Integrative sparse principal component analysis of gene expression data

Explainable machine learning approach for cancer prediction through binarilization of RNA sequencing data

In recent years, researchers have proven the effectiveness and speediness of machine learning-based cancer diagnosis models. However, it is difficult to explain the results generated by machine learning models, especially ones that utilized complex high-dimensional data like RNA sequencing data. In this study, we propose the binarilization technique as a novel way to treat RNA sequencing data and used it to construct explainable cancer prediction models. We tested our proposed data processing technique on five different models, namely neural network, random forest, xgboost, support vector machine, and decision tree, using four cancer datasets collected from the National Cancer Institute Genomic Data Commons. Since our datasets are imbalanced, we evaluated the performance of all models using metrics designed for imbalance performance like geometric mean, Matthews correlation coefficient, F-Measure, and area under the receiver operating characteristic curve. Our approach showed comparative performance while relying on less features. Additionally, we demonstrated that data binarilization offers higher explainability by revealing how each feature affects the prediction. These results demonstrate the potential of data binarilization technique in improving the performance and explainability of RNA sequencing based cancer prediction models.

Over-expression of mir-181a-3p in serum of breast cancer patients as diagnostic biomarker

BACKGROUND

Recently, the significance of epigenetics, particularly in breast cancer (BC), has become increasingly recognized. MicroRNAs (miRNAs), as an epigenetic factor, are offering valuable insights into various aspects of BC, such as its origins and clinical features. Therefore, studying the disruption of specific miRNAs through microarray and RNA-seq techniques is considered useful.

METHODS AND MATERIALS

We analyzed two microarray datasets (GSE106817 and GSE113486) in order to discover dysregulated miRNAs in the serum of BC patients. Subsequently, RNA-seq analysis was employed on the TCGA data. Two miRNAs, mir-450a-5p and mir-181a-3p, as novel miRNAs in BC studies, were selected for assessment in the serum of 100 BC patients versus 100 healthy female participants. The quantities of the miRNAs described above were determined through the utilization of RT-qPCR. Furthermore, ROC curve assessments were conducted for each individual miRNA. Next, an assessment was conducted to determine the prognostic significance of these miRNAs.

CONCLUSIONS

In summary, the utilization of microarray and RNA-seq analysis techniques has demonstrated that mir-450a-5p and mir-181a-3p exhibit elevated expression levels in the serum of BC patients. However, it is noteworthy that only mir-181a-3p displayed clinical dysregulation, as confirmed by RT-PCR findings. These miRNAs have been found to play a crucial role in modulating essential cellular processes and biological functions that contribute to cancer development. Furthermore, noteworthy outcomes have been observed for mir-181a-3p in relation to diagnostic and prognostic clinical characteristics.

Prior information-assisted integrative analysis of multiple datasets

MOTIVATION

Analyzing genetic data to identify markers and construct predictive models is of great interest in biomedical research. However, limited by cost and sample availability, genetic studies often suffer from the "small sample size, high dimensionality" problem. To tackle this problem, an integrative analysis that collectively analyzes multiple datasets with compatible designs is often conducted. For regularizing estimation and selecting relevant variables, penalization and other regularization techniques are routinely adopted. "Blindly" searching over a vast number of variables may not be efficient.

RESULTS

We propose incorporating prior information to assist integrative analysis of multiple genetic datasets. To obtain accurate prior information, we adopt a convolutional neural network with an active learning strategy to label textual information from previous studies. Then the extracted prior information is incorporated using a group LASSO-based technique. We conducted a series of simulation studies that demonstrated the satisfactory performance of the proposed method. Finally, data on skin cutaneous melanoma are analyzed to establish practical utility.

AVAILABILITY AND IMPLEMENTATION

Code is available at https://github.com/ldz7/PAIA. The data that support the findings in this article are openly available in TCGA (The Cancer Genome Atlas) at https://portal.gdc.cancer.gov/.

Virtual reality for the observation of oncology models (VROOM): immersive analytics for oncology patient cohorts

The significant advancement of inexpensive and portable virtual reality (VR) and augmented reality devices has re-energised the research in the immersive analytics field. The immersive environment is different from a traditional 2D display used to analyse 3D data as it provides a unified environment that supports immersion in a 3D scene, gestural interaction, haptic feedback and spatial audio. Genomic data analysis has been used in oncology to understand better the relationship between genetic profile, cancer type, and treatment option. This paper proposes a novel immersive analytics tool for cancer patient cohorts in a virtual reality environment, virtual reality to observe oncology data models. We utilise immersive technologies to analyse the gene expression and clinical data of a cohort of cancer patients. Various machine learning algorithms and visualisation methods have also been deployed in VR to enhance the data interrogation process. This is supported with established 2D visual analytics and graphical methods in bioinformatics, such as scatter plots, descriptive statistical information, linear regression, box plot and heatmap into our visualisation. Our approach allows the clinician to interrogate the information that is familiar and meaningful to them while providing them immersive analytics capabilities to make new discoveries toward personalised medicine.

A semi-supervised deep learning method based on stacked sparse auto-encoder for cancer prediction using RNA-seq data

BACKGROUND AND OBJECTIVE

Cancer has become a complex health problem due to its high mortality. Over the past few decades, with the rapid development of the high-throughput sequencing technology and the application of various machine learning methods, remarkable progress in cancer research has been made based on gene expression data. At the same time, a growing amount of high-dimensional data has been generated, such as RNA-seq data, which calls for superior machine learning methods able to deal with mass data effectively in order to make accurate treatment decision.

METHODS

In this paper, we present a semi-supervised deep learning strategy, the stacked sparse auto-encoder (SSAE) based classification, for cancer prediction using RNA-seq data. The proposed SSAE based method employs the greedy layer-wise pre-training and a sparsity penalty term to help capture and extract important information from the high-dimensional data and then classify the samples.

RESULTS

We tested the proposed SSAE model on three public RNA-seq data sets of three types of cancers and compared the prediction performance with several commonly-used classification methods. The results indicate that our approach outperforms the other methods for all the three cancer data sets in various metrics.

CONCLUSIONS

The proposed SSAE based semi-supervised deep learning model shows its promising ability to process high-dimensional gene expression data and is proved to be effective and accurate for cancer prediction.