A5036900590- Computational Drug Discovery Methods
- Machine Learning in Materials Science
- Analytical Chemistry and Chromatography
- Protein Tyrosine Phosphatases
- Optics and Image Analysis
- Protein Structure and Dynamics
- Bioinformatics and Genomic Networks
- Microbial Metabolic Engineering and Bioproduction
- Mitochondrial Function and Pathology
- Advanced Chemical Sensor Technologies
- Protein Kinase Regulation and GTPase Signaling
- Antimicrobial Peptides and Activities
- Microbial Metabolism and Applications
- Plant biochemistry and biosynthesis
- Sensory Analysis and Statistical Methods
- Plant Pathogens and Resistance
- Metabolomics and Mass Spectrometry Studies
- Library Science and Information Systems
- Historical Geography and Cartography
- Spectroscopy and Chemometric Analyses
- Biochemical and Structural Characterization
- Synthetic Organic Chemistry Methods
- Comparative International Legal Studies
- Endoplasmic Reticulum Stress and Disease
- Pharmacovigilance and Adverse Drug Reactions
Centro Científico Tecnológico - Tandil
2022-2024
Consejo Nacional de Investigaciones Científicas y Técnicas
2017-2023
Universidad Nacional del Centro de la Provincia de Buenos Aires
2022
New Mexico VA Health Care System
2018-2022
Biomedical Research Institute of New Mexico
2018-2022
Universidad Nacional del Sur
2015-2019
Centro Científico Tecnológico - Bahía Blanca
2016-2019
Universidad de Alcalá
2012
Alzheimer's disease is one of the most common neurodegenerative disorders in elder population. The β-site amyloid cleavage enzyme 1 (BACE1) major constituent plaques and plays a central role this brain pathogenesis, thus it constitutes an auspicious pharmacological target for its treatment. In paper, QSAR model identification potential inhibitors BACE1 protein designed by using classification methods. For building model, database with 215 molecules collected from different sources has been...
Quantitative structure-activity relationship modeling using machine learning techniques constitutes a complex computational problem, where the identification of most informative molecular descriptors for predicting specific target property plays critical role. Two main general approaches can be used this procedure: feature selection and learning. In paper, performance comparative study two state-of-art methods related to these is carried out. particular, regression classification models...
Receptor-type protein tyrosine phosphatase D (PTPRD) is a neuronal cell-adhesion molecule/synaptic specifier that has been implicated in addiction vulnerability and stimulant reward by human genomewide association mouse cocaine-conditioned place-preference data. However, there have no reports of effects reduced expression on cocaine self-administration. There PTPRD targeting any small molecule. are data about behavioral ligand. We now report (i) robust heterozygous KO self-administration...
The design of QSAR/QSPR models is a challenging problem, where the selection most relevant descriptors constitutes key step process. Several feature methods that address this are concentrated on statistical associations among and target properties, whereas chemical knowledge left out analysis. For reason, interpretability generality obtained by these drastically affected. Therefore, an approach for integrating domain expert's in process needed increase confidence final set descriptors. In...
Parkinson's disease is one of the most common neurodegenerative illnesses in older persons and leucine-rich repeat kinase 2 (LRRK2) an auspicious target for its pharmacological treatment. In this work, quantitative structure-activity relationship (QSAR) models identification putative inhibitors LRRK2 protein are developed by using in-house chemical library several machine learning techniques. The methodology applied paper has two steps: first, alternative subsets molecular descriptors useful...
The selection of the most relevant molecular descriptors to describe a target variable in context QSAR (Quantitative Structure-Activity Relationship) modelling is challenging combinatorial optimization problem. In this paper, novel software tool for addressing task regression and classification presented. methodology that implements organized into two phases. first phase uses multiobjective evolutionary technique perform subsets descriptors. second performs an external validation chosen...
The Ames mutagenicity test constitutes the most frequently used assay to estimate mutagenic potential of drug candidates. While this employs experimental results using various strains Salmonella typhimurium, vast majority published in silico models for predicting do not take into account individual experiments conducted each strain. Instead, such QSAR are generally trained employing overall labels (i.e., and nonmutagenic). Recently, neural-based combined with multitask learning strategies...
Volatile organic compounds (VOCs) are contained in a variety of chemicals that can be found household products and may have undesirable effects on health. Thereby, it is important to model blood-to-liver partition coefficients (log P(liver)) for VOCs fast inexpensive way. In this paper, we present two new quantitative structure-property relationship (QSPR) models the prediction log P(liver), where also propose hybrid approach selection descriptors. This methodology combines machine learning...
The feature selection (FS) process is a key step in the Quantitative Structure–Property Relationship (QSPR) modeling of physicochemical properties cheminformatics. In particular, inference QSPR models for polymeric material constitutes complex problem because uncertainty introduced by polydispersity these materials. main challenge how to capture information from molecular weight distribution (MWD) curve achieve more effective computational representation To date, most existing techniques use...
Several feature extraction approaches for QSPR modelling in Cheminformatics are discussed this paper. In particular, work is focused on the use of these strategies predicting mechanical properties, which relevant design polymeric materials. The methodology analysed study employs a learning method that uses quantification process 2D structural characterization materials with autoencoder method. Alternative models inferred tensile strength at break (a well-known property polymers) presented....
Formulae display:?Mathematical formulae have been encoded as MathML and are displayed in this HTML version using MathJax order to improve their display. Uncheck the box turn off. This feature requires Javascript. Click on a formula zoom.
With the increase of electrical/electronic equipment integration complexity, electromagnetic compatibility (EMC) becomes one key points to be respected in order meet constructor standard conformity. Electrical drives are known sources interferences due motor as well related power electronics. They principal radiated emissions source automotive applications. This paper shows that there is a direct relationship between input control voltage and corresponding level emissions. It also introduces...
Artificial intelligence (AI) is an emerging technology that revolutionizing the discovery of new materials. One key application AI virtual screening chemical libraries, which enables accelerated materials with desired properties. In this study, we developed computational models to predict dispersancy efficiency oil and lubricant additives, a critical property in their design can be estimated through quantity named blotter spot. We propose comprehensive approach combines machine learning...