Analysis and Comparison of Vector Space and Metric Space Representations in QSAR Modeling

Kausar, Samina; Falcão, André O.

doi:10.3390/molecules24091698

Cited by 21 publications

(18 citation statements)

References 105 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fingerprints are bit-wise strings with zeroes and ones which are folded to a fixed length [ 38 ]. Even though they work well in building QSAR models [ 39 , 40 ], the folding procedure can introduce bit collision [ 40 , 41 ] meaning that different sub-structural fragments can be assigned to the same position in the vector. As we observe this in our own work we followed recommendations to keep a longer vector and shorter radius [ 41 ].…”

Section: Resultsmentioning

confidence: 99%

Predictive Capability of QSAR Models Based on the CompTox Zebrafish Embryo Assays: An Imbalanced Classification Problem

et al. 2021

View full text Add to dashboard Cite

The CompTox Chemistry Dashboard (ToxCast) contains one of the largest public databases on Zebrafish (Danio rerio) developmental toxicity. The data consists of 19 toxicological endpoints on unique 1018 compounds measured in relatively low concentration ranges. The endpoints are related to developmental effects occurring in dechorionated zebrafish embryos for 120 hours post fertilization and monitored via gross malformations and mortality. We report the predictive capability of 209 quantitative structure–activity relationship (QSAR) models developed by machine learning methods using penalization techniques and diverse model quality metrics to cope with the imbalanced endpoints. All these QSAR models were generated to test how the imbalanced classification (toxic or non-toxic) endpoints could be predicted regardless which of three algorithms is used: logistic regression, multi-layer perceptron, or random forests. Additionally, QSAR toxicity models are developed starting from sets of classical molecular descriptors, structural fingerprints and their combinations. Only 8 out of 209 models passed the 0.20 Matthew’s correlation coefficient value defined a priori as a threshold for acceptable model quality on the test sets. The best models were obtained for endpoints mortality (MORT), ActivityScore and JAW (deformation). The low predictability of the QSAR model developed from the zebrafish embryotoxicity data in the database is mainly due to a higher sensitivity of 19 measurements of endpoints carried out on dechorionated embryos at low concentrations.

show abstract

Section: Resultsmentioning

confidence: 99%

Predictive Capability of QSAR Models Based on the CompTox Zebrafish Embryo Assays: An Imbalanced Classification Problem

et al. 2021

View full text Add to dashboard Cite

show abstract

“…To reach this goal, the molecular spaces of four data sets, captured as similarity matrices that were computed using NAMS, a graph matching algorithm. In a previous study NAMS-based molecular metric space representation was found a reliable approach to establish molecular similarity-activity relationship in QSAR modeling [38]. Accordingly NAMS-based molecular spaces for the selected data sets were reduced into a new reference space in 2D using four different algorithms.…”

Section: Resultsmentioning

confidence: 99%

“…We have thus integrated the advantages of the following different methods in the proposed molecular space mapping approach:Choice of molecular space representation: Molecular pairwise similarity was quantified using a graph matching algorithm: The Non-contiguous Atom Matching Structural similarity (NAMS) [17], which is a robust metric space representation method. This algorithm has a higher discriminative power for very similar molecules over other structural or graph matching approaches [17, 38]. However, any other similarity computation method can be used.DR methods: We applied four non-linear DR methods including Principal Coordinates Analysis (PCooA) [27], Kruskal Multidimensional Scaling (KMDS) [28], Sammon mapping (SM), [29] and t-Distributed Stochastic Neighbor Embedding (t-SNE) [39].…”

Section: Introductionmentioning

confidence: 99%

“…Choice of molecular space representation: Molecular pairwise similarity was quantified using a graph matching algorithm: The Non-contiguous Atom Matching Structural similarity (NAMS) [17], which is a robust metric space representation method. This algorithm has a higher discriminative power for very similar molecules over other structural or graph matching approaches [17, 38]. However, any other similarity computation method can be used.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A visual approach for analysis and inference of molecular activity spaces

Kausar

Falcão

2019

J Cheminform

Self Cite

View full text Add to dashboard Cite

BackgroundMolecular space visualization can help to explore the diversity of large heterogeneous chemical data, which ultimately may increase the understanding of structure-activity relationships (SAR) in drug discovery projects. Visual SAR analysis can therefore be useful for library design, chemical classification for their biological evaluation and virtual screening for the selection of compounds for synthesis or in vitro testing. As such, computational approaches for molecular space visualization have become an important issue in cheminformatics research. The proposed approach uses molecular similarity as the sole input for computing a probabilistic surface of molecular activity (PSMA). This similarity matrix is transformed in 2D using different dimension reduction algorithms (Principal Coordinates Analysis ( PCooA), Kruskal multidimensional scaling, Sammon mapping and t-SNE). From this projection, a kernel density function is applied to compute the probability of activity for each coordinate in the new projected space.ResultsThis methodology was tested over four different quantitative structure-activity relationship (QSAR) binary classification data sets and the PSMAs were computed for each. The generated maps showed internal consistency with active molecules grouped together for all data sets and all dimensionality reduction algorithms. To validate the quality of the generated maps, the 2D coordinates of test molecules were computed into the new reference space using a data transformation matrix. In total sixteen PSMAs were built, and their performance was assessed using the Area Under Curve (AUC) and the Matthews Coefficient Correlation (MCC). For the best projections for each data set, AUC testing results ranged from 0.87 to 0.98 and the MCC scores ranged from 0.33 to 0.77, suggesting this methodology can validly capture the complexities of the molecular activity space. All four mapping functions provided generally good results yet the overall performance of PCooA and t-SNE was slightly better than Sammon mapping and Kruskal multidimensional scaling.ConclusionsOur result showed that by using an appropriate combination of metric space representation and dimensionality reduction applied over metric spaces it is possible to produce a visual PSMA for which its consistency has been validated by using this map as a classification model. The produced maps can be used as prediction tools as it is simple to project any molecule into this new reference space as long as the similarities to the molecules used to compute the initial similarity matrix can be computed.

show abstract

“…Recently, QSAR analysis using the deep neural network (DNN) has shown superior prediction performance compared with other conventional machine learning (ML) methods [38][39][40][41][42]. Such high-performance prediction methods may rely on the clear definition of feature representation or selection as it depends on the chemical space [43,44]. For appropriate feature selection or representation, some exclusive procedures based on chemical intuition and observed properties or filtering methods that evaluate features according to a given criterion have been employed [43,45].…”

Section: Introductionmentioning

confidence: 99%

Prediction Model of Aryl Hydrocarbon Receptor Activation by a Novel QSAR Approach, DeepSnap–Deep Learning

et al. 2020

View full text Add to dashboard Cite

The aryl hydrocarbon receptor (AhR) is a ligand-dependent transcription factor that senses environmental exogenous and endogenous ligands or xenobiotic chemicals. In particular, exposure of the liver to environmental metabolism-disrupting chemicals contributes to the development and propagation of steatosis and hepatotoxicity. However, the mechanisms for AhR-induced hepatotoxicity and tumor propagation in the liver remain to be revealed, due to the wide variety of AhR ligands. Recently, quantitative structure–activity relationship (QSAR) analysis using deep neural network (DNN) has shown superior performance for the prediction of chemical compounds. Therefore, this study proposes a novel QSAR analysis using deep learning (DL), called the DeepSnap–DL method, to construct prediction models of chemical activation of AhR. Compared with conventional machine learning (ML) techniques, such as the random forest, XGBoost, LightGBM, and CatBoost, the proposed method achieves high-performance prediction of AhR activation. Thus, the DeepSnap–DL method may be considered a useful tool for achieving high-throughput in silico evaluation of AhR-induced hepatotoxicity.

show abstract

Analysis and Comparison of Vector Space and Metric Space Representations in QSAR Modeling

Cited by 21 publications

References 105 publications

Predictive Capability of QSAR Models Based on the CompTox Zebrafish Embryo Assays: An Imbalanced Classification Problem

Predictive Capability of QSAR Models Based on the CompTox Zebrafish Embryo Assays: An Imbalanced Classification Problem

A visual approach for analysis and inference of molecular activity spaces

Prediction Model of Aryl Hydrocarbon Receptor Activation by a Novel QSAR Approach, DeepSnap–Deep Learning

Contact Info

Product

Resources

About