Filters








2,242 Hits in 11.1 sec

Heterogeneous multiple kernel learning for breast cancer outcome evaluation

Xingheng Yu, Xinqi Gong, Hao Jiang
2020 BMC Bioinformatics  
The algorithm is named the heterogeneous multiple kernel learning (HMKL).  ...  On one hand, HMKL is effective for the breast cancer evaluation and can be utilized by physicians to better understand the patient's condition.  ...  Availability of data and materials All the datasets are publicly accessible through The Cancer Genome Atlas and National Center for Biotechnology Information Gene Expression Omnibus, where the accession  ... 
doi:10.1186/s12859-020-3483-0 pmid:32326887 pmcid:PMC7181520 fatcat:yjw4mcg5gjd5hce3zvueoodmey

Maximizing information through multiple kernel-based heterogeneous data integration and applications to ovarian cancer

Jaya Thomas, Lee Sael
2016 Proceedings of the Sixth International Conference on Emerging Databases Technologies, Applications, and Theory - EDB '16  
In this paper, we introduce a multiple kernel based pipeline for integrative analysis of highthroughput molecular and clinical data. We apply the pipeline on Ovarian cancer data from TCGA.  ...  After multiple kernel have been generated from weighted sum of individual kernels, it is used to stratify patients and predict clinical outcomes.  ...  Multiple kernel learning is well known for addressing various data heterogeneity.  ... 
doi:10.1145/3007818.3007831 dblp:conf/edb/ThomasS16 fatcat:mrddevuu7zhthjmmlvorskd4hu

Multi-Kernel LS-SVM Based Bio-Clinical Data Integration: Applications to Ovarian Cancer [article]

Jaya Thomas, Lee Sael
2017 arXiv   pre-print
After multiple kernels have been generated from the weighted sum of individual kernels, it is used to stratify patients and predict clinical outcomes.  ...  In this paper, we introduce a multiple kernel based pipeline for integrative analysis of high-throughput molecular data (somatic mutation, copy number alteration, DNA methylation and mRNA) and clinical  ...  Multiple kernel learning is well known for addressing various data heterogeneity.  ... 
arXiv:1704.02846v2 fatcat:p3qu6aiepbdslbyl3k2xu2yuva

Multi-kernel LS-SVM based integration bio-clinical data analysis and application to ovarian cancer

Lee Sael, Jaya Thomas
2017 International Journal of Data Mining and Bioinformatics  
After multiple kernels have been generated from the weighted sum of individual kernels, it is used to stratify patients and predict clinical outcomes.  ...  In this paper, we introduce a multiple kernel based pipeline for integrative analysis of highthroughput molecular data (somatic mutation, copy number alteration, DNA methylation and mRNA) and clinical  ...  Multiple kernel learning is well known for addressing various data heterogeneity.  ... 
doi:10.1504/ijdmb.2017.10010186 fatcat:oaltl4jn4nezranvmeu6aqbwpe

Integrating Somatic Mutations for Breast Cancer Survival Prediction Using Machine Learning Methods

Zongzhen He, Junying Zhang, Xiguo Yuan, Yuanyuan Zhang
2021 Frontiers in Genetics  
Therefore, we adopted multiple kernel learning (MKL) to efficiently integrate somatic mutation to currently molecular data including gene expression, copy number variation (CNV), methylation, and protein  ...  expression data for the prediction of breast cancer survival.  ...  was deployed on the learning dataset for breast cancer prognosis to train an optimal model; and (3) the prediction model on learning dataset and the validation dataset were evaluated for their ability  ... 
doi:10.3389/fgene.2020.632901 pmid:33537063 pmcid:PMC7848170 fatcat:ay2rz2m62ffs7puymea2jgycgi

Kernel Fusion Method for Detecting Cancer Subtypes via Selecting Relevant Expression Data

Shuhao Li, Limin Jiang, Jijun Tang, Nan Gao, Fei Guo
2020 Frontiers in Genetics  
For breast cancer, we find out that HSPA2A, RNASE1, CLIC6, and IFITM1 are highly expressed in some specific groups.  ...  Then, we construct one similarity kernel for each expression data by using Chebyshev distance.  ...  The unsupervised multiple kernel learning (UMKL) for multiple datasets was proposed by Mariette and Villa-Vialaneix (2017) .  ... 
doi:10.3389/fgene.2020.00979 pmid:33133130 pmcid:PMC7511763 fatcat:hbntohwlojajng5vukzs5gp3qq

Applications of Support Vector Machine (SVM) Learning in Cancer Genomics

2018 Cancer Genomics & Proteomics  
Machine learning with maximization (support) of separating margin (vector), called support vector machine (SVM) learning, is a powerful classification tool that has been used for cancer genomic classification  ...  There are two main types of ML learning -supervised SVM Model SVM is a powerful method for building a classifier.  ...  Cancer Foundation, the Research Institute of Oncology and Hematology Summer student research fund, and CancerCare Manitoba Foundation (CCMF).  ... 
doi:10.21873/cgp.20063 pmid:29275361 pmcid:PMC5822181 fatcat:o6l764hssnh2nbu4fm6b52f3mi

PIMKL: Pathway-Induced Multiple Kernel Learning

Matteo Manica, Joris Cadow, Roland Mathis, María Rodríguez Martínez
2019 npj Systems Biology and Applications  
PIMKL exploits prior knowledge in the form of a molecular interaction network and annotated gene sets, by optimizing a mixture of pathway-induced kernels using a Multiple Kernel Learning (MKL) algorithm  ...  We propose Pathway-Induced Multiple Kernel Learning (PIMKL), a methodology to reliably classify samples that can also help gain insights into the molecular mechanisms that underlie the classification.  ...  ACKNOWLEDGEMENTS We thank Yupeng Cun for kindly providing results 13 for the creation of Figs. 1a and S1.  ... 
doi:10.1038/s41540-019-0086-3 pmid:30854223 pmcid:PMC6401099 fatcat:nv7rall7crepdcnk6gwzyqwk3e

Integrated Multi-Omics Analyses in Oncology: A Review of Machine Learning Methods and Tools

Giovanna Nicora, Francesca Vitali, Arianna Dagliati, Nophar Geifman, Riccardo Bellazzi
2020 Frontiers in Oncology  
In recent years, high-throughput sequencing technologies provide unprecedented opportunity to depict cancer samples at multiple molecular levels.  ...  data, the machine learning methodologies that successfully tackled the complexity of multi-omics data, and the frameworks to deliver actionable results for clinical practice.  ...  ACKNOWLEDGMENTS We would like to acknowledge Simone Marini for his valuable help in the initial phases of the study.  ... 
doi:10.3389/fonc.2020.01030 pmid:32695678 pmcid:PMC7338582 fatcat:wr3auiukhrdm7o76ksgayy4aim

Machine Learning and Integrative Analysis of Biomedical Big Data

Bilal Mirza, Wei Wang, Jie Wang, Howard Choi, Neo Christopher Chung, Peipei Ping
2019 Genes  
In this review, we discuss state-of-the-art ML-based approaches for tackling five specific computational challenges associated with integrative analysis: curse of dimensionality, data heterogeneity, missing  ...  Traditionally, data from each source (e.g., genome) is analyzed in isolation using statistical and machine learning (ML) methods.  ...  ., for predicting drug sensitivity in breast cancer cell lines. It employed a Gaussian kernel for real-valued data and the Jaccard similarity coefficient for categorical data.  ... 
doi:10.3390/genes10020087 pmid:30696086 pmcid:PMC6410075 fatcat:vopnjgke4fculmr7t3n43ewfiy

Computational prediction of multidisciplinary team decision-making for adjuvant breast cancer drug therapies: a machine learning approach

Frank P. Y. Lin, Adrian Pokorny, Christina Teng, Rachel Dear, Richard J. Epstein
2016 BMC Cancer  
Methods: We analysed MDT decisions regarding adjuvant systemic therapy for 1065 breast cancer cases over eight years.  ...  To help standardise medical decision-making, we developed a machine learning model designed to predict MDT decisions about adjuvant breast cancer treatments.  ...  Availability of data and materials The datasets supporting the conclusions of this article cannot be shared for confidentiality reasons.  ... 
doi:10.1186/s12885-016-2972-z pmid:27905893 pmcid:PMC5131452 fatcat:pa7dlqpqnnfozkr2jao2q3iiku

The usage of deep learning algorithm in medical diagnostic of breast cancer

Arli Aditya Parikesit, Kevin Nathanael Ramanto
2019 Malaysian Journal of Fundamental and Applied Sciences  
One of the diseases that can be diagnosed by using deep learning algorithm is the breast cancer.  ...  Several studies showed that deep learning algorithm can be used for detecting and classifying lesions, detecting mitosis, and predicting specific gene status.  ...  Breast Cancer ANN* Evaluating the accuracy of ANN in detecting breast cancer Accuracy: 82% Bejnordi et al., 2017 399 whole-slide images Breast Cancer 32 different algorithms Evaluating  ... 
doi:10.11113/mjfas.v15n2.1231 fatcat:i7hwlbok2jazrdoxrlre35guba

DEEP LEARNING BASED ANALYSIS OF BREAST CANCER USING ADVANCED ENSEMBLE CLASSIFIER AND LINEAR DISCRIMINANT ANALYSIS

Xinfeng Zhang, Dianning He, Yue Zheng, Huaibi Huo, Simiao Li, Ruimei Chai, Ting Liu
2020 IEEE Access  
This work was supported by the Whole heart coronary plaque quantification and risk predictive model for plaque rupture based on deep learning neural network (NSFC 81871435).  ...  , as well as disease imaging based on multiple kernels of learning (MKL).  ...  methodology are ultimately applied to a set of labels for classifier learning to forecast clinical outcomes for cancer patients.  ... 
doi:10.1109/access.2020.3005228 fatcat:4zcjbivb3ne6dm27jdowpokve4

Deep Learning-Based Phenotyping of Breast Cancer Cells Using Lens-free Digital In-line Holography [article]

Tzu Hsi Song, Mengzhi Cao, Jouha Min, Hyungsoon Im, Hakho Lee, Kwonmoo Lee
2021 bioRxiv   pre-print
We demonstrate that our HoloNet efficiently enables LDIH to perform a more detailed analysis of heterogeneity of cell phenotypes for precise breast cancer diagnosis.  ...  This hologram embedding allowed us to identify rare and subtle subclusters of the phenotypes overlapped by multiple breast cancer cell types.  ...  Characterizing the Heterogeneity of Breast Cancer Cells from Patients The previous results are based on the multiple breast cancer cell lines.  ... 
doi:10.1101/2021.05.29.446284 fatcat:q3k7gccwereznkjhgsg6u34dom

A pathway-based data integration framework for prediction of disease progression

José A. Seoane, Ian N. M. Day, Tom R. Gaunt, Colin Campbell
2013 Computer applications in the biosciences : CABIOS  
Results: We use the METABRIC dataset for breast cancer, with prediction of survival at 2000 days from diagnosis.  ...  Implementation: We consider data integration via the use of multiple kernel learning supervised learning methods.  ...  called multiple kernel learning (MKL) (see Fig. 1 ).  ... 
doi:10.1093/bioinformatics/btt610 pmid:24162466 pmcid:PMC3957070 fatcat:ap7x3vauxfgsjhbwzcp2cglt6e
« Previous Showing results 1 — 15 out of 2,242 results