Identification Of Cancer Subtypes Research Articles

Dissecting super-enhancer heterogeneity: time to re-examine cancer subtypes?

The heterogeneity of transcriptional regulations by super-enhancers (SEs) is poorly understood in human cancers. Herein, we summarize a bioinformatics workflow for genome-wide SE profiling and identification of subtype-specific SEs and regulatory networks. Dissecting SE heterogeneity provides new insights into cancer biology and alternative therapeutic strategies for cancer precision medicine.

Identification of prostate cancer subtypes based on immune signature scores in bulk and single-cell transcriptomes.

Prostate cancer (PC) is heterogeneous in the tumor immune microenvironment (TIME). Subtyping of PC based on the TIME could provide new insights into intratumor heterogeneity and its correlates of clinical features. Based on the enrichment scores of 28 immune cell types in the TIME, we performed unsupervised clustering to identify immune-specific subtypes of PC. The clustering analysis was performed in ten different bulk tumor transcriptomic datasets and in a single-cell RNA-Seq (scRNA-seq) dataset, respectively. We identified two PC subtypes: PC immunity high (PC-ImH) and PC immunity low (PC-ImL), consistently in these datasets. Compared to PC-ImL, PC-ImH displayed stronger immune signatures, worse clinical outcomes, higher epithelial-mesenchymal transition (EMT) signature, tumor stemness, intratumor heterogeneity (ITH) and genomic instability, and lower incidence of TMPRSS2-ERG fusion. Tumor mutation burden (TMB) showed no significant difference between PC-ImH and PC-ImL, while copy number alteration (CNA) was more significant in PC-ImL than in PC-ImH. PC-ImH could be further divided into two subgroups, which had significantly different immune infiltration levels and clinical features. In conclusion, "hot" PCs have stronger anti-tumor immune response, while worse clinical outcomes versus "cold" PCs. CNA instead of TMB plays a crucial role in the regulation of TIME in PC. TMPRSS2-ERG fusion correlates with decreased anti-tumor immune response while better disease-free survival in PC. The identification of immune-specific subtypes has potential clinical implications for PC immunotherapy.

Abstract LB031: WNK are drug targets for triple negative breast cancer

Abstract Triple negative breast cancer (TNBC) accounts for 10-20% of breast cancer cases, and is associated with poor diagnosis and prognostics. Due to the lack of therapeutics available, it is urgent to identify biomolecular targets to develop more efficient treatments [1]. Depletion and inhibition of the protein kinase With No Lysine (WNK) reduces migration of breast cancer cells, slowing down TNBC metastasis [2][3]. For this reason, WNKs are promising cancer drug targets. Other works suggest WNKs are also targets for the treatment of hypertension and stroke. The main focus of this work is to understand the molecular mechanisms of this family of proteins, which will help to develop more efficient drugs. WNKs are serine-threonine kinases important in ion transport regulation [4]. WNKs are critical intracellular osmosensors, with their function related to an equilibrium between an inactive dimer and an autophosphorylation-competent monomer. The dimer conformation covers phosphorylation sites [5], while simultaneously trapping water molecules [6]. The water trapping feature is hypothesized to be linked to ion pairs and clusters of charges between the Activation loop and the Catalytic loop. To access the role of these ion pairs, we expressed and purified seven mutants of key amino acids, analyzed their activity, phosphorylation state and sensitivity to ions and pressure. Some of these mutants are more monomeric, active and autophosphorylation competent than the wild-type, elucidating the role of these amino acids in the function of WNKs. Interestingly, some mutants are more sensitive to potassium, which confirms the WNK inhibition site for this ion [7]. [1]B. D. Lehmann et al., “Identification of human triple-negative breast cancer subtypes and preclinical models for selection of targeted therapies,” J. Clin. Invest., vol. 121, no. 7, pp. 2750–67, 2011.[2]S. Shyamasundar, et al., “miR-93 inhibits the invasive potential of triple-negative breast cancer cells in vitro via protein kinase WNK1,” Int. J. Oncol., vol. 49, no. 6, pp. 2629–36, 2016.[3]A. B. Jaykumas et al., “WNK1 Enhances Migration and Invasion in Breast Cancer Models,” Mol. Cancer Ther., vol. 20, no. 10, pp. 1800–08, 2021.[4]D. R. Alessi, et al., “The WNK-SPAK/OSR1 pathway: master regulator of cation-chloride cotransporters,” Sci. Signal., vol. 7, p. 334, 2014.[5]X. Min, et al., “Crystal structure of the kinase domain of WNK1, a kinase that causes a hereditary form of hypertension,” Structure, vol. 12, no. 7, pp. 1303-11, 2004.[6]R. Akella et al., “Osmosensing by WNK Kinases,” Mol. Biol. Cell, vol. 32, no. 18, pp. 1614–23, 2021.[7]J. M. Pleinis et al., “WNKs are potassium-sensitive kinases,” Am. J. Physiol Cell Physiol, vol. 320, no. 5, pp. C703-21, 2021. Citation Format: Liliana dos Reis Teixeira, John Humphreys, Haixia He, Radha Akella, Elizabeth Goldsmith. WNK are drug targets for triple negative breast cancer [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr LB031.

Colorectal cancer subtype identification from differential gene expression levels using minimalist deep learning

BackgroundCancer molecular subtyping plays a critical role in individualized patient treatment. In previous studies, high-throughput gene expression signature-based methods have been proposed to identify cancer subtypes. Unfortunately, the existing ones suffer from the curse of dimensionality, data sparsity, and computational deficiency.MethodsTo address those problems, we propose a computational framework for colorectal cancer subtyping without any exploitation in model complexity and generality. A supervised learning framework based on deep learning (DeepCSD) is proposed to identify cancer subtypes. Specifically, based on the differentially expressed genes under cancer consensus molecular subtyping, we design a minimalist feed-forward neural network to capture the distinct molecular features in different cancer subtypes. To mitigate the overfitting phenomenon of deep learning as much as possible, L1 and L2 regularization and dropout layers are added.ResultsFor demonstrating the effectiveness of DeepCSD, we compared it with other methods including Random Forest (RF), Deep forest (gcForest), support vector machine (SVM), XGBoost, and DeepCC on eight independent colorectal cancer datasets. The results reflect that DeepCSD can achieve superior performance over other algorithms. In addition, gene ontology enrichment and pathology analysis are conducted to reveal novel insights into the cancer subtype identification and characterization mechanisms.ConclusionsDeepCSD considers all subtype-specific genes as input, which is pathologically necessary for its completeness. At the same time, DeepCSD shows remarkable robustness in handling cross-platform gene expression data, achieving similar performance on both training and test data without significant model overfitting or exploitation of model complexity.

Integrative analysis of mutated genes and mutational processes reveals novel mutational biomarkers in colorectal cancer

BackgroundColorectal cancer (CRC) is one of the leading causes of cancer-related deaths worldwide. Recent studies have observed causative mutations in susceptible genes related to colorectal cancer in 10 to 15% of the patients. This highlights the importance of identifying mutations for early detection of this cancer for more effective treatments among high risk individuals. Mutation is considered as the key point in cancer research. Many studies have performed cancer subtyping based on the type of frequently mutated genes, or the proportion of mutational processes. However, to the best of our knowledge, combination of these features has never been used together for this task. This highlights the potential to introduce better and more inclusive subtype classification approaches using wider range of related features to enable biomarker discovery and thus inform drug development for CRC.ResultsIn this study, we develop a new pipeline based on a novel concept called ‘gene-motif’, which merges mutated gene information with tri-nucleotide motif of mutated sites, for colorectal cancer subtype identification. We apply our pipeline to the International Cancer Genome Consortium (ICGC) CRC samples and identify, for the first time, 3131 gene-motif combinations that are significantly mutated in 536 ICGC colorectal cancer samples. Using these features, we identify seven CRC subtypes with distinguishable phenotypes and biomarkers, including unique cancer related signaling pathways, in which for most of them targeted treatment options are currently available. Interestingly, we also identify several genes that are mutated in multiple subtypes but with unique sequence contexts.ConclusionOur results highlight the importance of considering both the mutation type and mutated genes in identification of cancer subtypes and cancer biomarkers. The new CRC subtypes presented in this study demonstrates distinguished phenotypic properties which can be effectively used to develop new treatments. By knowing the genes and phenotypes associated with the subtypes, a personalized treatment plan can be developed that considers the specific phenotypes associated with their genomic lesion.

MDICC: novel method for multi-omics data integration and cancer subtype identification.

Each type of cancer usually has several subtypes with distinct clinical implications, and therefore the discovery of cancer subtypes is an important and urgent task in disease diagnosis and therapy. Using single-omics data to predict cancer subtypes is difficult because genomes are dysregulated and complicated by multiple molecular mechanisms, and therefore linking cancer genomes to cancer phenotypes is not an easy task. Using multi-omics data to effectively predict cancer subtypes is an area of much interest; however, integrating multi-omics data is challenging. Here, we propose a novel method of multi-omics data integration for clustering to identify cancer subtypes (MDICC) that integrates new affinity matrix and network fusion methods. Our experimental results show the effectiveness and generalization of the proposed MDICC model in identifying cancer subtypes, and its performance was better than those of currently available state-of-the-art clustering methods. Furthermore, the survival analysis demonstrates that MDICC delivered comparable or even better results than many typical integrative methods.

Identification of Breast Cancer Subtypes Based on Gene Expression Profiles in Breast Cancer Stroma

BackgroundTumor stroma is a heterogeneous cellular component in the tumor microenvironment of breast cancer. However, very few studies have explored the identification of breast cancer subtypes based on highly heterogeneous tumor stromal signatures. Materials and MethodsUsing a combined dataset composed of 8 gene expression profiling datasets for breast tumor stroma, we clustered breast cancers based on the expression levels of 100 genes whose expression values were most variable across all samples. Furthermore, we investigated the molecular features of the breast cancer subtypes identified. ResultsWe identified 2 breast cancer subtypes, termed SBCS-1 and SBCS-2. We found that the contents of stroma and immune cells were lower in SBCS-1 than in SBCS-2, while the proportion of tumor cells was higher in SBCS-1. SBCS-1 was enriched in cancer-associated pathways, including ribosomes, cell cycle, RNA degradation, RNA polymerase, DNA replication, oxidative phosphorylation, proteasome, spliceosome, and glycolysis/gluconeogenesis. SBCS-2 was enriched in pathways of graft versus host disease, type 1 diabetes mellitus, intestinal immune network for IgA production, allograft rejection, and steroid hormone biosynthesis. Moreover, many oncogenic biological processes were highly activated in SBCS-1, including proliferation, stemness, epithelial-to-mesenchymal transition (EMT), and angiogenesis. Gene co-expression network analysis identified prognostic hub genes, transcription factor encoding genes (PFDN5 and EZH2), and protein kinase encoding gene (AURKA) in a gene module highly enriched in SBCS-1. ConclusionBased on the gene expression profiles in breast cancer stroma, breast cancer can be divided into 2 subtypes, which have significantly different molecular, and clinical characteristics. The identification of new subtypes of breast cancer has clinical implications for the management of this disease.

MultiGATAE: A Novel Cancer Subtype Identification Method Based on Multi-Omics and Attention Mechanism.

Cancer is one of the leading causes of death worldwide, which brings an urgent need for its effective treatment. However, cancer is highly heterogeneous, meaning that one cancer can be divided into several subtypes with distinct pathogenesis and outcomes. This is considered as the main problem which limits the precision treatment of cancer. Thus, cancer subtypes identification is of great importance for cancer diagnosis and treatment. In this work, we propose a deep learning method which is based on multi-omics and attention mechanism to effectively identify cancer subtypes. We first used similarity network fusion to integrate multi-omics data to construct a similarity graph. Then, the similarity graph and the feature matrix of the patient are input into a graph autoencoder composed of a graph attention network and omics-level attention mechanism to learn embedding representation. The K-means clustering method is applied to the embedding representation to identify cancer subtypes. The experiment on eight TCGA datasets confirmed that our proposed method performs better for cancer subtypes identification when compared with the other state-of-the-art methods. The source codes of our method are available at https://github.com/kataomoi7/multiGATAE.

Identification of Molecular Subtypes of Breast Cancer Based on Multimodal Deep Learning

The identification of breast cancer subtypes plays a key role in the prognosis of breast cancer. In recent years, deep learning (DL) has shown good performance in intelligent identification of breast cancer subtypes. However, most of the traditional DL models use single-mode data, and the extracted features are limited, so the association between patient characteristics and breast cancer subtypes cannot be established stably. In order to improve the effect of recognition, this study proposes a multimodal fusion deep learning (MFDL) model. This model combined with the breast cancer gene modal data and image modal data established a multilayer perceptron network and the depth of the convolution neural network for feature extraction, and then based on the idea of weighted aggregation on the output of the two characteristics of the network integration. Finally, the fusion features were used to identify breast cancer subtypes. The experimental results show that compared with other models in AUC value, accuracy and other indicators, the MFDL model proposed in this study is more accurate and efficient in the identification of breast cancer subtypes.

Developing a label propagation approach for cancer subtype identification problem

Cancer is a disease in which abnormal cells grow uncontrollably and invade other tissues. Several types of cancer have various subtypes with different clinical and biological implications. Based on these differences, treatment methods need to be customized. The identification of distinct cancer subtypes is an important problem in bioinformatics, since it can guide future precision medicine applications. In order to design targeted treatments, bioinformatics methods attempt to discover common molecular pathology of different cancer subtypes. Along this line, several computational methods have been proposed to discover cancer subtypes or to stratify cancer into informative subtypes. However, existing works do not consider the sparseness of data (genes having low degrees) and result in an ill-conditioned solution. To address this shortcoming, in this paper, we propose an alternative unsupervised method to stratify cancer patients into subtypes using applied numerical algebra techniques. More specifically, we applied a label propagationbased approach to stratify somatic mutation profiles of colon, head and neck, uterine, bladder, and breast tumors. We evaluated the performance of our method by comparing it to the baseline methods. Extensive experiments demonstrate that our approach highly renders tumor classification tasks by largely outperforming the state-of-the-art unsupervised and supervised approaches.

Novel cancer subtyping method based on patient-specific gene regulatory network

The identification of cancer subtypes is important for the understanding of tumor heterogeneity. In recent years, numerous computational methods have been proposed for this problem based on the multi-omics data of patients. It is widely accepted that different cancer subtypes are induced by different molecular regulatory networks. However, only a few incorporate the differences between their molecular systems into the identification processes. In this study, we present a novel method to identify cancer subtypes based on patient-specific molecular systems. Our method realizes this by quantifying patient-specific gene networks, which are estimated from their transcriptome data, and by clustering their quantified networks. Comprehensive analyses of The Cancer Genome Atlas (TCGA) datasets applied to our method confirmed that they were able to identify more clinically meaningful cancer subtypes than the existing subtypes and found that the identified subtypes comprised different molecular features. Our findings also show that the proposed method can identify the novel cancer subtypes even with single omics data, which cannot otherwise be captured by existing methods using multi-omics data.

Prediction of Cancer-Related piRNAs Based on Network-Based Stratification Analysis

PIWI-interacting RNA (PiRNA) was discovered in 2006 and is expected to become a new biomarker for diagnosis and prognosis of various diseases. The purpose of this study is to explore functions of piRNAs and identify cancer subtypes on the basis of the pattern of transcriptome and somatic mutation data. A total of 285 510 SNPs in piRNAs and genes, which might affect piRNA biogenesis or piRNA targets binding were identified. Significant co-expression networks of piRNAs were then constructed separately for 12 major types of cancer. Finally, mutational matrices were mapped to piRNA network, propagated, and clustered for identification of cancer-related piRNAs and cancer subtypes. Findings showed that subtypes of three types of cancer (COAD, STAD and UCEC), which are significantly associated with survival were identified. Analysis of differentially expressed piRNAs in UCEC subtypes showed that piRNA function is closely related to cancer hallmarks “Enabling Replicative Immortality” and contributes to initiation of cancer.

Whole-Genome Analysis of De Novo Somatic Point Mutations Reveals Novel Mutational Biomarkers in Pancreatic Cancer.

Simple SummaryMany studies have identified cancer subtypes based on the cancer driver genes, or the proportion of mutational processes in cancer genomes, however, none of these cancer subtyping methods consider these features together to identify cancer subtypes. Accurate classification of cancer individuals with similar mutational profiles may help clinicians to identify individuals who could receive the same types of treatment. Here, we develop a new statistical pipeline and use a novel concept, “gene-motif”, to identify five pancreatic cancer subtypes, in which for most of them, targeted treatment options are currently available. More importantly, for the first time we provide a system-wide analysis of the enrichment of de novo mutations in a specific motif context of the driver genes in pancreatic cancer. By knowing the genes and motif associated with the mutations, a personalized treatment can be developed that considers the specific nucleotide sequence context of mutations within responsible genes.It is now known that at least 10% of samples with pancreatic cancers (PC) contain a causative mutation in the known susceptibility genes, suggesting the importance of identifying cancer-associated genes that carry the causative mutations in high-risk individuals for early detection of PC. In this study, we develop a statistical pipeline using a new concept, called gene-motif, that utilizes both mutated genes and mutational processes to identify 4211 3-nucleotide PC-associated gene-motifs within 203 significantly mutated genes in PC. Using these gene-motifs as distinguishable features for pancreatic cancer subtyping results in identifying five PC subtypes with distinguishable phenotypes and genotypes. Our comprehensive biological characterization reveals that these PC subtypes are associated with different molecular mechanisms including unique cancer related signaling pathways, in which for most of the subtypes targeted treatment options are currently available. Some of the pathways we identified in all five PC subtypes, including cell cycle and the Axon guidance pathway are frequently seen and mutated in cancer. We also identified Protein kinase C, EGFR (epidermal growth factor receptor) signaling pathway and P53 signaling pathways as potential targets for treatment of the PC subtypes. Altogether, our results uncover the importance of considering both the mutation type and mutated genes in the identification of cancer subtypes and biomarkers.

Similarity Network Fusion Based on Random Walk and Relative Entropy for Cancer Subtype Prediction of Multigenomic Data

It is a crucial task to design an integrated method to discover cancer subtypes and understand the heterogeneity of cancer based on multiple genomic data. In recent years, some clustering algorithms have been proposed and applied to cancer subtype prediction. Among them, similarity network fusion (SNF) can integrate multiple types of genomic data to identify cancer subtypes, which improves the understanding of tumorigenesis. SNF uses a dense similarity matrix to obtain the global information of the data, and the interconnection of samples between different categories will cause noise interference. Therefore, how to construct a more robust dense similarity matrix is an important research content to improve the performance of cancer subtype identification. In this paper, we proposed similarity network fusion based on random walk and relative entropy (R2SNF) for cancer subtype prediction. Firstly, the random walk algorithm was used to capture the complex relationship between samples in each genomic data. And the transition probability distribution of samples in the network was obtained. If two samples belong to the same class, the transition probability between the two samples is great. On the contrary, if the two samples do not belong to the same class, the transition probability between the two samples is small. In this way, the degree of correlation between samples can be well obtained, thereby reducing the noise interference caused by the interconnection of samples between different categories. Secondly, relative entropy was used to calculate the difference in the transition probability distribution between samples to construct a better dense similarity matrix which contains structural similarity information between samples. Thirdly, we iteratively fused the obtained dense similarity matrix with the KNN similarity matrix to construct the fused similarity matrix of all genomic data. Finally, by using spectral clustering, the fused similarity matrix was grouped into multiple clusters, which indicates the cancer subtypes. Experiments on seven cancer omics datasets show that the R2SNF algorithm performs well in identifying cancer subtypes.

Cancer subtype identification by consensus guided graph autoencoders.

Cancer subtype identification aims to divide cancer patients into subgroups with distinct clinical phenotypes and facilitate the development for subgroup specific therapies. The massive amount of multi-omics datasets accumulated in the public databases have provided unprecedented opportunities to fulfill this task. As a result, great computational efforts have been made to accurately identify cancer subtypes via integrative analysis of these multi-omics datasets. In this article, we propose a Consensus Guided Graph Autoencoder (CGGA) to effectively identify cancer subtypes. First, we learn for each omic a new feature matrix by using graph autoencoders, where both structure information and node features can be effectively incorporated during the learning process. Second, we learn a set of omic-specific similarity matrices together with a consensus matrix based on the features obtained in the first step. The learned omic-specific similarity matrices are then fed back to the graph autoencoders to guide the feature learning. By iterating the two steps above, our method obtains a final consensus similarity matrix for cancer subtyping. To comprehensively evaluate the prediction performance of our method, we compare CGGA with several approaches ranging from general-purpose multi-view clustering algorithms to multi-omics-specific integrative methods. The experimental results on both generic datasets and cancer datasets confirm the superiority of our method. Moreover, we validate the effectiveness of our method in leveraging multi-omics datasets to identify cancer subtypes. In addition, we investigate the clinical implications of the obtained clusters for glioblastoma and provide new insights into the treatment for patients with different subtypes. The source code of our method is freely available at https://github.com/alcs417/CGGA. Supplementary data are available at Bioinformatics online.

Uncovering the roles of microRNAs/lncRNAs in characterising breast cancer subtypes and prognosis

BackgroundAccurate prognosis and identification of cancer subtypes at molecular level are important steps towards effective and personalised treatments of breast cancer. To this end, many computational methods have been developed to use gene (mRNA) expression data for breast cancer subtyping and prognosis. Meanwhile, microRNAs (miRNAs) and long non-coding RNAs (lncRNAs) have been extensively studied in the last 2 decades and their associations with breast cancer subtypes and prognosis have been evidenced. However, it is not clear whether using miRNA and/or lncRNA expression data helps improve the performance of gene expression based subtyping and prognosis methods, and this raises challenges as to how and when to use these data and methods in practice.ResultsIn this paper, we conduct a comparative study of 35 methods, including 12 breast cancer subtyping methods and 23 breast cancer prognosis methods, on a collection of 19 independent breast cancer datasets. We aim to uncover the roles of miRNAs and lncRNAs in breast cancer subtyping and prognosis from the systematic comparison. In addition, we created an R package, CancerSubtypesPrognosis, including all the 35 methods to facilitate the reproducibility of the methods and streamline the evaluation.ConclusionsThe experimental results show that integrating miRNA expression data helps improve the performance of the mRNA-based cancer subtyping methods. However, miRNA signatures are not as good as mRNA signatures for breast cancer prognosis. In general, lncRNA expression data does not help improve the mRNA-based methods in both cancer subtyping and cancer prognosis. These results suggest that the prognostic roles of miRNA/lncRNA signatures in the improvement of breast cancer prognosis needs to be further verified.

Identification of gastric cancer subtypes based on pathway clustering

Gastric cancer (GC) is highly heterogeneous in the stromal and immune microenvironment, genome instability (GI), and oncogenic signatures. However, a classification of GC by combining these features remains lacking. Using the consensus clustering algorithm, we clustered GCs based on the activities of 15 pathways associated with immune, DNA repair, oncogenic, and stromal signatures in three GC datasets. We identified three GC subtypes: immunity-deprived (ImD), stroma-enriched (StE), and immunity-enriched (ImE). ImD showed low immune infiltration, high DNA damage repair activity, high tumor aneuploidy level, high intratumor heterogeneity (ITH), and frequent TP53 mutations. StE displayed high stromal signatures, low DNA damage repair activity, genomic stability, low ITH, and poor prognosis. ImE had strong immune infiltration, high DNA damage repair activity, high tumor mutation burden, prevalence of microsatellite instability, frequent ARID1A mutations, elevated PD-L1 expression, and favorable prognosis. Based on the expression levels of four genes (TAP2, SERPINB5, LTBP1, and LAMC1) in immune, DNA repair, oncogenic, and stromal pathways, we developed a prognostic model (IDOScore). The IDOScore was an adverse prognostic factor and correlated inversely with immunotherapy response in cancer. Our identification of new GC subtypes provides novel insights into tumor biology and has potential clinical implications for the management of GCs.

A self-organizing deep neuro-fuzzy system approach for classification of kidney cancer subtypes using miRNA genomics data

Kidney cancer is a dangerous disease affecting many patients all over the world. Early-stage diagnosis and correct identification of kidney cancer subtypes play an essential role in the patient's survival; therefore, its subtypes diagnosis and classification are the main challenges in kidney cancer treatment. Medical studies have proved that miRNA dysregulation can increase the risk of cancer. Thus, in this paper, we propose a new machine learning approach for significant miRNAs identification and kidney cancer subtype classification to design an automatic diagnostic tool. The proposed method contains two main steps: feature selection and classification. First, we apply the feature selection algorithm to choose the candidate miRNAs for each subtype. The feature selection algorithm utilizes the AMGM measure to select significant miRNAs with high discriminant power. Next, the candidate miRNAs are fed to a classifier to evaluate the candidate features. In the classification step, the proposed self-organizing deep neuro-fuzzy system is employed to classify kidney cancer subgroups. The new deep neuro-fuzzy system consists of a deep structure in the rule layer and novel architecture in the fuzzifier layer. The proposed self-organizing deep neuro-fuzzy system can help us to overcome the main obstacles in the field of neuro-fuzzy system applications, such as the curse of dimensionality. The goal of this paper is to illustrate that the neuro-fuzzy system can very useful in high dimensional data, such as genomics data, using the proposed deep neuro-fuzzy system. The obtained results illustrated that our proposed method has succeeded in classifying kidney cancer subtypes with high accuracy based on the selected miRNAs.

Deep learning-based six-type classifier for lung cancer and mimics from histopathological whole slide images: a retrospective study

BackgroundTargeted therapy and immunotherapy put forward higher demands for accurate lung cancer classification, as well as benign versus malignant disease discrimination. Digital whole slide images (WSIs) witnessed the transition from traditional histopathology to computational approaches, arousing a hype of deep learning methods for histopathological analysis. We aimed at exploring the potential of deep learning models in the identification of lung cancer subtypes and cancer mimics from WSIs.MethodsWe initially obtained 741 WSIs from the First Affiliated Hospital of Sun Yat-sen University (SYSUFH) for the deep learning model development, optimization, and verification. Additional 318 WSIs from SYSUFH, 212 from Shenzhen People’s Hospital, and 422 from The Cancer Genome Atlas were further collected for multi-centre verification. EfficientNet-B5- and ResNet-50-based deep learning methods were developed and compared using the metrics of recall, precision, F1-score, and areas under the curve (AUCs). A threshold-based tumour-first aggregation approach was proposed and implemented for the label inferencing of WSIs with complex tissue components. Four pathologists of different levels from SYSUFH reviewed all the testing slides blindly, and the diagnosing results were used for quantitative comparisons with the best performing deep learning model.ResultsWe developed the first deep learning-based six-type classifier for histopathological WSI classification of lung adenocarcinoma, lung squamous cell carcinoma, small cell lung carcinoma, pulmonary tuberculosis, organizing pneumonia, and normal lung. The EfficientNet-B5-based model outperformed ResNet-50 and was selected as the backbone in the classifier. Tested on 1067 slides from four cohorts of different medical centres, AUCs of 0.970, 0.918, 0.963, and 0.978 were achieved, respectively. The classifier achieved high consistence to the ground truth and attending pathologists with high intraclass correlation coefficients over 0.873.ConclusionsMulti-cohort testing demonstrated our six-type classifier achieved consistent and comparable performance to experienced pathologists and gained advantages over other existing computational methods. The visualization of prediction heatmap improved the model interpretability intuitively. The classifier with the threshold-based tumour-first label inferencing method exhibited excellent accuracy and feasibility in classifying lung cancers and confused nonneoplastic tissues, indicating that deep learning can resolve complex multi-class tissue classification that conforms to real-world histopathological scenarios.

Multi-Omics Data Fusion via a Joint Kernel Learning Model for Cancer Subtype Discovery and Essential Gene Identification.

The multiple sources of cancer determine its multiple causes, and the same cancer can be composed of many different subtypes. Identification of cancer subtypes is a key part of personalized cancer treatment and provides an important reference for clinical diagnosis and treatment. Some studies have shown that there are significant differences in the genetic and epigenetic profiles among different cancer subtypes during carcinogenesis and development. In this study, we first collect seven cancer datasets from the Broad Institute GDAC Firehose, including gene expression profile, isoform expression profile, DNA methylation expression data, and survival information correspondingly. Furthermore, we employ kernel principal component analysis (PCA) to extract features for each expression profile, convert them into three similarity kernel matrices by Gaussian kernel function, and then fuse these matrices as a global kernel matrix. Finally, we apply it to spectral clustering algorithm to get the clustering results of different cancer subtypes. In the experimental results, besides using the P-value from the Cox regression model and survival analysis as the primary evaluation measures, we also introduce statistical indicators such as Rand index (RI) and adjusted RI (ARI) to verify the performance of clustering. Then combining with gene expression profile, we obtain the differential expression of genes among different subtypes by gene set enrichment analysis. For lung cancer, GMPS, EPHA10, C10orf54, and MAGEA6 are highly expressed in different subtypes; for liver cancer, CMYA5, DEPDC6, FAU, VPS24, RCBTB2, LOC100133469, and SLC35B4 are significantly expressed in different subtypes.