Data Mining Practical Machine Learning Tools and Techniques

Thank you very much for reading plots transformations and regression an introduction to graphical methods of diagnostic regression analysis. Maybe you have knowledge that, people have look numerous times for their favorite readings like this plots transformations and regression an introduction to graphical methods of diagnostic regression analysis, but end up in malicious downloads. Rather than reading a good book with a cup of coffee in the afternoon, instead they are facing with some infectious bugs inside their laptop.

Plots Transformations And Regression An Introduction To Graphical Methods Of Diagnostic Regression Analysis

Tackling environmental challenges in pollution controls using artificial intelligence: A review

Design for Six Sigma.

Six Co(II)-based coordination polymers (CPs) with characteristic frameworks and topologies—namely, [Co(L1)(DCTP)]n (1), [Co(L2)(DCTP)]n (2), [Co(L3)(DCTP)]n (3), {[Co3(L4)3(DCTP)3·H2O]·H2O}n (4), [Co(L5)1.5(DCTP)]n (5) and [Co(L6)(DCTP)]n (6)—were successfully hydrothermally synthesized by employing the halogenated linear ligand 2,5-dichloroterephthalic acid (H2DCTP). The interpenetrated structures could be rationally modulated by auxiliary N-donor co-ligands containing 1,1′-(1,4-butanediyl)bis-1H-benzimidazole (L1), 1,4-bis(5,6-dimethylbenzimidazol-1-yl)-2-butylene (L2), 1,2-bis(2-methylbenzimidazol-1-ylmethyl)benzene (L3), 1,4-bis(2-methylbenzimidazol-1-ylmethyl)benzene (L4), 1,2-bis(5,6-dimethylbenzimidazol-1-ylmethyl)benzene (L5) and 1,4-bis(5,6-dimethylbenzimidazol-1-ylmethyl)benzene (L6). These diaphanous crystals were clearly characterized by elemental analysis, infrared (IR) spectra and X-ray powder diffraction (XRPD) as well as single-crystal X-ray diffraction analysis. With the aid of the flexible N-donor co-ligands, CP 1 occupies a non-interpenetrated 2D sheet with the point symbol {44·62} sql net topology, CP 2 possesses a 3D hexagon-shaped network with the point symbol {66} three-fold interpenetrated sqc6 topology, CP 3 exhibits a 2D layer with the point symbol {44·62} sql net topology, CP 4 reveals an unusual 3D framework with the point symbol {42·63·8} three-fold interpenetrated sra topology, CP 5 has a 3D hexagon-shaped network with the point symbol {66} two-fold interpenetrated sqc6 topology, while CP 6 displays a 3D hexagon-shaped network with the point symbol {66} three-fold interpenetrated sqc6 topology. The diverse structures of CPs 1–6 illustrate that the substitute group and position of the methyl group of the bis(benzimidazole) derivatives play a significant role in the assembly of such interpenetrated frameworks. Moreover, luminescence properties and thermal behavior, as well as the electrochemical and photocatalytic properties of CPs 1–6 on the degradation of methylene blue, are also presented.

Construction of noninterpenetrating and interpenetrating Co(ii) networks with halogenated carboxylate modulated by auxiliary N-donor co-ligands: structural diversity, electrochemical and photocatalytic properties

Machine learning in antibacterial discovery and development: A bibliometric and network analysis of research hotspots and trends

Globally, pesticides are toxic substances with wide applications. However, the widespread use of pesticides has received increasing attention from regulatory agencies due to their various acute and chronic effects on multiple organisms. In this study, Quantitative Structure-Toxicity Relationship (QSTR) models were established using Multiple Linear Regression (MLR) and five Machine Learning (ML) algorithms to predict pesticide toxicity in Americamysis bahia. The most inﬂuential descriptors included in the MLR model are RBF, JGI2, nCbH, nRCOOR, nRSR, nPO4 and 'Cl-090', with positive contributions to the dependent variable (negative decimal logarithm of median lethal concentration at 96-h). The Random Forest (RF) regression model was superior amongst the five ML models. We observed higher values of R2 (0.812) and lower values of RMSE (0.595) and MAE (0.462) in the cross-validation training set and external validation set. Similarly, this study had a high level of fitness and was internally robust and externally predictive compared to models presented in similar studies. The results suggest that the developed QSTR models are suitable for reliably predicting the aquatic toxicity of structurally diverse pesticides and can be used for screening, prioritising new pesticides, filling data gaps and overcoming the limitations of in vivo and in vitro tests. 

Prediction of acute toxicity of pesticides for Americamysis bahia using linear and nonlinear QSTR modelling approaches.

Leishmaniasis is a vector-borne parasite that affects 700,000&ndash;1 million people and kills 26,000&ndash;65,000 annually. This work presents a brief, comprehensive review of AI/ML studies performed in leishmania drug discovery. In this study, research was carried out using the Scopus and Web of Science (WoS) databases from 2013 to 2022. Between the two databases, 28 documents were found, eight of which were duplicates; hence, a total of 20 articles were analysed. Of these, nine were research articles, 10 review articles, and one editorial document. Current Topics in Medicinal Chemistry was the only journal that received more than one paper (three papers in total). The available literature on the topic is limited. The most relevant articles selected from the two databases, WoS and Scopus, provided an overview of the scientific topic (stages of drug discovery for leishmaniasis using AI/ML). This brief review can also serve as a starting point for integrating knowledge in this field through research and suggest future research avenues for AI and ML applications in protozoan infectious diseases 

https://sciforum.net/paper/download/13888/manuscript

Artificial intelligence and machine learning in Leishmania drug discovery

In this report are used two datasets involving the main antidiabetic enzymes targets α-amylase and α-glucosidase. The prediction of α-amylase and α -glucosidase inhibitory activity as Antidiabetic Agents is carried out using LDA and classification trees (CT). A large data set of 640 compounds for α-amylase and 1546 compounds in the case of α-glucosidase are selected to develop the tree model. In the case of CT-J48 have the better classification model performances for both targets with values above 80- 90% for the training and prediction sets, correspondingly. The best model shows an accuracy higher than 95% for training set; the model was also validated using 10-fold cross-validation procedure and through a test set achieving accuracies values of 85.32% and 86.80%, correspondingly. The main descriptors that influence the inhibitory activity of the antidiabetic enzymes are interpreted. Additionally, the obtained model is compared with other approaches previously published in the international literature showing better or goodness results. Finally, we can say that, the present results provided a double target approach for increasing the estimation of antidiabetic chemicals identification aimed by double-way workflow in virtual screenings pipelines

A Simple Method to Classification α-Amylase and α-Glucosidase Inhibitors Using LDA and Decision Trees

La elaboración de jugos y conservas de frutas desempeña un rol importante en la economía nacional. El objetivo de este estudio fue evaluar la viabilidad de la implementación de estrategias de producción más limpia (PML) en una fábrica de dulce de guayaba. Se realizó un diagnóstico inicial in situ de las condiciones del proceso. Se cuantificaron entradas y salidas del proceso de elaboración y se propusieron tres opciones de PML para ser evaluadas. La generación de residuos orgánicos y el elevado consumo de agua fueron los principales problemas detectados en el diagnóstico. Las alternativas de PML consideradas fueron la elaboración de harina de semillas de guayaba, recuperación del agua de las calderas y reúso del agua de lavado. Según los resultados de la viabilidad técnica económica y ambiental realizada, estas opciones de PML presentan resultados positivos pues la relación beneficio/costo se incrementa a 1,65 (1,63 sin PML). Además, se podría reducir el consumo de agua, la generación de residuos sólidos y las emisiones de CO2 en un 80 %, 85 % y 48,3 %, respectivamente. Este estudio muestra que las estrategias de PML son opciones viables y pueden mejorar el comportamiento ambiental de pequeñas y medianas empresas alimentarias.

/pdf/implementacion-de-produccion-mas-limpia-en-una-fabrica-de-2p1ksu0o.pdf

Karel Diéguez-Santana

Papers

Machine learning in antibacterial discovery and development: A bibliometric and network analysis of research hotspots and trends

Prediction of acute toxicity of pesticides for Americamysis bahia using linear and nonlinear QSTR modelling approaches.

Artificial intelligence and machine learning in Leishmania drug discovery

A Simple Method to Classification α-Amylase and α-Glucosidase Inhibitors Using LDA and Decision Trees

Implementación de producción más limpia en una fábrica de dulces de guayaba en Baños de Agua Santa, Ecuador