QSAR-Co-X: an open source toolkit for multitarget QSAR modelling

Abstract Quantitative structure activity relationships (QSAR) modelling is a well-known computational tool, often used in wide variety of applications. Yet one the major drawbacks conventional QSAR that models are set up based on limited number experimental and/or theoretical conditions. To overcome this, so-called multitasking or multitarget (mt-QSAR) approaches have emerged as new tools able to integrate diverse chemical and biological data into single model equation, thus extending improving reliability this type modelling. We developed QSAR-Co-X , an open source python–based toolkit (available download at https://github.com/ncordeirfcup/QSAR-Co-X ) for supporting mt-QSAR following Box-Jenkins moving average approach. The embodies several functionalities dataset selection curation plus computation descriptors, setting linear non-linear models, well comprehensive results analysis. workflow within guided by cohort multiple statistical parameters graphical outputs onwards assessing both predictivity robustness derived models. monitor demonstrate designed toolkit, four case-studies pertaining previously reported datasets examined here. believe along with our launched QSAR-Co code, will significantly contribute make widely routinely applicable.