Role of machine learning in molecular pathology for breast cancer: A review on gene expression profiling and RNA sequencing application

INTRODUCTION

Breast cancer is the most prevalent cancer among women, with growing incidence and mortality rates. Regardless of remarkable progress in cancer research, breast cancer remains a major concern due to its complex nature. These factors underscore the necessity of innovative research and diagnostic tools. Attention to gene signatures and biotechnology methods have shown significant performance in the diagnosis and management of breast cancer. Currently, artificial intelligence (AI) is known as a revolutionary tool to analyze data, identify biomarkers, and enrich diagnostic and prognostic accuracy. Therefore, the integration of breast cancer datasets with artificial intelligence can play a crucial role in the control of breast cancer. This review explores advanced machine learning techniques to analyze transcriptomic data while focusing on breast cancer subtype classification and its potential impact and limitations.

METHOD

A comprehensive literature search was performed in PubMed, Scopus, WoS, Embase, and IEEE Xplore. Duplicates were removed, two reviewers screened articles, and two additional reviewers resolved conflicts. Data extraction included details on molecular methods, AI techniques, clinical targets, study populations, and data analysis methods which were used to categorize relevant studies into RNA sequencing and gene expression profiling groups.

RESULT

In the initial stage, 7287 articles were identified, and 54 were retained following further screening, 24 in RNA sequencing and 30 in gene expression profiling. A review of these studies showed how artificial intelligence is advancing breast cancer research by using RNA sequencing and gene expression profiling. AI algorithms, including Random Forest, CNNs, SVMs, and LASSO, were the most applied techniques that showed significant potential to identify biomarkers, prognostic survival, and optimize drug responses to manage breast cancer.

CONCLUSION

The methods of artificial intelligence hold very great potential for change in the field of breast cancer. This promising progress can be seen in every aspect including diagnosis, prognosis, and treatment. However, it is important to note that we are still in the early stages of progress, and larger-scale studies and interdisciplinary collaborations in this field are needed.

A gene selection algorithm for microarray cancer classification using an improved particle swarm optimization

Gene selection is an essential step for the classification of microarray cancer data. Gene expression cancer data (deoxyribonucleic acid microarray] facilitates in computing the robust and concurrent expression of various genes. Particle swarm optimization (PSO) requires simple operators and less number of parameters for tuning the model in gene selection. The selection of a prognostic gene with small redundancy is a great challenge for the researcher as there are a few complications in PSO based selection method. In this research, a new variant of PSO (Self-inertia weight adaptive PSO) has been proposed. In the proposed algorithm, SIW-APSO-ELM is explored to achieve gene selection prediction accuracies. This novel algorithm establishes a balance between the exploitation and exploration capabilities of the improved inertia weight adaptive particle swarm optimization. The self-inertia weight adaptive particle swarm optimization (SIW-APSO) algorithm is employed for solution explorations. Each particle in the SIW-APSO increases its position and velocity iteratively through an evolutionary process. The extreme learning machine (ELM) has been designed for the selection procedure. The proposed method has been employed to identify several genes in the cancer dataset. The classification algorithm contains ELM, K-centroid nearest neighbor, and support vector machine to attain high forecast accuracy as compared to the start-of-the-art methods on microarray cancer datasets that show the effectiveness of the proposed method.

Common Attractors in Multiple Boolean Networks

Analyzing multiple networks is important to understand relevant features among different networks. Although many studies have been conducted for that purpose, not much attention has been paid to the analysis of attractors (i.e., steady states) in multiple networks. Therefore, we study common attractors and similar attractors in multiple networks to uncover hidden similarities and differences among networks using Boolean networks (BNs), where BNs have been used as a mathematical model of genetic networks and neural networks. We define three problems on detecting common attractors and similar attractors, and theoretically analyze the expected number of such objects for random BNs, where we assume that given networks have the same set of nodes (i.e., genes). We also present four methods for solving these problems. Computational experiments on randomly generated BNs are performed to demonstrate the efficiency of our proposed methods. In addition, experiments on a practical biological system, a BN model of the TGF- β signaling pathway, are performed. The result suggests that common attractors and similar attractors are useful for exploring tumor heterogeneity and homogeneity in eight cancers.

Deep Learning Based Methods for Breast Cancer Diagnosis: A Systematic Review and Future Direction

Breast cancer is one of the precarious conditions that affect women, and a substantive cure has not yet been discovered for it. With the advent of Artificial intelligence (AI), recently, deep learning techniques have been used effectively in breast cancer detection, facilitating early diagnosis and therefore increasing the chances of patients' survival. Compared to classical machine learning techniques, deep learning requires less human intervention for similar feature extraction. This study presents a systematic literature review on the deep learning-based methods for breast cancer detection that can guide practitioners and researchers in understanding the challenges and new trends in the field. Particularly, different deep learning-based methods for breast cancer detection are investigated, focusing on the genomics and histopathological imaging data. The study specifically adopts the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA), which offer a detailed analysis and synthesis of the published articles. Several studies were searched and gathered, and after the eligibility screening and quality evaluation, 98 articles were identified. The results of the review indicated that the Convolutional Neural Network (CNN) is the most accurate and extensively used model for breast cancer detection, and the accuracy metrics are the most popular method used for performance evaluation. Moreover, datasets utilized for breast cancer detection and the evaluation metrics are also studied. Finally, the challenges and future research direction in breast cancer detection based on deep learning models are also investigated to help researchers and practitioners acquire in-depth knowledge of and insight into the area.

Convolutional neural network for human cancer types prediction by integrating protein interaction networks and omics data

Many studies have proven the power of gene expression profile in cancer identification, however, the explosive growth of genomics data increasing needs of tools for cancer diagnosis and prognosis in high accuracy and short times. Here, we collected 6136 human samples from 11 cancer types, and integrated their gene expression profiles and protein-protein interaction (PPI) network to generate 2D images with spectral clustering method. To predict normal samples and 11 cancer tumor types, the images of these 6136 human cancer network were separated into training and validation dataset to develop convolutional neural network (CNN). Our model showed 97.4% and 95.4% accuracies in identification of normal versus tumors and 11 cancer types, respectively. We also provided the results that tumors located in neighboring tissues or in the same cell types, would induce machine make error classification due to the similar gene expression profiles. Furthermore, we observed some patients may exhibit better prognosis if their tumors often misjudged into normal samples. As far as we know, we are the first to generate thousands of cancer networks to predict and classify multiple cancer types with CNN architecture. We believe that our model not only can be applied to cancer diagnosis and prognosis, but also promote the discovery of multiple cancer biomarkers.

Molecular Subtypes of Oral Squamous Cell Carcinoma Based on Immunosuppression Genes Using a Deep Learning Approach

Background: The mechanisms through which immunosuppressed patients bear increased risk and worse survival in oral squamous cell carcinoma (OSCC) are unclear. Here, we used deep learning to investigate the genetic mechanisms underlying immunosuppression in the survival of OSCC patients, especially from the aspect of various survival-related subtypes. Materials and methods: OSCC samples data were obtained from The Cancer Genome Atlas (TCGA), International Cancer Genome Consortium (ICGC), and OSCC-related genetic datasets with survival data in the National Center for Biotechnology Information (NCBI). Immunosuppression genes (ISGs) were obtained from the HisgAtlas and DisGeNET databases. Survival analyses were performed to identify the ISGs with significant prognostic values in OSCC. A deep learning (DL)-based model was established for robustly differentiating the survival subpopulations of OSCC samples. In order to understand the characteristics of the different survival-risk subtypes of OSCC samples, differential expression analysis and functional enrichment analysis were performed. Results: A total of 317 OSCC samples were divided into one inferring cohort (TCGA) and four confirmation cohorts (ICGC set, GSE41613, GSE42743, and GSE75538). Eleven ISGs (i.e., BGLAP, CALCA, CTLA4, CXCL8, FGFR3, HPRT1, IL22, ORMDL3, TLR3, SPHK1, and INHBB) showed prognostic value in OSCC. The DL-based model provided two optimal subgroups of TCGA-OSCC samples with significant differences (p = 4.91E-22) and good model fitness [concordance index (C-index) = 0.77]. The DL model was validated by using four external confirmation cohorts: ICGC cohort (n = 40, C-index = 0.39), GSE41613 dataset (n = 97, C-index = 0.86), GSE42743 dataset (n = 71, C-index = 0.87), and GSE75538 dataset (n = 14, C-index = 0.48). Importantly, subtype Sub1 demonstrated a lower probability of survival and thus a more aggressive nature compared with subtype Sub2. ISGs in subtype Sub1 were enriched in the tumor-infiltrating immune cells-related pathways and cancer progression-related pathways, while those in subtype Sub2 were enriched in the metabolism-related pathways. Conclusion: The two survival subtypes of OSCC identified by deep learning can benefit clinical practitioners to divide immunocompromised patients with oral cancer into two subpopulations and give them target drugs and thus might be helpful for improving the survival of these patients and providing novel therapeutic strategies in the precision medicine area.

ReHiC: Enhancing Hi-C data resolution via residual convolutional network

High-throughput chromosome conformation capture (Hi-C) is one of the most popular methods for studying the three-dimensional organization of genomes. However, Hi-C protocols can be expensive since they require large amounts of sample material and may be time-consuming. Most commonly used Hi-C data are low-resolution. Such data can only be used to identify large-scale genomic interactions and are not sufficient to identify the small-scale patterns. We propose a novel deep learning-based computational approach (named ReHiC) that enhances the resolution of Hi-C data and allows us to achieve high-resolution Hi-C data at a relatively low cost. Our model only requires 1/16 down-sampling ratio of the original sequence reading to predict higher resolution Hi-C data. This is very close to high-resolution data in terms of numerical distribution and interaction distribution. More importantly, our framework stacks deeper and converges faster due to residual blocks in the core of the network. Extensive experiments show that ReHiC performs better than HiCPlus and HiCNN, two recently developed and frequently used methods to look at the spatial organization of chromatin structure in the cell. Moreover, the portability of our framework verified by extensive experiments shows that the trained model can also enhance the Hi-C matrix of other cell types efficiently. In conclusion, ReHiC offers more accurate high-resolution image reconstruction in a broad field.

An Overview of Bioinformatics Methods for Analyzing Autism Spectrum Disorders

Autism Spectrum Disorders (ASD) are a group of neurodevelopmental disorders and are well recognized to be biologically heterogeneous in which various factors are associated, including genetic, metabolic, and environmental ones. Despite its high prevalence, only a few drugs have been approved for the treatment of ASD. Therefore, extensive studies have been conducted to identify ASD risk genes and novel drug targets. Since many genes and many other factors are associated with ASD, various bioinformatics methods have also been developed for the analysis of ASD. In this paper, we review bioinformatics methods for analyzing ASD data with the focus on computational aspects. We classify existing methods into two categories: (i) methods based on genomic variants and gene expression data, and (ii) methods using biological networks, which include gene co-expression networks and protein-protein interaction networks. Next, for each method, we provide an overall flow and elaborate on the computational techniques used. We also briefly review other approaches and discuss possible future directions and strategies for developing bioinformatics approaches to analyze ASD.