Gene expression knowledge graph for patient representation and diabetes prediction

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.

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.

The widespread applications in microarray technology have produced the vast quantity of publicly available gene expression datasets. However, analysis of gene expression data using biostatistics and machine learning approaches is a challenging task due to (1) high noise; (2) small sample size with high dimensionality; (3) batch effects and (4) low reproducibility of significant biomarkers. These issues reveal the complexity of gene expression data, thus significantly obstructing microarray technology in clinical applications. The integrative analysis offers an opportunity to address these issues and provides a more comprehensive understanding of the biological systems, but current methods have several limitations. This work leverages state of the art machine learning development for multiple gene expression datasets integration, classification and identification of significant biomarkers. We design a novel integrative framework, MVIAm - Multi-View based Integrative Analysis of microarray data for identifying biomarkers. It applies multiple cross-platform normalization methods to aggregate multiple datasets into a multi-view dataset and utilizes a robust learning mechanism Multi-View Self-Paced Learning (MVSPL) for gene selection in cancer classification problems. We demonstrate the capabilities of MVIAm using simulated data and studies of breast cancer and lung cancer, it can be applied flexibly and is an effective tool for facing the four challenges of gene expression data analysis. Our proposed model makes microarray integrative analysis more systematic and expands its range of applications.

Recent research has focused on incorporating biological function and pathway information into the analysis of gene expression data, partly as a means of compensating for insufficient experimental replications, low signal to noise, lack of reproducibility and/or multiple testing confounds. A Bayesian approach seems to be ideal for incorporating functional information into gene expression data analysis. In this study, we tested the feasibility of using literature derived gene relationships in a Bayesian model to analyze gene expression data. Prior distributions were constructed based on gene associations derived from the biomedical literature using Latent Semantic Indexing (LSI). The LSI model was built using more than 1 million Medline abstracts corresponding to 22,000 human and mouse genes. A key advantage of LSI is that both explicit and implicit gene relationships can be derived from the literature. Gene neighborhoods were determined using latent Gaussian Markov random fields and logistic transformation of the latent variables. We tested the procedure on a microarray dataset for interferon-stimulated genes in mouse embryonic fibroblasts. By integrating functional information from literature, Bayesian approach identified relevant genes that previously did not meet the 0.05 significance level. In comparison to a standard mixture model, spatial mixture model has more power for identifying direct and indirect interferon regulated genes. The spatial model enhanced the ranks of some genes which are known to be affected by interferon treatment, such as Nmi (NMI N-myc and STAT interactor) and ifi35 (interferon-induced protein 35). It also identified some genes that previously were ignored because of the marginal p-values, such as dpysl2, map2k1, msn, Psck5, and Il6st. Interestingly, these genes appear to be indirectly related to interferon treatment. In summary, we show that our procedure increases statistical power and produces more biologically meaningful gene lists. These results suggest that Bayesian methods which incorporate functional information from the literature may improve analysis of gene expression data.

The emergence of large-scale multi-omics data warrants method development for data integration. Genomic studies from cancer patients have identified epigenetic and genetic regulators – such as methylation marks, somatic mutations, and somatic copy number alterations (SCNAs), among others – as predictive features of cancer outcome. However, identification of “driver genes” associated with a given alteration remains a challenge. To this end, we developed a computational tool, iEDGE, to model cis and trans effects of (epi-)DNA alterations and identify potential cis driver genes, where cis and trans genes denote those genes falling within and outside the genomic boundaries of a given (epi-)genetic alteration, respectively. iEDGE first identifies the cis and trans gene expression signatures associated with the presence/absence of a particular epi-DNA alteration across samples. It then applies tests of statistical mediation to determine the cis genes predictive of the trans gene expression. Finally, cis and trans effects are annotated by pathway enrichment analysis to gain insights into the underlying regulatory networks. We used iEDGE to perform integrative analysis of SCNAs and gene expression data from breast cancer and 18 additional cancer types included in The Cancer Genome Atlas (TCGA). Notably, cis gene drivers identified by iEDGE were found to be significantly enriched for known driver genes from multiple compendia of validated oncogenes and tumor suppressors, suggesting that the remainder are of equal importance. Furthermore, predicted drivers were enriched for functionally relevant cancer genes with amplification-driven dependencies, which are of potential prognostic and therapeutic value. All the analyses results are accessible at https://montilab.bu.edu/iEDGE. In summary, integrative analysis of SCNAs and gene expression using iEDGE successfully identified known cancer driver genes and putative cancer therapeutic targets across 19 cancer types in the TCGA. The proposed method can easily be applied to the integration of gene expression profiles with other epi-DNA assays in a variety of disease contexts.

The application of mathematics in the field of bioinformatics has been widely developed. For example Support Vector Machines (SVM) and Random Forest (RF) are state of the art for classification of cancer in many applications. One of them is Chronic Kidney Disease (CKD). CKD is one of the kidney diseases that sufferers are increasing and have symptoms that are difficult to detect at first. Later, microarrays in gene expression are important tools for this approach. Microarrays gene expression provides an overview of all transcription activities in biological samples. The purpose of this research is a hybrid model combining Random Forest (RF) and Support Vector Machine (SVM) can be used to classify gene expression data. RF can highly accurate, generelize better and are interpretable and SVM (called RF-SVM) to effectively predict gene expression data with very high dimensions. In addition, from the simulation results on data from the Gene Expression Omnibus (GEO) database, it is shown that the proposed RF-SVM is a more accurate algorithm on CKD data than RFE-SVM.

Analysis of temporal gene expression data poses a significant challenge due to the combination of high dimensionality and low sample size. The purpose of this paper is to present a methodology for classification, modelling, and analysis of short time-series gene expression data using spiking neural networks (SNN) and to uncover temporal expression patterns for knowledge discovery. The classification is based on the NeuCube SNN model. Time-series gene expression data of mouse primary cortical neurons is examined as a case study. The results of the analysis are promising, indicating that SNN methodologies can be effectively used to model and analyse temporal gene expression data with surpassing performance over traditional machine learning algorithms. Additionally, a gene interaction network is constructed from the temporal gene activity modelled using the NeuCube architecture offering a new way of knowledge discovery. Future work will be directed towards using gene interactions networks to help guide pharmacological research for dementia.

BackgroundMicroarray experiments enable simultaneous measurement of the expression levels of virtually all transcripts present in cells, thereby providing a ‘molecular picture’ of the cell state. On the other hand, the genomic responses to a pharmacological or hormonal stimulus are dynamic molecular processes, where time influences gene activity and expression. The potential use of the statistical analysis of microarray data in time series has not been fully exploited so far, due to the fact that only few methods are available which take into proper account temporal relationships between samples.ResultsWe compared here four different methods to analyze data derived from a time course mRNA expression profiling experiment which consisted in the study of the effects of estrogen on hormone-responsive human breast cancer cells. Gene expression was monitored with the innovative Illumina BeadArray platform, which includes an average of 30-40 replicates for each probe sequence randomly distributed on the chip surface. We present and discuss the results obtained by applying to these datasets different statistical methods for serial gene expression analysis. The influence of the normalization algorithm applied on data and of different parameter or threshold choices for the selection of differentially expressed transcripts has also been evaluated. In most cases, the selection was found fairly robust with respect to changes in parameters and type of normalization. We then identified which genes showed an expression profile significantly affected by the hormonal treatment over time. The final list of differentially expressed genes underwent cluster analysis of functional type, to identify groups of genes with similar regulation dynamics.ConclusionsSeveral methods for processing time series gene expression data are presented, including evaluation of benefits and drawbacks of the different methods applied. The resulting protocol for data analysis was applied to characterization of the gene expression changes induced by estrogen in human breast cancer ZR-75.1 cells over an entire cell cycle.

Several studies have reported mitochondrial dysfunction in rheumatoid arthritis (RA). Many nuclear DNA (nDNA) encoded proteins translocate to mitochondria, but their participation in the dysfunction of this cell organelle during RA is quite unclear. In this study, we have carried out an integrative analysis of gene expression, protein-protein interactions (PPI) and gene ontology data. The analysis has identified potential implications of the nDNA encoded proteins in RA mitochondrial dysfunction. Firstly, by analysing six synovial microarray datasets of RA patients and healthy controls obtained from the gene expression omnibus (GEO) database, we found differentially expressed nDNA genes that encode mitochondrial proteins. We uncovered some of the roles of these genes in RA mitochondrial dysfunction using literature search and gene ontology analysis. Secondly, by employing gene co-expression from microarrays and collating reliable PPI from seven databases, we created the first mitochondrial PPI network that is specific to the RA synovial joint tissue. Further, we identified hubs of this network, and moreover, by integrating gene expression and network analysis, we found differentially expressed neighbours of the hub proteins. The results demonstrate that nDNA encoded proteins are (i) crucial for the elevation of mitochondrial reactive oxygen species (ROS) and (ii) involved in membrane potential, transport processes, metabolism and intrinsic apoptosis during RA. Additionally, we proposed a model relating to mitochondrial dysfunction and inflammation in the disease. Our analysis presents a novel perspective on the roles of nDNA encoded proteins in mitochondrial dysfunction, especially in apoptosis, oxidative stress-related processes and their relation to inflammation in RA. These findings provide a plethora of information for further research.

Lung adenocarcinoma (LUAD) is a major challenge in oncology due to its complex molecular structure and generally poor prognosis. The aim of this study was to find diagnostic markers and therapeutic targets for LUAD by integrating differential gene expression analysis, weighted gene co-expression network analysis (WGCNA), and machine learning methods. Differentially expressed genes (DEGs) were identified through the analysis of gene expression data from the Gene Expression Omnibus (GEO) database. Ten of the gene co-expression modules constructed by WGCNA were identified, with the red module having the most significant correlation with clinical features. In addition, a machine learning model constructed based on Stepglm[backward] with the random forest algorithm achieved the highest C-index (0.999) and screened eight core genes, among which ST14 was noted for its excellent predictive ability. Single-cell RNA sequencing of the LUAD samples further analyzed the expression patterns of these genes in 29 cellular subtypes, revealing their significant association with immune cell infiltration. Of particular note, the association of ST14 with clinical prognosis, drug responsiveness, and immune infiltration was validated, while enrichment analysis further clarified its role in key biological pathways. Ultimately, the expression of the core genes was validated experimentally. This study provides new insights into the pathogenesis of LUAD, clarifies potential diagnostic markers and therapeutic targets, and provides an important basis for future clinical interventions.

BackgroundIn recent years, the differences between left-sided colon cancer (LCC) and right-sided colon cancer (RCC) have received increasing attention due to the clinicopathological variation between them. However, some of these differences have remained unclear and conflicting results have been reported.MethodsFrom The Cancer Genome Atlas (TCGA), we obtained RNA sequencing data and gene mutation data on 323 and 283 colon cancer patients, respectively. Differential analysis was firstly done on gene expression data and mutation data between LCC and RCC, separately. Machine learning (ML) methods were then used to select key genes or mutations as features to construct models to classify LCC and RCC patients. Finally, we conducted correlation analysis to identify the correlations between differentially expressed genes (DEGs) and mutations using logistic regression (LR) models.ResultsWe found distinct gene mutation and expression patterns between LCC and RCC patients and further selected the 30 most important mutations and 17 most important gene expression features using ML methods. The classification models created using these features classified LCC and RCC patients with high accuracy (areas under the curve (AUC) of 0.8 and 0.96 for mutation and gene expression data, respectively). The expression of PRAC1 and BRAF V600E mutation (rs113488022) were the most important feature for each model. Correlations of mutations and gene expression data were also identified using LR models. Among them, rs113488022 was found to have significance relevance to the expression of four genes, and thus should be focused on in further study.ConclusionsOn the basis of ML methods, we found some key molecular differences between LCC and RCC, which could differentiate these two groups of patients with high accuracy. These differences might be key factors behind the variation in clinical features between LCC and RCC and thus help to improve treatment, such as determining the appropriate therapy for patients.

Fuzzy C-Means (FCM) algorithm has been widely used in cluster analysis of gene expression data. It can converge rapidly and provide more information regarding relationships within the data thanks to the usage of fuzzy sets to represent the degrees of cluster membership for every data point. However, FCM has a shortcoming in that it requires a priori specification of cluster number and cluster validation. Most cluster validity indices are based on the data themselves and may not be applicable for gene expression data. In this paper, we propose a Bayesian method using Gene Ontology (GO) annotations for gene expression cluster validation. We show that our method outperforms popular validity indices on gene expression datasets.

Next-generation sequencing technologies provide a revolutionary tool for generating gene expression data. Starting with a fixed RNA sample, they construct a library of millions of differentially abundant short sequence tags or "reads", which constitute a fundamentally discrete measure of the level of gene expression. A common limitation in experiments using these technologies is the low number or even absence of biological replicates, which complicates the statistical analysis of digital gene expression data. Analysis of this type of data has often been based on modified tests originally devised for analysing microarrays; both these and even de novo methods for the analysis of RNA-seq data are plagued by the common problem of low replication. We propose a novel, non-parametric Bayesian approach for the analysis of digital gene expression data. We begin with a hierarchical model for modelling over-dispersed count data and a blocked Gibbs sampling algorithm for inferring the posterior distribution of model parameters conditional on these counts. The algorithm compensates for the problem of low numbers of biological replicates by clustering together genes with tag counts that are likely sampled from a common distribution and using this augmented sample for estimating the parameters of this distribution. The number of clusters is not decided a priori, but it is inferred along with the remaining model parameters. We demonstrate the ability of this approach to model biological data with high fidelity by applying the algorithm on a public dataset obtained from cancerous and non-cancerous neural tissues.

A proposal for direct-ordering gene expression data by self-organising maps

High throughput gene expression technologies have been widely used in many biological fields. Typical analysis of gene expression data is to find similarly expressed gene groups by clustering approaches and to identify differentially expressed genes by statistical approaches. The analysis, however, still has a difficulty in interpreting molecular level interaction or signaling transduction based on prior biological information. Recently, a Gene Set Analysis (GSA) approach was developed by a MIT group, which paved the first way for inferring molecular pathway mechanisms behind differentially express genes among sample groups. Current GSA approaches do not take hierarchical regulation among gene entries based on prior pathway information (e.g., KEGG pathways) into consideration. Our proposed approach is that GSA can be expanded not only to reflect the hierarchical structures among genes but also to identify specific subpathways that statistically agree with gene expression data as well as that could explain molecular level mechanism differences between two sample groups. We obtained the KEGG pathways (http://www.genome.jp/kegg/pathway.html) of which nodes and edges were taken into consideration by a probabilistic model. A statistic was calculated for each subpathway in every KEGG pathway based on the model. We identified significant subpathways in an expression dataset.