On the Investigation of Biological Phenomena through Computational Intelligence
Jyotsana Pandey,
B. K. Tripathi
Issue:
Volume 2, Issue 2, April 2014
Pages:
19-24
Received:
8 January 2014
Accepted:
16 April 2014
Published:
20 April 2014
Abstract: This paper presents the approach towards understanding and building integrative system to explain biological phenomena like splicing, promoter gene identification, disease and disorder identification through artificial neural network based computational intelligence technique. Bioinformatics and computational intelligence are new research area which integrates many core subjects such as chemistry, biology, medical science, mathematics, computer and information science. Since most of the problems in biological information processing are inherently hard, ill defined and possesses overlapping boundaries. Neural networks have proved to be effective in solving those problems where conventional computation tools failed to provide solution. Having a computational tool to predict genes and other meaningful information is therefore of great value, and can save a lot of expensive and time consuming experiments for biologists. This paper will focus on issues related to design methodology comprising neural network to analyze biological information and investigate them for powerful applications. This paper also presents an empirical evaluation on wide spectrum of complex problems to infer and analyze biological information. Our experiments demonstrate the endeavor of biological phenomena as an effective description for many intelligent applications
Abstract: This paper presents the approach towards understanding and building integrative system to explain biological phenomena like splicing, promoter gene identification, disease and disorder identification through artificial neural network based computational intelligence technique. Bioinformatics and computational intelligence are new research area whic...
Show More
QSAR Studies, Design, Synthesis and Antimicrobial Evaluation of Azole Derivatives
Vasyl Kovalishyn,
Iryna Kopernyk,
Svitlana Chumachenko,
Oleg Shablykin,
Kostyantyn Kondratyuk,
Stepan Pil’o,
Volodymyr Prokopenko,
Volodymyr Brovarets,
Larysa Metelytsia
Issue:
Volume 2, Issue 2, April 2014
Pages:
25-32
Received:
29 April 2014
Accepted:
14 May 2014
Published:
30 May 2014
Abstract: QSAR analysis of a set of previously synthesized azole derivatives tested for growth inhibitory activity against Candida albicans was performed by using Associative Neural Network. To overcome the problem of overfitting due to descriptor selection, 5-fold cross-validation with variable selection in each step of the analysis was used. The predictive ability of the models was tested through leave-one-out cross-validation, giving a Q2 = 0.77 - 0.79 for regression models. Predictions for the external evaluation sets obtained accuracies in the range of 0.70 - 0.80 for regressions. Biological testing of compounds was performed by disco-diffusion method on solid medium culture versus strain C. albicans ATCC 10231 M885. Most of compounds demonstrated high antifungal activity. Five synthesized compounds also showed activity against clinical isolate strain of C. albicans received from a biological material and resistant to fluconazole.
Abstract: QSAR analysis of a set of previously synthesized azole derivatives tested for growth inhibitory activity against Candida albicans was performed by using Associative Neural Network. To overcome the problem of overfitting due to descriptor selection, 5-fold cross-validation with variable selection in each step of the analysis was used. The predictive...
Show More
