Pasar al contenido principal

NUEVAS HERRAMIENTAS SINTETICAS Y QUIMIOINFORMATICAS PARA LA CONSTRUCCION Y DIVERSIFICACION DE HETEROCICLOS “DRUG-LIKE”. ACTIVACION C-H Y MACHINE LEARNING

PID2019-104148GB-I00

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Convocatoria Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2019
Plan Estatal 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSIDAD DEL PAIS VASCO EUSKAL HERRIKO UNIBERTSITATEA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

DIGITAL.CSIC. Repositorio Institucional del CSIC
Datos de investigación Set de datos (Dataset)

SI00 Experimental Section

  • González-Díaz, Humberto
The enantioselective Brønsted acid-catalyzed α-amidoalkylation reaction is a useful procedure is for the production of new drugs and natural products (products) or chiral catalysts (tools). The enantioselectivity is sensitive to many factors, from the nature of the nucleophile and the catalyst to the experimental conditions (solvent, temperature, etc.). Although computational chemistry has been used to rationalize experimental results, it is still difficult to understand the influence of different parameters (solvent, temperature, etc.) on the quantitative reaction outcome (as yield or regio- and stereoselectivities).Both experimental and computational (Quantum Chemistry) study of a large number of reactions may become costly in terms of resources and time. Thus, the development of fast-track public computational tools to predict the enantioselectivity [enantiomeric excess ee(%)obs] would be very useful. Furthermore, making the new tool available online could save time and experimental resources in many labs worldwide. We used an Heuristic Perturbation-Theory and Machine Learning (HPTML) algorithm to seek a predictive model with R2 = 0.91 in training and validation series has been developed. It involves a Monte Carlo sampling of>100,000 pairs of query and reference reactions. In addition, the computational and experimental investigation of a new set of intermolecular α-amidoalkylation reactions using BINOL-derived N-trifylphosphoramides as chiral catalysts is reported as a case of study. After validation of the model, it was implementedin a web server called MATEO: InterMolecular Amidoalkylation Theoretical Enantioselectivity Optimization. This tool is available online at:https://cptmltool.rnasa-imedir.com/CPTMLTools-Web/mateo.This new user-friendly online computational tool may become useful to explore a large number of combinations of reactants, catalysts, and experimental conditions. This public tool would enable sustainable optimization of reaction conditions that could lead to the design of new catalysts, substrates, nucleophiles, and/or products., Ministry of Science and Innovation (PID2019-104148GB-I00); Basque Government / Eusko Jaurlaritza (IT1558-22), Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Datos de investigación Set de datos (Dataset)

Drug Release Nanoparticle Systems Design:Dataset Compilation and Machine Learning Modeling

  • He, Shan
  • Barón, Ander
  • Munteanu, Cristian Robert
  • Bilbao, Begoña de
  • Bediaga, Harbil
  • Casañola, Gerardo
  • Ascencio, Estefania
  • Chelu, Mariana
  • Musuc, Adina Magdalena
  • Arrasate, Sonia
  • Pazos, Alejandro
  • Rasulev, Bakhtiyor
  • González-Díaz, Humberto
  • Castellanos-Rubio, Idoia
  • Insausti, Maite
Magnetic Nanoparticles (MNPs) are gaining significant interest in the field of biomedical functional nanomaterials because of their distinctive chemical and physical characteristics, particularly in drug delivery and magnetic hyperthermia applications. In this paper, we experimentally synthesized and characterized new Fe3O4 based MNPs, functionalizing its surface with a 5-TAMRA cadaverine modified copolymer consisting of PMAO and PEG. Despite these advancements, many combinations of NP cores and coatings remain unexplored. To address this, we created a new dataset of MNP systems from public sources. Herein 11 different AI/ML algorithms were used to develop the predictive AI/ML models. The Linear Discriminant Analysis (LDA) and Random Forest (RF) models showed high values of sensitivity and specificity (>0.9) in training/validation series and 3-fold cross validation, respectively. The AI/ML models are able to predict 14 output properties (CC50 (µM), EC50 (µM), Inhibition (%), etc.) for all combinations of 54 different NP cores classes vs. 15 different coats and vs. 41 different cell lines allowing to short list the best results for experimental assays. The results of this work may help to reduce the cost of the traditional trial and error procedures., ELKARTEK (KK-2022/00032); IT1558-22, 2022-2025; PID2019-104148GB-I00; 2022/IKER/000040; CITIC is funded by the Xunta de Galicia; ED431C 2022/46 – Competitive Reference Groups (GRC), Peer reviewed