WITHDRAWN: Improving classification of protein binders for virtual drug screening by novel swarm-based feature selection techniques

Li, Jinyan; Fong, Simon; Si, Yain-Whar; Mohammed, Sabah; Fiaidhi, Jinan; Wong, Kelvin Kian Loong

doi:10.1016/j.compmedimag.2016.08.004

Cited by 3 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A molecular descriptor (MD) represents a portion of information derived of the chemical structures. QSAR/QSPR approaches are applied in order to estimate physicochemical and biological properties of interest, acting as drug prioritization strategy for pharma discovery. , In this scenario, the process of choosing the most relevant MDs subgroup for the activity to be modeled is a particular case of the FS problem.…”

Section: Introductionmentioning

confidence: 99%

Feature Selection for Polymer Informatics: Evaluating Scalability and Robustness of the FS4RV_DD Algorithm Using Synthetic Polydisperse Data Sets

Cravero

Schustik

Martínez

et al. 2019

J. Chem. Inf. Model.

View full text Add to dashboard Cite

The feature selection (FS) process is a key step in the Quantitative Structure-Property Relationship (QSPR) modeling of physicochemical properties in Cheminformatics. In particular, the inference of QSPR models for polymeric material properties constitutes a complex problem because of the uncertainty introduced by the polydispersity of these materials. The main challenge is how to capture the polydispersity information from the molecular weight distribution (MWD) curve to achieve a more effective computational representation of polymeric materials. To date, most of the existing QSPR techniques use only a single molecule to represent each of these materials, but polydispersity is not considered. Consequently, QSPR models obtained by these approaches are being oversimplified. For this reason, we introduced in a previous work a new FS algorithm called Feature

show abstract

Section: Introductionmentioning

confidence: 99%

Feature Selection for Polymer Informatics: Evaluating Scalability and Robustness of the FS4RV_DD Algorithm Using Synthetic Polydisperse Data Sets

Cravero

Schustik

Martínez

et al. 2019

J. Chem. Inf. Model.

View full text Add to dashboard Cite

show abstract

FS4RVDD: A Feature Selection Algorithm for Random Variables with Discrete Distribution

Cravero

Schustik

Martínez

et al. 2018

Communications in Computer and Information Science

View full text Add to dashboard Cite

DNA sensors to assess the effect of VKORC1 and CYP2C9 gene polymorphisms on warfarin dose requirement in Chinese patients with atrial fibrillation

Huang

et al. 2017

Australas Phys Eng Sci Med

View full text Add to dashboard Cite

The optimal dose of warfarin depends on polymorphisms in the VKORC1 (the vitamin K epoxide reductase complex subunit (1) and CYP2C9 (cytochrome P450 2C9) genes. To minimize the risk of adverse reactions, warfarin dosages should be adjusted according to results from rapid and simple monitoring methods. However, there are few pharmacogenetic-guided warfarin dosing algorithms that are based on large cohorts from the Chinese population, especially patients with atrial fibrillation. This study aimed to validate a pharmacogenetic-guided warfarin dosing algorithm based on results from a new rapid electrochemical detection method used in a multicenter study. Three SNPs (CYP2C9 *2, *3 and VKORC1 c.-1639G > A) were genotyped by electrochemical detection using a sandwich-type format that included a 3' short thiol capture probe and a 5' ferrocene-labeled signal probe. A total of 1285 samples from four clinical hospitals were evaluated. Concordance rates between the results from the electrochemical DNA biosensor and the sequencing test were 99.8%. The results for gene distribution showed that most Chinese patients had higher warfarin susceptibility because mutant-type and heterozygotes were present in the majority of subjects (99.4%) at locus c.-1639G > A. When the International Warfarin Pharmacogenetics Consortium algorithm was used to estimate therapeutic dosages for 362 patients with AF and the values were compared with their actual dosages, the results revealed that 56.9% were similar to actual dosages (within the 20% range). A novel electrochemical detection method of CYP2C9 *2, *3and VKORC1 c.-1639G > A alleles was evaluated. The warfarin dosing algorithm based on data gathered from a large patient cohort can facilitate the reasonable and effective use of warfarin in Chinese patients with AF.

show abstract

WITHDRAWN: Improving classification of protein binders for virtual drug screening by novel swarm-based feature selection techniques

Cited by 3 publications

References 10 publications

Feature Selection for Polymer Informatics: Evaluating Scalability and Robustness of the FS4RV_DD Algorithm Using Synthetic Polydisperse Data Sets

Feature Selection for Polymer Informatics: Evaluating Scalability and Robustness of the FS4RV_DD Algorithm Using Synthetic Polydisperse Data Sets

FS4RVDD: A Feature Selection Algorithm for Random Variables with Discrete Distribution

DNA sensors to assess the effect of VKORC1 and CYP2C9 gene polymorphisms on warfarin dose requirement in Chinese patients with atrial fibrillation

Contact Info

Product

Resources

About

WITHDRAWN: Improving classification of protein binders for virtual drug screening by novel swarm-based feature selection techniques

Cited by 3 publications

References 10 publications

Feature Selection for Polymer Informatics: Evaluating Scalability and Robustness of the FS4RVDD Algorithm Using Synthetic Polydisperse Data Sets

Feature Selection for Polymer Informatics: Evaluating Scalability and Robustness of the FS4RVDD Algorithm Using Synthetic Polydisperse Data Sets

FS4RVDD: A Feature Selection Algorithm for Random Variables with Discrete Distribution

DNA sensors to assess the effect of VKORC1 and CYP2C9 gene polymorphisms on warfarin dose requirement in Chinese patients with atrial fibrillation

Contact Info

Product

Resources

About

Feature Selection for Polymer Informatics: Evaluating Scalability and Robustness of the FS4RV_DD Algorithm Using Synthetic Polydisperse Data Sets

Feature Selection for Polymer Informatics: Evaluating Scalability and Robustness of the FS4RV_DD Algorithm Using Synthetic Polydisperse Data Sets