Exploring Molecular Descriptors and Fingerprints to Predict mTOR Kinase Inhibitors using Machine Learning Techniques

Kumari, Chetna; Abulaish, Muhammad; Subbarao, Naidu

doi:10.1109/tcbb.2020.2964203

Cited by 8 publications

(7 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Balanced Accuracy (BA) overcomes regular accuracy problems as it accounts for imbalanced classes 24,41 . It is calculated based on the confusion matrix as shown in Eq.…”

Section: (Ct Ii−i 1mentioning

confidence: 99%

“…Mathew's correlation coefficient (MCC) is another widely used metric that has a high level of confidence and is considered the most important indicator when a training dataset is imbalanced 24 . MCC can be calculated from the confusion matrix as in Eq.…”

Section: (Ct Ii−i 1mentioning

confidence: 99%

“…The large amount of data about kinase inhibitors, 115000 inhibitors with a measured activity, made them a subject to data analysis and modelling in different studies 8 There are many studies that used machine learning to target kinase related problems such as predicting kinase activity state 23 , and predicting bioactivity of compounds against mTOR kinase 24 , and others. However, few studies targeted the problem of predicting inhibitor binding modes.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Prediction of kinase inhibitors binding modes with machine learning and reduced descriptor sets

Abdelbaky

Tayara

Chong

2021

Sci Rep

View full text Add to dashboard Cite

Protein kinases are receiving wide research interest, from drug perspective, due to their important roles in human body. Available kinase-inhibitor data, including crystallized structures, revealed many details about the mechanism of inhibition and binding modes. The understanding and analysis of these binding modes are expected to support the discovery of kinase-targeting drugs. The huge amounts of data made it possible to utilize computational techniques, including machine learning, to help in the discovery of kinase-targeting drugs. Machine learning gave reasonable predictions when applied to differentiate between the binding modes of kinase inhibitors, promoting a wider application in that domain. In this study, we applied machine learning supported by feature selection techniques to classify kinase inhibitors according to their binding modes. We represented inhibitors as a large number of molecular descriptors, as features, and systematically reduced these features in a multi-step manner while trying to attain high classification accuracy. Our predictive models could satisfy both goals by achieving high accuracy while utilizing at most 5% of the modeling features. The models could differentiate between binding mode types with MCC values between 0.67 and 0.92, and balanced accuracy values between 0.78 and 0.97 for independent test sets.

show abstract

“…Balanced Accuracy (BA) overcomes regular accuracy problems as it accounts for imbalanced classes 24,41 . It is calculated based on the confusion matrix as shown in Eq.…”

Section: (Ct Ii−i 1mentioning

confidence: 99%

Section: (Ct Ii−i 1mentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Prediction of kinase inhibitors binding modes with machine learning and reduced descriptor sets

Abdelbaky

Tayara

Chong

2021

Sci Rep

View full text Add to dashboard Cite

show abstract

“…In addition to the fingerprint metrics, maximum common substructure (MCS, which is based on overlap between the two molecules represented as chemical graphs) [ 53 ] and the physicochemical descriptors (numerical properties) were included as additional predictor variables based on their previously noted utility [ 25 , 54 , 55 ]. The MCS calculation reports several statistics, amongst which the MCS size (median = 8), tanimoto score (median = 0.19) and OC (overlapping coefficient) (median = 0.43) score are important measures to assess similarity.…”

Section: Resultsmentioning

confidence: 99%

Bioactivity assessment of natural compounds using machine learning models trained on target similarity between drugs

et al. 2022

View full text Add to dashboard Cite

Natural compounds constitute a rich resource of potential small molecule therapeutics. While experimental access to this resource is limited due to its vast diversity and difficulties in systematic purification, computational assessment of structural similarity with known therapeutic molecules offers a scalable approach. Here, we assessed functional similarity between natural compounds and approved drugs by combining multiple chemical similarity metrics and physicochemical properties using a machine-learning approach. We computed pairwise similarities between 1410 drugs for training classification models and used the drugs shared protein targets as class labels. The best performing models were random forest which gave an average area under the ROC of 0.9, Matthews correlation coefficient of 0.35, and F1 score of 0.33, suggesting that it captured the structure-activity relation well. The models were then used to predict protein targets of circa 11k natural compounds by comparing them with the drugs. This revealed therapeutic potential of several natural compounds, including those with support from previously published sources as well as those hitherto unexplored. We experimentally validated one of the predicted pair’s activities, viz., Cox-1 inhibition by 5-methoxysalicylic acid, a molecule commonly found in tea, herbs and spices. In contrast, another natural compound, 4-isopropylbenzoic acid, with the highest similarity score when considering most weighted similarity metric but not picked by our models, did not inhibit Cox-1. Our results demonstrate the utility of a machine-learning approach combining multiple chemical features for uncovering protein binding potential of natural compounds.

show abstract

“…The vectors from drug molecules with known effectiveness to one targeted biological assay (active vs. inactive) will be used to build predictive QSAR models based on machine learning algorithms such as support vector machines (SVM), decision trees, k-nearest neighbors (KNN), and artificial neural network (ANN) [6], [12]. The resulting QSAR models have succeeded in predicting effective drugs of psychological disorders [13], protein-ligand binding affinities [14], and mTOR kinase inhibitors [15].…”

Section: Introductionmentioning

confidence: 99%

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

Kokabi¹,

Donnelly²,

Xu³

2020

IEEE Access

View full text Add to dashboard Cite

Exploring Molecular Descriptors and Fingerprints to Predict mTOR Kinase Inhibitors using Machine Learning Techniques

Cited by 8 publications

References 43 publications

Prediction of kinase inhibitors binding modes with machine learning and reduced descriptor sets

Prediction of kinase inhibitors binding modes with machine learning and reduced descriptor sets

Bioactivity assessment of natural compounds using machine learning models trained on target similarity between drugs

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

Contact Info

Product

Resources

About