Rainfall Prediction System Using Machine Learning Fusion for Smart Cities.

Precipitation in any form-such as rain, snow, and hail-can affect day-to-day outdoor activities. Rainfall prediction is one of the challenging tasks in weather forecasting process. Accurate rainfall prediction is now more difficult than before due to the extreme climate variations. Machine learning techniques can predict rainfall by extracting hidden patterns from historical weather data. Selection of an appropriate classification technique for prediction is a difficult job. This research proposes a novel real-time rainfall prediction system for smart cities using a machine learning fusion technique. The proposed framework uses four widely used supervised machine learning techniques, i.e., decision tree, Naïve Bayes, K-nearest neighbors, and support vector machines. For effective prediction of rainfall, the technique of fuzzy logic is incorporated in the framework to integrate the predictive accuracies of the machine learning techniques, also known as fusion. For prediction, 12 years of historical weather data (2005 to 2017) for the city of Lahore is considered. Pre-processing tasks such as cleaning and normalization were performed on the dataset before the classification process. The results reflect that the proposed machine learning fusion-based framework outperforms other models.

Synthesis of oxadiazole-coupled-thiadiazole derivatives as a potent ß-glucuronidase inhibitors and their molecular docking study.

A new series of oxadiazole with thiadiazole moiety (6-27) were synthesized, characterized by different spectroscopic techniques and evaluated for ß-glucuronidase inhibitory potential. Sixteen analogs such as 6, 7, 8, 9, 10, 12, 13, 14, 17, 18, 20, 23, 24, 25, 26 and 27 showed IC50 values in the range of 0.96 ±â€¯0.01 to 46.46 ±â€¯1.10 µM, and hence were found to have excellent inhibitory potential in comparison to standard d-saccharic acid 1,4-lactone (IC50 = 48.4 ±â€¯1.25 µM). Two analogs such as 16 and 19 showed moderate inhibitory potential while analogs 11, 15, 21 and 22 were found inactive. Our study identifies new series of potent ß-glucuronidase inhibitors for further investigation. Structure activity relationships were established for all compounds which showed that the activity is varied due to different substituents on benzene ring. The interaction of the compounds with enzyme active site were confirmed with the help of docking studies, which reveals that the electron withdrawing group and hydroxy group make the molecules more favorable for enzyme inhibition.

Synthesis, thymidine phosphorylase, angiogenic inhibition and molecular docking study of isoquinoline derivatives.

Isoquinoline analogues (KA-1 to 16) have been synthesized and evaluated for their E. coli thymidine phosphorylase inhibitory activity. Except compound 11, all other analogs showed outstanding thymidine inhibitory potential ranging in between 4.40 ±â€¯0.20 to 69.30 ±â€¯1.80 µM when compared with standard drug 7-Deazaxanthine (IC50 = 38.68 ±â€¯4.42 µM). Structure Activity Relationships has been established for all compounds, mainly based on substitution pattern on phenyl ring. All analogs were characterized by various spectroscopic techniques such as 1H NMR, 13C NMR and EI-MS. The binding interactions of isoquinoline analogues with the active site of TP enzyme, the molecular docking studies were performed. Furthermore, the angiogenic inhibitory potentials of isoquinoline analogues (KA-1-9, 14, 12 and 16) were determined in the presence of standard drug Dexamethasone based on percentage inhibitions at various concentrations. Herein this work analogue KA-12, 14 and 16 emerged with most potent angiogenic inhibitory potentials among the synthesized analogues.

2,5-Disubstituted thiadiazoles as potent ß-glucuronidase inhibitors; Synthesis, in vitro and in silico studies.

Twenty-five thiadiazole derivatives 1-25 were synthesized from methyl 4-methoxybenzoate via hydrazide and thio-hydrazide intermediates, and evaluated for their potential against ß-glucuronidase enzyme. Most of the compounds including 1 (IC50 = 26.05 ±â€¯0.60 µM), 2 (IC50 = 42.53 ±â€¯0.80 µM), 4 (IC50 = 38.74 ±â€¯0.70 µM), 5 (IC50 = 9.30 ±â€¯0.29 µM), 6 (IC50 = 6.74 ±â€¯0.26 µM), 7 (IC50 = 18.40 ±â€¯0.66 µM), and 15 (IC50 = 18.10 ±â€¯0.53 µM) exhibited superior activity potential than the standard d-saccharic acid-1,4-lactone (IC50 = 48.4 ±â€¯1.25 µM). Molecular docking studies were conducted to correlate the in vitro results and to identify possible mode of interaction with enzyme active site.

Synthesis of novel quinoline-based thiadiazole, evaluation of their antileishmanial potential and molecular docking studies.

New series of quinoline-based thiadiazole analogs (1-20) were synthesized, characterized by EI-MS, 1H NMR and 13C NMR. All synthesized compounds were subjected to their antileishmanial potential. Sixteen analogs 1-10, 12, 13, 16, 17, 18 and 19 with IC50 values in the range of 0.04 ±â€¯0.01 to 5.60 ±â€¯0.21 µM showed tremendously potent inhibition as compared to the standard pentamidine with IC50 value 7.02 ±â€¯0.09 µM. Analogs 11, 14, 15 and 20 with IC50 8.20 ±â€¯0.35, 9.20 ±â€¯0.40, 7.20 ±â€¯0.20 and 9.60 ±â€¯0.40 µM respectively showed good inhibition when compared with the standard. Structure-activity relationships have been also established for all compounds. Molecular docking studies were performed to determine the binding interaction of the compounds with the active site target.

Synthesis of benzothiazole derivatives as a potent α-glucosidase inhibitor.

Diabetes is one of the pre-dominant metabolic disorders all over the world. It is the prime reason of mortality and morbidity due to hyperglycemia which is link with numerus obstacles. Delaying absorption and digestion of carbohydrate has great therapeutic impact for governing postprandial hyperglycemia. Consequently, alpha glucosidase is one of the potential therapeutic approaches that reduce absorption of glucose and delay carbohydrate digestion hence maintaining blood glucose level. In this regard we have synthesized benzothiazole based oxadiazole in search of potent anti-diabetic agent as α-glucosidase Inhibitors. Benzothiazole based oxadiazole derivatives 1-23 have been synthesized, characterized by 1HNMR, 13CNMR, and MS and evaluated for α-glucosidase Inhibition. All analogs exhibited a varying degree of α-glucosidase inhibitory activity with IC50 values ranging in between 0.5 ±â€¯0.01-30.90 ±â€¯0.70 µM when compared with the standard acarbose (IC50 = 866.30 ±â€¯3.20 µM). Structure activity relationship has been established for all compounds. Molecular docking studies were performed to predict the binding interaction of the compounds with the active site of enzyme.

Synthesis, in vitro urease inhibitory potential and molecular docking study of Benzimidazole analogues.

Despite of many diverse biological activities exhibited by benzimidazole scaffold, it is rarely explored for the urease inhibitory potential. For that purpose, benzimidazole analogues 1-19 were synthesized and screened for in vitro urease inhibitory potential. Structures of all synthetic analogues were deduced by different spectroscopic techniques. All analogues revealed inhibition potential with IC50 values of 0.90 ±â€¯0.01 to 35.20 ±â€¯1.10 µM, when compared with the standard thiourea (IC50 = 21.40 ±â€¯0.21 µM). Limited SAR suggested that the variations in the inhibitory potentials of the analogues are the result of different substitutions on phenyl ring. In order to rationalize the binding interactions of most active compounds with the active site of urease enzyme, molecular docking study was conducted.

Synthesis of new arylhydrazide bearing Schiff bases/thiazolidinone: α-Amylase, urease activities and their molecular docking studies.

Alpha-amylase and urease enzyme over expression endorses various complications like rheumatoid arthritis, urinary tract infection, colon cancer, metabolic disorder, cardiovascular risk, and chronic kidney disease. To overcome these complications, we have synthesized new arylhydrazide bearing Schiff bases/thiazolidinone analogues as α-amylase and urease inhibitors. The analogues 1a-r were evaluated for α-amylase inhibitory potential. All analogues were found active and show IC50 value ranging between 0.8 ±â€¯0.05 and 12.50 ±â€¯0.5 µM as compare to standard acarbose (IC50 = 1.70 ±â€¯0.10 µM). Among the synthesized analogs, compound 1j, 1r, 1k, 1e, 1b and 1f having IC50 values 0.8 ±â€¯0.05, 0.9 ±â€¯0.05, 1.00 ±â€¯0.05, 1.10 ±â€¯0.10, 1.20 ±â€¯0.10 and 1.30 ±â€¯0.10 µM respectively showed an excellent inhibitory potential. Analogs 2a-o were evaluated against urease activity. All analogues were found active and show IC50 value ranging between 4.10 ±â€¯0.02 and 38.20 ±â€¯1.10 µM as compare to standard thiourea (IC50 = 21.40 ±â€¯0.21 µM). Among the synthesized analogs, compound 2k, 2a, 2h, 2j, 2f, 2e, 2g, 2b and 2l having IC50 values 4.10 ±â€¯0.02, 4.60 ±â€¯0.02, 4.70 ±â€¯0.03, 5.40 ±â€¯0.02, 6.70 ±â€¯0.05, 8.30 ±â€¯0.3, 11.20 ±â€¯0.04, 16.90 ±â€¯0.8 and 19.80 ±â€¯0.60 µM respectively showed an excellent inhibitory potential. All compounds were characterized through 1H, 13C NMR and HR-EIMS analysis. Structure activity relationship of the synthesized analogs were recognized and confirmed through molecular docking studies.

Synthesis of Chromen-4-One-Oxadiazole Substituted Analogs as Potent ß-Glucuronidase Inhibitors.

Chromen-4-one substituted oxadiazole analogs 1-19 have been synthesized, characterized and evaluated for ß-glucuronidase inhibition. All analogs exhibited a variable degree of ß-glucuronidase inhibitory activity with IC50 values ranging in between 0.8 ± 0.1-42.3 ± 0.8 µM when compared with the standard d-saccharic acid 1,4 lactone (IC50 = 48.1 ± 1.2 µM). Structure activity relationship has been established for all compounds. Molecular docking studies were performed to predict the binding interaction of the compounds with the active site of enzyme.

Synthesis of Thymidine Phosphorylase Inhibitor Based on Quinoxaline Derivatives and Their Molecular Docking Study.

We have synthesized quinoxaline analogs (1⁻25), characterized by ¹H-NMR and HREI-MS and evaluated for thymidine phosphorylase inhibition. Among the series, nineteen analogs showed better inhibition when compared with the standard inhibitor 7-Deazaxanthine (IC50 = 38.68 ± 4.42 µM). The most potent compound among the series is analog 25 with IC50 value 3.20 ± 0.10 µM. Sixteen analogs 1, 2, 3, 4, 5, 6, 7, 12, 13, 14, 15, 16, 17, 18, 21 and 24 showed outstanding inhibition which is many folds better than the standard 7-Deazaxanthine. Two analogs 8 and 9 showed moderate inhibition. A structure-activity relationship has been established mainly based upon the substitution pattern on the phenyl ring. The binding interactions of the active compounds were confirmed through molecular docking studies.

Synthesis of Bis-indolylmethane sulfonohydrazides derivatives as potent α-Glucosidase inhibitors.

In search of better α-glucosidase inhibitors, a series of bis-indolylmethane sulfonohydrazides derivatives (1-14) were synthesized and evaluated for their α-glucosidase inhibitory potential. All derivatives exhibited outstanding α-glucosidase inhibition with IC50 values ranging between 0.10 ±â€¯0.05 to 5.1 ±â€¯0.05 µM when compared with standard drug acarbose having IC50 value 856.28 ±â€¯3.15 µM. Among the series, analog 7 (0.10 ±â€¯0.05 µM) with tri-chloro substitution on phenyl ring was identified as the most potent inhibitor of α-glucosidase (∼ 8500 times). The structure activity relationship has been also established. Molecular docking studies were also performed to help understand the binding interaction of the most active analogs with receptors. From the docking studies, it was observed that all the active bis-indolylmethane sulfonohydrazides derivatives showed considerable binding interactions within the active site (acarbose inhibition site) of α-glucosidase. We also evaluated toxicity of all derivatives and found none of them are toxic.

IoMT-Based Mitochondrial and Multifactorial Genetic Inheritance Disorder Prediction Using Machine Learning.

A genetic disorder is a serious disease that affects a large number of individuals around the world. There are various types of genetic illnesses, however, we focus on mitochondrial and multifactorial genetic disorders for prediction. Genetic illness is caused by a number of factors, including a defective maternal or paternal gene, excessive abortions, a lack of blood cells, and low white blood cell count. For premature or teenage life development, early detection of genetic diseases is crucial. Although it is difficult to forecast genetic disorders ahead of time, this prediction is very critical since a person's life progress depends on it. Machine learning algorithms are used to diagnose genetic disorders with high accuracy utilizing datasets collected and constructed from a large number of patient medical reports. A lot of studies have been conducted recently employing genome sequencing for illness detection, but fewer studies have been presented using patient medical history. The accuracy of existing studies that use a patient's history is restricted. The internet of medical things (IoMT) based proposed model for genetic disease prediction in this article uses two separate machine learning algorithms: support vector machine (SVM) and K-Nearest Neighbor (KNN). Experimental results show that SVM has outperformed the KNN and existing prediction methods in terms of accuracy. SVM achieved an accuracy of 94.99% and 86.6% for training and testing, respectively.

Supervised Machine Learning Empowered Multifactorial Genetic Inheritance Disorder Prediction.

Fatal diseases like cancer, dementia, and diabetes are very dangerous. This leads to fear of death if these are not diagnosed at early stages. Computer science uses biomedical studies to diagnose cancer, dementia, and diabetes. With the advancement of machine learning, there are various techniques which are accessible to predict and prognosis these diseases based on different datasets. These datasets varied (image datasets and CSV datasets) around the world. So, there is a need for some machine learning classifiers to predict cancer, dementia, and diabetes in a human. In this paper, we used a multifactorial genetic inheritance disorder dataset to predict cancer, dementia, and diabetes. Several studies used different machine learning classifiers to predict cancer, dementia, and diabetes separately with the help of different types of datasets. So, in this paper, multiclass classification proposed methodology used support vector machine (SVM) and K-nearest neighbor (KNN) machine learning techniques to predict three diseases and compared these techniques based on accuracy. Simulation results have shown that the proposed model of SVM and KNN for prediction of dementia, cancer, and diabetes from multifactorial genetic inheritance disorder achieved 92.8% and 92.5%, 92.8% and 91.2% accuracy during training and testing, respectively. So, it is observed that proposed SVM-based dementia, cancer, and diabetes from multifactorial genetic inheritance disorder prediction (MGIDP) give attractive results as compared with the proposed model of KNN. The application of the proposed model helps to prognosis and prediction of cancer, dementia, and diabetes before time and plays a vital role to minimize the death ratio around the world.

A novel stacking ensemble for detecting three types of diabetes mellitus using a Saudi Arabian dataset: Pre-diabetes, T1DM, and T2DM.

Glucose is the primary source of energy for cells, which are the building blocks of life. It is given to the body by insulin that carries out the metabolic tasks that keep people alive. Glucose level imbalance is a sign of diabetes mellitus (DM), a common type of chronic disease. It leads to long-term complications, such as blindness, kidney failure, and heart disease, having a negative impact on one's quality of life. In Saudi Arabia, a ten-fold increase in diabetic cases has been documented within the last three years. DM is broadly categorized as Type 1 Diabetes (T1DM), Type 2 Diabetes (T2DM), and Pre-diabetes. The diagnosis of the correct type is sometimes ambiguous to medical professionals causing difficulties in managing the illness progression. Intensive efforts have been made to predict T2DM. However, there is a lack of studies focusing on accurately identifying T1DM and Pre-diabetes. Therefore, this study aims to utilize Machine Learning (ML) to distinguish and predict the three types of diabetes based on a Saudi Arabian hospital dataset to control their progression. Four different experiments have been conducted to achieve the highest results, where several algorithms were used, including Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbor (K-NN), Decision Tree (DT), Bagging, and Stacking. In experiments 2, 3, and 4, the Synthetic Minority Oversampling Technique (SMOTE) was applied to balance the dataset. The empirical results demonstrated promising results of the novel Stacking model that combined Bagging K-NN, Bagging DT, and K-NN, with a K-NN meta-classifier attaining an accuracy, weighted recall, weighted precision, and cohen's kappa score of 94.48%, 94.48%, 94.70%, and 0.9172, respectively. Five principal features were identified to significantly affect the model accuracy using the permutation feature importance, namely Education, AntiDiab, Insulin, Nutrition, and Sex.

Exploring indole-based-thiadiazole derivatives as potent acetylcholinesterase and butyrylcholinesterase enzyme inhibitors.

Indole based thiadiazole derivatives (1-18) were synthesized and evaluated for their acetylcholinesterase (AChE) and butyrylcholinesterase (BChE) inhibition. The IC50 values of the synthesized analogues ranging between 0.17 ± 0.05 to 33.10 ± 0.6 µM against (AChE) and 0.30 ± 0.1 to 37.60 ± 0.6 µM against (BChE) enzymes. Among the series compounds 8 (IC50 = 0.17 ± 0.05 µM) (IC50 = 0.30 ± 0.1 µM), 9 (IC50 = 0.30 ± 0.05 µM) (IC50 = 0.60 ± 0.05 µM) and 10 (IC50 = 1.30 ± 0.1 µM) (IC50 = 2.60 ± 0.1) were found to be the most potent analogues bearing para, ortho, and meta-fluoro substitutions on phenyl ring attached to thiadiazole. In addition, all the synthesized scaffolds were characterized by using 1H NMR, 13C NMR spectroscopy, and high-resolution Mass Spectrometry (HR-MS). To apprehend the binding mode of interaction of the most potent synthesized derivatives, a molecular docking study was performed.

Inhibition potential of phenyl linked benzimidazole-triazolothiadiazole modular hybrids against ß-glucuronidase and their interactions thereof.

ß-Glucuronidase is responsible for the catalytic deconjugation of ß-d-glucuronides. ß-Glucuronidase has evolved to be a viable molecular target for numerous therapeutic treatments. It plays a pivotal role in the metabolism of drugs and endogenous substances. Herein, we report the inhibitory potentials of newly developed and modular benzimidazole-triazolothiadiazole hybrids spaced through a phenyl linker (1-26) and their interactions with the ß-glucuronidase. All analogues showed IC50 values in the range of 1.30 ±â€¯0.10 to 44.10 ±â€¯0.80 µM, and hence were found to have outstanding inhibitory potential as compare to the standard D-saccharic acid 1,4-lactone (IC50 = 48.4 ±â€¯1.25 µM). These modular hybrids were successfully synthesized, rigorously characterized through various spectroscopic techniques. Molecular docking studies further revealed the potential interactions between the inhibitor and active amino acid site in ß-glucuronidase. These findings helped in identifying the potential for new drug candidates. A Plausible structure activity relationship (SAR) were established which suggested that variation in the inhibitory potential was mainly based upon the substituents attached to the phenyl ring.

Indole bearing thiadiazole analogs: synthesis, ß-glucuronidase inhibition and molecular docking study.

Indole based thiadiazole derivatives (1-22) have synthesized, characterized by NMR and HREI-MS and evaluated for ß-Glucuronidase inhibition. All compounds showed outstanding ß-glucuronidase activity with IC50 values ranging between 0.5 ± 0.08 to 38.9 ± 0.8 µM when compared with standard d-saccharic acid 1,4 lactone (IC50 value of 48.1 ± 1.2 µM). The compound 6, a 2,3-dihydroxy analog was found the most potent among the series with IC50 value 0.5 ± 0.08 µM. Structure activity relationship has been established for all compounds. To confirm the binding interactions of these newly synthesized compounds, molecular docking study have been carried out which reveal that these compounds established stronger hydrogen bonding networks with active site residues.

Synthesis, anti-leishmanial and molecular docking study of bis-indole derivatives.

We have synthesized new series of bisindole analogs (1-27), characterized by 1HNMR and HR-EI-MS and evaluated for their anti-leishmanial potential. All compounds showed outstanding inhibitory potential with IC50 values ranging from 0.7 ± 0.01 to 13.30 ± 0.50 µM respectively when compared with standard pentamidine with IC50 value of 7.20 ± 0.20 µM. All analogs showed greater potential than standard except 10, 19 and 23 when compared with standard. Structure activity relationship has been also established for all compounds. Molecular docking studies were carried out to understand the binding interaction of active molecules.