Stacked Ensemble for Bioactive Molecule Prediction

Abstract

Bioactive molecular compounds are essential for drug discovery. The biological activity of these compounds needs to be predicted as this is used to determine the drug-target ability. As ineffective drugs are discarded after production, leading to resource and time wastage, it is important to predict bioactive molecules with models having high predictive performance. This study utilizes the stacked ensemble which uses the prediction of multiple base classifiers as features, used to train a meta classifier which makes the final prediction. Using three datasets DS1, DS2, and DS3 gotten from MDL Drug Data Report (MDDR) database, the performance of stacked ensemble was compared to three other ensembles: adaboost, bagging, and vote ensemble, based on different evaluation criteria and also a statistical method, Kendall's W test. The accuracy of Stacked ensemble ranged from 96.7002%, 98.2260% and 94.9007% for the three datasets respectively, although Vote had the best accuracy using dataset DS2 which consist of structurally homogeneous bioactive molecules. Also, using Kendall's W test to rank the ensembles, Stacked ensemble was ranked best with datasets DS1 and DS3, with both having a mean average of 4.00 and an overall level of agreement, W, of 0.986 and 1.000 respectively. Using dataset DS2, it was ranked after Vote and Adaboost with mean average of 2.33 and an overall level of agreement, W of 0.857. Stacked ensemble is recommended for the prediction of heterogeneous bioactive molecules during drug discovery and can also be implemented in other research areas.INDEX TERMS Bioactive molecule prediction, chemoinformatics, drug discovery, ensemble, stacked ensemble.

Benchmarking Small-Dataset Structure-Activity-Relationship Models for Prediction of Wnt Signaling Inhibition

“…However, these assays have yet to experimentally test a sufficient number of active or inactive compounds, therefore making the QSAR modeling challenging (e.g., 3 active compounds in [36]). On the other hand, we found that the size of our dataset, 70, is on par with other small-dataset QSAR studies (e.g., 16 in [19], and 48 in [20]); we thus believe this dataset has a sufficient number of data to build goodperforming QSAR models.…”

“…Nonetheless, current 2D QSAR analysis often relies on training machine learning algorithms with a large-sized drug activity dataset (size > 1000) [6], [16], which requires significant time and effort on both benchwork and statistical analysis. For this reason, developing new drugs can cost hundreds of millions of U.S. dollars [17] and can take over a decade to transition to a marketable state [18].…”

Smart factory floor safety monitoring using UWB sensor

“…The stacked ensemble (SE) learning was first demonstrated by Wolpert [40], where authors exhibited a stacked formation of strong and weak ML algorithms which could improvise framework accuracy and filter samples by boosting training competency and lessening overfitting issues. Several researchers have represented their approaches based on SE classification for numerous areas such as network intrusion detection (NID), statistics, forecasting big data, and human activity recognition [40,41]. The primary concept of SE architecture is the combination of weak ML algorithms to generate a strong framework.…”

Reactions’ Descriptors Selection and Yield Estimation Using Metaheuristic Algorithms and Voting Ensemble

“…It is also used to yield poly (arylene-amine) from arylamines polymerisation [5], yield aryl and heteroaryl chlorides in an aqueous condition free from solvent [6], and synthesise iron (II) clathrochelate unit bearing secondary arylamine copolymers due to the strong compounds which it yields. Surveys carried out by Gómez-Bombarelli et al [7] and Rodrigues et al [8] shows that chemical space search and optimization, virtual screening, discovery of drug target, the prediction of protein structures, chemical properties, gene-gene interaction, bioactivity of molecules in a compound [9], and toxicity [10], are some of the ways predictive analysis has been applied to the vast data produced in biochemical studies [11].…”