Supervisión y regulación del sistema financiero: modelos, implicaciones y alcances

Estrada, Dairo Ayiber; R, Javier Gutiérrez

doi:10.32468/be.490

Cited by 10 publications

(9 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Traditional molecular descriptors such as the atom- and bond-based connectivity indices, shape descriptors, and others widely reported in the literature constituted the second set of molecular descriptors used in this study; 45 they were calculated by the program ModesLab v1.5 using the SMILES codes stored in the *.txt file. 46 One should note that the molecular descriptors reported in eqs 3 – 6 characterize only the chemical structure of the molecules, being incapable of discriminating the effect of the chemical structure of a molecule when this is assayed against more than one target. In this context, the Box–Jenkins approach can solve this inconvenience.…”

Section: Methodsmentioning

confidence: 99%

Combining Ensemble Learning with a Fragment-Based Topological Approach To Generate New Molecular Diversity in Drug Discovery: In Silico Design of Hsp90 Inhibitors

Speck‐Planche

2018

ACS Omega

View full text Add to dashboard Cite

Machine learning methods have revolutionized modern science, providing fast and accurate solutions to multiple problems. However, they are commonly treated as “black boxes”. Therefore, in important scientific fields such as medicinal chemistry and drug discovery, machine learning methods are restricted almost exclusively to the task of performing predictions of large and heterogeneous data sets of chemicals. The lack of interpretability prevents the full exploitation of the machine learning models as generators of new chemical knowledge. This work focuses on the development of an ensemble learning model for the prediction and design of potent dual heat shock protein 90 (Hsp90) inhibitors. The model displays accuracy higher than 80% in both training and test sets. To use the ensemble model as a generator of new chemical knowledge, three steps were followed. First, a physicochemical and/or structural interpretation was provided for each molecular descriptor present in the ensemble learning model. Second, the term “pseudolinear equation” was introduced within the context of machine learning to calculate the relative quantitative contributions of different molecular fragments to the inhibitory activity against the two Hsp90 isoforms studied here. Finally, by assembling the fragments with positive contributions, new molecules were designed, being predicted as potent Hsp90 inhibitors. According to Lipinski’s rule of five, the designed molecules were found to exhibit potentially good oral bioavailability, a primordial property that chemicals must have to pass early stages in drug discovery. The present approach based on the combination of ensemble learning and fragment-based topological design holds great promise in drug discovery, and it can be adapted and applied to many different scientific disciplines.

show abstract

Section: Methodsmentioning

confidence: 99%

Combining Ensemble Learning with a Fragment-Based Topological Approach To Generate New Molecular Diversity in Drug Discovery: In Silico Design of Hsp90 Inhibitors

Speck‐Planche

2018

ACS Omega

View full text Add to dashboard Cite

show abstract

“…For the compounds, 92 atom-centred fragment and 100 functional group count descriptors were calculated using DRAGON 5.3 [135]. Also, 195 spectral moments were calculated by employing MODESLAB 1.5 [136]. They were weighted by standard bond distances, dipole moments, atomic hydrophobicities, atomic polar surface, atomic molar refractivities, atomic polarizabilities, Van der Waals atomic radii, Gasteiger-Marsilli atomic charges and Abraham molecular descriptors [137,138].…”

Section: Selection Of the Data Set: Calculation Of The Descriptors Anmentioning

confidence: 99%

Application of Bioinformatics for the Search of Novel Anti-Viral Therapies: Rational Design of Anti-Herpes Agents

Cordeiro¹

2011

CBIO

View full text Add to dashboard Cite

Human herpes viruses (HHV) are leading cause of human viral diseases, second after influenza and cold viruses. They cause overt disease or can remain silent for many years waiting for reactivation. HHV are associated to several side-effects or co-conditions like Alzheimer's disease, cholangiocarcinoma and pancreatic cancer, and with the time, they have become resistant to the available commercial drugs like acyclovir, whose final target is the DNApolymerase. For this reason there is an increasing interest for the search of novel compounds against herpes viruses. In this sense, Bioinformatics is determinant for a better understanding of the mechanisms of resistance, and also for the search of new biomolecular targets for the design of more potent and versatile anti-herpes agents. This review is focused on the role of Bioinformatics toward the design of compounds with anti-herpetic activity and also we propose a model based fragment descriptors for the design, search and prediction of anti-herpes compounds through the inhibition of 5 targets belonging to different herpes viruses.

show abstract

“…This method have been intensively studied and applied in both academia and industry in the last years. In all cases MODESLAB software version 1.5 (88), has served as the computational platform for making these studies. They have permitted the development of models for drug discovery of anti-cancer and anti-HIV compounds, for predicting eco-toxicity of chemicals, for generating knowledge for toxicity expert systems, and for predicting several physicochemical, ADME, and biological properties of organic compounds.…”

Section: Tops-mode Approachmentioning

confidence: 99%

Regulatory issues in management of chemicals in OECD member countries

Kleandrova

2013

Front Biosci

View full text Add to dashboard Cite

The chemical risk assessment is determinant for the approval of any kind of chemical. Each aspect of chemical is taken into consideration for the new chemical legislation registration, evaluation, and authorization of chemicals (REACH). However, some improvements can be made in order to select and authorize a chemical. QSAR techniques have been used for the study of several kind of toxicological properties in order to realize a deeper study concerning to risk assessment. For this reason, this work is focused into present a review of chemical legislation policies in the European Union (EU) and in Russia, and changes in chemicals regulations to meet the requirement of REACH. Also, we reported the used of several approaches and chemo- bioinformatics tools applied to QSAR methodologies for the several parameters relative to toxicity and how they can be used for regulatory purposes in risk assessment.

show abstract

Supervisión y regulación del sistema financiero: modelos, implicaciones y alcances

Cited by 10 publications

References 10 publications

Combining Ensemble Learning with a Fragment-Based Topological Approach To Generate New Molecular Diversity in Drug Discovery: In Silico Design of Hsp90 Inhibitors

Combining Ensemble Learning with a Fragment-Based Topological Approach To Generate New Molecular Diversity in Drug Discovery: In Silico Design of Hsp90 Inhibitors

Application of Bioinformatics for the Search of Novel Anti-Viral Therapies: Rational Design of Anti-Herpes Agents

Regulatory issues in management of chemicals in OECD member countries

Contact Info

Product

Resources

About