Integration of RNA-Seq and RPPA data for survival time prediction in cancer patients

Işık, Zerrin; Ercan, Muserref Ece

doi:10.1016/j.compbiomed.2017.08.028

Cited by 13 publications

(6 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The format of the labels in supervised learning can be either discrete categories (classification) or continuous numeric values (regression). For example, clinical outcomes (such as survival time) can be predicted from quantitative proteomics data with models trained from samples collected from patients with known clinical information [150]. Applications of supervised learning in proteomics usually involve taking the quantitative results from MS as input and manually labeled or experimentally verified annotations as the target output.…”

Section: Machine Learning Approachesmentioning

confidence: 99%

Bioinformatics Methods for Mass Spectrometry-Based Proteomics Data Analysis

Chen

Hou

Tanner

2020

IJMS

166

102

View full text Add to dashboard Cite

Recent advances in mass spectrometry (MS)-based proteomics have enabled tremendous progress in the understanding of cellular mechanisms, disease progression, and the relationship between genotype and phenotype. Though many popular bioinformatics methods in proteomics are derived from other omics studies, novel analysis strategies are required to deal with the unique characteristics of proteomics data. In this review, we discuss the current developments in the bioinformatics methods used in proteomics and how they facilitate the mechanistic understanding of biological processes. We first introduce bioinformatics software and tools designed for mass spectrometry-based protein identification and quantification, and then we review the different statistical and machine learning methods that have been developed to perform comprehensive analysis in proteomics studies. We conclude with a discussion of how quantitative protein data can be used to reconstruct protein interactions and signaling networks.

show abstract

Section: Machine Learning Approachesmentioning

confidence: 99%

Bioinformatics Methods for Mass Spectrometry-Based Proteomics Data Analysis

Chen

Hou

Tanner

2020

IJMS

166

102

View full text Add to dashboard Cite

show abstract

“…Takahashi et al [26] introduced a parallel omic prediction of survival subtypes in lung cancer based on RPPA data, the results presented in this research exhibit and confirm the consistency of protemics in cancer classification. Another work presented by Isik et al [27] that inspired our RPPA based omic biomarker discovery, uses the protein-protein interaction network to select the most correlated proteins, the gene expression of the selected proteins' coding genes have been used to predict the clinical outcome of patients. R.Kim [28], used RPPA with multiomic data for breast cancer survival prediction based on pathway activity inference to address the biological process and implication of learnt features.…”

Section: Related Workmentioning

confidence: 99%

Efficient Bioinspired Feature Selection and Machine Learning Based Framework Using Omics Data and Biological Knowledge Data Bases in Cancer Clinical Endpoint Prediction

et al. 2023

View full text Add to dashboard Cite

Cancer Research has advanced during the past few years. Using high throughput technology and advances in artificial intelligence, it is now possible to improve cancer diagnosis and targeted therapy, by integrating the investigation and analysis of clinical and omics profiles. The high dimensionality and class imbalance of the majority of available data sets represent a serious challenge to the development of computational methods and tools for cancer diagnosis and biomarker discovery. Taking into account multi-omics data further complicates the undertaking. In this paper, we describe a five-step integrative architecture for dealing with the three aforementioned problems by incorporating proteomics data, proteinprotein interaction networks, and signaling pathways in order to identify protein biomarkers with a direct association to cancerous patients' overall survival (OS) and progression free interval (PFI). The core parts of this architecture are a cluster based grey wolf optimization algorithm (CB-GWO) for feature selection and a deep stacked canonical correlation autoencoder (DSCC-AE) for clinical endpoint prediction. A thorough experimental study was carried out to evaluate the performance of the proposed optimization algorithm for feature selection, as well as the performance of the deep learning model in terms of Mathew coefficient correlation (MCC) and Area under the curve (AUC) on breast, lung, colon, and rectum cancers. The results were compared to other methods in the literature. The results are very promising and show the effectiveness of the proposed framework and its ability to outperform the other algorithms and models in terms of AUC (0.91) and MCC (0.64).

show abstract

“…Nie et al utilized the 3-dimensional convolution neural network (CNN) to extract features for an SVM model and predicted with an accuracy 89.9% whether a patient had a long or short overall survival time [88]. Lsik et al employed a random walk-based algorithm to predict whether a patient had a long-or short-term survival by integrating transcriptome, proteome and protein-protein interaction data [89]. The proposed method achieved the accuracies between 66% and 78% for three cancer types.…”

Section: Crystall a Feature Selection Algorithm To Estimate Thementioning

confidence: 99%

Survival Time Prediction of Breast Cancer Patients Using Feature Selection Algorithm Crystall

Liu

Zheng

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Breast cancer is one of main causes of death for women. Most of the existing survival analyses focus on the features' associations with whether the patients may survive five years or not. The personalized question remains largely unresolved about how long a breast cancer patient will live. This study aims to predict the patient-specific survival time of breast cancer patients. It formulates the personalized question into two machine learning problems. The first problem is the binary classification of whether a patient will live longer than five years or not. The second one is to build a regression model to predict the patient's survival time within five years. The methylome of a breast cancer patient is used for the prediction. A new algorithm Crystall is presented to find the methylomic features for this regression model. Our models perform well in the above two problems, and achieve the mean absolute error (MAE) of about 1 month for predicting how long a breast cancer patient will live within five years. The detected biomarker genes demonstrate close connections with breast cancers.

show abstract

Integration of RNA-Seq and RPPA data for survival time prediction in cancer patients

Cited by 13 publications

References 33 publications

Bioinformatics Methods for Mass Spectrometry-Based Proteomics Data Analysis

Bioinformatics Methods for Mass Spectrometry-Based Proteomics Data Analysis

Efficient Bioinspired Feature Selection and Machine Learning Based Framework Using Omics Data and Biological Knowledge Data Bases in Cancer Clinical Endpoint Prediction

Survival Time Prediction of Breast Cancer Patients Using Feature Selection Algorithm Crystall

Contact Info

Product

Resources

About