Chemoinformatics Taking Biology into Account: Proteochemometrics

Wikberg, Jarl E. S.; Spjuth, Ola; Eklund, Martin; Lapins, Maris

doi:10.1002/9781118131411.ch3

Cited by 5 publications

(6 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PLS aims to find the quantitative relationship between 2 matrix of independent variables X and dependent matrix or vector of response variables Y through the simultaneous projection of X and Y to latent variables (PLS components) . This approach has been frequently used in PCM modeling, due to its robustness and interpretability …”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Probing the origin of dihydrofolate reductase inhibition via proteochemometric modeling

Hariri

Ghasemi

Shirini

et al. 2018

Journal of Chemometrics

View full text Add to dashboard Cite

Dihydrofolate reductase (DHFR) is an essential enzyme in the folate metabolism pathway and an important target of antineoplastic, antimicrobial, antiprotozoal, and antiinflammatory drugs. Despite the clinical effectiveness of current antifolate treatments, new drugs are needed to be designed due to developing resistance of this enzyme through multiple‐site mutagenesis. Understanding the factors affecting the ligand binding selectivity profiles among DHFR families is critical for the design of novel potent and selective inhibitors, with the least side effects, against DHFR of pathogens. Hybrid scaffolds containing pyrimidine ring are effective in DHFR inhibition. In this study, using proteochemometric (PCM) modeling, we designed and evaluated new potent pyrimidine scaffold‐based inhibitors via 3‐dimensional alignment‐free GRid‐INdependent Descriptors (GRIND), VolSurf molecular, and sequence‐based (z‐scale) descriptors to provide ligand and receptor descriptors, respectively. Validation and robustness of the model were confirmed by venetian blinds cross‐validation and Y‐scrambling approaches, respectively. Applicability domain (AD) analysis was performed to estimate the likelihood of reliable prediction for compounds. To show the applicability of the PCM model, new ligands were designed using structural data retrieved from this model. Inhibitory activities of the designs were then predicted, and selectivity ratio profiles were investigated. Finally, potent and highly selective inhibitors were identified regarding the protozoan parasite Toxoplasma gondii, followed by evaluating the ADMET parameters of the ligands.

show abstract

Section: Methodsmentioning

confidence: 99%

“…37 This approach has been frequently used in PCM modeling, due to its robustness and interpretability. 58 For a PLS model constructed of ligand descriptors (L), receptor descriptors (R), and their cross-terms (L*R), the regression equation can be expressed as follows:…”

Section: Pls Modelingmentioning

confidence: 99%

Probing the origin of dihydrofolate reductase inhibition via proteochemometric modeling

Hariri

Ghasemi

Shirini

et al. 2018

Journal of Chemometrics

View full text Add to dashboard Cite

show abstract

“…For example, a unified proteochemometric (PCM) model for the prediction of the inhibition of CYP450 isoforms was developed and made publicly available under the Bioclipse Decision Support open source system [97]. PCM creates a unification of models for multiple proteins that interaction with multiple ligands through the correlation descriptors [98, 99]. The descriptors are based on the following amino acid properties: hydrophobicity, normalized van der Waals volume, polarity, polarizability, charge, secondary structure and solvent accessibility [97].…”

Section: Computational Tools For Studies Of Drug Metabolismmentioning

confidence: 99%

Drug Metabolism in Preclinical Drug Development: A Survey of the Discovery Process, Toxicology, and Computational Tools

Issa

Wathieu

Ojo

et al. 2017

CDM

View full text Add to dashboard Cite

Increased R & D spending and high failure rates exist in drug development, due in part to inadequate prediction of drug metabolism and its consequences in the human body. Hence, there is a need for computational methods to supplement and complement current biological assessment strategies. In this review, we provide an overview of drug metabolism in pharmacology, and discuss the current in vitro and in vivo strategies for assessing drug metabolism in preclinical drug development. We highlight computational tools available to the scientific community for the in silico prediction of drug metabolism, and examine how these tools have been implemented to produce drug-target signatures relevant to metabolic routes. Computational workflows that assess drug metabolism and its toxicological and pharmacokinetic effects, such as by applying the adverse outcome pathway framework for risk assessment, may improve the efficiency and speed of preclinical drug development.

show abstract

“…The PCM modeling approach concurrently takes into account both the ligand chemical features and the sequence-based descriptors of transporter proteins. 8 Another distinct advantage of the combined model for multiple transporters is that it can identify, and therefore predict, promiscuous binding of substrates to multiple proteins, which is a commonly known phenomenon in biological systems. The PCM modeling approach has been successfully employed for various classes of proteins such as kinases 9 and G-proteincoupled receptors 10 as well as for the development of proteome-wide models.…”

Section: Introductionmentioning

confidence: 99%

Selective Fusion of Heterogeneous Classifiers for Predicting Substrates of Membrane Transporters

Shaikh

Sharma

Garg

2017

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Membrane transporters play a crucial role in determining fate of administered drugs in a biological system. Early identification of plausible transporters for a drug molecule can provide insights into its therapeutic, pharmacokinetic, and toxicological profiles. In the present study, predictive models for classifying small molecules into substrates and nonsubstrates of various pharmaceutically important membrane transporters were developed using quantitative structure-activity relationship (QSAR) and proteochemometric (PCM) approaches. For this purpose, 4575 substrate interactions for these transporters were collected from the Metabolism and Transport Database (Metrabase) and the literature. The transporters selected for this study include (i) six efflux transporters, viz., breast cancer resistance protein (BCRP/ABCG2), P-glycoprotein (P-gp/MDR1), and multidrug resistance proteins (MRP1, MRP2, MRP3, and MRP4), and (ii) seven influx transporters, viz., organic cation transporter (OCT1/SO22A1), peptide transporter (PEPT1/SO15A1), apical sodium-bile acid transporter (ASBT/NTCP2), and organic anion transporting peptides (OATP1A2/SO1A2, OATP1B/SO1B1, OATP1B3/SO1B3, and OATP2B1/SO2B1). Various types of descriptors and machine learning methods (classifiers) were evaluated for the development of robust predictive models. Additionally, ensemble models were developed by bagging of homogeneous classifiers and selective fusion of heterogeneous classifiers. It was observed that the latter approach improves the accuracy of substrate/nonsubstrate prediction for transporters (average correct classification rate of more than 0.80 for external validation). Moreover, structural fragments important in determining the substrate specificity across the various transporters were identified. To demonstrate these fragments on the query molecule, contour maps were generated. The prediction efficacy of the developed models was illustrated by a good correlation between the reported logBB value of a molecule and its predicted substrate propensity for blood-brain barrier transporters. Conclusively, this comprehensive modeling analysis can be efficiently employed for the prediction of membrane transporters of a drug, thereby providing insights into its pharmacological profile.

show abstract

Chemoinformatics Taking Biology into Account: Proteochemometrics

Cited by 5 publications

References 48 publications

Probing the origin of dihydrofolate reductase inhibition via proteochemometric modeling

Probing the origin of dihydrofolate reductase inhibition via proteochemometric modeling

Drug Metabolism in Preclinical Drug Development: A Survey of the Discovery Process, Toxicology, and Computational Tools

Selective Fusion of Heterogeneous Classifiers for Predicting Substrates of Membrane Transporters

Contact Info

Product

Resources

About