Evaluation of a Published in Silico Model and Construction of a Novel Bayesian Model for Predicting Phospholipidosis Inducing Potential

Pelletier, Dennis; Gehlhaar, Daniel K.; Tilloy‐Ellul, Anne; Johnson, Theodore; Greene, Nigel

doi:10.1021/ci6004542

Cited by 91 publications

(106 citation statements)

References 36 publications

Supporting

Mentioning

106

Contrasting

Order By: Relevance

“…Starting with a lead that is active for PL, modifications can be made to the chemical structure to alter properties linked to PL induction such as clogP, pKa, reducing the number of basic nitrogen atoms, and making the molecule less linear. Ploemen's model (Ploemen et al 2004) as well as Pelletier's modification (Pelletier et al 2007) of the model can be used to predict PL liability of a molecule. …”

Section: Tier 1: Chemistry Selection Of Compounds With Minimal Pl Liamentioning

confidence: 99%

A Strategy for Risk Management of Drug-Induced Phospholipidosis

et al. 2009

Self Cite

View full text Add to dashboard Cite

Drug-induced phospholipidosis (PL) is an excessive accumulation of phospholipids and drug in lysosomes. Phospholipidosis signals a change in cell membrane integrity and accumulation of intracellular drug or metabolite in tissues. The sensitivity and susceptibility of preclinical models to detect PL vary with therapeutic agents, and PL is expected to be reversible after discontinuation of drug treatment. The prevailing scientific opinion is that PL by itself is not adverse; however, some regulatory authorities consider PL to be adverse because a small number of chemicals are able to cause PL and concurrent organ toxicity. Until a greater understanding of PL emerges, a well-thought-out risk management strategy for PL will increase confidence in safety and improve selection and development of new drugs. This paper provides a tiered approach to risk management of drug-induced PL. It begins with use of in silico and in vitro tools to design and select compounds with reduced potential to produce PL. Early in vivo studies in two species are used to better characterize potential for toxicity and PL. Finally, routine risk management tools (i.e., translational biomarkers, assessment of reversibility) are used to support confidence in safety of compounds that induce PL in animals.

show abstract

Section: Tier 1: Chemistry Selection Of Compounds With Minimal Pl Liamentioning

confidence: 99%

A Strategy for Risk Management of Drug-Induced Phospholipidosis

et al. 2009

Self Cite

View full text Add to dashboard Cite

show abstract

“…If the score is lower than 90, or pK a < 8, or if ClogP < 1 then it is predicted that the compound does not induce PPL. The prediction of the phospholipidosis inducing potential may be improved with a naïve Bayes classifier by adding to these three descriptors (pK a , ClogP, and ClogP 2 + pK a 2 ) several other relevant indices, such as the number of acidic and basic atoms, the amphiphilic moment, and Scitegic structural fingerprints FCFP_4 [56]. It was found also that other machine learning methods, such as support vector machines and k-nearest neighbors give better predictions compared with the naïve Bayes classifier [57].…”

Section: Drugs With Phospholipidosis Inducing Potentialmentioning

confidence: 99%

“…The dataset of 117 chemicals is based on the non-proprietary part of the Pelletier PPL model [56], and consists of 56 PPL+ compounds and 61 PPLcompounds. The structural descriptors were computed with E-Dragon [60], plus six molecular descriptors from the Pelletier PPL model, namely pK a , ClogP, ClogP 2 + pK a 2 , the amphiphilic moment, the number of basic centers, and the number of acidic centers.…”

Section: Drugs With Phospholipidosis Inducing Potentialmentioning

confidence: 99%

Weka Machine Learning for Predicting the Phospholipidosis Inducing Potential

Ivanciuc

2008

CTMC

View full text Add to dashboard Cite

Abstract:The drug discovery and development process is lengthy and expensive, and bringing a drug to market may take up to 18 years and may cost up to 2 billion $US. The extensive use of computer-assisted drug design techniques may considerably increase the chances of finding valuable drug candidates, thus decreasing the drug discovery time and costs. The most important computational approach is represented by structure-activity relationships that can discriminate between sets of chemicals that are active/inactive towards a certain biological receptor. An adverse effect of some cationic amphiphilic drugs is phospholipidosis that manifests as an intracellular accumulation of phospholipids and formation of concentric lamellar bodies. Here we present structure-activity relationships (SAR) computed with a wide variety of machine learning algorithms trained to identify drugs that have phospholipidosis inducing potential. All SAR models are developed with the machine learning software Weka, and include both classical algorithms, such as k-nearest neighbors and decision trees, as well as recently introduced methods, such as support vector machines and artificial immune systems. The best predictions are obtained with support vector machines, followed by a perceptron artificial neural network, logistic regression, and k-nearest neighbors.

show abstract

“…These tools used some physicochemical properties such as (C)logP ow (ClogP, hydrophobicity), most basic pKa (MB-pKa, cationic) or net charge (Pleoman et al, 2004;Tomizawa et al, 2006), and the volume of distribution (Hanumegowda et al, 2010). Some models also have been reported such as toxicophore model (Goracci et al, 2015) and Bayesian model (Pelletier et al, 2007). In this research, we replaced these physicochemical properties as follows: ClogP is a descriptor for hydrophobic interactions, and most basic pKa and net charge are descriptors for electrostatic interactions.…”

Section: Introductionmentioning

confidence: 99%

Establishment of an <i>in silico</i> phospholipidosis prediction method using descriptors related to molecular interactions causing phospholipid–compound complex formation

et al. 2016

View full text Add to dashboard Cite

-Although phospholipidosis (PLD) often affects drug development, there is no convenient in vitro or in vivo test system for PLD detection. In this study, we developed an in silico PLD prediction method based on the PLD-inducing mechanism. We focused on phospholipid (PL)-compound complex formation, which inhibits PL degradation by phospholipase. Thus, we used some molecular interactions, such as electrostatic interactions, hydrophobic interactions, and intermolecular forces, between PL and compounds as descriptors. First, we performed descriptor screening for intermolecular force and then developed a new in silico PLD prediction using descriptors related to molecular interactions. Based on the screening, we identified molecular refraction (MR) as a descriptor of intermolecular force. It is known that ClogP and most-basic pKa can be used for PLD prediction. Thereby, we developed an in silico prediction method using ClogP, most-basic pKa, and MR, which were related to hydrophobic interactions, electrostatic interactions, and intermolecular forces. In addition, a resampling method was used to determine the cut-off values for each descriptor. We obtained good results for 77 compounds as follows: sensitivity = 95.8%, specificity = 75.9%, and concordance = 88.3%. Although there is a concern regarding false-negative compounds for pKa calculations, this predictive ability will be adequate for PLD screening.In conclusion, the mechanism-based in silico PLD prediction method provided good prediction ability, and this method will be useful for evaluating the potential of drugs to cause PLD, particularly in the early stage of drug development, because this method only requires knowledge of the chemical structure.

show abstract

Evaluation of a Published in Silico Model and Construction of a Novel Bayesian Model for Predicting Phospholipidosis Inducing Potential

Cited by 91 publications

References 36 publications

A Strategy for Risk Management of Drug-Induced Phospholipidosis

A Strategy for Risk Management of Drug-Induced Phospholipidosis

Weka Machine Learning for Predicting the Phospholipidosis Inducing Potential

Establishment of an <i>in silico</i> phospholipidosis prediction method using descriptors related to molecular interactions causing phospholipid–compound complex formation

Contact Info

Product

Resources

About