Development and implementation of a prognostic model for clear cell renal cell carcinoma based on heterogeneous TLR4 expression

Objective

Clear cell renal cell carcinoma (ccRCC) is the most common subtype among renal cell carcinomas and has the worst prognosis, originating from renal tubular epithelial cells. Toll-like receptor 4 (TLR4) plays a crucial role in ccRCC proliferation, infiltration, and metastasis. The aim of this study was to construct a prognostic scoring model for ccRCC based on TLR4 expression heterogeneity and to explore its association with immune infiltration, thereby providing insights for the treatment and prognostic evaluation of ccRCC.

Methods

Using R software, a differential analysis was conducted on normal samples and ccRCC samples, and in conjunction with the KEGG database, a correlation analysis for the clear cell renal cell carcinoma pathway (hsa05211) was carried out. We observed the expression heterogeneity of TLR4 in the TCGA-KIRC cohort and identified its related differential genes (TRGs). Based on the expression levels of TRGs, consensus clustering was employed to identify TLR4-related subtypes, and further clustering heatmaps, principal component, and single-sample gene set enrichment analyses were conducted. Overlapping differential genes (ODEGs) between subtypes were analysed, and combined with survival data, univariate Cox regression, LASSO, and multivariate Cox regression were used to establish a prognostic risk model for ccRCC. This model was subsequently evaluated through ROC analysis, risk factor correlation analysis, independent prognostic factor analysis, and intergroup differential analysis. The ssGSEA model was employed to explore immune heterogeneity in ccRCC, and the performance of the model in predicting patient prognosis was evaluated using box plots and the oncoPredict software package.

Results

In the TCGA-KIRC cohort, TLR4 expression was notably elevated in ccRCC samples compared to normal samples, correlating with improved survival in the high-expression group. The study identified distinct TLR4-related differential genes and categorized ccRCC into three subtypes with varied survival outcomes. A risk prognosis model based on overlapping differential genes was established, showing significant associations with immune cell infiltration and key immune checkpoints (PD-1, PD-L1, CTLA4). Additionally, drug sensitivity differences were observed between risk groups.

Conclusion

In the TCGA-KIRC cohort, the expression of TLR4 in ccRCC samples exhibited significant heterogeneity. Through clustering analysis, we identified that the primary immune cells across subtypes are myeloid-derived suppressor cells, central memory CD4 T cells, and regulatory T cells. Furthermore, we successfully constructed a prognostic risk model for ccRCC composed of 17 genes. This model provides valuable references for the prognosis prediction and treatment of ccRCC patients.

Molecular subtype identification and prognosis stratification based on lysosome-related genes in breast cancer

Background

Lysosomes are known to have a significant impact on the development and recurrence of breast cancer. However, the association between lysosome-related genes (LRGs) and breast cancer remains unclear. This study aims to explore the potential role of LRGs in predicting the prognosis and treatment response of breast cancer.

Methods

Breast cancer gene expression profile data and clinical information were downloaded from TCGA and GEO databases, and prognosis-related LRGs were screened for consensus clustering analysis. Lasso Cox regression analysis was used to construct risk features derived from LRGs, and immune cell infiltration, immune therapy response, drug sensitivity, and clinical pathological feature differences were evaluated for different molecular subtypes and risk groups. A nomogram based on risk features derived from LRGs was constructed and evaluated.

Results

Our study identified 176 differentially expressed LRGs that are associated with breast cancer prognosis. Based on these genes, we divided breast cancer into two molecular subtypes with significant prognostic differences. We also found significant differences in immune cell infiltration between these subtypes. Furthermore, we constructed a prognostic risk model consisting of 7 LRGs, which effectively divides breast cancer patients into high-risk and low-risk groups. Patients in the low-risk group have better prognostic characteristics, respond better to immunotherapy, and have lower sensitivity to chemotherapy drugs, indicating that the low-risk group is more likely to benefit from immunotherapy and chemotherapy. Additionally, the risk score based on LRGs is significantly correlated with immune cell infiltration, including CD8 T cells and macrophages. This risk score model, along with age, chemotherapy, clinical stage, and N stage, is an independent prognostic factor for breast cancer. Finally, the nomogram composed of these factors has excellent performance in predicting overall survival of breast cancer.

Conclusions

In conclusion, this study has constructed a novel LRG-derived breast cancer risk feature, which performs well in prognostic prediction when combined with clinical pathological features.

Molecular subtype identification and prognosis stratification based on golgi apparatus-related genes in head and neck squamous cell carcinoma

BACKGROUND

Abnormal dynamics of the Golgi apparatus reshape the tumor microenvironment and immune landscape, playing a crucial role in the prognosis and treatment response of cancer. This study aims to investigate the potential role of Golgi apparatus-related genes (GARGs) in the heterogeneity and prognosis of head and neck squamous cell carcinoma (HNSCC).

METHODS

Transcriptional data and corresponding clinical information of HNSCC were obtained from public databases for differential expression analysis, consensus clustering, survival analysis, immune infiltration analysis, immune therapy response assessment, gene set enrichment analysis, and drug sensitivity analysis. Multiple machine learning algorithms were employed to construct a prognostic model based on GARGs. A nomogram was used to integrate and visualize the multi-gene model with clinical pathological features.

RESULTS

A total of 321 GARGs that were differentially expressed were identified, out of which 69 were associated with the prognosis of HNSCC. Based on these prognostic genes, two molecular subtypes of HNSCC were identified, which showed significant differences in prognosis. Additionally, a risk signature consisting of 28 GARGs was constructed and demonstrated good performance for assessing the prognosis of HNSCC. This signature divided HNSCC into the high-risk and low-risk groups with significant differences in multiple clinicopathological characteristics, including survival outcome, grade, T stage, chemotherapy. Immune response-related pathways were significantly activated in the high-risk group with better prognosis. There were significant differences in chemotherapy drug sensitivity and immune therapy response between the high-risk and low-risk groups, with the low-risk group being more suitable for receiving immunotherapy. Riskscore, age, grade, and radiotherapy were independent prognostic factors for HNSCC and were used to construct a nomogram, which had good clinical applicability.

CONCLUSIONS

We successfully identified molecular subtypes and prognostic signature of HNSCC that are derived from GARGs, which can be used for the assessment of HNSCC prognosis and treatment responses.

Integrated bioinformatics analysis identifies a Ferroptosis-related gene signature as prognosis model and potential therapeutic target of bladder cancer

Background

Bladder cancer (BLCA) is one of the most prevalent cancers worldwide. Ferroptosis is a newly discovered form of non-apoptotic cell death that plays an important role in tumors. However, the prognostic value of ferroptosis-related genes (FRGs) in BLCA has not yet been well studied.

Method and materials

In this study, we performed consensus clustering based on FRGS and categorized BLCA patients into 2 clusters (C1 and C2). Immune cell infiltration score and immune score for each sample were computed using the CIBERSORT and ESTIMATE methods. Functional annotation of differentially expressed genes were performed by Gene Ontology (GO) and KEGG pathway enrichment analysis. Protein expression validation were confirmed in Human Protein Atlas. Gene expression validation were performed by qPCR in human bladder cancer cell lines lysis samples.

Result

C2 had a significant survival advantage and higher immune infiltration levels than C1. Additionally, C2 showed substantially higher expression levels of immune checkpoint markers than C1. According to the Cox and LASSO regression analyses, a novel ferroptosis-related prognostic signature was developed to predict the prognosis of BLCA effectively. High-risk and low-risk groups were divided according to risk scores. Kaplan-Meier survival analyses showed that the high-risk group had a shorter overall survival than the low-risk group throughout the cohort. Furthermore, a nomogram combining risk score and clinical features was developed. Finally, SLC39A7 was identified as a potential target in bladder cancer.

Discussion

In conclusion, we identified two ferroptosis-clusters with different prognoses using consensus clustering in BLCA. We also developed a ferroptosis-related prognostic signature and nomogram, which could indicate the outcome.

Significance of Oxidative Stress in the Diagnosis and Subtype Classification of Intervertebral Disc Degeneration

Intervertebral disc degeneration (IVDD) is a common illness of aging, and its pathophysiological process is mainly manifested by cell aging and apoptosis, an imbalance in the production and catabolism of extracellular matrix, and an inflammatory response. Oxidative stress (OS) is an imbalance that decreases the body's intrinsic antioxidant defense system and/or raises the formation of reactive oxygen species and performs multiple biological functions in the body. However, our current knowledge of the effect of OS on the progression and treatment of IVDD is still extremely limited. In this study, we obtained 35 DEGs by differential expression analysis of 437 OS-related genes (OSRGs) between IVDD patients and healthy individuals from GSE124272 and GSE150408. Then, we identified six hub OSRGs (ATP7A, MELK, NCF1, NOX1, RHOB, and SP1) from 35 DEGs, and the high accuracy of these hub genes was confirmed by constructing ROC curves. In addition, to forecast the risk of IVDD patients, we developed a nomogram. We obtained two OSRG clusters (clusters A and B) by consensus clustering based on the six hub genes. Then, 3147 DEGs were obtained by differential expression analysis in the two clusters, and all samples were further divided into two gene clusters (A and B). We investigated differences in immune cell infiltration levels between different clusters and found that most immune cells had higher infiltration levels in OSRG cluster B or gene cluster B. In conclusion, OS is important in the formation and progression of IVDD, and we believe that our work will help guide future research on OS in IVDD.

PWSC: a novel clustering method based on polynomial weight-adjusted sparse clustering for sparse biomedical data and its application in cancer subtyping

BACKGROUND

Clustering analysis is widely used to interpret biomedical data and uncover new knowledge and patterns. However, conventional clustering methods are not effective when dealing with sparse biomedical data. To overcome this limitation, we propose a hierarchical clustering method called polynomial weight-adjusted sparse clustering (PWSC).

RESULTS

The PWSC algorithm adjusts feature weights using a polynomial function, redefines the distances between samples, and performs hierarchical clustering analysis based on these adjusted distances. Additionally, we incorporate a consensus clustering approach to determine the optimal number of classifications. This consensus approach utilizes relative change in the cumulative distribution function to identify the best number of clusters, resulting in more stable clustering results. Leveraging the PWSC algorithm, we successfully classified a cohort of gastric cancer patients, enabling categorization of patients carrying different types of altered genes. Further evaluation using Entropy showed a significant improvement (p = 2.905e-05), while using the Calinski-Harabasz index demonstrates a remarkable 100% improvement in the quality of the best classification compared to conventional algorithms. Similarly, significantly increased entropy (p = 0.0336) and comparable CHI, were observed when classifying another colorectal cancer cohort with microbial abundance. The above attempts in cancer subtyping demonstrate that PWSC is highly applicable to different types of biomedical data. To facilitate its application, we have developed a user-friendly tool that implements the PWSC algorithm, which canbe accessed at http://pwsc.aiyimed.com/ .

CONCLUSIONS

PWSC addresses the limitations of conventional approaches when clustering sparse biomedical data. By adjusting feature weights and employing consensus clustering, we achieve improved clustering results compared to conventional methods. The PWSC algorithm provides a valuable tool for researchers in the field, enabling more accurate and stable clustering analysis. Its application can enhance our understanding of complex biological systems and contribute to advancements in various biomedical disciplines.

Recognition of the Subtypes Classification and Diagnostic Signature Based on RNA N6-Methyladenosine Regulators in Recurrent Spontaneous Abortion

Recurrent spontaneous abortion (RSA) is a common reproductive disease in female patients that seriously affects the quality of life of patients. N6-methyladenosine (m6A), as the most common modification, plays an important role in various biological behaviors; however, the relationship between m6A and RSA is still unknown. In the present study, we utilized RNA sequencing data and clinical information of RSA patients and normal women in the GEO database to identify the expression profiles of m6A regulators in RSA. Based on the m6A regulators' expression profiles, we constructed a random forest model consisting of 4 genes to predict the prevalence of RSA patients, including FMR1, METTL14, LRPPRC, and RBMX. The predictive performance of the nomogram was constructed and validated. Not only that, consensus clustering was performed to divide RSA patients into 3 clusters based on the expression of m6A regulators and calculated the m6A scores and immune infiltration of patients in different clusters. It was found that the TH1-type immune response was dominant in the A cluster, the B-type immune activity was poor, and the C cluster was the strongest. In addition, on the basis of m6A typing, we further used the differentially expressed genes between clusters to perform consensus clustering verification, and the results were consistent with the previous findings. In conclusion, the m6A regulators played an indispensable role in the occurrence of RSA, and the m6A-based typing could effectively identify the immune characteristics of different RSA patients to a certain extent, providing a new direction and strategy for the diagnosis and treatment of RSA patients.

Machine learning-identified stemness features and constructed stemness-related subtype with prognosis, chemotherapy, and immunotherapy responses for non-small cell lung cancer patients

AIM

This study aimed to explore a novel subtype classification method based on the stemness characteristics of patients with non-small cell lung cancer (NSCLC).

METHODS

Based on the Cancer Genome Atlas database to calculate the stemness index (mRNAsi) of NSCLC patients, an unsupervised consensus clustering method was used to classify patients into two subtypes and analyze the survival differences, somatic mutational load, copy number variation, and immune characteristics differences between them. Subsequently, four machine learning methods were used to construct and validate a stemness subtype classification model, and cell function experiments were performed to verify the effect of the signature gene ARTN on NSCLC.

RESULTS

Patients with Stemness Subtype I had better PFS and a higher somatic mutational burden and copy number alteration than patients with Stemness Subtype II. In addition, the two stemness subtypes have different patterns of tumor immune microenvironment. The immune score and stromal score and overall score of Stemness Subtype II were higher than those of Stemness Subtype I, suggesting a relatively small benefit to immune checkpoints. Four machine learning methods constructed and validated classification model for stemness subtypes and obtained multiple logistic regression equations for 22 characteristic genes. The results of cell function experiments showed that ARTN can promote the proliferation, invasion, and migration of NSCLC and is closely related to cancer stem cell properties.

CONCLUSION

This new classification method based on stemness characteristics can effectively distinguish patients' characteristics and thus provide possible directions for the selection and optimization of clinical treatment plans.

Clinical characteristics and prognosis in systemic lupus erythematosus-associated pulmonary arterial hypertension based on consensus clustering and risk prediction model

BACKGROUND

Pulmonary arterial hypertension (PAH) is a severe complication of systemic lupus erythematosus (SLE). This study aims to explore the clinical characteristics and prognosis in SLE-PAH based on consensus clustering and risk prediction model.

METHODS

A total of 205 PAH (including 163 SLE-PAH and 42 idiopathic PAH) patients were enrolled retrospectively based on medical records at the First Affiliated Hospital of Zhengzhou University from July 2014 to June 2021. Unsupervised consensus clustering was used to identify SLE-PAH subtypes that best represent the data pattern. The Kaplan-Meier survival was analyzed in different subtypes. Besides, the least absolute shrinkage and selection operator combined with Cox proportional hazards regression model were performed to construct the SLE-PAH risk prediction model.

RESULTS

Clustering analysis defined two subtypes, cluster 1 (n = 134) and cluster 2 (n = 29). Compared with cluster 1, SLE-PAH patients in cluster 2 had less favorable levels of poor cardiac, kidney, and coagulation function markers, with higher SLE disease activity, less frequency of PAH medications, and lower survival rate within 2 years (86.2% vs. 92.8%) (P < 0.05). The risk prediction model was also constructed, including older age at diagnosis (≥ 38 years), anti-dsDNA antibody, neuropsychiatric lupus, and platelet distribution width (PDW).

CONCLUSIONS

Consensus clustering identified two distinct SLE-PAH subtypes which were associated with survival outcomes. Four prognostic factors for death were discovered to construct the SLE-PAH risk prediction model.

Pancancer network analysis reveals key master regulators for cancer invasiveness

BACKGROUND

Tumor invasiveness reflects numerous biological changes, including tumorigenesis, progression, and metastasis. To decipher the role of transcriptional regulators (TR) involved in tumor invasiveness, we performed a systematic network-based pan-cancer assessment of master regulators of cancer invasiveness.

MATERIALS AND METHODS

We stratified patients in The Cancer Genome Atlas (TCGA) into invasiveness high (INV-H) and low (INV-L) groups using consensus clustering based on an established robust 24-gene signature to determine the prognostic association of invasiveness with overall survival (OS) across 32 different cancers. We devise a network-based protocol to identify TRs as master regulators (MRs) unique to INV-H and INV-L phenotypes. We validated the activity of MRs coherently associated with INV-H phenotype and worse OS across cancers in TCGA on a series of additional datasets in the Prediction of Clinical Outcomes from the Genomic Profiles (PRECOG) repository.

RESULTS

Based on the 24-gene signature, we defined the invasiveness score for each patient sample and stratified patients into INV-H and INV-L clusters. We observed that invasiveness was associated with worse survival outcomes in almost all cancers and had a significant association with OS in ten out of 32 cancers. Our network-based framework identified common invasiveness-associated MRs specific to INV-H and INV-L groups across the ten prognostic cancers, including COL1A1, which is also part of the 24-gene signature, thus acting as a positive control. Downstream pathway analysis of MRs specific to INV-H phenotype resulted in the identification of several enriched pathways, including Epithelial into Mesenchymal Transition, TGF-β signaling pathway, regulation of Toll-like receptors, cytokines, and inflammatory response, and selective expression of chemokine receptors during T-cell polarization. Most of these pathways have connotations of inflammatory immune response and feasibility for metastasis.

CONCLUSION

Our pan-cancer study provides a comprehensive master regulator analysis of tumor invasiveness and can suggest more precise therapeutic strategies by targeting the identified MRs and downstream enriched pathways for patients across multiple cancers.

M6A RNA methylation modification and tumor immune microenvironment in lung adenocarcinoma

Lung adenocarcinoma is one of the deadliest tumors. Studies have shown that N6-methyladenosine RNA methylation regulators, as a dynamic chemical modification, affect the occurrence and development of lung adenocarcinoma. To investigate the relationship between mutations and expression levels of m6A regulators in lung adenocarcinoma, we investigated the mutations and expression levels of 38 m6A regulators. We found that mutations in m6A regulatory factors did not affect the changes in expression levels, and 19 differentially expressed genes were identified. All tumor samples were classified into two subtypes based on the expression levels of 19 differentially expressed m6A-regulated genes. Survival analysis showed significant differences in survival between the two subtypes. To explore the relationship between immune cell infiltration and survival in both subtypes, we calculated the infiltration of 23 immune cells in both subtypes, and we found that the subtype with high immune cell infiltration had better survival. We found that subtypes with low tumor purity and high stromal and immune scores had better survival. The m6A-related immune genes were identified by taking the intersection of differentially expressed genes and immune genes in the two isoforms and calculating the Pearson correlation coefficients between the intersecting immune genes and the differentially expressed m6A-regulated genes. Finally, a prognostic model associated with m6A and associated with immunity was developed using prognostic genes screened from m6A-associated immune genes. The predictive power of the model was evaluated and our model was able to achieve good prediction.

WormTensor: a clustering method for time-series whole-brain activity data from C. elegans

BACKGROUND

In the field of neuroscience, neural modules and circuits that control biological functions have been found throughout entire neural networks. Correlations in neural activity can be used to identify such neural modules. Recent technological advances enable us to measure whole-brain neural activity with single-cell resolution in several species including [Formula: see text]. Because current neural activity data in C. elegans contain many missing data points, it is necessary to merge results from as many animals as possible to obtain more reliable functional modules.

RESULTS

In this work, we developed a new time-series clustering method, WormTensor, to identify functional modules using whole-brain activity data from C. elegans. WormTensor uses a distance measure, modified shape-based distance to account for the lags and the mutual inhibition of cell-cell interactions and applies the tensor decomposition algorithm multi-view clustering based on matrix integration using the higher orthogonal iteration of tensors (HOOI) algorithm (MC-MI-HOOI), which can estimate both the weight to account for the reliability of data from each animal and the clusters that are common across animals.

CONCLUSION

We applied the method to 24 individual C. elegans and successfully found some known functional modules. Compared with a widely used consensus clustering method to aggregate multiple clustering results, WormTensor showed higher silhouette coefficients. Our simulation also showed that WormTensor is robust to contamination from noisy data. WormTensor is freely available as an R/CRAN package https://cran.r-project.org/web/packages/WormTensor .

The theranostic value of acetylation gene signatures in obstructive sleep apnea derived by machine learning

Epigenetic modifications are implicated in the onset and progression of obstructive sleep apnea (OSA) and its complications through their bidirectional relationship with long-term chronic intermittent hypoxia (IH). However, the exact role of epigenetic acetylation in OSA is unclear. Here we explored the relevance and impact of acetylation-related genes in OSA by identifying molecular subtypes modified by acetylation in OSA patients. Twenty-nine significantly differentially expressed acetylation-related genes were screened in a training dataset (GSE135917). Six common signature genes were identified using the lasso and support vector machine algorithms, with the powerful SHAP algorithm used to judge the importance of each identified feature. DSCC1, ACTL6A, and SHCBP1 were best calibrated and discriminated OSA patients from normal in both training and validation (GSE38792) datasets. Decision curve analysis showed that patients could benefit from a nomogram model developed using these variables. Finally, a consensus clustering approach characterized OSA patients and analyzed the immune signatures of each subgroup. OSA patients were divided into two acetylation patterns (higher acetylation scores in Group B than in Group A) that differed significantly in terms of immune microenvironment infiltration. This is the first study to reveal the expression patterns and key role played by acetylation in OSA, laying the foundation for OSA epitherapy and refined clinical decision-making.

Development and validation of a prognostic 15-gene signature for stratifying HER2+/ER+ breast cancer

Background

Human epidermal growth receptor 2-positive (HER2+) breast cancer (BC) is a heterogeneous subgroup. Estrogen receptor (ER) status is emerging as a predictive marker within HER2+ BCs, with the HER2+/ER+ cases usually having better survival in the first 5 years after diagnosis but have higher recurrence risk after 5 years compared to HER2+/ER-. This is possibly because sustained ER signaling in HER2+ BCs helps escape the HER2 blockade. Currently HER2+/ER+ BC is understudied and lacks biomarkers. Thus, a better understanding of the underlying molecular diversity is important to find new therapy targets for HER2+/ER+ BCs.

Methods

In this study, we performed unsupervised consensus clustering together with genome-wide Cox regression analyses on the gene expression data of 123 HER2+/ER+ BC from The Cancer Genome Atlas Breast Invasive Carcinoma (TCGA-BRCA) cohort to identify distinct HER2+/ER+ subgroups. A supervised eXtreme Gradient Boosting (XGBoost) classifier was then built in TCGA using the identified subgroups and validated in another two independent datasets (Molecular Taxonomy of Breast Cancer International Consortium (METABRIC) and Gene Expression Omnibus (GEO) (accession number GSE149283)). Computational characterization analyses were also performed on the predicted subgroups in different HER2+/ER+ BC cohorts.

Results

We identified two distinct HER2+/ER+ subgroups with different survival outcomes using the expression profiles of 549 survival-associated genes from the Cox regression analyses. Genome-wide gene expression differential analyses found 197 differentially expressed genes between the two identified subgroups, with 15 genes overlapping the 549 survival-associated genes.XGBoost classifier, using the expression values of the 15 genes, achieved a strong cross-validated performance (Area under the curve (AUC) = 0.85, Sensitivity = 0.76, specificity = 0.77) in predicting the subgroup labels. Further investigation partially confirmed the differences in survival, drug response, tumor-infiltrating lymphocytes, published gene signatures, and CRISPR-Cas9 knockout screened gene dependency scores between the two identified subgroups.

Conclusion

This is the first study to stratify HER2+/ER+ tumors. Overall, the initial results from different cohorts showed there exist two distinct subgroups in HER2+/ER+ tumors, which can be distinguished by a 15-gene signature. Our findings could potentially guide the development of future precision therapies targeted on HER2+/ER+ BC.

Diagnostic signature composed of seven genes in HIF-1 signaling pathway for preeclampsia

PURPOSE

In this study, we explored the relationship of genes in HIF-1 signaling pathway with preeclampsia and establish a logistic regression model for diagnose preeclampsia using bioinformatics analysis.

METHOD

Two microarray datasets GSE75010 and GSE35574 were downloaded from the Gene Expression Omnibus database, which was using for differential expression analysis. DEGs were performed the Gene Ontology (GO) analysis, Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis and Gene set enrichment analysis (GSEA). Then we performed unsupervised consensus clustering analysis using genes in HIF-1 signaling pathway, and clinical features and immune cell infiltration were compared between these clusters, as well as the least absolute shrinkage and selection operator (LASSO) method to screened out key genes to constructed logistic regression model, and receiver operating characteristic (ROC) curve was plotted to evaluate the accuracy of the model.

RESULTS

57 DEGs were identified, of which GO, KEGG and analysis GSEA showed DEGs were mostly involved in HIF-1 signaling pathway. Two subtypes were identified of preeclampsia and 7 genes in HIF1-signaling pathway were screened out to establish the logistic regression model for discrimination preeclampsia from controls, of which the AUC are 0.923 and 0.845 in training and validation datasets respectively.

CONCLUSION

Seven genes (including MKNK1, ARNT, FLT1, SERPINE1, ENO3, LDHA, BCL2) were screen out to build potential diagnostic model of preeclampsia.

Epithelial-mesenchymal transition-related gene prognostic index and phenotyping clusters for hepatocellular carcinoma patients

Epithelial-mesenchymal transition (EMT) contributes to high tumor heterogeneity and the immunosuppressive environment of the HCC tumor microenvironment (TME). Here, we developed EMT-related genes phenotyping clusters and systematically evaluated their impact on HCC prognosis, the TME, and drug efficacy prediction. We identified HCC specific EMT-related genes using weighted gene co-expression network analysis (WGCNA). An EMT-related genes prognostic index (EMT-RGPI) capable of effectively predicting HCC prognosis was then constructed. Consensus clustering of 12 HCC specific EMT-related hub genes uncovered two molecular clusters C1 and C2. Cluster C2 preferentially associated with unfavorable prognosis, higher stemness index (mRNAsi) value, elevated immune checkpoint expression, and immune cell infiltration. The TGF-β signaling, EMT, glycolysis, Wnt β-catenin signaling, and angiogenesis were markedly enriched in cluster C2. Moreover, cluster C2 exhibited higher TP53 and RB1 mutation rates. The TME subtypes and tumor immune dysfunction and exclusion (TIDE) score showed that cluster C1 patients responded well to immune checkpoint inhibitors (ICIs). Half-maximal inhibitory concentration (IC50) revealed that cluster C2 patients were more sensitive to chemotherapeutic and antiangiogenic agents. These findings may guide risk stratification and precision therapy for HCC patients.

A clustering method for small scRNA-seq data based on subspace and weighted distance

Background

Identifying the cell types using unsupervised methods is essential for scRNA-seq research. However, conventional similarity measures introduce challenges to single-cell data clustering because of the high dimensional, high noise, and high dropout.

Methods

We proposed a clustering method for small ScRNA-seq data based on Subspace and Weighted Distance (SSWD), which follows the assumption that the sets of gene subspace composed of similar density-distributing genes can better distinguish cell groups. To accurately capture the intrinsic relationship among cells or genes, a new distance metric that combines Euclidean and Pearson distance through a weighting strategy was proposed. The relative Calinski-Harabasz (CH) index was used to estimate the cluster numbers instead of the CH index because it is comparable across degrees of freedom.

Results

We compared SSWD with seven prevailing methods on eight publicly scRNA-seq datasets. The experimental results show that the SSWD has better clustering accuracy and the partitioning ability of cell groups. SSWD can be downloaded at https://github.com/ningzilan/SSWD.

Feature stability and setup minimization for EEG-EMG-enabled monitoring systems

Delivering health care at home emerged as a key advancement to reduce healthcare costs and infection risks, as during the SARS-Cov2 pandemic. In particular, in motor training applications, wearable and portable devices can be employed for movement recognition and monitoring of the associated brain signals. This is one of the contexts where it is essential to minimize the monitoring setup and the amount of data to collect, process, and share. In this paper, we address this challenge for a monitoring system that includes high-dimensional EEG and EMG data for the classification of a specific type of hand movement. We fuse EEG and EMG into the magnitude squared coherence (MSC) signal, from which we extracted features using different algorithms (one from the authors) to solve binary classification problems. Finally, we propose a mapping-and-aggregation strategy to increase the interpretability of the machine learning results. The proposed approach provides very low mis-classification errors ( < 0.1 ), with very few and stable MSC features ( < 10 % of the initial set of available features). Furthermore, we identified a common pattern across algorithms and classification problems, i.e., the activation of the centro-parietal brain areas and arm's muscles in 8-80 Hz frequency band, in line with previous literature. Thus, this study represents a step forward to the minimization of a reliable EEG-EMG setup to enable gesture recognition.

Bayesian tensor factorization-drive breast cancer subtyping by integrating multi-omics data

Breast cancer is a highly heterogeneous disease. Subtyping the disease and identifying the genomic features driving these subtypes are critical for precision oncology for breast cancer. This study focuses on developing a new computational approach for breast cancer subtyping. We proposed to use Bayesian tensor factorization (BTF) to integrate multi-omics data of breast cancer, which include expression profiles of RNA-sequencing, copy number variation, and DNA methylation measured on 762 breast cancer patients from The Cancer Genome Atlas. We applied a consensus clustering approach to identify breast cancer subtypes using the factorized latent features by BTF. Subtype-specific survival patterns of the breast cancer patients were evaluated using Kaplan-Meier (KM) estimators. The proposed approach was compared with other state-of-the-art approaches for cancer subtyping. The BTF-subtyping analysis identified 17 optimized latent components, which were used to reveal six major breast cancer subtypes. Out of all different approaches, only the proposed approach showed distinct survival patterns (p < 0.05). Statistical tests also showed that the identified clusters have statistically significant distributions. Our results showed that the proposed approach is a promising strategy to efficiently use publicly available multi-omics data to identify breast cancer subtypes.

Risk profiles for negative and positive COVID-19 hospitalized patients

COVID-19 is a viral infection that affects people differently, where the majority of cases develop mild symptoms, some people require hospitalization, and unfortunately, a small number of patients perish. Hence, identifying risk factors is critical for physicians to make treatment decisions. The purpose of this article is to determine whether unsupervised analysis of risk factors in positive and negative COVID-19 subjects can aid in the identification of a set of reliable and clinically relevant risk profiles. Positive and negative patients hospitalized were randomly selected from the Mexican Open Registry between March and May 2020. Thirteen risk factors, three distinct outcomes, and COVID-19 test results were used to categorize registry patients. As a result, the dataset was reported via 6144 different risk profiles for each age group. The unsupervised learning method is proposed in this study to discover the most prevalent risk profiles. The data was partitioned into discovery (70%) and validation (30%) sets. The discovery set was analyzed using the partition around medoids (PAM) method, and the stable set of risk profiles was estimated using robust consensus clustering. The PAM models' reliability was validated by predicting the risk profile of subjects from the validation set and patients admitted in November 2020. In the validation set, the clinical relevance of the risk profiles was evaluated by determining the prevalence of three patient outcomes: pneumonia diagnosis, ICU admission, or death. Six positive and five negative COVID-19 risk profiles were identified, with significant statistical differences between them. As a result, PAM clustering with consensus mapping is a viable method for discovering unsupervised risk profiles in subjects with severe respiratory health problems.

Consensus clustering applied to multi-omics disease subtyping

BACKGROUND

Facing the diversity of omics data and the difficulty of selecting one result over all those produced by several methods, consensus strategies have the potential to reconcile multiple inputs and to produce robust results.

RESULTS

Here, we introduce ClustOmics, a generic consensus clustering tool that we use in the context of cancer subtyping. ClustOmics relies on a non-relational graph database, which allows for the simultaneous integration of both multiple omics data and results from various clustering methods. This new tool conciliates input clusterings, regardless of their origin, their number, their size or their shape. ClustOmics implements an intuitive and flexible strategy, based upon the idea of evidence accumulation clustering. ClustOmics computes co-occurrences of pairs of samples in input clusters and uses this score as a similarity measure to reorganize data into consensus clusters.

CONCLUSION

We applied ClustOmics to multi-omics disease subtyping on real TCGA cancer data from ten different cancer types. We showed that ClustOmics is robust to heterogeneous qualities of input partitions, smoothing and reconciling preliminary predictions into high-quality consensus clusters, both from a computational and a biological point of view. The comparison to a state-of-the-art consensus-based integration tool, COCA, further corroborated this statement. However, the main interest of ClustOmics is not to compete with other tools, but rather to make profit from their various predictions when no gold-standard metric is available to assess their significance.

AVAILABILITY

The ClustOmics source code, released under MIT license, and the results obtained on TCGA cancer data are available on GitHub: https://github.com/galadrielbriere/ClustOmics .

scLM: Automatic Detection of Consensus Gene Clusters Across Multiple Single-cell Datasets

In gene expression profiling studies, including single-cell RNAsequencing (scRNA-seq) analyses, the identification and characterization of co-expressed genes provides critical information on cell identity and function. Gene co-expression clustering in scRNA-seq data presents certain challenges. We show that commonly used methods for single-cell data are not capable of identifying co-expressed genes accurately, and produce results that substantially limit biological expectations of co-expressed genes. Herein, we present single-cell Latent-variable Model (scLM), a gene co-clustering algorithm tailored to single-cell data that performs well at detecting gene clusters with significant biologic context. Importantly, scLM can simultaneously cluster multiple single-cell datasets, i.e., consensus clustering, enabling users to leverage single-cell data from multiple sources for novel comparative analysis. scLM takes raw count data as input and preserves biological variation without being influenced by batch effects from multiple datasets. Results from both simulation data and experimental data demonstrate that scLM outperforms the existing methods with considerably improved accuracy. To illustrate the biological insights of scLM, we apply it to our in-house and public experimental scRNA-seq datasets. scLM identifies novel functional gene modules and refines cell states, which facilitates mechanism discovery and understanding of complex biosystems such as cancers. A user-friendly R package with all the key features of the scLM method is available at https://github.com/QSong-github/scLM.

m6A RNA methylation regulators correlate with malignant progression and have potential predictive values in clear cell renal cell carcinoma

N6-methyladenosine (m6A) has been reported to be involved in several biological processes in tumors. In this study, we found that most of the m6A RNA methylation regulators were not only differentially expressed between clear cell renal cell carcinoma (ccRCC) and normal but also among ccRCC stratified by different clinicopathologic characters. Two ccRCC subgroups, cluster 1 and 2, were identified using consensus clustering based on the expression of m6A methylation regulators. Although no obvious differences were observed between two subgroups regarding clinicopathologic characters, except gender, patients in cluster 1 had a relatively more favorable survival rate than cluster 2. Moreover, we established a risk signature with two m6A methylation regulators, METTL3 and METTL14, which was not only of great value for prognosis prediction but also closely associated with clinicopathological features. In conclusion, m6A RNA methylation regulators play an important role in ccRCC progression and are potentially favorable for prognostic stratification.

Fast tree aggregation for consensus hierarchical clustering

BACKGROUND

In unsupervised learning and clustering, data integration from different sources and types is a difficult question discussed in several research areas. For instance in omics analysis, dozen of clustering methods have been developed in the past decade. When a single source of data is at play, hierarchical clustering (HC) is extremely popular, as a tree structure is highly interpretable and arguably more informative than just a partition of the data. However, applying blindly HC to multiple sources of data raises computational and interpretation issues.

RESULTS

We propose mergeTrees, a method that aggregates a set of trees with the same leaves to create a consensus tree. In our consensus tree, a cluster at height h contains the individuals that are in the same cluster for all the trees at height h. The method is exact and proven to be [Formula: see text], n being the individuals and q being the number of trees to aggregate. Our implementation is extremely effective on simulations, allowing us to process many large trees at a time. We also rely on mergeTrees to perform the cluster analysis of two real -omics data sets, introducing a spectral variant as an efficient and robust by-product.

CONCLUSIONS

Our tree aggregation method can be used in conjunction with hierarchical clustering to perform efficient cluster analysis. This approach was found to be robust to the absence of clustering information in some of the data sets as well as an increased variability within true clusters. The method is implemented in R/C++ and available as an R package named mergeTrees, which makes it easy to integrate in existing or new pipelines in several research areas.

Integration of molecular features with clinical information for predicting outcomes for neuroblastoma patients

Background

Neuroblastoma is one of the most common types of pediatric cancer. In current neuroblastoma prognosis, patients can be stratified into high- and low-risk groups. Generally, more than 90% of the patients in the low-risk group will survive, while less than 50% for those with the high-risk disease will survive. Since the so-called “high-risk” patients still contain patients with mixed good and poor outcomes, more refined stratification needs to be established so that for the patients with poor outcome, they can receive prompt and individualized treatment to improve their long-term survival rate, while the patients with good outcome can avoid unnecessary over treatment.

Methods

We first mined co-expressed gene modules from microarray and RNA-seq data of neuroblastoma samples using the weighted network mining algorithm lmQCM, and summarize the resulted modules into eigengenes. Then patient similarity weight matrix was constructed with module eigengenes using two different approaches. At the last step, a consensus clustering method called Molecular Regularized Consensus Patient Stratification (MRCPS) was applied to aggregate both clinical information (clinical stage and clinical risk level) and multiple eigengene data for refined patient stratification.

Results

The integrative method MRCPS demonstrated superior performance to clinical staging or transcriptomic features alone for the NB cohort stratification. It successfully identified the worst prognosis group from the clinical high-risk group, with less than 40% survived in the first 50 months of diagnosis. It also identified highly differentially expressed genes between best prognosis group and worst prognosis group, which can be potential gene biomarkers for clinical testing.

Conclusions

To address the need for better prognosis and facilitate personalized treatment on neuroblastoma, we modified the recently developed bioinformatics workflow MRCPS for refined patient prognosis. It integrates clinical information and molecular features such as gene co-expression for prognosis. This clustering workflow is flexible, allowing the integration of both categorical and numerical data. The results demonstrate the power of survival prognosis with this integrative analysis workflow, with superior prognostic performance to only using transcriptomic data or clinical staging/risk information alone.

Reviewers

This article was reviewed by Lan Hu, Haibo Liu, Julie Zhu and Aleksandra Gruca.

Electronic supplementary material

The online version of this article (10.1186/s13062-019-0244-y) contains supplementary material, which is available to authorized users.

Connectome sorting by consensus clustering increases separability in group neuroimaging studies

A fundamental challenge in preprocessing pipelines for neuroimaging datasets is to increase the signal-to-noise ratio for subsequent analyses. In the same line, we suggest here that the application of the consensus clustering approach to brain connectivity matrices can be a valid additional step for connectome processing to find subgroups of subjects with reduced intragroup variability and therefore increasing the separability of the distinct subgroups when connectomes are used as a biomarker. Moreover, by partitioning the data with consensus clustering before any group comparison (for instance, between a healthy population vs. a pathological one), we demonstrate that unique regions within each cluster arise and bring new information that could be relevant from a clinical point of view.

Identification of cancer subtypes from single-cell RNA-seq data using a consensus clustering method

Background

Human cancers are complex ecosystems composed of cells with distinct molecular signatures. Such intratumoral heterogeneity poses a major challenge to cancer diagnosis and treatment. Recent advancements of single-cell techniques such as scRNA-seq have brought unprecedented insights into cellular heterogeneity. Subsequently, a challenging computational problem is to cluster high dimensional noisy datasets with substantially fewer cells than the number of genes.

Methods

In this paper, we introduced a consensus clustering framework conCluster, for cancer subtype identification from single-cell RNA-seq data. Using an ensemble strategy, conCluster fuses multiple basic partitions to consensus clusters.

Results

Applied to real cancer scRNA-seq datasets, conCluster can more accurately detect cancer subtypes than the widely used scRNA-seq clustering methods. Further, we conducted co-expression network analysis for the identified melanoma subtypes.

Conclusions

Our analysis demonstrates that these subtypes exhibit distinct gene co-expression networks and significant gene sets with different functional enrichment.

Nearest Consensus Clustering Classification to Identify Subclasses and Predict Disease

Disease subtyping, which helps to develop personalized treatments, remains a challenge in data analysis because of the many different ways to group patients based upon their data. However, if we can identify subclasses of disease, then it will help to develop better models that are more specific to individuals and should therefore improve prediction and understanding of the underlying characteristics of the disease in question. This paper proposes a new algorithm that integrates consensus clustering methods with classification in order to overcome issues with sample bias. The new algorithm combines K-means with consensus clustering in order build cohort-specific decision trees that improve classification as well as aid the understanding of the underlying differences of the discovered groups. The methods are tested on a real-world freely available breast cancer dataset and data from a London hospital on systemic sclerosis, a rare potentially fatal condition. Results show that "nearest consensus clustering classification" improves the accuracy and the prediction significantly when this algorithm has been compared with competitive similar methods.

GiniClust2: a cluster-aware, weighted ensemble clustering method for cell-type detection

Single-cell analysis is a powerful tool for dissecting the cellular composition within a tissue or organ. However, it remains difficult to detect rare and common cell types at the same time. Here, we present a new computational method, GiniClust2, to overcome this challenge. GiniClust2 combines the strengths of two complementary approaches, using the Gini index and Fano factor, respectively, through a cluster-aware, weighted ensemble clustering technique. GiniClust2 successfully identifies both common and rare cell types in diverse datasets, outperforming existing methods. GiniClust2 is scalable to large datasets.

Molecular subtyping of nasopharyngeal carcinoma (NPC) and a microRNA-based prognostic model for distant metastasis

BACKGROUND

Nasopharyngeal carcinoma (NPC) is a highly invasive and metastatic cancer, with diverse molecular characteristics and clinical outcomes. This study aims to dissect the molecular heterogeneity of NPC, followed by the construction of a microRNA (miRNA)-based prognostic model for prediction of distant metastasis.

METHODS

We retrieved two NPC datasets: GSE32960 and GSE70970 as training and validation cohorts, respectively. Consensus clustering was employed for cluster discovery, and support vector machine was used to build a classifier. Finally, Cox regression analysis was applied to constructing a prognostic model for predicting risk of distant metastasis.

RESULTS

Three NPC subtypes (immunogenic, classical and mesenchymal) were identified that are molecularly distinct and clinically relevant, of which mesenchymal subtype (~ 36%) is associated with poor prognosis, characterized by suppressing tumor suppressor miRNAs and the activation of epithelial--mesenchymal transition. Out of the 25 most differentially expressed miRNAs in mesenchymal subtype, miR-142, miR-26a, miR-141 and let-7i have significant prognostic power (P < 0.05).

CONCLUSIONS

We proposed for the first time that NPC can be stratified into three subtypes. Using a panel of 4 miRNAs, we established a prognostic model that can robustly stratify NPC patients into high- and low- risk groups of distant metastasis.

Consensus clustering approach to group brain connectivity matrices

A novel approach rooted on the notion of consensus clustering, a strategy developed for community detection in complex networks, is proposed to cope with the heterogeneity that characterizes connectivity matrices in health and disease. The method can be summarized as follows: (a) define, for each node, a distance matrix for the set of subjects by comparing the connectivity pattern of that node in all pairs of subjects; (b) cluster the distance matrix for each node; (c) build the consensus network from the corresponding partitions; and (d) extract groups of subjects by finding the communities of the consensus network thus obtained. Different from the previous implementations of consensus clustering, we thus propose to use the consensus strategy to combine the information arising from the connectivity patterns of each node. The proposed approach may be seen either as an exploratory technique or as an unsupervised pretraining step to help the subsequent construction of a supervised classifier. Applications on a toy model and two real datasets show the effectiveness of the proposed methodology, which represents heterogeneity of a set of subjects in terms of a weighted network, the consensus matrix.

Integrative clustering reveals a novel split in the luminal A subtype of breast cancer with impact on outcome

BACKGROUND

Breast cancer is a heterogeneous disease at the clinical and molecular level. In this study we integrate classifications extracted from five different molecular levels in order to identify integrated subtypes.

METHODS

Tumor tissue from 425 patients with primary breast cancer from the Oslo2 study was cut and blended, and divided into fractions for DNA, RNA and protein isolation and metabolomics, allowing the acquisition of representative and comparable molecular data. Patients were stratified into groups based on their tumor characteristics from five different molecular levels, using various clustering methods. Finally, all previously identified and newly determined subgroups were combined in a multilevel classification using a "cluster-of-clusters" approach with consensus clustering.

RESULTS

Based on DNA copy number data, tumors were categorized into three groups according to the complex arm aberration index. mRNA expression profiles divided tumors into five molecular subgroups according to PAM50 subtyping, and clustering based on microRNA expression revealed four subgroups. Reverse-phase protein array data divided tumors into five subgroups. Hierarchical clustering of tumor metabolic profiles revealed three clusters. Combining DNA copy number and mRNA expression classified tumors into seven clusters based on pathway activity levels, and tumors were classified into ten subtypes using integrative clustering. The final consensus clustering that incorporated all aforementioned subtypes revealed six major groups. Five corresponded well with the mRNA subtypes, while a sixth group resulted from a split of the luminal A subtype; these tumors belonged to distinct microRNA clusters. Gain-of-function studies using MCF-7 cells showed that microRNAs differentially expressed between the luminal A clusters were important for cancer cell survival. These microRNAs were used to validate the split in luminal A tumors in four independent breast cancer cohorts. In two cohorts the microRNAs divided tumors into subgroups with significantly different outcomes, and in another a trend was observed.

CONCLUSIONS

The six integrated subtypes identified confirm the heterogeneity of breast cancer and show that finer subdivisions of subtypes are evident. Increasing knowledge of the heterogeneity of the luminal A subtype may add pivotal information to guide therapeutic choices, evidently bringing us closer to improved treatment for this largest subgroup of breast cancer.

Conservation of immune gene signatures in solid tumors and prognostic implications

Background

Tumor-infiltrating leukocytes can either limit cancer growth or facilitate its spread. Diagnostic strategies that comprehensively assess the functional complexity of tumor immune infiltrates could have wide-reaching clinical value. In previous work we identified distinct immune gene signatures in breast tumors that reflect the relative abundance of infiltrating immune cells and exhibited significant associations with patient outcomes. Here we hypothesized that immune gene signatures agnostic to tumor type can be identified by de novo discovery of gene clusters enriched for immunological functions and possessing internal correlation structure conserved across solid tumors from different anatomic sites.

Methods

We assembled microarray expression datasets encompassing 5,295 tumors of the breast, colon, lung, ovarian and prostate. Unsupervised clustering methods were used to determine number and composition of gene clusters within each dataset. Immune-enriched gene clusters (signatures) identified by gene ontology enrichment were analyzed for internal correlation structure and conservation across tumors then compared against expression profiles of: 1) flow-sorted leukocytes from peripheral blood and 2) >300 cancer cell lines from solid and hematologic cancers. Cox regression analysis was used to identify signatures with significant associations with clinical outcome.

Results

We identified nine distinct immune-enriched gene signatures conserved across all five tumor types. The signatures differentiated specific leukocyte lineages with moderate discernment overall, and naturally organized into six discrete groups indicative of admixed lineages. Moreover, seven of the signatures exhibit minimal and uncorrelated expression in cancer cell lines, suggesting that these signatures derive predominantly from infiltrating immune cells. All nine immune signatures achieved statistically significant associations with patient prognosis (p<0.05) in one or more tumor types with greatest significance observed in breast and skin cancers. Several signatures indicative of myeloid lineages exhibited poor outcome associations that were most apparent in brain and colon cancers.

Conclusions

These findings suggest that tumor infiltrating immune cells can be differentiated by immune-specific gene expression patterns that quantify the relative abundance of multiple immune infiltrates across a range of solid tumor types. That these markers of immune involvement are significantly associated with patient prognosis in diverse cancers suggests their clinical utility as pan-cancer markers of tumor behavior and immune responsiveness.

Electronic supplementary material

The online version of this article (doi:10.1186/s12885-016-2948-z) contains supplementary material, which is available to authorized users.

Decomposition of brain diffusion imaging data uncovers latent schizophrenias with distinct patterns of white matter anisotropy

Fractional anisotropy (FA) analysis of diffusion tensor-images (DTI) has yielded inconsistent abnormalities in schizophrenia (SZ). Inconsistencies may arise from averaging heterogeneous groups of patients. Here we investigate whether SZ is a heterogeneous group of disorders distinguished by distinct patterns of FA reductions. We developed a Generalized Factorization Method (GFM) to identify biclusters (i.e., subsets of subjects associated with a subset of particular characteristics, such as low FA in specific regions). GFM appropriately assembles a collection of unsupervised techniques with Non-negative Matrix Factorization to generate biclusters, rather than averaging across all subjects and all their characteristics. DTI tract-based spatial statistics images, which output is the locally maximal FA projected onto the group white matter skeleton, were analyzed in 47 SZ and 36 healthy subjects, identifying 8 biclusters. The mean FA of the voxels of each bicluster was significantly different from those of other SZ subjects or 36 healthy controls. The eight biclusters were organized into four more general patterns of low FA in specific regions: 1) genu of corpus callosum (GCC), 2) fornix (FX)+external capsule (EC), 3) splenium of CC (SCC)+retrolenticular limb (RLIC)+posterior limb (PLIC) of the internal capsule, and 4) anterior limb of the internal capsule. These patterns were significantly associated with particular clinical features: Pattern 1 (GCC) with bizarre behavior, pattern 2 (FX+EC) with prominent delusions, and pattern 3 (SCC+RLIC+PLIC) with negative symptoms including disorganized speech. The uncovered patterns suggest that SZ is a heterogeneous group of disorders that can be distinguished by different patterns of FA reductions associated with distinct clinical features.

Development and validation of consensus clustering-based framework for brain segmentation using resting fMRI

BACKGROUND

Clustering methods are increasingly employed to segment brain regions into functional subdivisions using resting-state functional magnetic resonance imaging (rs-fMRI). However, these methods are highly sensitive to the (i) precise algorithms employed, (ii) their initializations, and (iii) metrics used for uncovering the optimal number of clusters from the data.

NEW METHOD

To address these issues, we develop a novel consensus clustering evidence accumulation (CC-EAC) framework, which effectively combines multiple clustering methods for segmenting brain regions using rs-fMRI data. Using extensive computer simulations, we examine the performance of widely used clustering algorithms including K-means, hierarchical, and spectral clustering as well as their combinations. We also examine the accuracy and validity of five objective criteria for determining the optimal number of clusters: mutual information, variation of information, modified silhouette, Rand index, and probabilistic Rand index.

RESULTS

A CC-EAC framework with a combination of base K-means clustering (KC) and hierarchical clustering (HC) with probabilistic Rand index as the criterion for choosing the optimal number of clusters, accurately uncovered the correct number of clusters from simulated datasets. In experimental rs-fMRI data, these methods reliably detected functional subdivisions of the supplementary motor area, insula, intraparietal sulcus, angular gyrus, and striatum.

COMPARISON WITH EXISTING METHODS

Unlike conventional approaches, CC-EAC can accurately determine the optimal number of stable clusters in rs-fMRI data, and is robust to initialization and choice of free parameters.

CONCLUSIONS

A novel CC-EAC framework is proposed for segmenting brain regions, by effectively combining multiple clustering methods and identifying optimal stable functional clusters in rs-fMRI data.

Long noncoding RNA profiles identify five distinct molecular subtypes of colorectal cancer with clinical relevance

Colorectal cancer (CRC) is a heterogeneous disease in terms of clinical behavior and response to therapy. Increasing evidence suggests that long noncoding RNAs (lncRNAs) are frequently aberrantly expressed in cancers, and some of them have been implicated in CRC biogenesis and prognosis. Using an lncRNA-mining approach, we constructed lncRNAs expression profiles in approximately 888 CRC samples. By applying unsupervised consensus clustering to LncRNA expression profiles, we identified five distinct molecular subtypes of CRC with different biological pathways and phenotypically distinct in their clinical outcome in both univariate and multivariate analysis. The prognostic significance of the lncRNA-based classifier was confirmed in independent patient cohorts. Further analysis revealed that most of the signature lncRNAs positively correlated with somatic copy number alterations (SCNAs). This lncRNAs-based classification schema thus provides a molecular classification applicable to individual tumors that has implications to influence treatment decisions.

Semi-supervised consensus clustering for gene expression data analysis

Background

Simple clustering methods such as hierarchical clustering and k-means are widely used for gene expression data analysis; but they are unable to deal with noise and high dimensionality associated with the microarray gene expression data. Consensus clustering appears to improve the robustness and quality of clustering results. Incorporating prior knowledge in clustering process (semi-supervised clustering) has been shown to improve the consistency between the data partitioning and domain knowledge.

Methods

We proposed semi-supervised consensus clustering (SSCC) to integrate the consensus clustering with semi-supervised clustering for analyzing gene expression data. We investigated the roles of consensus clustering and prior knowledge in improving the quality of clustering. SSCC was compared with one semi-supervised clustering algorithm, one consensus clustering algorithm, and k-means. Experiments on eight gene expression datasets were performed using h-fold cross-validation.

Results

Using prior knowledge improved the clustering quality by reducing the impact of noise and high dimensionality in microarray data. Integration of consensus clustering with semi-supervised clustering improved performance as compared to using consensus clustering or semi-supervised clustering separately. Our SSCC method outperformed the others tested in this paper.

Breast cancer patient stratification using a molecular regularized consensus clustering method

Breast cancers are highly heterogeneous with different subtypes that lead to different clinical outcomes including prognosis, response to treatment and chances of recurrence and metastasis. An important task in personalized medicine is to determine the subtype for a breast cancer patient in order to provide the most effective treatment. In order to achieve this goal, integrative genomics approach has been developed recently with multiple modalities of large datasets ranging from genotypes to multiple levels of phenotypes. A major challenge in integrative genomics is how to effectively integrate multiple modalities of data to stratify the breast cancer patients. Consensus clustering algorithms have often been adopted for this purpose. However, existing consensus clustering algorithms are not suitable for the situation of integrating clustering results obtained from a mixture of numerical data and categorical data. In this work, we present a mathematical formulation for integrative clustering of multiple-source data including both numerical and categorical data to resolve the above issue. Specifically, we formulate the problem as a novel consensus clustering method called Molecular Regularized Consensus Patient Stratification (MRCPS) based on an optimization process with regularization. Unlike the traditional consensus clustering methods, MRCPS can automatically and spontaneously cluster both numerical and categorical data with any option of similarity metrics. We apply this new method by applying it on the TCGA breast cancer datasets and evaluate using both statistical criteria and clinical relevance on predicting prognosis. The result demonstrates the superiority of this method in terms of effectiveness of aggregation and differentiating patient outcomes. Our method, while motivated by the breast cancer research, is nevertheless universal for integrative genomics studies.

Dissecting cancer heterogeneity--an unsupervised classification approach

Gene-expression-based classification studies have changed the way cancer is traditionally perceived. It is becoming increasingly clear that many cancer types are in fact not single diseases but rather consist of multiple molecular distinct subtypes. In this review, we discuss unsupervised classification studies of common malignancies during the recent years. We found that the bioinformatic workflow of many of these studies follows a common main stream, although different statistical tools may be preferred from case to case. Here we summarize the employed methods, with a special focus on consensus clustering and classification. For each critical step of the bioinformatic analysis, we explain the biological relevance and implications of the technical principles. We think that a better understanding of these ever more frequently used methods to study cancer heterogeneity by the biomedical community is relevant as these type of studies will have an important impact on patient stratification and cancer subtype-specific drug development in the future.