Using neural networks for reducing the dimensions of single-cell RNA-Seq data

An interpretable survival model for diffuse large B-cell lymphoma patients using a biologically informed visible neural network

Diffuse large B-cell lymphoma (DLBCL) is the most common subtype of non-Hodgkin lymphoma (NHL) and is characterized by high heterogeneity. Assessment of its prognosis and genetic subtyping hold significant clinical implications. However, existing DLBCL prognostic models are mainly based on transcriptomic profiles, while genetic variation detection is more commonly used in clinical practice. In addition, current clustering-based subtyping methods mostly focus on genes with high mutation frequencies, providing insufficient explanations for the heterogeneity of DLBCL. Here, we proposed VNNSurv (https://bio-web1.nscc-gz.cn/app/VNNSurv), a survival model for DLBCL patients based on a biologically informed visible neural network (VNN). VNNSurv achieved an average C-index of 0.72 on the cross-validation set (HMRN cohort, n = 928), outperforming the baseline methods. The remarkable interpretability of VNNSurv facilitated the identification of the most impactful genes and the underlying pathways through which they act on patient outcomes. When only the 30 highest-impact genes were used as genetic input, the overall performance of VNNSurv improved, and a C-index of 0.70 was achieved on the external TCGA cohort (n = 48). Leveraging these high-impact genes, including 16 genes with low (<5 %) alteration frequencies, we devised a genetic-based prognostic index (GPI) for risk stratification and a subtype identification method. We stratified the patient group according to the International Prognostic Index (IPI) into three risk grades with significant prognostic differences. Furthermore, the defined subtypes exhibited greater prognostic consistency than clustering-based methods. Broadly, VNNSurv is a valuable DLBCL survival model. Its high interpretability has significant value for precision medicine, and its framework is scalable to other diseases.

Effectiveness of Artificial Intelligence Technologies in Cancer Treatment for Older Adults: A Systematic Review

Background: Aging is a multifaceted process that may lead to an increased risk of developing cancer. Artificial intelligence (AI) applications in clinical cancer research may optimize cancer treatments, improve patient care, and minimize risks, prompting AI to receive high levels of attention in clinical medicine. This systematic review aims to synthesize current articles about the effectiveness of artificial intelligence in cancer treatments for older adults. Methods: We conducted a systematic review by searching CINAHL, PsycINFO, and MEDLINE via EBSCO. We also conducted forward and backward hand searching for a comprehensive search. Eligible studies included a study population of older adults (60 and older) with cancer, used AI technology to treat cancer, and were published in a peer-reviewed journal in English. This study was registered on PROSPERO (CRD42024529270). Results: This systematic review identified seven articles focusing on lung, breast, and gastrointestinal cancers. They were predominantly conducted in the USA (42.9%), with others from India, China, and Germany. The measures of overall and progression-free survival, local control, and treatment plan concordance suggested that AI interventions were equally or less effective than standard care in treating older adult cancer patients. Conclusions: Despite promising initial findings, the utility of AI technologies in cancer treatment for older adults remains in its early stages, as further developments are necessary to enhance accuracy, consistency, and reliability for broader clinical use.

A review of artificial intelligence-assisted omics techniques in plant defense: current trends and future directions

Plants intricately deploy defense systems to counter diverse biotic and abiotic stresses. Omics technologies, spanning genomics, transcriptomics, proteomics, and metabolomics, have revolutionized the exploration of plant defense mechanisms, unraveling molecular intricacies in response to various stressors. However, the complexity and scale of omics data necessitate sophisticated analytical tools for meaningful insights. This review delves into the application of artificial intelligence algorithms, particularly machine learning and deep learning, as promising approaches for deciphering complex omics data in plant defense research. The overview encompasses key omics techniques and addresses the challenges and limitations inherent in current AI-assisted omics approaches. Moreover, it contemplates potential future directions in this dynamic field. In summary, AI-assisted omics techniques present a robust toolkit, enabling a profound understanding of the molecular foundations of plant defense and paving the way for more effective crop protection strategies amidst climate change and emerging diseases.

Multiscale differential geometry learning of networks with applications to single-cell RNA sequencing data

Single-cell RNA sequencing (scRNA-seq) has emerged as a transformative technology, offering unparalleled insights into the intricate landscape of cellular diversity and gene expression dynamics. scRNA-seq analysis represents a challenging and cutting-edge frontier within the field of biological research. Differential geometry serves as a powerful mathematical tool in various applications of scientific research. In this study, we introduce, for the first time, a multiscale differential geometry (MDG) strategy for addressing the challenges encountered in scRNA-seq data analysis. We assume that intrinsic properties of cells lie on a family of low-dimensional manifolds embedded in the high-dimensional space of scRNA-seq data. Multiscale cell-cell interactive manifolds are constructed to reveal complex relationships in the cell-cell network, where curvature-based features for cells can decipher the intricate structural and biological information. We showcase the utility of our novel approach by demonstrating its effectiveness in classifying cell types. This innovative application of differential geometry in scRNA-seq analysis opens new avenues for understanding the intricacies of biological networks and holds great potential for network analysis in other fields.

Deep learning in spatially resolved transcriptfomics: a comprehensive technical view

Spatially resolved transcriptomics (SRT) is a pioneering method for simultaneously studying morphological contexts and gene expression at single-cell precision. Data emerging from SRT are multifaceted, presenting researchers with intricate gene expression matrices, precise spatial details and comprehensive histology visuals. Such rich and intricate datasets, unfortunately, render many conventional methods like traditional machine learning and statistical models ineffective. The unique challenges posed by the specialized nature of SRT data have led the scientific community to explore more sophisticated analytical avenues. Recent trends indicate an increasing reliance on deep learning algorithms, especially in areas such as spatial clustering, identification of spatially variable genes and data alignment tasks. In this manuscript, we provide a rigorous critique of these advanced deep learning methodologies, probing into their merits, limitations and avenues for further refinement. Our in-depth analysis underscores that while the recent innovations in deep learning tailored for SRT have been promising, there remains a substantial potential for enhancement. A crucial area that demands attention is the development of models that can incorporate intricate biological nuances, such as phylogeny-aware processing or in-depth analysis of minuscule histology image segments. Furthermore, addressing challenges like the elimination of batch effects, perfecting data normalization techniques and countering the overdispersion and zero inflation patterns seen in gene expression is pivotal. To support the broader scientific community in their SRT endeavors, we have meticulously assembled a comprehensive directory of readily accessible SRT databases, hoping to serve as a foundation for future research initiatives.

scFED: Clustering Identifying Cell Types of scRNA-Seq Data Based on Feature Engineering Denoising

Recently developed single-cell RNA-seq (scRNA-seq) technology has given researchers the chance to investigate single-cell level of disease development. Clustering is one of the most essential strategies for analyzing scRNA-seq data. Choosing high-quality feature sets can significantly enhance the outcomes of single-cell clustering and classification. But computationally burdensome and highly expressed genes cannot afford a stabilized and predictive feature set for technical reasons. In this study, we introduce scFED, a feature-engineered gene selection framework. scFED identifies prospective feature sets to eliminate the noise fluctuation. And fuse them with existing knowledge from the tissue-specific cellular taxonomy reference database (CellMatch) to avoid the influence of subjective factors. Then present a reconstruction approach for noise reduction and crucial information amplification. We apply scFED on four genuine single-cell datasets and compare it with other techniques. According to the results, scFED improves clustering, decreases dimension of the scRNA-seq data, improves cell type identification when combined with clustering algorithms, and has higher performance than other methods. Therefore, scFED offers certain benefits in scRNA-seq data gene selection.

Vis-SPLIT: Interactive Hierarchical Modeling for mRNA Expression Classification

We propose an interactive visual analytics tool, Vis-SPLIT, for partitioning a population of individuals into groups with similar gene signatures. Vis-SPLIT allows users to interactively explore a dataset and exploit visual separations to build a classification model for specific cancers. The visualization components reveal gene expression and correlation to assist specific partitioning decisions, while also providing overviews for the decision model and clustered genetic signatures. We demonstrate the effectiveness of our framework through a case study and evaluate its usability with domain experts. Our results show that Vis-SPLIT can classify patients based on their genetic signatures to effectively gain insights into RNA sequencing data, as compared to an existing classification system.

Deep learning-based prediction model for diagnosing gastrointestinal diseases using endoscopy images

BACKGROUND

Gastrointestinal (GI) infections are quite common today around the world. Colonoscopy or wireless capsule endoscopy (WCE) are noninvasive methods for examining the whole GI tract for abnormalities. Nevertheless, it requires a great deal of time and effort for doctors to visualize a large number of images, and diagnosis is prone to human error. As a result, developing automated artificial intelligence (AI) based GI disease diagnosis methods is a crucial and emerging research area. AI-based prediction models may lead to improvements in the early diagnosis of gastrointestinal disorders, assessing severity, and healthcare systems for the benefit of patients as well as clinicians. The focus of this research is on the early diagnosis of gastrointestinal diseases using a convolution neural network (CNN) to enhance diagnosis accuracy.

METHODS

Various CNN models (baseline model and using transfer learning (VGG16, InceptionV3, and ResNet50)) were trained on a benchmark image dataset, KVASIR, containing images from inside the GI tract using n-fold cross-validation. The dataset comprises images of three disease states-polyps, ulcerative colitis, and esophagitis-as well as images of the healthy colon. Data augmentation strategies together with statistical measures were used to improve and evaluate the model's performance. Additionally, the test set comprising 1200 images was used to evaluate the model's accuracy and robustness.

RESULTS

The CNN model using the weights of the ResNet50 pre-trained model achieved the highest average accuracy of approximately 99.80% on the training set (100% precision and approximately 99% recall) and accuracies of 99.50% and 99.16% on the validation and additional test set, respectively, while diagnosing GI diseases. When compared to other existing systems, the proposed ResNet50 model outperforms them all.

CONCLUSION

The findings of this study indicate that AI-based prediction models using CNNs, specifically ResNet50, can improve diagnostic accuracy for detecting gastrointestinal polyps, ulcerative colitis, and esophagitis. The prediction model is available at https://github.com/anjus02/GI-disease-classification.git.

Exploring the optimization of autoencoder design for imputing single-cell RNA sequencing data

Autoencoders are the backbones of many imputation methods that aim to relieve the sparsity issue in single-cell RNA sequencing (scRNA-seq) data. The imputation performance of an autoencoder relies on both the neural network architecture and the hyperparameter choice. So far, literature in the single-cell field lacks a formal discussion on how to design the neural network and choose the hyperparameters. Here, we conducted an empirical study to answer this question. Our study used many real and simulated scRNA-seq datasets to examine the impacts of the neural network architecture, the activation function, and the regularization strategy on imputation accuracy and downstream analyses. Our results show that (i) deeper and narrower autoencoders generally lead to better imputation performance; (ii) the sigmoid and tanh activation functions consistently outperform other commonly used functions including ReLU; (iii) regularization improves the accuracy of imputation and downstream cell clustering and DE gene analyses. Notably, our results differ from common practices in the computer vision field regarding the activation function and the regularization strategy. Overall, our study offers practical guidance on how to optimize the autoencoder design for scRNA-seq data imputation.

Review of single-cell RNA-seq data clustering for cell-type identification and characterization

In recent years, the advances in single-cell RNA-seq techniques have enabled us to perform large-scale transcriptomic profiling at single-cell resolution in a high-throughput manner. Unsupervised learning such as data clustering has become the central component to identify and characterize novel cell types and gene expression patterns. In this study, we review the existing single-cell RNA-seq data clustering methods with critical insights into the related advantages and limitations. In addition, we also review the upstream single-cell RNA-seq data processing techniques such as quality control, normalization, and dimension reduction. We conduct performance comparison experiments to evaluate several popular single-cell RNA-seq clustering approaches on simulated and multiple single-cell transcriptomic data sets.

SigPrimedNet: A Signaling-Informed Neural Network for scRNA-seq Annotation of Known and Unknown Cell Types

Single-cell RNA sequencing is increasing our understanding of the behavior of complex tissues or organs, by providing unprecedented details on the complex cell type landscape at the level of individual cells. Cell type definition and functional annotation are key steps to understanding the molecular processes behind the underlying cellular communication machinery. However, the exponential growth of scRNA-seq data has made the task of manually annotating cells unfeasible, due not only to an unparalleled resolution of the technology but to an ever-increasing heterogeneity of the data. Many supervised and unsupervised methods have been proposed to automatically annotate cells. Supervised approaches for cell-type annotation outperform unsupervised methods except when new (unknown) cell types are present. Here, we introduce SigPrimedNet an artificial neural network approach that leverages (i) efficient training by means of a sparsity-inducing signaling circuits-informed layer, (ii) feature representation learning through supervised training, and (iii) unknown cell-type identification by fitting an anomaly detection method on the learned representation. We show that SigPrimedNet can efficiently annotate known cell types while keeping a low false-positive rate for unseen cells across a set of publicly available datasets. In addition, the learned representation acts as a proxy for signaling circuit activity measurements, which provide useful estimations of the cell functionalities.

MulCNN: An efficient and accurate deep learning method based on gene embedding for cell type identification in single-cell RNA-seq data

Advancements in single-cell sequencing research have revolutionized our understanding of cellular heterogeneity and functional diversity through the analysis of single-cell transcriptomes and genomes. A crucial step in single-cell RNA sequencing (scRNA-seq) analysis is identifying cell types. However, scRNA-seq data are often high dimensional and sparse, and manual cell type identification can be time-consuming, subjective, and lack reproducibility. Consequently, analyzing scRNA-seq data remains a computational challenge. With the increasing availability of well-annotated scRNA-seq datasets, advanced methods are emerging to aid in cell type identification by leveraging this information. Deep learning neural networks have great potential for analyzing single-cell data. This paper proposes MulCNN, a multi-level convolutional neural network that uses a unique cell type-specific gene expression feature extraction method. This method extracts critical features through multi-scale convolution while filtering noise. Extensive testing using datasets from various species and comparisons with popular classification methods show that MulCNN has outstanding performance and offers a new and scalable direction for scRNA-seq analysis.

Semi-Supervised Deep Learning for Cell Type Identification From Single-Cell Transcriptomic Data

Cell type identification from single-cell transcriptomic data is a common goal of single-cell RNA sequencing (scRNAseq) data analysis. Deep neural networks have been employed to identify cell types from scRNAseq data with high performance. However, it requires a large mount of individual cells with accurate and unbiased annotated types to train the identification models. Unfortunately, labeling the scRNAseq data is cumbersome and time-consuming as it involves manual inspection of marker genes. To overcome this challenge, we propose a semi-supervised learning model "SemiRNet" to use unlabeled scRNAseq cells and a limited amount of labeled scRNAseq cells to implement cell identification. The proposed model is based on recurrent convolutional neural networks (RCNN), which includes a shared network, a supervised network and an unsupervised network. The proposed model is evaluated on two large scale single-cell transcriptomic datasets. It is observed that the proposed model is able to achieve encouraging performance by learning on the very limited amount of labeled scRNAseq cells together with a large number of unlabeled scRNAseq cells.

Trends and Potential of Machine Learning and Deep Learning in Drug Study at Single-Cell Level

Cancer treatments always face challenging problems, particularly drug resistance due to tumor cell heterogeneity. The existing datasets include the relationship between gene expression and drug sensitivities; however, the majority are based on tissue-level studies. Study drugs at the single-cell level are perspective to overcome minimal residual disease caused by subclonal resistant cancer cells retained after initial curative therapy. Fortunately, machine learning techniques can help us understand how different types of cells respond to different cancer drugs from the perspective of single-cell gene expression. Good modeling using single-cell data and drug response information will not only improve machine learning for cell-drug outcome prediction but also facilitate the discovery of drugs for specific cancer subgroups and specific cancer treatments. In this paper, we review machine learning and deep learning approaches in drug research. By analyzing the application of these methods on cancer cell lines and single-cell data and comparing the technical gap between single-cell sequencing data analysis and single-cell drug sensitivity analysis, we hope to explore the trends and potential of drug research at the single-cell data level and provide more inspiration for drug research at the single-cell level. We anticipate that this review will stimulate the innovative use of machine learning methods to address new challenges in precision medicine more broadly.

scCapsNet-mask: an updated version of scCapsNet with extended applicability in functional analysis related to scRNA-seq data

BACKGROUND

With the rapid accumulation of scRNA-seq data, more and more automatic cell type identification methods have been developed, especially those based on deep learning. Although these methods have reached relatively high prediction accuracy, many issues still exist. One is the interpretability. The second is how to deal with the non-standard test samples that are not encountered in the training process.

RESULTS

Here we introduce scCapsNet-mask, an updated version of scCapsNet. The scCapsNet-mask provides a reasonable solution to the issues of interpretability and non-standard test samples. Firstly, the scCapsNet-mask utilizes a mask to ease the task of model interpretation in the original scCapsNet. The results show that scCapsNet-mask could constrain the coupling coefficients, and make a one-to-one correspondence between the primary capsules and type capsules. Secondly, the scCapsNet-mask can process non-standard samples more reasonably. In one example, the scCapsNet-mask was trained on the committed cells, and then tested on less differentiated cells as the non-standard samples. It could not only estimate the lineage bias of less differentiated cells, but also distinguish the development stages more accurately than traditional machine learning models. Therefore, the pseudo-temporal order of cells for each lineage could be established. Following these pseudo-temporal order, lineage specific genes exhibit a gradual increase expression pattern and stem cell associated genes exhibit a gradual decrease expression pattern. In another example, the scCapsNet-mask was trained on scRNA-seq data, and then used to assign cell type in spatial transcriptomics that may contain non-standard sample of doublets. The results show that the scCapsNet-mask not only restored the spatial map but also identified several non-standard samples of doublet.

CONCLUSIONS

The scCapsNet-mask offers a suitable solution to the challenge of interpretability and non-standard test samples. By adding a mask, it has the advantages of automatic processing and easy interpretation compared with the original scCapsNet. In addition, the scCapsNet-mask could more accurately reflect the composition of non-standard test samples than traditional machine learning methods. Therefore, it can extend its applicability in functional analysis, such as fate bias prediction in less differentiated cells and cell type assignment in spatial transcriptomics.

Spatially aware dimension reduction for spatial transcriptomics

Spatial transcriptomics are a collection of genomic technologies that have enabled transcriptomic profiling on tissues with spatial localization information. Analyzing spatial transcriptomic data is computationally challenging, as the data collected from various spatial transcriptomic technologies are often noisy and display substantial spatial correlation across tissue locations. Here, we develop a spatially-aware dimension reduction method, SpatialPCA, that can extract a low dimensional representation of the spatial transcriptomics data with biological signal and preserved spatial correlation structure, thus unlocking many existing computational tools previously developed in single-cell RNAseq studies for tailored analysis of spatial transcriptomics. We illustrate the benefits of SpatialPCA for spatial domain detection and explores its utility for trajectory inference on the tissue and for high-resolution spatial map construction. In the real data applications, SpatialPCA identifies key molecular and immunological signatures in a detected tumor surrounding microenvironment, including a tertiary lymphoid structure that shapes the gradual transcriptomic transition during tumorigenesis and metastasis. In addition, SpatialPCA detects the past neuronal developmental history that underlies the current transcriptomic landscape across tissue locations in the cortex.

MPVNN: Mutated Pathway Visible Neural Network architecture for interpretable prediction of cancer-specific survival risk

MOTIVATION

Survival risk prediction using gene expression data is important in making treatment decisions in cancer. Standard neural network (NN) survival analysis models are black boxes with a lack of interpretability. More interpretable visible neural network architectures are designed using biological pathway knowledge. But they do not model how pathway structures can change for particular cancer types.

RESULTS

We propose a novel Mutated Pathway Visible Neural Network (MPVNN) architecture, designed using prior signaling pathway knowledge and random replacement of known pathway edges using gene mutation data simulating signal flow disruption. As a case study, we use the PI3K-Akt pathway and demonstrate overall improved cancer-specific survival risk prediction of MPVNN over other similar-sized NN and standard survival analysis methods. We show that trained MPVNN architecture interpretation, which points to smaller sets of genes connected by signal flow within the PI3K-Akt pathway that is important in risk prediction for particular cancer types, is reliable.

AVAILABILITY AND IMPLEMENTATION

The data and code are available at https://github.com/gourabghoshroy/MPVNN.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Using expression quantitative trait loci data and graph-embedded neural networks to uncover genotype–phenotype interactions

Motivation: A central goal of current biology is to establish a complete functional link between the genotype and phenotype, known as the so-called genotype–phenotype map. With the continuous development of high-throughput technology and the decline in sequencing costs, multi-omics analysis has become more widely employed. While this gives us new opportunities to uncover the correlation mechanisms between single-nucleotide polymorphism (SNP), genes, and phenotypes, multi-omics still faces certain challenges, specifically: 1) When the sample size is large enough, the number of omics types is often not large enough to meet the requirements of multi-omics analysis; 2) each omics’ internal correlations are often unclear, such as the correlation between genes in genomics; 3) when analyzing a large number of traits (p), the sample size (n) is often smaller than p, n &lt;&lt; p, hindering the application of machine learning methods in the classification of disease outcomes.

Results: To solve these issues with multi-omics and build a robust classification model, we propose a graph-embedded deep neural network (G-EDNN) based on expression quantitative trait loci (eQTL) data, which achieves sparse connectivity between network layers to prevent overfitting. The correlation within each omics is also considered such that the model more closely resembles biological reality. To verify the capabilities of this method, we conducted experimental analysis using the GSE28127 and GSE95496 data sets from the Gene Expression Omnibus (GEO) database, tested various neural network architectures, and used prior data for feature selection and graph embedding. Results show that the proposed method could achieve a high classification accuracy and easy-to-interpret feature selection. This method represents an extended application of genotype–phenotype association analysis in deep learning networks.

Integration of computational analysis and spatial transcriptomics in single-cell study

Recent advances of single-cell transcriptomics technologies and allied computational methodologies have revolutionized molecular cell biology. Meanwhile, pioneering explorations in spatial transcriptomics have opened avenues to address fundamental biological questions in health and diseases. Here, we review the technical attributes of single-cell RNA sequencing and spatial transcriptomics, and the core concepts of computational data analysis. We further highlight the challenges in the application of data integration methodologies and the interpretation of the biological context of the findings.

Large-Scale Integrative Analysis of Soybean Transcriptome Using an Unsupervised Autoencoder Model

Plant tissues are distinguished by their gene expression patterns, which can help identify tissue-specific highly expressed genes and their differential functional modules. For this purpose, large-scale soybean transcriptome samples were collected and processed starting from raw sequencing reads in a uniform analysis pipeline. To address the gene expression heterogeneity in different tissues, we utilized an adversarial deconfounding autoencoder (AD-AE) model to map gene expressions into a latent space and adapted a standard unsupervised autoencoder (AE) model to help effectively extract meaningful biological signals from the noisy data. As a result, four groups of 1,743, 914, 2,107, and 1,451 genes were found highly expressed specifically in leaf, root, seed and nodule tissues, respectively. To obtain key transcription factors (TFs), hub genes and their functional modules in each tissue, we constructed tissue-specific gene regulatory networks (GRNs), and differential correlation networks by using corrected and compressed gene expression data. We validated our results from the literature and gene enrichment analysis, which confirmed many identified tissue-specific genes. Our study represents the largest gene expression analysis in soybean tissues to date. It provides valuable targets for tissue-specific research and helps uncover broader biological patterns. Code is publicly available with open source at https://github.com/LingtaoSu/SoyMeta.

SLRRSC: single-cell type recognition method based on similarity and graph regularization constraints

Single-cell clustering is a crucial task of scRNA-seq analysis, which reveals the natural grouping of cells. However, due to the high noise and high dimension in scRNA-seq data, how to effectively and accurately identify cell types from a great quantity of cell mixtures is still a challenge. Considering this, in this paper, we propose a novel subspace clustering algorithm termed SLRRSC. This method is developed based on the low-rank representation model, and it aims to capture the global and local properties inherent in data. In order to make the LRR matrix describe the spatial relationship of samples more accurately, we introduce the manifold-based graph regularization and similarity constraint into the LRR-based method SLRRSC. The graph regularization can preserve the local geometric structure of the data in low-rank decomposition, so that the low-rank representation matrix contains more local structure information. By imposing similarity constraint on the low-rank matrix, the similarity information between sample pairs is further introduced into the SLRRSC model to improve the learning ability of low-rank method for global structure. At the same time, the similarity constraint makes the low-rank representation matrix symmetric, which makes it better interpretable in clustering application. We compare the effectiveness of the SLRRSC algorithm with other single-cell clustering methods on simulated data and real single-cell datasets. The results show that this method can obtain more accurate sample similarity matrix and effectively solve the problem of cell type recognition.

Single-cell RNA profiling identifies diverse cellular responses to EWSR1/FLI1 downregulation in Ewing sarcoma cells

BACKGROUND

The EWSR1/FLI1 gene fusion is the most common rearrangement leading to cell transformation in Ewing sarcoma (ES). Previous studies have indicated that expression at the cellular level is heterogeneous, and that levels of expression may oscillate, conferring different cellular characteristics. In ES the role of EWSR1/FLI1 in regulating subpopulation dynamics is currently unknown.

METHODS

We used siRNA to transiently suppress EWSR1/FLI1 expression and followed population dynamics using both single cell expression profiling, CyTOF and functional assays to define characteristics of exponentially growing ES cells and of ES cells in which EWSR1/FLI1 had been downregulated. Novel transcriptional states with distinct features were assigned using random forest feature selection in combination with machine learning. Cells isolated from ES xenografts in immune-deficient mice were interrogated to determine whether characteristics of specific subpopulations of cells in vitro could be identified. Stem-like characteristics were assessed by primary and secondary spheroid formation in vitro, and invasion/motility was determined for each identified subpopulation. Autophagy was determined by expression profiling, cell sorting and immunohistochemical staining.

RESULTS

We defined a workflow to study EWSR1/FLI1 driven transcriptional states and phenotypes. We tracked EWSR1/FLI1 dependent proliferative activity over time to discover sources of intra-tumoral diversity. Single-cell RNA profiling was used to compare expression profiles in exponentially growing populations (si-Control) or in two dormant populations (D1, D2) in which EWSR1/FLI1 had been suppressed. Three distinct transcriptional states were uncovered contributing to ES intra-heterogeneity. Our predictive model identified ~1% cells in a dormant-like state and ~ 2-4% cells with stem-like and neural stem-like features in an exponentially proliferating ES cell line and in ES xenografts. Following EWSR1/FLI1 knockdown, cells re-entering the proliferative cycle exhibited greater stem-like properties, whereas for those cells remaining quiescent, FAM134B-dependent dormancy may provide a survival mechanism.

CONCLUSIONS

We show that time-dependent changes induced by suppression of oncogenic EWSR1/FLI1 expression induces dormancy, with different subpopulation dynamics. Cells re-entering the proliferative cycle show enhanced stem-like characteristics, whereas those remaining dormant for prolonged periods appear to survive through autophagy. Cells with these characteristics identified in exponentially growing cell populations and in tumor xenografts may confer drug resistance and could potentially contribute to metastasis.

Temporal modelling using single-cell transcriptomics

Methods for profiling genes at the single-cell level have revolutionized our ability to study several biological processes and systems including development, differentiation, response programmes and disease progression. In many of these studies, cells are profiled over time in order to infer dynamic changes in cell states and types, sets of expressed genes, active pathways and key regulators. However, time-series single-cell RNA sequencing (scRNA-seq) also raises several new analysis and modelling issues. These issues range from determining when and how deep to profile cells, linking cells within and between time points, learning continuous trajectories, and integrating bulk and single-cell data for reconstructing models of dynamic networks. In this Review, we discuss several approaches for the analysis and modelling of time-series scRNA-seq, highlighting their steps, key assumptions, and the types of data and biological questions they are most appropriate for.

Deep learning tackles single-cell analysis-a survey of deep learning for scRNA-seq analysis

Since its selection as the method of the year in 2013, single-cell technologies have become mature enough to provide answers to complex research questions. With the growth of single-cell profiling technologies, there has also been a significant increase in data collected from single-cell profilings, resulting in computational challenges to process these massive and complicated datasets. To address these challenges, deep learning (DL) is positioned as a competitive alternative for single-cell analyses besides the traditional machine learning approaches. Here, we survey a total of 25 DL algorithms and their applicability for a specific step in the single cell RNA-seq processing pipeline. Specifically, we establish a unified mathematical representation of variational autoencoder, autoencoder, generative adversarial network and supervised DL models, compare the training strategies and loss functions for these models, and relate the loss functions of these models to specific objectives of the data processing step. Such a presentation will allow readers to choose suitable algorithms for their particular objective at each step in the pipeline. We envision that this survey will serve as an important information portal for learning the application of DL for scRNA-seq analysis and inspire innovative uses of DL to address a broader range of new challenges in emerging multi-omics and spatial single-cell sequencing.

Integrating pathway knowledge with deep neural networks to reduce the dimensionality in single-cell RNA-seq data

Background

Single-cell RNA sequencing (scRNA-seq) data provide valuable insights into cellular heterogeneity which is significantly improving the current knowledge on biology and human disease. One of the main applications of scRNA-seq data analysis is the identification of new cell types and cell states. Deep neural networks (DNNs) are among the best methods to address this problem. However, this performance comes with the trade-off for a lack of interpretability in the results. In this work we propose an intelligible pathway-driven neural network to correctly solve cell-type related problems at single-cell resolution while providing a biologically meaningful representation of the data.

Results

In this study, we explored the deep neural networks constrained by several types of prior biological information, e.g. signaling pathway information, as a way to reduce the dimensionality of the scRNA-seq data. We have tested the proposed biologically-based architectures on thousands of cells of human and mouse origin across a collection of public datasets in order to check the performance of the model. Specifically, we tested the architecture across different validation scenarios that try to mimic how unknown cell types are clustered by the DNN and how it correctly annotates cell types by querying a database in a retrieval problem. Moreover, our approach demonstrated to be comparable to other less interpretable DNN approaches constrained by using protein-protein interactions gene regulation data. Finally, we show how the latent structure learned by the network could be used to visualize and to interpret the composition of human single cell datasets.

Conclusions

Here we demonstrate how the integration of pathways, which convey fundamental information on functional relationships between genes, with DNNs, that provide an excellent classification framework, results in an excellent alternative to learn a biologically meaningful representation of scRNA-seq data. In addition, the introduction of prior biological knowledge in the DNN reduces the size of the network architecture. Comparative results demonstrate a superior performance of this approach with respect to other similar approaches. As an additional advantage, the use of pathways within the DNN structure enables easy interpretability of the results by connecting features to cell functionalities by means of the pathway nodes, as demonstrated with an example with human melanoma tumor cells.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13040-021-00285-4.

MultiCapsNet: A General Framework for Data Integration and Interpretable Classification

The latest progresses of experimental biology have generated a large number of data with different formats and lengths. Deep learning is an ideal tool to deal with complex datasets, but its inherent “black box” nature needs more interpretability. At the same time, traditional interpretable machine learning methods, such as linear regression or random forest, could only deal with numerical features instead of modular features often encountered in the biological field. Here, we present MultiCapsNet (https://github.com/wanglf19/MultiCapsNet), a new deep learning model built on CapsNet and scCapsNet, which possesses the merits such as easy data integration and high model interpretability. To demonstrate the ability of this model as an interpretable classifier to deal with modular inputs, we test MultiCapsNet on three datasets with different data type and application scenarios. Firstly, on the labeled variant call dataset, MultiCapsNet shows a similar classification performance with neural network model, and provides importance scores for data sources directly without an extra importance determination step required by the neural network model. The importance scores generated by these two models are highly correlated. Secondly, on single cell RNA sequence (scRNA-seq) dataset, MultiCapsNet integrates information about protein-protein interaction (PPI), and protein-DNA interaction (PDI). The classification accuracy of MultiCapsNet is comparable to the neural network and random forest model. Meanwhile, MultiCapsNet reveals how each transcription factor (TF) or PPI cluster node contributes to classification of cell type. Thirdly, we made a comparison between MultiCapsNet and SCENIC. The results show several cell type relevant TFs identified by both methods, further proving the validity and interpretability of the MultiCapsNet.

Deep learning-based advances and applications for single-cell RNA-sequencing data analysis

The rapid development of single-cell RNA-sequencing (scRNA-seq) technology has raised significant computational and analytical challenges. The application of deep learning to scRNA-seq data analysis is rapidly evolving and can overcome the unique challenges in upstream (quality control and normalization) and downstream (cell-, gene- and pathway-level) analysis of scRNA-seq data. In the present study, recent advances and applications of deep learning-based methods, together with specific tools for scRNA-seq data analysis, were summarized. Moreover, the future perspectives and challenges of deep-learning techniques regarding the appropriate analysis and interpretation of scRNA-seq data were investigated. The present study aimed to provide evidence supporting the biomedical application of deep learning-based tools and may aid biologists and bioinformaticians in navigating this exciting and fast-moving area.

Computational tools for analyzing single-cell data in pluripotent cell differentiation studies

Single-cell technologies are revolutionizing the ability of researchers to infer the causes and results of biological processes. Although several studies of pluripotent cell differentiation have recently utilized single-cell sequencing data, other aspects related to the optimization of differentiation protocols, their validation, robustness, and usage are still not taking full advantage of single-cell technologies. In this review, we focus on computational approaches for the analysis of single-cell omics and imaging data and discuss their use to address many of the major challenges involved in the development, validation, and use of cells obtained from pluripotent cell differentiation.

A Survey of Autoencoder Algorithms to Pave the Diagnosis of Rare Diseases

Rare diseases (RDs) concern a broad range of disorders and can result from various origins. For a long time, the scientific community was unaware of RDs. Impressive progress has already been made for certain RDs; however, due to the lack of sufficient knowledge, many patients are not diagnosed. Nowadays, the advances in high-throughput sequencing technologies such as whole genome sequencing, single-cell and others, have boosted the understanding of RDs. To extract biological meaning using the data generated by these methods, different analysis techniques have been proposed, including machine learning algorithms. These methods have recently proven to be valuable in the medical field. Among such approaches, unsupervised learning methods via neural networks including autoencoders (AEs) or variational autoencoders (VAEs) have shown promising performances with applications on various type of data and in different contexts, from cancer to healthy patient tissues. In this review, we discuss how AEs and VAEs have been used in biomedical settings. Specifically, we discuss their current applications and the improvements achieved in diagnostic and survival of patients. We focus on the applications in the field of RDs, and we discuss how the employment of AEs and VAEs would enhance RD understanding and diagnosis.

A comparison of deep learning-based pre-processing and clustering approaches for single-cell RNA sequencing data

The emergence of single cell RNA sequencing has facilitated the studied of genomes, transcriptomes and proteomes. As available single-cell RNA-seq datasets are released continuously, one of the major challenges facing traditional RNA analysis tools is the high-dimensional, high-sparsity, high-noise and large-scale characteristics of single-cell RNA-seq data. Deep learning technologies match the characteristics of single-cell RNA-seq data perfectly and offer unprecedented promise. Here, we give a systematic review for most popular single-cell RNA-seq analysis methods and tools based on deep learning models, involving the procedures of data preprocessing (quality control, normalization, data correction, dimensionality reduction and data visualization) and clustering task for downstream analysis. We further evaluate the deep model-based analysis methods of data correction and clustering quantitatively on 11 gold standard datasets. Moreover, we discuss the data preferences of these methods and their limitations, and give some suggestions and guidance for users to select appropriate methods and tools.

Machine Learning Approaches on High Throughput NGS Data to Unveil Mechanisms of Function in Biology and Disease

In this review, the fundamental basis of machine learning (ML) and data mining (DM) are summarized together with the techniques for distilling knowledge from state-of-the-art omics experiments. This includes an introduction to the basic mathematical principles of unsupervised/supervised learning methods, dimensionality reduction techniques, deep neural networks architectures and the applications of these in bioinformatics. Several case studies under evaluation mainly involve next generation sequencing (NGS) experiments, like deciphering gene expression from total and single cell (scRNA-seq) analysis; for the latter, a description of all recent artificial intelligence (AI) methods for the investigation of cell sub-types, biomarkers and imputation techniques are described. Other areas of interest where various ML schemes have been investigated are for providing information regarding transcription factors (TF) binding sites, chromatin organization patterns and RNA binding proteins (RBPs), while analyses on RNA sequence and structure as well as 3D dimensional protein structure predictions with the use of ML are described. Furthermore, we summarize the recent methods of using ML in clinical oncology, when taking into consideration the current omics data with pharmacogenomics to determine personalized treatments. With this review we wish to provide the scientific community with a thorough investigation of main novel ML applications which take into consideration the latest achievements in genomics, thus, unraveling the fundamental mechanisms of biology towards the understanding and cure of diseases.

Nature-Inspired Compressed Sensing for Transcriptomic Profiling From Random Composite Measurements

Transcriptomic profiling is a high-throughput approach to measure gene expression levels under different experimental conditions at different timings. With the development of the related technologies such as single-cell RNA-Seq, the dimensions of gene expression data are increased to hundreds of thousands or more for high-resolution insights. There is a long-lasting challenge in exploiting the relations between transcriptomic profiles and random composite measurements. To address it, we proposed a mathematical framework based on differential evolution (global search) with the help of compressed sensing (local search) termed as DECS. Exploiting the inherent sparse nature of gene expression data, the proposed DECS method can learn the sparse module dictionaries and levels from the low-dimensional random composite measurements for reconstructing the high-dimensional gene expression data with significant orders of magnitude (e.g. 200 × ). Several experiments were conducted to compare DECS with three benchmark methods, demonstrating that the proposed DECS outperforms the benchmark methods and can recover most of the gene expression patterns. The underlying reasons are discussed and illustrated by revealing the related mechanistic insights through extensive benchmarks on nine GSE datasets and their sensitivity analysis.

A primer on machine learning techniques for genomic applications

High throughput sequencing technologies have enabled the study of complex biological aspects at single nucleotide resolution, opening the big data era. The analysis of large volumes of heterogeneous "omic" data, however, requires novel and efficient computational algorithms based on the paradigm of Artificial Intelligence. In the present review, we introduce and describe the most common machine learning methodologies, and lately deep learning, applied to a variety of genomics tasks, trying to emphasize capabilities, strengths and limitations through a simple and intuitive language. We highlight the power of the machine learning approach in handling big data by means of a real life example, and underline how described methods could be relevant in all cases in which large amounts of multimodal genomic data are available.

Dhaka: variational autoencoder for unmasking tumor heterogeneity from single cell genomic data

MOTIVATION

Intra-tumor heterogeneity is one of the key confounding factors in deciphering tumor evolution. Malignant cells exhibit variations in their gene expression, copy numbers and mutation even when originating from a single progenitor cell. Single cell sequencing of tumor cells has recently emerged as a viable option for unmasking the underlying tumor heterogeneity. However, extracting features from single cell genomic data in order to infer their evolutionary trajectory remains computationally challenging due to the extremely noisy and sparse nature of the data.

RESULTS

Here we describe 'Dhaka', a variational autoencoder method which transforms single cell genomic data to a reduced dimension feature space that is more efficient in differentiating between (hidden) tumor subpopulations. Our method is general and can be applied to several different types of genomic data including copy number variation from scDNA-Seq and gene expression from scRNA-Seq experiments. We tested the method on synthetic and six single cell cancer datasets where the number of cells ranges from 250 to 6000 for each sample. Analysis of the resulting feature space revealed subpopulations of cells and their marker genes. The features are also able to infer the lineage and/or differentiation trajectory between cells greatly improving upon prior methods suggested for feature extraction and dimensionality reduction of such data.

AVAILABILITY AND IMPLEMENTATION

All the datasets used in the paper are publicly available and developed software package and supporting info is available on Github https://github.com/MicrosoftGenomics/Dhaka.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Modeling gene regulatory networks using neural network architectures

Gene regulatory networks (GRNs) encode the complex molecular interactions that govern cell identity. Here we propose DeepSEM, a deep generative model that can jointly infer GRNs and biologically meaningful representation of single-cell RNA sequencing (scRNA-seq) data. In particular, we developed a neural network version of the structural equation model (SEM) to explicitly model the regulatory relationships among genes. Benchmark results show that DeepSEM achieves comparable or better performance on a variety of single-cell computational tasks, such as GRN inference, scRNA-seq data visualization, clustering and simulation, compared with the state-of-the-art methods. In addition, the gene regulations predicted by DeepSEM on cell-type marker genes in the mouse cortex can be validated by epigenetic data, which further demonstrates the accuracy and efficiency of our method. DeepSEM can provide a useful and powerful tool to analyze scRNA-seq data and infer a GRN.

Machine learning for perturbational single-cell omics

Cell biology is fundamentally limited in its ability to collect complete data on cellular phenotypes and the wide range of responses to perturbation. Areas such as computer vision and speech recognition have addressed this problem of characterizing unseen or unlabeled conditions with the combined advances of big data, deep learning, and computing resources in the past 5 years. Similarly, recent advances in machine learning approaches enabled by single-cell data start to address prediction tasks in perturbation response modeling. We first define objectives in learning perturbation response in single-cell omics; survey existing approaches, resources, and datasets (https://github.com/theislab/sc-pert); and discuss how a perturbation atlas can enable deep learning models to construct an informative perturbation latent space. We then examine future avenues toward more powerful and explainable modeling using deep neural networks, which enable the integration of disparate information sources and an understanding of heterogeneous, complex, and unseen systems.

scDetect: a rank-based ensemble learning algorithm for cell type identification of single-cell RNA sequencing in cancer

MOTIVATION

Single-cell RNA sequencing (scRNA-seq) has enabled the characterization of different cell types in many tissues and tumor samples. Cell type identification is essential for single-cell RNA profiling, currently transforming the life sciences. Often, this is achieved by searching for combinations of genes that have previously been implicated as being cell-type specific, an approach that is not quantitative and does not explicitly take advantage of other scRNA-seq studies. Batch effects and different data platforms greatly decrease the predictive performance in inter-laboratory and different data type validation.

RESULTS

Here, we present a new ensemble learning method named as "scDetect" that combines gene expression rank-based analysis and a majority vote ensemble machine-learning probability-based prediction method capable of highly accurate classification of cells based on scRNA-seq data by different sequencing platforms. Because of tumor heterogeneity, in order to accurately predict tumor cells in the single cell RNA-seq data, we have also incorporated cell copy number variation consensus clustering and epithelial score in the classification. We applied scDetect to scRNA-seq data from pancreatic tissue, mononuclear cells, and tumor biopsies cells and show that scDetect classified individual cells with high accuracy and better than other publicly available tools.

AVAILABILITY

scDetect is an open source software. Source code and test data is freely available from Github (https://github.com/IVDgenomicslab/scDetect/) and Zenodo (https://zenodo.org/record/4764132#.YKCOlrH5AYN). The examples and tutorial page is at https://ivdgenomicslab.github.io/scDetect-Introduction/.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Using Interpretable Deep Learning to Model Cancer Dependencies

Motivation

Cancer dependencies provide potential drug targets. Unfortunately, dependencies differ among cancers and even individuals. To this end, visible neural networks (VNNs) are promising due to robust performance and the interpretability required for the biomedical field.

Results

We design Biological visible neural network (BioVNN) using pathway knowledge to predict cancer dependencies. Despite having fewer parameters, BioVNN marginally outperforms traditional neural networks (NNs) and converges faster. BioVNN also outperforms an NN based on randomized pathways. More importantly, dependency predictions can be explained by correlating with the neuron output states of relevant pathways, which suggest dependency mechanisms. In feature importance analysis, BioVNN recapitulates known reaction partners and proposes new ones. Such robust and interpretable VNNs may facilitate the understanding of cancer dependency and the development of targeted therapies.

Availability and implementation

Code and data are available at https://github.com/LichtargeLab/BioVNN

Supplementary information

Supplementary data are available at Bioinformatics online.

Identifying cell types from single-cell data based on similarities and dissimilarities between cells

Background

With the development of the technology of single-cell sequence, revealing homogeneity and heterogeneity between cells has become a new area of computational systems biology research. However, the clustering of cell types becomes more complex with the mutual penetration between different types of cells and the instability of gene expression. One way of overcoming this problem is to group similar, related single cells together by the means of various clustering analysis methods. Although some methods such as spectral clustering can do well in the identification of cell types, they only consider the similarities between cells and ignore the influence of dissimilarities on clustering results. This methodology may limit the performance of most of the conventional clustering algorithms for the identification of clusters, it needs to develop special methods for high-dimensional sparse categorical data.

Results

Inspired by the phenomenon that same type cells have similar gene expression patterns, but different types of cells evoke dissimilar gene expression patterns, we improve the existing spectral clustering method for clustering single-cell data that is based on both similarities and dissimilarities between cells. The method first measures the similarity/dissimilarity among cells, then constructs the incidence matrix by fusing similarity matrix with dissimilarity matrix, and, finally, uses the eigenvalues of the incidence matrix to perform dimensionality reduction and employs the K-means algorithm in the low dimensional space to achieve clustering. The proposed improved spectral clustering method is compared with the conventional spectral clustering method in recognizing cell types on several real single-cell RNA-seq datasets.

Conclusions

In summary, we show that adding intercellular dissimilarity can effectively improve accuracy and achieve robustness and that improved spectral clustering method outperforms the traditional spectral clustering method in grouping cells.

RVAgene: Generative modeling of gene expression time series data

Motivation

Methods to model dynamic changes in gene expression at a genome-wide level are not currently sufficient for large (temporally rich or single-cell) datasets. Variational autoencoders offer means to characterize large datasets and have been used effectively to characterize features of single-cell datasets. Here, we extend these methods for use with gene expression time series data.

Results

We present RVAgene: a recurrent variational autoencoder to model gene expression dynamics. RVAgene learns to accurately and efficiently reconstruct temporal gene profiles. It also learns a low dimensional representation of the data via a recurrent encoder network that can be used for biological feature discovery, and from which we can generate new gene expression data by sampling the latent space. We test RVAgene on simulated and real biological datasets, including embryonic stem cell differentiation and kidney injury response dynamics. In all cases, RVAgene accurately reconstructed complex gene expression temporal profiles. Via cross validation, we show that a low-error latent space representation can be learnt using only a fraction of the data. Through clustering and gene ontology term enrichment analysis on the latent space, we demonstrate the potential of RVAgene for unsupervised discovery. In particular, RVAgene identifies new programs of shared gene regulation of Lox family genes in response to kidney injury.

Availability and implementation

All datasets analyzed in this manuscript are publicly available and have been published previously. RVAgene is available in Python, at GitHub: https://github.com/maclean-lab/RVAgene; Zenodo archive: http://doi.org/10.5281/zenodo.4271097.

Supplementary information

Supplementary data are available at Bioinformatics online.

ChrNet: A re-trainable chromosome-based 1D convolutional neural network for predicting immune cell types

Cells from our immune system detect and kill pathogens to protect our body against various diseases. However, current methods for determining cell types have some major limitations, such as being time-consuming and with low throughput, etc. Immune cells that are associated with cancer tissues play a critical role in revealing tumor development. Identifying the immune composition within tumor microenvironment in a timely manner will be helpful in improving clinical prognosis and therapeutic management for cancer. Although unsupervised clustering approaches have been prevailing to process scRNA-seq datasets, their results vary among studies with different input parameters and sizes, and the identification of the cell types of the clusters is still very challenging. Genes in human genome can be aligned to chromosomes with specific orders. Hence, we hypothesize incorporating this information into our learning model will potentially improve the cell type classification performance. In order to utilize gene positional information, we introduced ChrNet, a novel chromosome-specific re-trainable supervised learning method based on one-dimensional convolutional neural network (1D-CNN). By benchmarking with several models, our model shows superior performance in immune cell type profiling with larger than 90% accuracy. It is expected that this approach can become a reference architecture for other cell type classification methods. Our ChrNet tool is available online at: https://github.com/Krisloveless/ChrNet.

Latent representation learning in biology and translational medicine

Current data generation capabilities in the life sciences render scientists in an apparently contradicting situation. While it is possible to simultaneously measure an ever-increasing number of systems parameters, the resulting data are becoming increasingly difficult to interpret. Latent variable modeling allows for such interpretation by learning non-measurable hidden variables from observations. This review gives an overview over the different formal approaches to latent variable modeling, as well as applications at different scales of biological systems, such as molecular structures, intra- and intercellular regulatory up to physiological networks. The focus is on demonstrating how these approaches have enabled interpretable representations and ultimately insights in each of these domains. We anticipate that a wider dissemination of latent variable modeling in the life sciences will enable a more effective and productive interpretation of studies based on heterogeneous and high-dimensional data modalities.

Supervised Adversarial Alignment of Single-Cell RNA-seq Data

Dimensionality reduction is an important first step in the analysis of single-cell RNA-sequencing (scRNA-seq) data. In addition to enabling the visualization of the profiled cells, such representations are used by many downstream analyses methods ranging from pseudo-time reconstruction to clustering to alignment of scRNA-seq data from different experiments, platforms, and laboratories. Both supervised and unsupervised methods have been proposed to reduce the dimension of scRNA-seq. However, all methods to date are sensitive to batch effects. When batches correlate with cell types, as is often the case, their impact can lead to representations that are batch rather than cell-type specific. To overcome this, we developed a domain adversarial neural network model for learning a reduced dimension representation of scRNA-seq data. The adversarial model tries to simultaneously optimize two objectives. The first is the accuracy of cell-type assignment and the second is the inability to distinguish the batch (domain). We tested the method by using the resulting representation to align several different data sets. As we show, by overcoming batch effects our method was able to correctly separate cell types, improving on several prior methods suggested for this task. Analysis of the top features used by the network indicates that by taking the batch impact into account, the reduced representation is much better able to focus on key genes for each cell type.

Sparsely-connected autoencoder (SCA) for single cell RNAseq data mining

Single-cell RNA sequencing (scRNAseq) is an essential tool to investigate cellular heterogeneity. Thus, it would be of great interest being able to disclose biological information belonging to cell subpopulations, which can be defined by clustering analysis of scRNAseq data. In this manuscript, we report a tool that we developed for the functional mining of single cell clusters based on Sparsely-Connected Autoencoder (SCA). This tool allows uncovering hidden features associated with scRNAseq data. We implemented two new metrics, QCC (Quality Control of Cluster) and QCM (Quality Control of Model), which allow quantifying the ability of SCA to reconstruct valuable cell clusters and to evaluate the quality of the neural network achievements, respectively. Our data indicate that SCA encoded space, derived by different experimentally validated data (TF targets, miRNA targets, Kinase targets, and cancer-related immune signatures), can be used to grasp single cell cluster-specific functional features. In our implementation, SCA efficacy comes from its ability to reconstruct only specific clusters, thus indicating only those clusters where the SCA encoding space is a key element for cells aggregation. SCA analysis is implemented as module in rCASC framework and it is supported by a GUI to simplify it usage for biologists and medical personnel.

Applying Machine Learning for Integration of Multi-Modal Genomics Data and Imaging Data to Quantify Heterogeneity in Tumour Tissues

With rapid advances in experimental instruments and protocols, imaging and sequencing data are being generated at an unprecedented rate contributing significantly to the current and coming big biomedical data. Meanwhile, unprecedented advances in computational infrastructure and analysis algorithms are realizing image-based digital diagnosis not only in radiology and cardiology but also oncology and other diseases. Machine learning methods, especially deep learning techniques, are already and broadly implemented in diverse technological and industrial sectors, but their applications in healthcare are just starting. Uniquely in biomedical research, a vast potential exists to integrate genomics data with histopathological imaging data. The integration has the potential to extend the pathologist's limits and boundaries, which may create breakthroughs in diagnosis, treatment, and monitoring at molecular and tissue levels. Moreover, the applications of genomics data are realizing the potential for personalized medicine, making diagnosis, treatment, monitoring, and prognosis more accurate. In this chapter, we discuss machine learning methods readily available for digital pathology applications, new prospects of integrating spatial genomics data on tissues with tissue morphology, and frontier approaches to combining genomics data with pathological imaging data. We present perspectives on how artificial intelligence can be synergized with molecular genomics and imaging to make breakthroughs in biomedical and translational research for computer-aided applications.

Pathogenic gene prediction based on network embedding

In disease research, the study of gene-disease correlation has always been an important topic. With the emergence of large-scale connected data sets in biology, we use known correlations between the entities, which may be from different sets, to build a biological heterogeneous network and propose a new network embedded representation algorithm to calculate the correlation between disease and genes, using the correlation score to predict pathogenic genes. Then, we conduct several experiments to compare our method to other state-of-the-art methods. The results reveal that our method achieves better performance than the traditional methods.

GCNG: graph convolutional networks for inferring gene interaction from spatial transcriptomics data

Most methods for inferring gene-gene interactions from expression data focus on intracellular interactions. The availability of high-throughput spatial expression data opens the door to methods that can infer such interactions both within and between cells. To achieve this, we developed Graph Convolutional Neural networks for Genes (GCNG). GCNG encodes the spatial information as a graph and combines it with expression data using supervised training. GCNG improves upon prior methods used to analyze spatial transcriptomics data and can propose novel pairs of extracellular interacting genes. The output of GCNG can also be used for downstream analysis including functional gene assignment.Supporting website with software and data: https://github.com/xiaoyeye/GCNG .