High-dimensional Gene Expression Research Articles

Interpretable spatially aware dimension reduction of spatial transcriptomics with STAMP

Spatial transcriptomics produces high-dimensional gene expression measurements with spatial context. Obtaining a biologically meaningful low-dimensional representation of such data is crucial for effective interpretation and downstream analysis. Here, we present Spatial Transcriptomics Analysis with topic Modeling to uncover spatial Patterns (STAMP), an interpretable spatially aware dimension reduction method built on a deep generative model that returns biologically relevant, low-dimensional spatial topics and associated gene modules. STAMP can analyze data ranging from a single section to multiple sections and from different technologies to time-series data, returning topics matching known biological domains and associated gene modules containing established markers highly ranked within. In a lung cancer sample, STAMP delineated cell states with supporting markers at a higher resolution than the original annotation and uncovered cancer-associated fibroblasts concentrated on the tumor edge’s exterior. In time-series data of mouse embryonic development, STAMP disentangled the erythro-myeloid hematopoiesis and hepatocytes developmental trajectories within the liver. STAMP is highly scalable and can handle more than 500,000 cells.

Feature selection via robust weighted score for high dimensional binary class-imbalanced gene expression data

In this paper, a robust weighted score for unbalanced data (ROWSU) is proposed for selecting the most discriminative features for high dimensional gene expression binary classification with class-imbalance problem. The method addresses one of the most challenging problems of highly skewed class distributions in gene expression datasets that adversely affect the performance of classification algorithms. First, the training dataset is balanced by synthetically generating data points from minority class observations. Second, a minimum subset of genes is selected using a greedy search approach. Third, a novel weighted robust score, where the weights are computed by support vectors, is introduced to obtain a refined set of genes. The highest scoring genes based on this approach are combined with the minimum subset of genes selected by the greedy search approach to form the final set of genes. The novel method ensures the selection of the most discriminative genes, even in the presence of skewed class distribution, thereby improving the performance of the classifiers. The performance of the proposed ROWSU method is evaluated on 7 gene expression datasets. Classification accuracy, sensitivity and F1-score are used as performance metrics to compare the proposed ROWSU algorithm with several other state-of-the-art methods. Boxplots and stability plots are also constructed for a better understanding of the results. The results show that the proposed method outperforms the existing feature selection procedures based on classification performance from k nearest neighbors (kNN) and random forest (RF) classifiers.

RNAseqCovarImpute: a multiple imputation procedure that outperforms complete case and single imputation differential expression analysis

Missing covariate data is a common problem that has not been addressed in observational studies of gene expression. Here, we present a multiple imputation method that accommodates high dimensional gene expression data by incorporating principal component analysis of the transcriptome into the multiple imputation prediction models to avoid bias. Simulation studies using three datasets show that this method outperforms complete case and single imputation analyses at uncovering true positive differentially expressed genes, limiting false discovery rates, and minimizing bias. This method is easily implemented via an R Bioconductor package, RNAseqCovarImpute that integrates with the limma-voom pipeline for differential expression analysis.

Gene selection and cancer classification using interaction-based feature clustering and improved-binary Bat algorithm

In high-dimensional gene expression data, selecting an optimal subset of genes is crucial for achieving high classification accuracy and reliable diagnosis of diseases. This paper proposes a two-stage hybrid model for gene selection based on clustering and a swarm intelligence algorithm to identify the most informative genes with high accuracy. First, a clustering-based multivariate filter approach is performed to explore the interactions between the features and eliminate any redundant or irrelevant ones. Then, by controlling for the problem of premature convergence in the binary Bat algorithm, the optimal gene subset is determined using different classifiers with the Monte Carlo cross-validation data partitioning model. The effectiveness of our proposed framework is evaluated using eight gene expression datasets, by comparison with other recently published algorithms in the literature. Experiments confirm that in seven out of eight datasets, the proposed method can achieve superior results in terms of classification accuracy and gene subset size. In particular, it achieves a classification accuracy of 100% in Lymphoma and Ovarian datasets and above 97.4% in the rest with a minimum number of genes. The results demonstrate that our proposed algorithm has the potential to solve the feature selection problem in different applications with high-dimensional datasets.

Inferring pattern-driving intercellular flows from single-cell and spatial transcriptomics.

From single-cell RNA-sequencing (scRNA-seq) and spatial transcriptomics (ST), one can extract high-dimensional gene expression patterns that can be described by intercellular communication networks or decoupled gene modules. These two descriptions of information flow are often assumed to occur independently. However, intercellular communication drives directed flows of information that are mediated by intracellular gene modules, in turn triggering outflows of other signals. Methodologies to describe such intercellular flows are lacking. We present FlowSig, a method that infers communication-driven intercellular flows from scRNA-seq or ST data using graphical causal modeling and conditional independence. We benchmark FlowSig using newly generated experimental cortical organoid data and synthetic data generated from mathematical modeling. We demonstrate FlowSig's utility by applying it to various studies, showing that FlowSig can capture stimulation-induced changes to paracrine signaling in pancreatic islets, demonstrate shifts in intercellular flows due to increasing COVID-19 severity and reconstruct morphogen-driven activator-inhibitor patterns in mouse embryogenesis.

Fast Variational Inference for Bayesian Factor Analysis in Single and Multi-Study Settings

Factors models are commonly used to analyze high-dimensional data in both single-study and multi-study settings. Bayesian inference for such models relies on Markov chain Monte Carlo (MCMC) methods, which scale poorly as the number of studies, observations, or measured variables increase. To address this issue, we propose new variational inference algorithms to approximate the posterior distribution of Bayesian latent factor models using the multiplicative gamma process shrinkage prior. The proposed algorithms provide fast approximate inference at a fraction of the time and memory of MCMC-based implementations while maintaining comparable accuracy in characterizing the data covariance matrix. We conduct extensive simulations to evaluate our proposed algorithms and show their utility in estimating the model for high-dimensional multi-study gene expression data in ovarian cancers. Overall, our proposed approaches enable more efficient and scalable inference for factor models, facilitating their use in high-dimensional settings. An R package VIMSFA implementing our methods is available on GitHub (github.com/blhansen/VI-MSFA). Supplementary materials for this article are available online.

Improved aquila optimizer with mRMR for feature selection of high-dimensional gene expression data

Improved aquila optimizer with mRMR for feature selection of high-dimensional gene expression data

ScZAG: Integrating ZINB-Based Autoencoder with Adaptive Data Augmentation Graph Contrastive Learning for scRNA-seq Clustering.

Single-cell RNA sequencing (scRNA-seq) is widely used to interpret cellular states, detect cell subpopulations, and study disease mechanisms. In scRNA-seq data analysis, cell clustering is a key step that can identify cell types. However, scRNA-seq data are characterized by high dimensionality and significant sparsity, presenting considerable challenges for clustering. In the high-dimensional gene expression space, cells may form complex topological structures. Many conventional scRNA-seq data analysis methods focus on identifying cell subgroups rather than exploring these potential high-dimensional structures in detail. Although some methods have begun to consider the topological structures within the data, many still overlook the continuity and complex topology present in single-cell data. We propose a deep learning framework that begins by employing a zero-inflated negative binomial (ZINB) model to denoise the highly sparse and over-dispersed scRNA-seq data. Next, scZAG uses an adaptive graph contrastive representation learning approach that combines approximate personalized propagation of neural predictions graph convolution (APPNPGCN) with graph contrastive learning methods. By using APPNPGCN as the encoder for graph contrastive learning, we ensure that each cell's representation reflects not only its own features but also its position in the graph and its relationships with other cells. Graph contrastive learning exploits the relationships between nodes to capture the similarity among cells, better representing the data's underlying continuity and complex topology. Finally, the learned low-dimensional latent representations are clustered using Kullback-Leibler divergence. We validated the superior clustering performance of scZAG on 10 common scRNA-seq datasets in comparison to existing state-of-the-art clustering methods.

A robust ensemble feature selection approach to prioritize genes associated with survival outcome in high-dimensional gene expression data

Exploring features associated with the clinical outcome of interest is a rapidly advancing area of research. However, with contemporary sequencing technologies capable of identifying over thousands of genes per sample, there is a challenge in constructing efficient prediction models that balance accuracy and resource utilization. To address this challenge, researchers have developed feature selection methods to enhance performance, reduce overfitting, and ensure resource efficiency. However, applying feature selection models to survival analysis, particularly in clinical datasets characterized by substantial censoring and limited sample sizes, introduces unique challenges. We propose a robust ensemble feature selection approach integrated with group Lasso to identify compelling features and evaluate its performance in predicting survival outcomes. Our approach consistently outperforms established models across various criteria through extensive simulations, demonstrating low false discovery rates, high sensitivity, and high stability. Furthermore, we applied the approach to a colorectal cancer dataset from The Cancer Genome Atlas, showcasing its effectiveness by generating a composite score based on the selected genes to correctly distinguish different subtypes of the patients. In summary, our proposed approach excels in selecting impactful features from high-dimensional data, yielding better outcomes compared to contemporary state-of-the-art models.

Stable feature selection utilizing Graph Convolutional Neural Network and Layer-wise Relevance Propagation for biomarker discovery in breast cancer

High-throughput technologies are becoming increasingly important in discovering prognostic biomarkers and in identifying novel drug targets. With Mammaprint, Oncotype DX, and many other prognostic molecular signatures breast cancer is one of the paradigmatic examples of the utility of high-throughput data to deliver prognostic biomarkers, that can be represented in a form of a rather short gene list. Such gene lists can be obtained as a set of features (genes) that are important for the decisions of a Machine Learning (ML) method applied to high-dimensional gene expression data. Several studies have identified predictive gene lists for patient prognosis in breast cancer, but these lists are unstable and have only a few genes in common. Instability of feature selection impedes biological interpretability: genes that are relevant for cancer pathology should be members of any predictive gene list obtained for the same clinical type of patients. Stability and interpretability of selected features can be improved by including information on molecular networks in ML methods. Graph Convolutional Neural Network (GCNN) is a contemporary deep learning approach applicable to gene expression data structured by a prior knowledge molecular network. Layer-wise Relevance Propagation (LRP) and SHapley Additive exPlanations (SHAP) are methods to explain individual decisions of deep learning models. We used both GCNN+LRP and GCNN+SHAP techniques to construct feature sets by aggregating individual explanations. We suggest a methodology to systematically and quantitatively analyze the stability, the impact on the classification performance, and the interpretability of the selected feature sets. We used this methodology to compare GCNN+LRP to GCNN+SHAP and to more classical ML-based feature selection approaches. Utilizing a large breast cancer gene expression dataset we show that, while feature selection with SHAP is useful in applications where selected features have to be impactful for classification performance, among all studied methods GCNN+LRP delivers the most stable (reproducible) and interpretable gene lists.

Predicting drug activity against cancer through genomic profiles and SMILES

Due to the constant increase in cancer rates, the disease has become a leading cause of death worldwide, enhancing the need for its detection and treatment. In the era of personalized medicine, the main goal is to incorporate individual variability in order to choose more precisely which therapy and prevention strategies suit each person. However, predicting the sensitivity of tumors to anticancer treatments remains a challenge. In this work, we propose two deep neural network models to predict the impact of anticancer drugs in tumors through the half-maximal inhibitory concentration (IC50). These models join biological and chemical data to apprehend relevant features of the genetic profile and the drug compounds, respectively. In order to predict the drug response in cancer cell lines, this study employed different DL methods, resorting to Recurrent Neural Networks (RNNs) and Convolutional Neural Networks (CNNs). In the first stage, two autoencoders were pre-trained with high-dimensional gene expression and mutation data of tumors. Afterward, this genetic background is transferred to the prediction models that return the IC50 value that portrays the potency of a substance in inhibiting a cancer cell line. When comparing RSEM Expected counts and TPM as methods for displaying gene expression data, RSEM has been shown to perform better in deep models and CNNs model can obtain better insight in these types of data. Moreover, the obtained results reflect the effectiveness of the extracted deep representations in the prediction of the IC50 value that portrays the potency of a substance in inhibiting a tumor, achieving a performance of a mean squared error of 1.06 and surpassing previous state-of-the-art models.

Autosurv: interpretable deep learning framework for cancer survival analysis incorporating clinical and multi-omics data

Accurate prognosis for cancer patients can provide critical information for optimizing treatment plans and improving life quality. Combining omics data and demographic/clinical information can offer a more comprehensive view of cancer prognosis than using omics or clinical data alone and can also reveal the underlying disease mechanisms at the molecular level. In this study, we developed and validated a deep learning framework to extract information from high-dimensional gene expression and miRNA expression data and conduct prognosis prediction for breast cancer and ovarian-cancer patients using multiple independent multi-omics datasets. Our model achieved significantly better prognosis prediction than the current machine learning and deep learning approaches in various settings. Moreover, an interpretation method was applied to tackle the “black-box” nature of deep neural networks and we identified features (i.e., genes, miRNA, demographic/clinical variables) that were important to distinguish predicted high- and low-risk patients. The significance of the identified features was partially supported by previous studies.

FG-HFS: A feature filter and group evolution hybrid feature selection algorithm for high-dimensional gene expression data

High dimensional and small samples characterize gene expression data and contain a large number of genes unrelated to disease. Feature selection improves the efficiency of disease diagnosis by selecting a small number of important genes. Unfortunately, existing algorithms do not consider the correlation between features, and search algorithms tend to fall into the local optimal solution in the feature search process. To this end, this paper proposes a feature filter and group evolution hybrid feature selection algorithm (FG-HFS) for high-dimensional gene expression data. Unlike existing algorithms, we propose using spectral clustering to group redundant features into a group. Then, we propose a redundant feature filter algorithm. According to the principle of approximate Markov blanket, grouped feature groups are filtered to delete these redundant features. Among them, filtered features are evenly divided by density according to the feature exponential strategy. Most importantly, we propose using the group evolution multi-objective genetic algorithm to search the filtered feature subsets and evaluate the candidate feature subsets according to the in-group and out-group so as to select the feature subsets with the highest accuracy and the least number. Experimental results show that the average accuracy (ACC) and Matthews correlation coefficient (MCC) indexes of the selected feature subsets (FSs) by the FG-HFS algorithm on 5 gene expression datasets are 92.76% and 88.76%, respectively, which are significantly better than the existing algorithms. In addition, the FSs and ACC/FSs indexes of the FG-HFS algorithm are also better than the existing algorithms, which fully proves the superiority of the FG-HFS algorithm. More importantly, the Wilcoxon and Friedman statistical experiments results show that the feature selection effect of FG-HFS algorithm is significantly better than that of existing algorithms, no matter in pairwise comparison or multiple comparison.

Factorized discriminant analysis for genetic signatures of neuronal phenotypes.

Navigating the complex landscape of single-cell transcriptomic data presents significant challenges. Central to this challenge is the identification of a meaningful representation of high-dimensional gene expression patterns that sheds light on the structural and functional properties of cell types. Pursuing model interpretability and computational simplicity, we often look for a linear transformation of the original data that aligns with key phenotypic features of cells. In response to this need, we introduce factorized linear discriminant analysis (FLDA), a novel method for linear dimensionality reduction. The crux of FLDA lies in identifying a linear function of gene expression levels that is highly correlated with one phenotypic feature while minimizing the influence of others. To augment this method, we integrate it with a sparsity-based regularization algorithm. This integration is crucial as it selects a subset of genes pivotal to a specific phenotypic feature or a combination thereof. To illustrate the effectiveness of FLDA, we apply it to transcriptomic datasets from neurons in the Drosophila optic lobe. We demonstrate that FLDA not only captures the inherent structural patterns aligned with phenotypic features but also uncovers key genes associated with each phenotype.

Proposed Two-Steps Procedure of Classification High Dimensional Data with Regularized Logistic Regression

The field of Bioinformatics has developed in response to the rapid increase in biological data, particularly high-dimensional gene expression data. Bioinformatics utilizes optimization, computational science, and statistical methods to effectively address challenges in the field of molecular biology. Numerous genes (variables) in gene expression are irrelevant to their study. Gene selection has been demonstrated to be an effective means of enhancing the performance of numerous methods of classification. The job of acquiring significant variables via the use of ranking variable selection (RVS) techniques and then picking the most effective classifier is an enormous challenge in the context of high-dimensional data. in this study, we proposed a new ranking filter method using smooth clipped absolute deviation depending on the resampling technique (RSVS) to obtain a proficient subset of genes with strong classification abilities. This is achieved by merging A screening technique employed as a filtering method in conjunction with Regularized Logistic Regression, such as LASSO,ALASSO,ENET, and MCP. The study involved the utilization of both simulated and real datasets to conduct an empirical evaluation of the proposed approach. The findings indicated that the proposed method outperformed other established methods. it was tested using three publicly data sets about Cancer. The Results demonstrate that the suggested approach is highly effective and viable, thus showing a strong level of performance with regards to accuracy, geometric mean, and the area under the curve. Furthermore, The findings suggest that the genes most often chosen are physiologically associated with the specific form of cancer. Therefore, the method that has been suggested has potential advantages for the classification of cancer via the use of DNA gene expression data within a clinical setting.

An embedded feature selection method based on generalized classifier neural network for cancer classification

The selection of relevant genes plays a vital role in classifying high-dimensional microarray gene expression data. Sparse group Lasso and its variants have been employed for gene selection to capture the interactions of genes within a group. Most of the embedded methods are linear sparse learning models that fail to capture the non-linear interactions. Additionally, very less attention is given to solving multi-class problems. The existing methods create overlapping groups, which further increases dimensionality. The paper proposes a neural network-based embedded feature selection method that can represent the non-linear relationship. In an effort toward an explainable model, a generalized classifier neural network (GCNN) is adopted as the model for the proposed embedded feature selection. GCNN has well-defined architecture in terms of the number of layers and neurons within each layer. Each layer has a distinct functionality, eliminating the obscure nature of most neural networks. The paper proposes a feature selection approach called Weighted GCNN (WGCNN) that embeds feature weighting as a part of training the neural network. Since the gene expression data comprises a large number of features, to avoid overfitting of the model a statistical guided dropout is implemented at the input layer. The proposed method works for binary as well as multi-class classification problems likewise. Experimental validation is carried out on seven microarray datasets on three learning models and compared with six state-of-art methods that are popularly employed for feature selection. The WGCNN performs well in terms of the F1 score and the number of features selected.

Expansion of extrafollicular B and T cell subsets in childhood-onset systemic lupus erythematosus.

Most childhood-onset SLE patients (cSLE) develop lupus nephritis (cLN), but only a small proportion achieve complete response to current therapies. The prognosis of children with LN and end-stage renal disease is particularly dire. Mortality rates within the first five years of renal replacement therapy may reach 22%. Thus, there is urgent need to decipher and target immune mechanisms that drive cLN. Despite the clear role of autoantibody production in SLE, targeted B cell therapies such as rituximab (anti-CD20) and belimumab (anti-BAFF) have shown only modest efficacy in cLN. While many studies have linked dysregulation of germinal center formation to SLE pathogenesis, other work supports a role for extrafollicular B cell activation in generation of pathogenic antibody secreting cells. However, whether extrafollicular B cell subsets and their T cell collaborators play a role in specific organ involvement in cLN and/or track with disease activity remains unknown. We analyzed high-dimensional mass cytometry and gene expression data from 24 treatment naïve cSLE patients at the time of diagnosis and longitudinally, applying novel computational tools to identify abnormalities associated with clinical manifestations (cLN) and disease activity (SLEDAI). cSLE patients have an extrafollicular B cell expansion signature, with increased frequency of i) DN2, ii) Bnd2, iii) plasmablasts, and iv) peripheral T helper cells. Most importantly, we discovered that this extrafollicular signature correlates with disease activity in cLN, supporting extrafollicular T/B interactions as a mechanism underlying pediatric renal pathogenesis. This study integrates established and emerging themes of extrafollicular B cell involvement in SLE by providing evidence for extrafollicular B and peripheral T helper cell expansion, along with elevated type 1 IFN activation, in a homogeneous cohort of treatment-naïve cSLE patients, a point at which they should display the most extreme state of their immune dysregulation.

Designs for the simultaneous inference of concentration–response curves

BackgroundAn important problem in toxicology in the context of gene expression data is the simultaneous inference of a large number of concentration–response relationships. The quality of the inference substantially depends on the choice of design of the experiments, in particular, on the set of different concentrations, at which observations are taken for the different genes under consideration. As this set has to be the same for all genes, the efficient planning of such experiments is very challenging. We address this problem by determining efficient designs for the simultaneous inference of a large number of concentration–response models. For that purpose, we both construct a D-optimality criterion for simultaneous inference and a K-means procedure which clusters the support points of the locally D-optimal designs of the individual models.ResultsWe show that a planning of experiments that addresses the simultaneous inference of a large number of concentration–response relationships yields a substantially more accurate statistical analysis. In particular, we compare the performance of the constructed designs to the ones of other commonly used designs in terms of D-efficiencies and in terms of the quality of the resulting model fits using a real data example dealing with valproic acid. For the quality comparison we perform an extensive simulation study.ConclusionsThe design maximizing the D-optimality criterion for simultaneous inference improves the inference of the different concentration–response relationships substantially. The design based on the K-means procedure also performs well, whereas a log-equidistant design, which was also included in the analysis, performs poorly in terms of the quality of the simultaneous inference. Based on our findings, the D-optimal design for simultaneous inference should be used for upcoming analyses dealing with high-dimensional gene expression data.

High-dimensional deconstruction of pancreatic cancer identifies tumor microenvironmental and developmental stemness features that predict survival

Numerous cell states are known to comprise the pancreatic ductal adenocarcinoma (PDAC) tumor microenvironment (TME). However, the developmental stemness and co-occurrence of these cell states remain poorly defined. Here, we performed single-cell RNA sequencing (scRNA-seq) on a cohort of treatment-naive PDAC time-of-diagnosis endoscopic ultrasound-guided fine needle biopsy (EUS-FNB) samples (n = 25). We then combined these samples with surgical resection (n = 6) and publicly available samples to increase statistical power (n = 80). Following annotation into 25 distinct cell states, cells were scored for developmental stemness, and a customized version of the Ecotyper tool was used to identify communities of co-occurring cell states in bulk RNA-seq samples (n = 268). We discovered a tumor microenvironmental community comprised of aggressive basal-like malignant cells, tumor-promoting SPP1+ macrophages, and myofibroblastic cancer-associated fibroblasts associated with especially poor prognosis. We also found a developmental stemness continuum with implications for survival that is present in both malignant cells and cancer-associated fibroblasts (CAFs). We further demonstrated that high-dimensional analyses predictive of survival are feasible using standard-of-care, time-of-diagnosis EUS-FNB specimens. In summary, we identified tumor microenvironmental and developmental stemness characteristics from a high-dimensional gene expression analysis of PDAC using human tissue specimens, including time-of-diagnosis EUS-FNB samples. These reveal new connections between tumor microenvironmental composition, CAF and malignant cell stemness, and patient survival that could lead to better upfront risk stratification and more personalized upfront clinical decision-making.

Identifying a developmental transition in honey bees using gene expression data.

In many organisms, interactions among genes lead to multiple functional states, and changes to interactions can lead to transitions into new states. These transitions can be related to bifurcations (or critical points) in dynamical systems theory. Characterizing these collective transitions is a major challenge for systems biology. Here, we develop a statistical method for identifying bistability near a continuous transition directly from high-dimensional gene expression data. We apply the method to data from honey bees, where a known developmental transition occurs between bees performing tasks in the nest and leaving the nest to forage. Our method, which makes use of the expected shape of the distribution of gene expression levels near a transition, successfully identifies the emergence of bistability and links it to genes that are known to be involved in the behavioral transition. This proof of concept demonstrates that going beyond correlative analysis to infer the shape of gene expression distributions might be used more generally to identify collective transitions from gene expression data.