Abstract
Quantitative structure-activity relationship (QSAR) models based on machine learning algorithms are powerful tools to expedite drug discovery processes and therapeutics development. Given the cost in acquiring large-sized training datasets, it is useful to examine if QSAR analysis can reasonably predict drug activity with only a small-sized dataset (size <; 100) and benchmark these small-dataset QSAR models in application-specific studies. To this end, here we present a systematic benchmarking study on small-dataset QSAR models built for prediction of effective Wnt signaling inhibitors, which are essential to therapeutics development in prevalent human diseases (e.g., cancer). Specifically, we examined a total of 72 two-dimensional (2D) QSAR models based on 4 best-performing algorithms, 6 commonly used molecular fingerprints, and 3 typical fingerprint lengths. We trained these models using a training dataset (56 compounds), benchmarked their performance on 4 figures-of-merit (FOMs), and examined their prediction accuracy using an external validation dataset (14 compounds). Our data show that the model performance is maximized when: 1) molecular fingerprints are selected to provide sufficient, unique, and not overly detailed representations of the chemical structures of drug compounds; 2) algorithms are selected to reduce the number of false predictions due to class imbalance in the dataset; and 3) models are selected to reach balanced performance on all 4 FOMs. These results may provide general guidelines in developing high-performance small-dataset QSAR models for drug activity prediction.
Highlights
Drug development often involves extensive investment and time effort on experimental screening of drug candidates
Our data show that the model performance is maximized when: 1) molecular fingerprints are selected to provide sufficient, unique, and not overly detailed representations of the chemical structures of drug compounds; 2) algorithms are selected to reduce the number of false predictions due to class imbalance in the dataset; and 3) models are selected to reach balanced performance on all 4 FOMs
ALGORITHMS Using the fingerprint representations of 56 compounds in the training dataset with known activity for Wnt signaling inhibition, we developed predictive QSAR models based on four machine learning algorithms: QSVM, fine tree, bagged tree, and RUSboosted tree
Summary
Drug development often involves extensive investment and time effort on experimental screening of drug candidates. Computational methods based on threedimensional quantitative structure-activity relationship (3D QSAR) analysis, high-throughput imaging (HTI), and pharmacophore modeling [5], [6]-[10] have succeeded in predicting the effectiveness of drug compounds towards prevalent human diseases (e.g., cancer [10]). These high-performance methods often require user intervention steps on molecular/ligand alignment [5], [8], [9]. This analysis correlates the structural details of drug molecules to their effectiveness in biological assays that correspond to specific diseases and builds models that can predict the bioactivity or physiochemical properties of unknown drug compounds [1], [2], [3], [6]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
