Applying particle swarm optimization-based decision tree classifier for cancer classification on gene expression data

Chen, Kun-Huang; Wang, Kung‐Jeng; Wang, Kung-Min; Angelia, Melani-Adrian

doi:10.1016/j.asoc.2014.08.032

Cited by 103 publications

(39 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…29, in this section, copyright is owing to the author who wrote "Magnetic resonance imaging" in the Ref. 15. We scanned all animals with 7-Tesla Bruker Clinscan, which had a volume coil for signal excitation and a brain surface coil for signal receiving.…”

Section: Magnetic Resonance Imagingmentioning

confidence: 99%

“…Our purpose is to demonstrate whether C4.5 can offer a better way to help us observe and detect power law. Decision tree is a very popular tool for classification in data mining, which is widely used in deep-learning and machine learning 9,10 , industrial application 11,12 , medical treatments 13,14,15 , and bioinformatics 16,17,18 . To familiarize the readers with how decision tree can be of use in practical problems, let's imagine if we want to know who was dead among the passengers who boarded the Titanic.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Categorizing SHR and WKY rats by chi2 algorithm and decision tree

Tsai

Chen

Hong

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

In the past two decades neuroscience has offered many popular methods for the analysis of mental disorder, such as seedbased analysis, ICA, and graph methods. They are widely used in the study of brain network. We offer a new procedure that can simplify the analysis and has a high ROC index over 0.9. This method uses the graph theory to build a connectivity network, which is characterized by degrees and measures the number of effective links for each voxel. When the degree is ranked from low to high, the network equation can be fit by the power-law distribution. It has been proposed that distinct and yet robust exponents of the power law can differentiate human behavior. Using the mentally disordered SHR and WKY rats as samples, we employ chi2 algorithm and Decision Tree to classify different states of mental disorder by analyzing different traits in degree of connectivity.

show abstract

Section: Magnetic Resonance Imagingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Categorizing SHR and WKY rats by chi2 algorithm and decision tree

Tsai

Chen

Hong

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Следствием накопления в ОС тяжелых металлов, пестицидов, по-верхностно-активных веществ, компонентов ракетного топлива становятся рост заболеваемости населения, де-стабилизация природных экосистем и снижение биоло-гического разнообразия [5][6][7][8][9]. Возникновение мутаций в зародышевых клетках приводит к выкидышам и вро-жденным порокам развития, в половых клетках -к воз-никновению наследственных заболеваний, а в соматиче-ских -к возникновению и развитию злокачественных новообразований [10,11].…”

Section: генетическая токсикологияunclassified

Genotoxic effects of N-nitrosodimethylamine in somatic and generative cells of mice

Lovinskaya

Владимировна²,

Kolumbayeva

et al. 2017

Ecological genetics

View full text Add to dashboard Cite

N-Nitrosodimethylamine (NDMA) was shown to have genotoxic properties in acute and subacute studies on laboratory mice. The organ-specificity of the genotoxic effect of NDMA was revealed using the Comet assay. The most sensitive organs to the action of NDMA were kidneys and liver. DNA damage in liver cells of NDMA-treated animals at doses of 4.0 and 8.0 mg/kg, increased compared to control in 6.9 and 12.5 (р < 0.001), and in kidney cells – in 8.1 and 14.2 times (р < 0.001), respectively. NDMA also showed genotoxic activity in the reproductive cells of experimental animals, causing structural disorders of synaptonemal complexes in spermatocyte. In NDMA-treated animals at a dose of 2.0 mg/kg in acute and subacute studies, the level of spermatocytes with damaged synaptonemal complexes increased statistically significantly compared to control in 6.0 and 7.0 (р < 0.05) times, respectively.

show abstract

“…Genetik algoritma ile bir hibrit metod geliştirilebilir. Bu hibrit metoddaki genetik algoritmanın mutasyon operatörü kullanılarak parçacıkların çeşitlilik göstermesi sağlanarak yerel optimum sorunu çözülebileceği söylenerek gelecekte yapılabilecek çalışmalara dikkat çekmişlerdir [15]. H. Banka ve S. Dara (2015), ikili parçacık sürüsü optimizasyonu tabanlı Hamming uzaklığı yöntemi önermişlerdir.…”

Section: Li̇teratürdeki̇ çAlişmalarunclassified

Yumurtalık Kanseri Veri Kümesindeki Gen İfadelerinin Veri Madenciliği ile Analizi

Demircioğlu¹,

Bilge²

2015

Mar. J. Pure Appl. Sci.

View full text Add to dashboard Cite

ÖZETBiyoinformatik, moleküllerle ilgili bilgiyi anlamak ve düzenlemek için bilgisayar bilimleri, matematik, istatistik, biyoloji ve fizik gibi karmaşık disiplinlerden türetilen bir alandır. Biyoinformatiğin temel görevi, genomu verilen bir organizma ile ilgili fonksiyonların anlaşılması ve yaşam kalitesinin yükseltilmesidir. Biyoinformatik veritabanları nükleotid dizileri, protein dizileri, makro moleküler üç boyutlu (3D) yapılar gibi farklı veri türlerinden oluşabilmektedir. Biyoinformatik alanında elde edilen devasa boyuttaki verileri veri madenciliği yöntemleri kullanarak işlemek büyük önem kazanmaktadır. Bu çalışmada bioinformatik alanında veri madenciliğinin günümüz disiplinleri arasında geldiği noktaya değinilmiş ve kanser veri kümeleri ile veri madenciliği üzerine yapılan çalışmalar ve gerçekleştirilen uygulamalar incelenmiştir. Yapılmış uygulamalar ışığında yumurtalık kanseri verilerinin çeşitli öznitelik seçme ve sınıflandırma yöntemleri ile modellenerek algoritmaların doğruluk oranları incelenip karşılaştırılmıştır.Anahtar kelimeler: Biyoinformatik, veri madenciliği, öznitelik seçimi, yumurtalık kanseri, boyut indirgeme, sınıflandırma. Analysis of Gene Expressions in Ovarian Cancer Data Set by using Data Mining ABSTRACTBioinformatics is a field that is derived from the complicated disciplines such as computer sciences, mathematics, statistics, biology, and physics, in order understand and organize the knowledge with molecules. The fundamental role of bioinformatics is to understand the organism that is given its genomes and to increase the quality of the standard life. Bioinformatics data bases may consist of different data types such as nucleoid sequences, protein sequences, 3D structures of the macro molecules. The processing of the huge amount of bioinformatics data is one of the exciting area for researchers. In this study, state-of-the-art of the data mining in bioinformatics is shortly explained and the studies are investigated that have performed on the cancer databases by using data mining. Ovarian cancer database is used and different feature selection and classification methods are implemented and the results are compared.

show abstract

Applying particle swarm optimization-based decision tree classifier for cancer classification on gene expression data

Cited by 103 publications

References 44 publications

Categorizing SHR and WKY rats by chi2 algorithm and decision tree

Categorizing SHR and WKY rats by chi2 algorithm and decision tree

Genotoxic effects of N-nitrosodimethylamine in somatic and generative cells of mice

Yumurtalık Kanseri Veri Kümesindeki Gen İfadelerinin Veri Madenciliği ile Analizi

Contact Info

Product

Resources

About