Subir Samanta

Computational Intelligence in Early Diabetes Diagnosis: A Review

The development of an effective diabetes diagnosis system by taking advantage of computational intelligence is regarded as a primary goal nowadays. Many approaches based on artificial network and machine learning algorithms have been developed and tested against diabetes datasets, which were mostly related to individuals of Pima Indian origin. Yet, despite high accuracies of up to 99% in predicting the correct diabetes diagnosis, none of these approaches have reached clinical application so far. One reason for this failure may be that diabetologists or clinical investigators are sparsely informed about, or trained in the use of, computational diagnosis tools. Therefore, this article aims at sketching out an outline of the wide range of options, recent developments, and potentials in machine learning algorithms as diabetes diagnosis tools. One focus is on supervised and unsupervised methods, which have made significant impacts in the detection and diagnosis of diabetes at primary and advanced stages. Particular attention is paid to algorithms that show promise in improving diabetes diagnosis. A key advance has been the development of a more in-depth understanding and theoretical analysis of critical issues related to algorithmic construction and learning theory. These include trade-offs for maximizing generalization performance, use of physically realistic constraints, and incorporation of prior knowledge and uncertainty. The review presents and explains the most accurate algorithms, and discusses advantages and pitfalls of methodologies. This should provide a good resource for researchers from all backgrounds interested in computational intelligence-based diabetes diagnosis methods, and allows them to extend their knowledge into this kind of research.

“Hepatocellular carcinoma: A life-threatening disease”

An estimated rise in liver cancer incidence will increase to 95374 new cases by 2020. Hepatocellular Carcinoma (HCC), the most common primary malignant tumour of the liver, is considered to be the third leading cause of all cancer-related deaths and fifth common cancer worldwide. The reported data shows that the rate of HCC incidence in male population is three to four times higher compared with the female population. In the United States, HCV-induced liver cancer is increasing very fast because of the lack of proper treatment option. There are various treatment strategies available for HCC like liver transplantation, resection, ablation, embolization and chemotherapy still the prognosis is destitute. If the patient is eligible, liver transplantation is the only therapeutic option that may give around 90% survival rate, but the scarcity of liver donor limits its broad applicability. A sudden address is necessary to develop specific drugs, personalized medicine, for HCC.

Current perspective of HCV NS5B inhibitors: a review.

Hepatitis C virus (HCV) infection has emerged as one of the most significant disease to affect humans. Despite its large medical and economical impact, there are no vaccines or efficient therapies without major side effects. The HCV non-structural protein 5B (NS5B) is the RNA-dependent RNA polymerase responsible for the complete copy of the RNA viral genome and is a target of choice for the development of anti-HCV drugs. Although many small molecules have been identified as allosteric inhibitors of NS5B, very few are active in clinical applications. Developments in the field have prompted us to review the research work on HCV NS5B polymerase inhibitors, especially their structure activity relationships and molecular modeling studies. This review will focus on the journey of drug discovery of HCV NS5B inhibitors covering both nucleoside and non-nucleosides.

Java-Based Diabetes Type 2 Prediction Tool for Better Diagnosis

BACKGROUND The concept of classification of clinical data can be utilized in the development of an effective diagnosis system by taking the advantage of computational intelligence. Diabetes disease diagnosis via proper interpretation of the diabetes data is an important problem in neural networks. Unfortunately, although several classification studies have been carried out with significant performance, many of the current methods often fail to reach out to patients. Graphical user interface-enabled tools need to be developed through which medical practitioners can simply enter the health profiles of their patients and receive an instant diabetes prediction with an acceptable degree of confidence. METHODS In this study, the neural network approach was used for a dataset of 768 persons from a Pima Indian population living near Phoenix, AZ. A neural network mixture of experts model was trained with these data using the expectation-minimization algorithm. RESULTS The mixture of experts method was used to train the algorithm with 97% accuracy. A graphical user interface was developed that would work in conjunction with the trained network to provide the output in a presentable format. CONCLUSIONS This study provides a machine-implementable approach that can be used by physicians and patients to minimize the extent of error in diagnosis. The authors are hopeful that replication of results of this study in other populations may lead to improved diagnosis. Physicians can simply enter the health profile of patients and get the diagnosis for diabetes type 2.

3D QSAR kNN-MFA studies on thiouracil derivatives as hepatitis C virus inhibitors

The development of new therapies to treat hepatitis C virus (HCV) infection effectively is currently an intensive area of research. To achieve this objective quantitative structure–activity relationship (QSAR) study was carried as it provides the rationale for the changes in the structure to have more potent analogs. In this article, we report 3D QSAR studies for the set of 50 HCV NS5B RNA-dependent RNA polymerase inhibitors using k-Nearest Neighbor Molecular Field Analysis (kNN-MFA) method combined with various selection procedures. By using kNN-MFA approach, various 3D QSAR models were generated to study the effect of steric and electrostatic descriptors on anti-HCV activity. The model with good external and internal predictivity for the training and test set has shown cross validation (q2) and external validation (pred_r2) values of 0.85 and 0.75, respectively. The steric descriptors at the grid points S_430, S_1065, and S_1165 play an important role in the design of new molecule. It also suggests the importance of aromatic or large bulky ring substituent at R1 to increase the HCV inhibitory activity as well as large bulky substituent at R2 reduces activity. This model was found to yield reliable clues for further optimization of thiouracil derivatives in the data set.

A novel approach towards design, synthesis and evaluation of some Schiff base analogues of 2-aminopyridine and 2-aminobezothiazole against hepatocellular carcinoma

Hepatocellular carcinoma is the most common primary malignancy of the liver with poor prognosis. In this study novel, Schiffs bases of 2-aminopyridine (SSSC-26 to 31) and 2-aminobenzothiazole (SSSC-32 to 37) were designed, synthesised and evaluated for antioxidant potential using DPPH method, and anti-hepatocellular carcinoma property using diethylnitrosamine (DEN) induced hepatocellular carcinoma rat model. The in-silico pharmacokinetic, rule of five and toxicity studies reveals that all the leads have an excellent intrinsic quality and sufficient structural features necessary for an oral activity. Molecular docking studies of all compounds into the ligand binding pocket of checkpoint kinase1 and vascular endothelial growth factor receptor-2 was also performed using Schrodinger software suite v8.5, and which have shown good Glide scores. Further compounds were synthesised based on the docking score and ADMET profile. The 1,1-diphenyl-2-picrylhydrazil (DPPH) scavenging study was carried out, and results showed that SSSC-29 (IC50-63.60) and SSSC-33 (IC50-60.32) were having good anti-oxidant potential in comparison with ascorbic acid (IC50-55.27). SSSC-33 further evaluated for anti-cancer potential against diethylnitrosamine (200mg/kg bw) induced hepatocellular carcinoma in rats. The biochemical, histopathological and morphological data showed that SSSC-33 can reverse the changes occurred in the cancerous liver significantly. All these findings suggested that SSSC-33-((benzo[d]thiazol-2-ylimino) methyl)phenol) could be a potential compound in combating the oxidative damage of hepatic cells occurred due to the development of hepatocellular carcinoma induced by a chemical carcinogen, DEN.

Design, Synthesis and Antidiabetic, Cardiomyopathy Studies of Cinnamic Acid-Amino Acid Hybrid Analogs

Diabetes mellitus is a chronic metabolism disorder characterized by hyperglycemia due to insulin deficiency or insulin resistance. Associated complications include Myocardial infarction, cardiomyopathy, retinopathy, neuropathy, nephropathy, etc. Cinnamic acid analogs (SSPC0-SSPC20) containing different amino acids were designed and docked into crystal structure of AMPK and PPARs. Among the 20 designed compounds five compounds namely SSPC5, SSPC8, SSPC11, SSPC14, SSPC15 showed good docking scores using Glide 5.0 Maestro program and were subjected to ADME prediction by using software Quickprop version 3.1. These were then selected for synthesis, characterized and antidiabetic activity carried out using Alloxan induced diabetic rat model by measuring blood glucose levels using glucometer at 0, 1, 2, 4, 6, 8 and 24 hrs through the tail vein puncture method. SSPC5, SSPC8, SSPC11, SSPC14 showed % reduction in blood glucose of 23.02%, 37.02%, 14.04% and 15.96% as compared to standard with 33.53% reduction. As SSPC14 had good and comparable docking scores in both AMPK and PPAR γ receptor, so it was subjected for the Diabetic as well as diabetic cardiomyopathy activity by recording the electrocardiogram of both diabetic and control rat. It was found to be very efficient at low dose and had a prolong duration of action on the heart (Up to 54 hrs). Thus this study indicated that such hybrid antidiabetic drug with dual action on hyperglycemia and cardiac function is desirable and cost effective.

k nearest neighbor-molecular field analysis on human HCV NS5B polymerase inhibitors: 2,5-disubstituted imidazo[4,5-c]pyridines

The k nearest neighbor-molecular field analysis (kNN-MFA) is used to study the correlation between the molecular properties and biological activities of the recently reported 2,5-disubstituted imidazo[4,5-c]pyridines as anti-HCV agents. The most predictive kNN-MFA model derived from the superposition of docked conformations, has good cross-validated q2 (0.96) and satisfied predictive ability

Novel Thiosemicarbazide Hybrids with Amino Acids and Peptides Against Hepatocellular Carcinoma: A Molecular Designing Approach Towards Multikinase Inhibitor.

r_{\text{pred}}^{2}