Web-Based Application for Accurately Classifying Cancer Type from Microarray Gene Expression Data Using a Support Vector Machine (SVM) Learning Algorithm

Pawar, Shrikant

doi:10.1007/978-3-030-17935-9_14

Cited by 5 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Case of another direct relapse model can be Poisson's straight relapse model which has been utilized by Lie Nie et al [47] to explain the relationship model of transcriptomic and proteomic networks. In area 5.6, we quickly clarify the numerous relapse examination utilized in [81].…”

Section: Methods and Resultsmentioning

confidence: 99%

<sup></sup>Techniques of Transcriptomic and Proteomic Data Integration

Patil¹,

Len²,

Bharat³

et al. 2020

Preprint

View full text Add to dashboard Cite

As of not long ago, understanding the administrative conduct of cells has been sought after through autonomous investigation of the transcriptome or the proteome. In view of the focal creed, it was commonly accepted that there exist an immediate correspondence between mRNA records and produced protein articulations. In any case, late examinations have demonstrated that the relationship among's mRNA and Protein articulations can be low because of different factors, for example, unique half lives and post record apparatus. In this manner, a joint investigation of the transcriptomic and proteomic information can give valuable experiences that may not be translated from singular examination of mRNA or protein articulations. This article audits the current significant methodologies for joint investigation of transcriptomic and proteomic information. We order the various methodologies into eight primary classes dependent on the underlying calculation and last investigation objective. We further present analogies with different spaces and talk about the current exploration issues around there.

show abstract

Section: Methods and Resultsmentioning

confidence: 99%

<sup></sup>Techniques of Transcriptomic and Proteomic Data Integration

Patil¹,

Len²,

Bharat³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Various subsets of this feature vector were investigated. A Radial Basis Function (RBF) kernel was employed for SVM training with the regularization parameter (i.e., C parameter) set to 1.0 as is commonly employed in the field [35], [36]. This C value was not experimented with in this study.…”

Section: Classifiers Trained Using Time-resolved and Spectral Flim Pa...mentioning

confidence: 99%

Intraoperative Margin Assessment in Oral and Oropharyngeal Cancer Using Label-Free Fluorescence Lifetime Imaging and Machine Learning

Marsden

Weyers

Bec

et al. 2021

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

To demonstrate the diagnostic ability of label-free, point-scanning, fiber-based Fluorescence Lifetime Imaging (FLIm) as a means of intraoperative guidance during oral and oropharyngeal cancer removal surgery. Methods: FLIm point-measurements acquired from 53 patients (n = 67893 pre-resection in vivo, n = 89695 post-resection ex vivo) undergoing oral or oropharyngeal cancer removal surgery were used for analysis. Discrimination of healthy tissue and cancer was investigated using various FLIm-derived parameter sets and classifiers (Support Vector Machine, Random Forests, CNN). Classifier output for the acquired set of point-measurements was visualized through an interpolation-based approach to generate a probabilistic heatmap of cancer within the surgical field. Classifier output for dysplasia at the resection margins was also investigated. Results: Statistically significant change (P < 0.01) between healthy and cancer was observed in vivo for the acquired FLIm signal parameters (e.g., average lifetime) linked with metabolic activity. Superior classification was achieved at the tissue region level using the Random Forests method (ROC-AUC: 0.88). Classifier output for dysplasia (% probability of cancer) was observed to lie between that of cancer and healthy tissue, highlighting FLIm's ability to distinguish various conditions. Conclusion: The developed approach demonstrates the potential of FLIm for fast, reliable intraoperative margin assessment without the

show abstract

“…Microarray data has been widely used for health care analytics (He, Zhou, Lin, & Zhu, ; Mohammadi, Saraee, & Salehi, ; Pawar, ; Yuan, Lu, Zhang, Wang, & Cai, ). Pavlidis, Qin, Arango, Mann, and Sibille () conducted a study on using the GO for mining microarray data describing gene expression changes in the brain.…”

Section: Mining Gene Expression Data Using the Gomentioning

confidence: 99%

“…Recent applications of microarray data have increasingly focused on healthcare analytics—primarily cancer informatics. Ongoing and future applications of microarray data will involve predictions of cancer types using various machine learning models (Pawar, ). Statistical concerns surrounding the use of gene expression data such as the high dimensionality and imbalance will also be areas of focus as researchers develop novel methods to address these concerns (He et al, ).…”

Section: Mining Gene Expression Data Using the Gomentioning

confidence: 99%

Data mining powered by the gene ontology

Manda

2020

WIREs Data Min & Knowl

View full text Add to dashboard Cite

The gene ontology (GO) is a widely used resource for describing molecular functions, biological processes, and cellular components of gene products.Since its inception in 2006, the GO has been used to describe millions of gene products resulting in a massive data store of over 6 million annotations. The staggering amount of data that has resulted from annotating gene products with GO terms has led the way and opened new avenues for a wide variety of large-scale computational analyses. Specifically, a variety of data mining techniques such as association rule mining, clustering etc. have been applied successfully to a range of biological applications.

show abstract

Web-Based Application for Accurately Classifying Cancer Type from Microarray Gene Expression Data Using a Support Vector Machine (SVM) Learning Algorithm

Cited by 5 publications

References 9 publications

<sup></sup>Techniques of Transcriptomic and Proteomic Data Integration

<sup></sup>Techniques of Transcriptomic and Proteomic Data Integration

Intraoperative Margin Assessment in Oral and Oropharyngeal Cancer Using Label-Free Fluorescence Lifetime Imaging and Machine Learning

Data mining powered by the gene ontology

Contact Info

Product

Resources

About