alvaDesc: A Tool to Calculate and Analyze Molecular Descriptors and Fingerprints

Mauri, Andrea

doi:10.1007/978-1-0716-0150-1_32

Cited by 196 publications

(134 citation statements)

References 56 publications

Supporting

Mentioning

133

Contrasting

Order By: Relevance

“…The internal database contains approximately 200k unique structures with wSFLogD data and approximately 80k unique structures with wELogD data. Models on both datasets are constructed using descriptors generated by MoKa (Molecular Discovery Ltd 2020) , alvaDesc (Mauri 2020), and counts of a set of internally developed SMARTS fragments (calculated using OpenEye OEChemTK (OpenEye Scientific Software 2020). For a MoKa pKa prediction where no value is given (e.g., neutrals), the value of ApKa is set to 14 and BpKa is set to 0.…”

Section: Methodsmentioning

confidence: 99%

Providing the ‘Best’ Lipophilicity Assessment in a Drug Discovery Environment

Chang

Woody²,

Keefer³

2021

Preprint

View full text Add to dashboard Cite

Lipophilicity is a fundamental structural property that influences almost every aspect of drug discovery. Within Pfizer, we have two complementary high-throughput screens for measuring lipophilicity as a distribution coefficient (LogD) – a miniaturized shake-flask method (SFLogD) and a chromatographic method (ELogD). The results from these two assays are not the same (see Figure 1), with each assay being applicable or more reliable in particular chemical spaces. In addition to LogD assays, the ability to predict the LogD value for virtual compounds is equally vital. Here we present an in-silico LogD model, applicable to all chemical spaces, based on the integration of the LogD data from both assays. We developed two approaches towards a single LogD model – a Rule-based and a Machine Learning approach. Ultimately, the Machine Learning LogD model was found to be superior to both internally developed and commercial LogD models.<br>

show abstract

Section: Methodsmentioning

confidence: 99%

Providing the ‘Best’ Lipophilicity Assessment in a Drug Discovery Environment

Chang

Woody²,

Keefer³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…We used alvaDesc to calculate molecular descriptors [ 35 ]. The alvaDesc software can be used to calculate various molecular descriptors and molecular fingerprints.…”

Section: Methodsmentioning

confidence: 99%

Novel QSAR Models for Molecular Initiating Event Modeling in Two Intersecting Adverse Outcome Pathways Based Pulmonary Fibrosis Prediction for Biocidal Mixtures

Seo

Chae

Lee

et al. 2021

Toxics

View full text Add to dashboard Cite

The adverse outcome pathway (AOP) was introduced as an alternative method to avoid unnecessary animal tests. Under the AOP framework, an in silico methods, molecular initiating event (MIE) modeling is used based on the ligand-receptor interaction. Recently, the intersecting AOPs (AOP 347), including two MIEs, namely peroxisome proliferator-activated receptor-gamma (PPAR-γ) and toll-like receptor 4 (TLR4), associated with pulmonary fibrosis was proposed. Based on the AOP 347, this study developed two novel quantitative structure-activity relationship (QSAR) models for the two MIEs. The prediction performances of different MIE modeling methods (e.g., molecular dynamics, pharmacophore model, and QSAR) were compared and validated with in vitro test data. Results showed that the QSAR method had high accuracy compared with other modeling methods, and the QSAR method is suitable for the MIE modeling in the AOP 347. Therefore, the two QSAR models based on the AOP 347 can be powerful models to screen biocidal mixture related to pulmonary fibrosis.

show abstract

“…The dataset was first randomly divided into a training set containing 3867 data points (70% of the data) and a validation set containing 1656 data-points (30% of the data) using the random division technique of QSAR-Co tool [22]. A total of 5305 input descriptors (D i ) were calculated for the training set by employing the alvaDesc tool [38], and these descriptors were subsequently converted to 15,915 deviation descriptors with the help of QSAR-Co tool [22]. It must be noted here that all models were set up solely on the basis of the training set, which was further split into a sub-training set containing 2707 data points (70% of the training set) and a test set containing 1160 data points (30% of the training set) by applying the random division technique of QSAR-Co tool [22] for models' development purposes.…”

Section: Linear Interpretable Mt-qsar Modelsmentioning

confidence: 99%

“…The topological distance between Firstly, it is noteworthy that all the experimental elements considered in this work (i.e., a t , m e , and b t ) consistently appeared in the final LDA models demonstrating their importance (Table 4). To set up the models, 30 distinct categories of descriptors (available in alvaDesc [38]) were considered but only 10 persisted. The latter pertained more frequently to 2D atom pairs (pairs of atoms at a given topological distance) and functional group counts descriptors, as well as to atom-centered fragments [49].…”

Section: Interpretation Of Molecular Descriptorsmentioning

confidence: 99%

See 1 more Smart Citation

AKT Inhibitors: The Road Ahead to Computational Modeling-Guided Discovery

Halder

Cordeiro

2021

IJMS

View full text Add to dashboard Cite

AKT, is a serine/threonine protein kinase comprising three isoforms—namely: AKT1, AKT2 and AKT3, whose inhibitors have been recognized as promising therapeutic targets for various human disorders, especially cancer. In this work, we report a systematic evaluation of multi-target Quantitative Structure-Activity Relationship (mt-QSAR) models to probe AKT’ inhibitory activity, based on different feature selection algorithms and machine learning tools. The best predictive linear and non-linear mt-QSAR models were found by the genetic algorithm-based linear discriminant analysis (GA-LDA) and gradient boosting (Xgboost) techniques, respectively, using a dataset containing 5523 inhibitors of the AKT isoforms assayed under various experimental conditions. The linear model highlighted the key structural attributes responsible for higher inhibitory activity whereas the non-linear model displayed an overall accuracy higher than 90%. Both these predictive models, generated through internal and external validation methods, were then used for screening the Asinex kinase inhibitor library to identify the most potential virtual hits as pan-AKT inhibitors. The virtual hits identified were then filtered by stepwise analyses based on reverse pharmacophore-mapping based prediction. Finally, results of molecular dynamics simulations were used to estimate the theoretical binding affinity of the selected virtual hits towards the three isoforms of enzyme AKT. Our computational findings thus provide important guidelines to facilitate the discovery of novel AKT inhibitors.

show abstract

alvaDesc: A Tool to Calculate and Analyze Molecular Descriptors and Fingerprints

Cited by 196 publications

References 56 publications

Providing the ‘Best’ Lipophilicity Assessment in a Drug Discovery Environment

Providing the ‘Best’ Lipophilicity Assessment in a Drug Discovery Environment

Novel QSAR Models for Molecular Initiating Event Modeling in Two Intersecting Adverse Outcome Pathways Based Pulmonary Fibrosis Prediction for Biocidal Mixtures

AKT Inhibitors: The Road Ahead to Computational Modeling-Guided Discovery

Contact Info

Product

Resources

About