of blood-to-brain partitioning behavior using support vector machine." European Journal of Pharmaceutical Sciences 47.2 (2012): 421-429.