A pattern recognition model to distinguish cancerous DNA sequences via signal processing methods

Khodaei, Amin; Feizi‐Derakhshi, Mohammad‐Reza; Tazehkand, Behzad Mozaffari

doi:10.1007/s00500-020-04942-4

Cited by 11 publications

(8 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Secondly, the dataset with 5 features as proposed in Liu et al [5]. Thirdly, the dataset with one feature as proposed in Khodaei et al [7]. Table 4 shows the obtained accuracy for all three types of data sets for various epochs.…”

Section: Resultsmentioning

confidence: 99%

“…We have also compared the proposed model with existing model as shown in Table 6. Existing ANN model Khodaei et al [7] was a dataset with 750 DNA sequences with one feature. The dataset is an imbalanced dataset with 82% cancerous genes and 18% noncancerous genes.…”

Section: Resultsmentioning

confidence: 99%

“…The drawback of this technique is the imbalance dataset. Khodaei et al [7] introduced a pattern recognition model to differentiate cancerous genes via machine learning algorithms. In their study, peak value versus standard deviation is taken as the discriminating feature that in turn applied to a machine-learning model.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Robust Feature Extraction and Deep Learning Approach for Cancer Gene Prognosis

Kumari

Seventline

2022

International Journal of Biology and Biomedical Engineering

View full text Add to dashboard Cite

Mutated genes are one of the prominent factors in origination and spread of cancer disease. Here we have used Genomic signal processing methods to identify the patterns that differentiate cancer and non-cancerous genes. Furthermore, Deep learning algorithms were used to model a system that automatically predicts the cancer gene. Unlike the existing methods, two feature extraction modules are deployed to extract six attributes. Power Spectral Density based module was used to extract statistical parameters like Mean, Median, Standard deviation, Mean Deviation and Median Deviation. Adaptive Functional Link Network (AFLN) based filter module was used to extract Normalized Mean Square Error (NMSE). The uniqueness of this paper is identification of six input features that differentiates cancer genes. In this work artificial neural network is developed to predict cancer genes. Comparison is done on three sets of datasets with 6 attributes, 5 attributes and one attribute. We performed all the training and testing on the Tensorflow using the Keras library in Python using Google Colab. The developed approach proved its efficiency with 6 attributes attaining an accuracy of 98% for 150 epochs. The ANN model was also compared with existing work and attained a 10 fold cross validation accuracy of 96.26% with an increase of 1.2%.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

A Robust Feature Extraction and Deep Learning Approach for Cancer Gene Prognosis

Kumari

Seventline

2022

International Journal of Biology and Biomedical Engineering

View full text Add to dashboard Cite

show abstract

“…It provides the repair of injured tissues and regeneration of dead cells [1]. However, with the effect of genetic or environmental factors, some changes may occur in the genetic components of the cells [1,2]. These changes are expressed with chromosomes.…”

Section: Introductionmentioning

confidence: 99%

Detection of Exon and Intron Regions in Dna Sequences by the Proposed Hashing Function

AKALIN

Yumuşak

2023

Journal of Scientific Reports-A

View full text Add to dashboard Cite

Chromosomes, which are formed by the combination of DNA and special proteins, are structures that can show some changes with the effect of genetic or environmental factors. The DNA molecule in these structures carries vital information in elucidating critical information about life. DNA, which is formed by the combination of sugar, phosphate and organic bases, has exon and intron regions separation. Information about the processes in the life cycle of cells, the changes experienced by stem cells, the regulations in the growth and development stage, the development status of cancer, mutation occurrences and protein synthesis are stored in exon regions. Distinguishing exon regions that form %3 of a cell's DNA is considered a challenging problem. However, the detection of diseases on genetically based facts offers more precise outputs. In this study, the BCR-ABL gene, which is an important indicator in the diagnosis of ALL and CML malignancies, was obtained from the NCBI dataset. In the first step, sequences were digitized using the integer mapping technique to detect exon and intron regions in the BCR-ABL gene region. The digitized sequences were given as input to the hash function. The outputs obtained from the hash function, which has a mathematical basis suitable for the structure of DNA, were expressed in the binary system and placed in the hash table. Then, these key values, which define the exon and intron regions, were shown as clusters in order to find the region of the new input easily. As a result of the analysis performed for the BCR-ABL gene, one collision occurred. However, to test the power of the proposed hierarchy, the same processes were used again on the BRCA-1 mutation carrier gene seen in high-risk breast cancer patients. As a result of the study also carried out on the BRCA-1 gene, one collision occurred. This shows the success and stability of the proposed method. By this study, a simple hierarchy based on a mathematical basis, independent of nucleotide length, was created.

show abstract

“…dünyası, DNA parçaları içerisindeki gizli özelliklerin ve periyodiklik durumlarının elde edilmesi amacıyla genomik sinyal işleme alanını da kullanarak güçlü analizler sunmayı hedeflemiştir[12][13]. Aynı zamanda DNA dizilimleri üzerindeki mevcut düzensizliklerin tespiti ve genetik tabanlı hastalıklar üzerinde doğru tanının konulabilmesi…”

unclassified

Lösemi hastalığının temel türlerinden ALL ve KML malignitelerinin grafik sinir ağları ve bulanık mantık algoritması ile sınıflandırılması

AKALIN

Yumuşak

2022

Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi

View full text Add to dashboard Cite

Beyaz kan hücresi kanseri olan lösemi, yaşam kalitesini düşüren ve ilerleyen aşamalarda ölüme sebep olabilen maliyeti yüksek bir malignitedir. Farklı yaş gruplarında görülebilen bu hastalığın erken ve doğru teşhisinin sağlanması tedavi sürecini etkilemekte ve hastalığın ilerlemesini engellemektedir. Bu çalışmada löseminin temel türlerinden olan ALL ve KML malignitelerinin sınıflandırılması amaçlanmıştır. Genetik temelli maligniteler olan bu türlerin ayırt edilmesinde DNA’da bir mutasyon sonucunda beliren BCR-ABL geni analiz edilmiştir. Tıp dünyasında BCR-ABL geni üzerinden mevcut türlerin ayırt edilmesi hususunda PCR tekniği kullanılarak değerlendirmeler yapılabilmektedir. Teşhis ve tedavi sürecindeki maliyetin ve zamanın indirgenmesi amacıyla disiplinlerarası çalışmalar da mevcuttur . İki aşamadan oluşan bu çalışmanın ilk aşamasında farklı nükleotit uzunluklarına sahip ALL ve KML DNA dizilimlerinin spektral yoğunluk bilgisi sinyal işleme teknikleri kullanılarak spektogramlara yansıtılmıştır. Ardından CNN ve GNN teknolojilerinin hibrit yaklaşımı olan DGCNN teknolojisi ile ALL ve KML malignitelerine ait spektogramlar sınıflandırılmıştır. Ancak nükleotitlerin farklı uzunluklarda olmasından dolayı spektogramlar üzerinde net ifadeler elde edilememiştir. Çalışmanın ikinci aşamasında farklı uzunluklara sahip DNA dizilimleri, kodon dağılımlarının esas alındığı entropi temelli haritalama tekniği ile sayısallaştırılmıştır. Sayısallaştırılan bu dizilimler üzerinden çıkarılan istatiktiksel ve yapısal özellikler uyarlanabilir bulanık mantık algoritması ile sınıflandırılarak nükleotit uzunluğundan bağımsız bir çalışma gerçekleştirilmiştir. Böylece KML ve ALL malignitelerinin sınıflandırılmasında %80’lik bir başarı düzeyi yakalanmıştır.

show abstract

A pattern recognition model to distinguish cancerous DNA sequences via signal processing methods

Cited by 11 publications

References 57 publications

A Robust Feature Extraction and Deep Learning Approach for Cancer Gene Prognosis

A Robust Feature Extraction and Deep Learning Approach for Cancer Gene Prognosis

Detection of Exon and Intron Regions in Dna Sequences by the Proposed Hashing Function

Lösemi hastalığının temel türlerinden ALL ve KML malignitelerinin grafik sinir ağları ve bulanık mantık algoritması ile sınıflandırılması

Contact Info

Product

Resources

About