Wyniki wyszukiwania - BazTech

1

Cancer gene recognition from microarray data with manta ray based enhanced ANFIS technique

Mishra Purnendu, Bhoi Nilamani

Biocybernetics and Biomedical Engineering

|

2021

|

Vol. 41, no. 3

916--932

EN

Recognizing the cancer genes from the microarray dataset is considered as the most essential research topic in bioinformatics and computational biology domain. Microarray dataset represents the state of each cell at the molecular level which is identified as the important diagnostic tool in medical field. Analyzing the microarray data may provide a huge support for cancer gene classification. Therefore recently a number of artificial intelligence and machine learning techniques are developed which utilize the microarray data for distinguishing the cancer and non-cancer cells. But still now these techniques does not achieved a satisfactory performance. Therefore, an efficient technique that provides a crisp output for cancer classification is required. To overcome such defect, an enhanced ANFIS (EANFIS) method is used in this proposed architecture for classifying the cancer genes. The convergence time of ANFIS gets increased during learning process, therefore to avoid such issue the Manta ray foraging optimization (MaFO) algorithm is hybrid along with ANFIS which improves the overall classification performance. The data given as an input to the classification process is pre-processed at the initial phase using the Ensemble Kalman Filter (EnKF) technique. After pre-processing, the genes having similar properties are clustered using an adaptive density-based spatial clustering with noise (ADBSCAN) clustering technique. Finally, the performance of proposed enhanced ANFIS is evaluated using the precision, accuracy, f-measure, recall, sensitivity, and specificity metrics. Further, the clustering based performance evaluation is also carried out using the cluster index metrics. Finally, the comparison with the state-of-the-art techniques is also performed to show the effectiveness of proposed approach.

2

MicroRNA expression prediction: Regression from regulatory elements

Oğul H., Tuncer M. E.

Biocybernetics and Biomedical Engineering

|

2016

|

Vol. 36, no. 1

89--94

EN

MicroRNAs are known as important actors in post-transcriptional regulation and relevant biological processes. Their expression levels do not only provide information about their own activities but also implicitly explain the behaviors of their targets, thus, in turn, the circuitry of underlying gene regulatory network. In this study, we consider the problem of estimating the expression of a newly discovered microRNA with known promoter sequence in a certain condition where the expression values of some known microRNAs are available. To this end, we offer a regression model to be learnt from the expression levels of other microRNAs obtained through a microarray experiment. To our knowledge, this is the first study that evaluates the predictability of microRNA expression from the regulatory elements found in its promoter sequence. The results obtained through the experiments on real microarray data justify the applicability of the framework in practice.

3

Strategiczny projekt badawczy Narodowego Centrum Badań i Rozwoju pt. " Technologie wspomagające rozwój bezpiecznej energetyki jądrowej" Zadanie nr 6. Rozwój metod zapewnienia bezpieczeństwa jądrowego i ochrony radiologicznej dla bieżących i przyszłych potrzeb energetyki jądrowej. Cel 2: Rozwój metod dozymetrii biologicznej oraz biofizycznych markerów i indykatorów wpływu promieniowania na organizmy żywe. (Etapy 6, 7, 8, 9, i 10)

Brzóska K., Kowalska M., Kruszewski M., Lankoff A., Sommer S.

Postępy Techniki Jądrowej

|

2015

|

z. 2

42--46

PL

Dozymetria biologiczna pozwala odczytać dawkę pochłoniętą promieniowania jonizującego w organizmie i jest niezbędnym elementem systemu ochrony radiologicznej. Aby zapewnić większą wiarygodność uzyskanych wyników metoda analizy dicentryków zostanie akredytowana w 2 laboratoriach, a w jednym istniejąca akredytacja zostanie rozszerzona o biodozymetrię mieszanego promieniowania gamma i neutronowego. Jedną ze strategii dostosowania dozymetrii biologicznej do scenariusza masowego zdarzenia jest łączenie laboratoriów we współdziałającą sieć. Założenia takiej sieci zostały opracowane i opisane. W trakcie projektu wypróbowano nowe, obiecujące metody: analizę ekspresji genów (m.in. FDXR, GADD45A) na poziomie mRNA z wykorzystaniem techniki PCR oraz metody oparte na PCC (przedwczesnej kondensacji chromosomów), w szczególności RICA (The Rapid Interphase Chromosome Assay). Obie metody okazały się skutecznymi metodami dozymetrii biologicznej.

EN

Biological dosimetry allows to read the absorbed dose of ionizing radiation in the body and is an essential element of the system of radiological protection. To ensure greater reliability of the results obtained by dicentric assay method will be accredited in 2 laboratories, and one existing accreditation will be extended to biodosimetry of mixed gamma and neutron radiation. One of the strategies to adapt biological dosimetry to the mass events scenario is to combine laboratories in cooperating network. Assumptions of such a network have been developed and described. The new methods of biological dosimetry have been investigated: analysis of gene expression (including FDXR, GADD45A) at the mRNA level using PCR method and methods based on the PCC (premature chromosome condensation), in particular RICA (The Interphase Chromosome Rapid Assay). Both methods have proven to be effective methods of biological dosimetry.

4

Feature selection methods in application to gene expression: autism data

Latkowski T, Osowski S.

Przegląd Elektrotechniczny

|

2014

|

R. 90, nr 8

199-204

EN

The paper presents the application of several different feature selection methods for recognizing the most significant genes and gene sequences (treated as features) stored in dataset of gene expression microarray related to autism. The outcomes of each method have been examined by analyzing gene expression profiles of selected genes. In the next step fusion of the most relevant features selected by different methods, has been implemented. The optimal number of features has been defined as the set providing the best clustering purity.

PL

Praca prezentuje badanie wybranych metod selekcji cech diagnostycznych w celu wyodrębnienia najbardziej znaczących sekwencji genowych z mikromacierzy ekspresji genów dotyczącej autyzmu. Dla wyselekcjonowanych cech przeanalizowano wartości poziomów ekspresji genów. W kolejnym etapie dokonano fuzji wyselekcjonowanych cech. Optymalny zbiór cech wyznaczono na podstawie czystości przestrzeni klasteryzacji.

5

Data mining methods for gene selection on the basis of gene expression arrays

Muszyński M., Osowski S.

International Journal of Applied Mathematics and Computer Science

|

2014

|

Vol. 24, no. 3

657--668

EN

The paper presents data mining methods applied to gene selection for recognition of a particular type of prostate cancer on the basis of gene expression arrays. Several chosen methods of gene selection, including the Fisher method, correlation of gene with a class, application of the support vector machine and statistical hypotheses, are compared on the basis of clustering measures. The results of applying these individual selection methods are combined together to identify the most often selected genes forming the required pattern, best associated with the cancerous cases. This resulting pattern of selected gene lists is treated as the input data to the classifier, performing the task of the final recognition of the patterns. The numerical results of the recognition of prostate cancer from normal (reference) cases using the selected genes and the support vector machine confirm the good performance of the proposed gene selection approach.

6

Analiza zmian w ekspresji genów cyklu komórkowego w komórkach osteoblastów hodowanych na powierzchniach stopów tytanu

Walkowiak-Przybyło M., Komorowski P., Jakubowski W., Klimek L., Walkowiak B.

Engineering of Biomaterials

|

2012

|

Vol. 15, no. 116-117 spec. iss.

46--48

7

Evaluation of how low frequency magnetic field 50 Hz affect living cells

Sztafrowski D., Wróblewski Z., Łukaszewicz M.

Przegląd Elektrotechniczny

|

2011

|

R. 87, nr 2

250-254

EN

The mechanism of ELF-MF impact on the metabolic processes occurring in cells of the living organisms is discussed. Existing research suggests that biological membranes may be composite antenna for stimulation by an electromagnetic field. To further elucidate this mechanism the use of fluorescent probes is suggested.

PL

W referacie przedstawiono postulowany mechanizm oddziaływania ELF-MF na procesy metaboliczne zachodzące w komórkach organizmów żywych. Błony biologiczne mogą być anteną zbiorczą dla bodźca, jakim jest pole elektromagnetyczne. Postuluje się wykorzystanie sond fluorescencyjnych do dalszych badań.

8

Benzo[a]pyrene and cyclopenta[c]phenanthrene suppress expression of p53 in head kidney of rainbow trout

Brzuzan P., Woźny M., Góra M., Łuczyński M. K., Jabłońska A.

Environmental Biotechnology

|

2011

|

Vol. 7, No. 1

41-45

EN

Although p53, a protein of important tumor suppressive function, has been extensively studied in mammals, relatively little is known about the p53 pathways in lower vertebrates. Particularly, limited information exists on possible influences of environmental contaminants on the expression of the p53 gene in fish. In the current study, we assessed the effects of benzo[a]pyrene (B[a]P; potent tumor promoter) and cyclopenta[c]phenanthrene (CP[c]Ph; clastogenic agent) exposure on a 24h profile of p53 gene expression in head kidney of juvenile rainbow trout (Oncorhynchus mykiss). To analyze the p53 transcription rate, we developed protocol for the examination of both mRNA and heterogeneous nuclear (hn) RNA of the gene, using Real-Time RTPCR approach. The results show that both compounds are capable of suppressing p53 transcriptional activity within 12h of the treatment. Our finding supports the idea that structurally different PAHs may influence cell physiologic functions controlled by p53 in fish, in part, by down-regulating its RNA expression levels.

9

An Extension of TSP-family Algorithms for Microarray Classification

Czajkowski M., Krętowski M.

Zeszyty Naukowe Politechniki Białostockiej. Informatyka

|

2009

|

Z. 4

31-45

EN

Classification of microarray data and generation of simple and efficient decision rules may be successfully performed with Top Scoring Pair algorithms. TSP-family methods are based on pairwise comparisons of gene expression values. This paper presents a new method, referred as Linked TSP that extends previous approaches kˇTSP and Weight kˇTSP algorithms by linking top pairwise mRNA comparisons of gene expressions in different classes. Opposite to existing TSP-family classifiers, the proposed approach creates decision rules involving single genes that most frequently appeared in top scoring pairs. Motivation of this paper is to improve classification accuracy results and to extract simple, readily interpretable rules providing biological insight as to how classification is performed. Experimental validation was performed on several human microarray datasets and obtained results are promising.

PL

Klasyfikacja danych mikromacierzowych a także późniejsza interpretacja reguł decyzyjnych może być skutecznie przeprowadzona za pomocą metod z rodziny Top Scoring Pair, polegających na analizie par genow o przeciwstawych poziomach ekspresji w róźnych klasach. W poniższym artykule zaprezentowano nową metodę: Linked TSP, ktora rozszerza działanie klasyfikatorów k-TSP i Weight k-TSP. W przeciwieństwie do algorytmow z rodziny TSP proponowane rozwiązanie tworzy reguły decyzyjne zbudowane z pojedynczych genów, co znacznie ułatwia ich późniejszą interpretację medyczną. W algorytmie wykorzystywane są pary genow uzyskane z algorytmow TSP z których następnie, wybierane są pojedyncze, najczęściej powtarzające się geny. Testy algorytmu Linked TSP przeprowadzone zostająy na rzeczywistych zbiorach danych pacjentow a uzyskane wyniki są obiecujące.

10

Krótkie cząsteczki kwasów nukleinowych jako terapeutyki

Sipa K.

Laboratorium - Przegląd Ogólnopolski

|

2004

|

nr 4

38--42

PL

Pół wieku po opisaniu przez Watsona i Cricka struktury DNA nasze rozumienie procesów leżących u podstaw życia jest coraz pełniejsze, ale wciąż dalekie od kompletnego. Uniwersalne zasady przepływu informacji genetycznej w komórce są uzupełniane przez odkrycia rzucające światło na procesy regulacji ekspresji genów, w których doniosłą rolę pełnią cząsteczki RNA – drugiego, starszego ewolucyjnie kwasu nukleinowego.

11

Wprowadzenie do technologii mikromacierzy DNA

Skommer J.

LAB Laboratoria, Aparatura, Badania

|

2004

|

R. 9, nr 1

18-20

PL

Pierwotnie badania wzoru ekspresji genów polegały na praco- i czasochłonnej analizie pojedynczych genów. Wprowadzenie technologii mikromacierzy DNA umożliwiło badanie całego genomu danego organizmu na chipie wielkości szkiełka mikroskopowego.

12

Selecting Differentially Expressed Genes for Colon Tumor Classification

Fujarewicz K., Wiench M.

International Journal of Applied Mathematics and Computer Science

|

2003

|

Vol. 13, no 3

327-335

EN

DNA microarrays provide a new technique of measuring gene expression, which has attracted a lot of research interest in recent years. It was suggested that gene expression data from microarrays (biochips) can be employed in many biomedical areas, e.g., in cancer classification. Although several, new and existing, methods of classification were tested, a selection of proper (optimal) set of genes, the expressions of which can serve during classification, is still an open problem. Recently we have proposed a new recursive feature replacement (RFR) algorithm for choosing a suboptimal set of genes. The algorithm uses the support vector machines (SVM) technique. In this paper we use the RFR method for finding suboptimal gene subsets for tumor/normal colon tissue classification. The obtained results are compared with the results of applying other methods recently proposed in the literature. The comparison shows that the RFR method is able to find the smallest gene subset (only six genes) that gives no misclassifications in leave-one-out cross-validation for a tumor/normal colon data set. In this sense the RFR algorithm outperforms all other investigated methods.

13

Properties of a Singular Value Decomposition Based Dynamical Model of Gene Expression Data

Simek K.

International Journal of Applied Mathematics and Computer Science

|

2003

|

Vol. 13, no 3

337-345

EN

Recently, data on multiple gene expression at sequential time points were analyzed using the Singular Value Decomposition (SVD) as a means to capture dominant trends, called characteristic modes, followed by the fitting of a linear discrete-time dynamical system in which the expression values at a given time point are linear combinations of the values at a previous time point. We attempt to address several aspects of the method. To obtain the model, we formulate a nonlinear optimization problem and present how to solve it numerically using the standard MATLAB procedures. We use freely available data to test the approach. We discuss the possible consequences of data regularization, called sometimes "polishing", on the outcome of the analysis, especially when the model is to be used for prediction purposes. Then, we investigate the sensitivity of the method to missing measurements and its abilities to reconstruct the missing data. Summarizing, we point out that approximation of multiple gene expression data preceded by SVD provides some insight into the dynamics, but may also lead to unexpected difficulties, like overfitting problems.

14

Improved classification of microarray gene expression data using support vector machines

Fujarewicz K., Kimmel M., Rzeszowska-Wolny J., Świerniak A.

Journal of Medical Informatics & Technologies

|

2001

|

Vol. 2, Part. 1

MI9--MI17

EN

Microarrays are new technique of gene expression measurements that attracted a great deal of research interest in recent years. It has been suggested that gene expression data from microarrays (biochips) can be utilized in many biomedical areas, for example in cancer classification. Whereas several, new and existing, methods of classification has been tested, a selection of proper (optimal) set of genes, which expression serves during classification, is still an open problem. In this paper we propose a heuristic method of choosing suboptimal set of genes by using support vector machines (SVMs). Obtained set of genes optimizes one-leave-out cross-validation error. The method is tested on microarray gene expression data of samples of two cancer types: acute myeloid leukemia (AML) and acute lymphoblastic leukemia (ALL). The results show that quality of classification of selected set of genes is much better than for sets obtained using another methods of feature selection.