Clustering Genes Using Heterogeneous Data Sources

Clustering is a useful exploratory technique for the analysis of gene expression data. Many different heuristic clustering algorithms have been proposed in this context. Clustering algorithms based on probability models offer a principled alternative to heuristic algorithms. In particular, model-based clustering assumes that the data is generated by a finite mixture of underlying probability distributions such as multivariate normal distributions. The issues of selecting a 'good' clustering method and determining the 'correct' number of clusters are reduced to model selection problems in the probability framework. Gaussian mixture models have been shown to be a powerful tool for clustering in many applications. We benchmarked the performance of model-based clustering on several synthetic and real gene expression data sets for which external evaluation criteria were available. The model-based approach has superior performance on our synthetic data sets, consistently selecting the correct model and the number of clusters. On real expression data, the model-based approach produced clusters of quality comparable to a leading heuristic clustering algorithm, but with the key advantage of suggesting the number of clusters and an appropriate model. We also explored the validity of the Gaussian mixture assumption on different transformations of real data. We also assessed the degree to which these real gene expression data sets fit multivariate Gaussian distributions both before and after subjecting them to commonly used data transformations. Suitably chosen transformations seem to result in reasonable fits. MCLUST is available at http://www.stat.washington.edu/fraley/mclust. The software for the diagonal model is under development. kayee@cs.washington.edu. http://www.cs.washington.edu/homes/kayee/model.

BackgroundSerial Analysis of Gene Expression (SAGE) is a DNA sequencing-based method for large-scale gene expression profiling that provides an alternative to microarray analysis. Most analyses of SAGE data aimed at identifying co-expressed genes have been accomplished using various versions of clustering approaches that often result in a number of false positives.Principal FindingsHere we explore the use of seriation, a statistical approach for ordering sets of objects based on their similarity, for large-scale expression pattern discovery in SAGE data. For this specific task we implement a seriation heuristic we term ‘progressive construction of contigs’ that constructs local chains of related elements by sequentially rearranging margins of the correlation matrix. We apply the heuristic to the analysis of simulated and experimental SAGE data and compare our results to those obtained with a clustering algorithm developed specifically for SAGE data. We show using simulations that the performance of seriation compares favorably to that of the clustering algorithm on noisy SAGE data.ConclusionsWe explore the use of a seriation approach for visualization-based pattern discovery in SAGE data. Using both simulations and experimental data, we demonstrate that seriation is able to identify groups of co-expressed genes more accurately than a clustering algorithm developed specifically for SAGE data. Our results suggest that seriation is a useful method for the analysis of gene expression data whose applicability should be further pursued.

Heterogeneity and Interoperability in Local Public Health Information Systems.

Many clustering algorithms have been proposed for the analysis of gene expression data, but little guidance is available to help choose among them. We provide a systematic framework for assessing the results of clustering algorithms. Clustering algorithms attempt to partition the genes into groups exhibiting similar patterns of variation in expression level. Our methodology is to apply a clustering algorithm to the data from all but one experimental condition. The remaining condition is used to assess the predictive power of the resulting clusters-meaningful clusters should exhibit less variation in the remaining condition than clusters formed by chance. We successfully applied our methodology to compare six clustering algorithms on four gene expression data sets. We found our quantitative measures of cluster quality to be positively correlated with external standards of cluster quality.

K-means clustering has become an important tool for the analysis of gene expression data, which can also look for the expression of cluster with the same fluctuation from two directions of genes and conditions. But the K-means clustering is a multi-objective local search algorithm, which is easy to fall into local optimum when dealing with complex data of the gene. In order to improve the global search capability of the algorithm, this paper presents a semi supervised K clustering algorithm. Firstly, the K—means clustering algorithm is used to deal with gene data. Then the improved semi supervised K mean clustering is used for the greedy iteration to find the K mean clustering, so as to achieve better results. Through the simulation experiment, the results prove the global semi supervised K clustering algorithm has better optimization ability and better cluster effect compared with MDO algorithm.

Aboveground biomass quantification is essential for determining carbon stocks in forests. Multiple tree biomass models are available, but estimations can be biased outside the fitting range. This is due to the lack of data for larger trees, mainly because of the cost and time required. This study proposed a methodology based on tree crown biomass ratio (crown biomass: total aboveground biomass) modelling. The original data used in the existing biomass models in Spain have been notably extended by the inclusion of stem data from First Spanish National Forest Inventory and other databases, covering better tree size variability. The analysis of the crown biomass ratio against tree size (d2h), allowed us to distinguish three different patterns: an increasing pattern, a constant one, and a decreasing pattern. A new system of biomass models was fitted simultaneously by species, including a model for crown biomass ratio according to the identified pattern, a stem biomass model, and a total aboveground biomass model. Using this methodology, models were fitted for the 29 most important species in Spain. The fitted models result in more accurate and unbiased predictions for stem biomass, and realistic estimations for the crown biomass. This methodology means more robust and flexible biomass estimations with the possibility of using different data sources. The absence of crown information is not an obstacle because this component is a percentage of total aboveground biomass. Moreover, determining the crown biomass ratio pattern allows improving the accuracy of tree biomass estimation beyond the range of tree sizes (2–70 cm) for which these models were fitted.

Based on the previously proposed Quantum-behaved Particle Swarm Optimization (QPSO) algorithm, in this paper, we focus on the application of QPSO in gene expression data clustering which can be reduced to an optimization problem. The proposed clustering algorithm partitions the N patterns of the gene expression dataset into user-defined K categories to minimize the fitness function of Total Within-Cluster Variation. Thus a partition with high performance is obtained. The experiment results on four gene expression data sets show that our QPSO-based clustering algorithm will be an effective and promising tool for gene expression data analysis.

Selection of genes that are differentially expressed and critical to a particular biological process has been a major challenge in post-array analysis. Recent development in bioinformatics has made various data sources available such as mRNA and miRNA expression profiles, biological pathway and gene annotation, etc. Efficient and effective integration of multiple data sources helps enrich our knowledge about the involved samples and genes for selecting genes bearing significant biological relevance. In this work, we studied a novel problem of multi-source gene selection: given multiple heterogeneous data sources (or data sets), select genes from expression profiles by integrating information from various data sources. We investigated how to effectively employ information contained in multiple data sources to extract an intrinsic global geometric pattern and use it in covariance analysis for gene selection. We designed and conducted experiments to systematically compare the proposed approach with representative methods in terms of statistical and biological significance, and showed the efficacy and potential of the proposed approach with promising findings.

BackgroundEach organ has a specific function in the body. “Organ-specificity” refers to differential expressions of the same gene across different organs. An organ-specific gene/protein is defined as a gene/protein whose expression is significantly elevated in a specific human organ. An “organ-specific marker” is defined as an organ-specific gene/protein that is also implicated in human diseases related to the organ. Previous studies have shown that identifying specificity for the organ in which a gene or protein is significantly differentially expressed, can lead to discovery of its function. Most currently available resources for organ-specific genes/proteins either allow users to access tissue-specific expression over a limited range of organs, or do not contain disease information such as disease-organ relationship and disease-gene relationship.ResultsWe designed an integrated Human Organ-specific Molecular Electronic Repository (HOMER, http://bio.informatics.iupui.edu/homer), defining human organ-specific genes/proteins, based on five criteria: 1) comprehensive organ coverage; 2) gene/protein to disease association; 3) disease-organ association; 4) quantification of organ-specificity; and 5) cross-linking of multiple available data sources.HOMER is a comprehensive database covering about 22,598 proteins, 52 organs, and 4,290 diseases integrated and filtered from organ-specific proteins/genes and disease databases like dbEST, TiSGeD, HPA, CTD, and Disease Ontology. The database has a Web-based user interface that allows users to find organ-specific genes/proteins by gene, protein, organ or disease, to explore the histogram of an organ-specific gene/protein, and to identify disease-related organ-specific genes by browsing the disease data online.Moreover, the quality of the database was validated with comparison to other known databases and two case studies: 1) an association analysis of organ-specific genes with disease and 2) a gene set enrichment analysis of organ-specific gene expression data.ConclusionsHOMER is a new resource for analyzing, identifying, and characterizing organ-specific molecules in association with disease-organ and disease-gene relationships. The statistical method we developed for organ-specific gene identification can be applied to other organism. The current HOMER database can successfully answer a variety of questions related to organ specificity in human diseases and can help researchers in discovering and characterizing organ-specific genes/proteins with disease relevance.

Background - In the NeoTRIPaPDL1 phase III trial, triple-negative breast cancer (TNBC) patients were randomized to receive nab-paclitaxel/carboplatin for 8 cycles (CT arm) with or without atezolizumab (CT/A arm). We previously reported that the majority of patients (65%) with PD-L1- at baseline converted to PD-L1+ (the majority with IC2/IC3) after the first cycle of treatment in the atezolizumab arm. Here we studied treatment associated changes in the molecular tumour features and immune microenvironment by PD-L1 expression. Methods – A total of 158 (56.4%) of patients enrolled in the NeoTRIPaPDL1 trial (76 and 82 from CT/A and CT arm, respectively) were included in this analysis by satisfying the following criteria: i) availability of a paired core biopsy at baseline and at day 1 of the second treatment cycle (D1C2); ii) evaluation of stromal TILs (sTILs) and staining for PD-L1 (Ventana SP142); iii) successful RNA-seq gene expression profiling. PD-L1 groups were defined as IC0/IC1 (<5% PD-L1low) vs IC2/IC3 (>=5% PD-L1high). Presence of different immune cell populations was quantified by gene expression profile deconvolution using ConsensusTME R package. Cancer hallmark gene set collection and custom signature activation status were estimated in each sample using singscore R package. Differences in score distribution were evaluated by 2-sided t-test. Results At baseline, both sTILs and immune cell signatures were upregulated in PD-L1high compared to PD-L1low tumours (p<0.001). No significant differences were found between the two treatment arms in the PD-L1high subpopulation. In the PD-L1low cases, both sTILs and immune related signatures were slightly downregulated in the CT/A arm (p<0.05), suggesting a modest unbalance among treatment arms with CT arm being slightly more inflamed than CT/A arm.At D1C2, PD-L1high tumours in the CT arm systematically had high sTILs (median=70%, range=30-90%), while PD-L1low tumours receiving CT/A had low sTILs in a significant proportion of cases (median=30%, range=0-90%; p<0.001). Similarly, at D1C2 several gene expression-estimated immune cell populations and immune-related signatures were upregulated in the CT arm compared to CT/A arm in PD-L1high tumours, with the weakest association observed for M2 macrophages (p=0.058). No tumour-related signatures were differentially expressed among the two treatment arms within groups with PD-L1high, suggesting that different treatment. modulate PD-L1 by engaging a different immune mileau instead of modulating tumor related features.Considering PD-L1low groups at D1C2, in the CT arm 21 tumors had >30% sTILs (n=21/69, 30.4%), while in the CT/A arm only 2 had sTILs >30% (2/27, 7.4%) (p<0.001). Analysis of gene expression data identified IFN-related signatures as the most upregulated in the CT compared to CT/A arm in PD-L1low cases at D1C2 (p<0.05). Conclusions Integrated dynamic analysis of PD-L1 expression and gene expression data highlighted significant treatment-specific changes of the immune landscape according to PD-L1 expression, when this biomarker is assessed during treatment. This indicates that the immune milieu associated with PD-L1 status is strongly dependent on the time of assessment in relationship to treatment received. Such observation may explain why in the NeoTRIP trial, baseline PD-L1 but not on-treatment PD-L1 was predictive of pCR in CT/A arm. In addition, our findings could have implications related to the use of PD-L1 as a predictive biomarker in pre-treated patients, especially when assessed early on during treatment. Citation Format: Maurizio Callari, Chiun-Sheng Huang, Daniel Egle, Begoña Bermejo, Claudio Zamagni, Matteo Dugo, Marc Thill, Antonio Anton, Marco Barreca, Stefania Russo, Eva Maria Ciruelos, Richard Greil, Stefania Zambelli, Balázs Gyorffy, Chanel Smart, Olivia Biasi, Pinuccia Valagussa, Giuseppe Viale, Luca Gianni, Giampaolo Bianchini. Immune milieu associated with PD-L1 status in TNBC is dependent on time of biomarker assessment and treatment received: A secondary analysis of the NeoTRIPaPDL1 trial [abstract]. In: Proceedings of the 2021 San Antonio Breast Cancer Symposium; 2021 Dec 7-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2022;82(4 Suppl):Abstract nr P1-04-02.

It is challenging to identify meaningful gene networks because biological interactions are often condition-specific and confounded with external factors. It is necessary to integrate multiple sources of genomic data to facilitate network inference. For example, one can jointly model expression datasets measured from multiple tissues with molecular marker data in so-called genetical genomic studies. In this paper, we propose a joint conditional Gaussian graphical model (JCGGM) that aims for modeling biological processes based on multiple sources of data. This approach is able to integrate multiple sources of information by adopting conditional models combined with joint sparsity regularization. We apply our approach to a real dataset measuring gene expression in four tissues (kidney, liver, heart, and fat) from recombinant inbred rats. Our approach reveals that the liver tissue has the highest level of tissue-specific gene regulations among genes involved in insulin responsive facilitative sugar transporter mediated glucose transport pathway, followed by heart and fat tissues, and this finding can only be attained from our JCGGM approach.

In recent years, huge different biological databases have been stored in various locations. Using distinct data sets from multiple sources results in more reliable data analysis. However, it is so difficult to combine heterogeneous data in one single server. The most obvious reasons include data privacy, large data sizes, costs, and different geographical locations of data sources. In this paper, we present two new algorithms for clustering data from multiple remote data sources using kernel k-means. The first algorithm is the center-based algorithm built on k-means algorithm. The second algorithm uses distributed kernel k-means over multiple data sources. In the distributed scheme, clustering methods are executed only on their local data sources themselves. Partial clustering results are synched between data sources. To evaluate performance of our proposed algorithms, we merged all data from different sources into one large data set to perform kernel k-means. The results showed that our center-based algorithm greatly reduced transmission data between data sources while still yielding acceptable clustering results. Our distributed kernel k-means algorithm achieved even better performance. The clustering results are very close to those generated by kernel k-means on one merged data set.

Microarrays have become a central tool in biological research. Their applications range from functional annotation to tissue classification and genetic network inference. A key step in the analysis of gene expression data is the identification of groups of genes that manifest similar expression patterns. This translates to the algorithmic problem of clustering genes based on their expression patterns. We present a novel clustering algorithm, called CLICK, and its applications to gene expression analysis. The algorithm utilizes graph-theoretic and statistical techniques to identify tight groups (kernels) of highly similar elements, which are likely to belong to the same true cluster. Several heuristic procedures are then used to expand the kernels into the full clusters. We report on the application of CLICK to a variety of gene expression data sets. In all those applications it outperformed extant algorithms according to several common figures of merit. We also point out that CLICK can be successfully used for the identification of common regulatory motifs in the upstream regions of co-regulated genes. Furthermore, we demonstrate how CLICK can be used to accurately classify tissue samples into disease types, based on their expression profiles. Finally, we present a new java-based graphical tool, called EXPANDER, for gene expression analysis and visualization, which incorporates CLICK and several other popular clustering algorithms. http://www.cs.tau.ac.il/~rshamir/expander/expander.html

Introduction: The discovery of tumor subtypes helps to explore tumor pathogenesis, determine the operability of clinical treatment, and improve patient survival. Clustering analysis is increasingly applied to multi-genomic data. However, due to the diversity and complexity of multi-omics data, developing a complete clustering algorithm for tumor molecular typing is still challenging. Methods: In this study, we present an adaptive density-aware spectral clustering method based on a variational autoencoder (ADSVAE). ADSVAE first learns the underlying spatial information of each omics data using a variational autoencoder (VAE) based on the Wasserstein distance metric. Secondly, a similarity matrix is built for each gene set using an adaptive density-aware kernel. Thirdly, tensor product graphs (TPGs) are used to merge different data sources and reduce noise. Finally, ADSVAE employs a spectral clustering algorithm and utilizes the Gaussian mixture model (GMM) to cluster the final eigenvector matrix to identify cancer subtypes. Results: We tested ADSVAE on 5 TCGA datasets, all with good performance in comparison with several advanced multi-omics clustering algorithms. Compared with the existing multi-group clustering algorithms, the variational autoencoder based on the Wasserstein distance measure in the ADSVAE algorithm can learn the underlying spatial information on each omics data, which has a better effect on learning complex data distribution. The self-tuning density-aware kernel used by the ADSVAE algorithm enhances the similarity between shared near neighbor points, and the process of tensor product plot data integration and diffusion can better reduce the noise and reveal the underlying structure, improving the performance. Conclusion: Due to the inherent pitfalls of computational biology in the study of cancer subtype identification, although some research conclusions have been made in this paper on the related issues, as the research in related fields continues to deepen, the clustering study of cancer subtype identification based on genomic data needs further improvement and refinement.

Predicting functions of genes is an important issue in biology. Clustering gene expression profiles has been widely used for gene function prediction, but most clustering methods are unstable and sensitive to input parameters such as starting values and number of clusters. In this article, we develop a novel consensus clustering method to address the instability issue and thus improve the performance of clustering methods. The biological function of an unannotated gene is predicted based on the most enriched functional category in its consensus cluster. The MIPS gene annotations are used to evaluate the predictive performance. It is shown that the consensus clustering-based classification method has a significantly better predictive performance than a previously used clustering-based classification method while performing as well as support vector machines (SVMs). In addition to the obvious applicability of consensus clustering to unsupervised learning, the method's advantages in supervised learning include its being a multiclass classifier that can be trained much faster than SVMs, its generality to include any of the many existing clustering algorithms, and its flexibility to be integrated with other predictive models built with other types of data, suggesting its potential for further improved performance. As a concrete example, we consider its combined use with protein-protein interaction data for gene function prediction. It is shown that the combined analysis has a significantly higher predictive accuracy and a much broader functional coverage than using either data source alone.