Machine Intelligence in Single-Cell Data Analysis: Advances and New Challenges

Single cell RNA sequencing improves the next generation of approaches to AML treatment: challenges and perspectives

Acute myeloid leukemia (AML) is caused by altered maturation and differentiation of myeloid blasts, as well as transcriptional/epigenetic alterations, all leading to excessive proliferation of malignant blood cells in the bone marrow. Tumor heterogeneity due to the acquisition of new somatic alterations leads to a high rate of resistance to current therapies or reduces the efficacy of hematopoietic stem cell transplantation (HSCT), thus increasing the risk of relapse and mortality. Single-cell RNA sequencing (scRNA-seq) will enable the classification of AML and guide treatment approaches by profiling patients with different facets of the same disease, stratifying risk, and identifying new potential therapeutic targets at the time of diagnosis or after treatment. ScRNA-seq allows the identification of quiescent stem-like cells, and leukemia stem cells responsible for resistance to therapeutic approaches and relapse after treatment. This method also introduces the factors and mechanisms that enhance the efficacy of the HSCT process. Generated data of the transcriptional profile of the AML could even allow the development of cancer vaccines and CAR T-cell therapies while saving valuable time and alleviating dangerous side effects of chemotherapy and HSCT in vivo. However, scRNA-seq applications face various challenges such as a large amount of data for high-dimensional analysis, technical noise, batch effects, and finding small biological patterns, which could be improved in combination with artificial intelligence models.

scGO: interpretable deep neural network for cell status annotation and disease diagnosis

Machine learning has emerged as a transformative tool for elucidating cellular heterogeneity in single-cell RNA sequencing. However, a significant challenge lies in the "black box" nature of deep learning models, which obscures the decision-making process and limits interpretability in cell status annotation. In this study, we introduced scGO, a Gene Ontology (GO)-inspired deep learning framework designed to provide interpretable cell status annotation for scRNA-seq data. scGO employs sparse neural networks to leverage the intrinsic biological relationships among genes, transcription factors, and GO terms, significantly augmenting interpretability and reducing computational cost. scGO outperforms state-of-the-art methods in the precise characterization of cell subtypes across diverse datasets. Our extensive experimentation across a spectrum of scRNA-seq datasets underscored the remarkable efficacy of scGO in disease diagnosis, prediction of developmental stages, and evaluation of disease severity and cellular senescence status. Furthermore, we incorporated in silico individual gene manipulations into the scGO model, introducing an additional layer for discovering therapeutic targets. Our results provide an interpretable model for accurately annotating cell status, capturing latent biological knowledge, and informing clinical practice.

Integrating Molecular Perspectives: Strategies for Comprehensive Multi-Omics Integrative Data Analysis and Machine Learning Applications in Transcriptomics, Proteomics, and Metabolomics

With the advent of high-throughput technologies, the field of omics has made significant strides in characterizing biological systems at various levels of complexity. Transcriptomics, proteomics, and metabolomics are the three most widely used omics technologies, each providing unique insights into different layers of a biological system. However, analyzing each omics data set separately may not provide a comprehensive understanding of the subject under study. Therefore, integrating multi-omics data has become increasingly important in bioinformatics research. In this article, we review strategies for integrating transcriptomics, proteomics, and metabolomics data, including co-expression analysis, metabolite-gene networks, constraint-based models, pathway enrichment analysis, and interactome analysis. We discuss combined omics integration approaches, correlation-based strategies, and machine learning techniques that utilize one or more types of omics data. By presenting these methods, we aim to provide researchers with a better understanding of how to integrate omics data to gain a more comprehensive view of a biological system, facilitating the identification of complex patterns and interactions that might be missed by single-omics analyses.

Mouse Corneal Immune Cell Heterogeneity Revealed by Single-Cell RNA Sequencing

Purpose

This study aimed to define the heterogeneity, spatial localization, and functional roles of immune cells in the mouse cornea using single-cell RNA sequencing (scRNA-seq) and immunofluorescent staining.

Methods

Enriched mouse corneal immune cells (C57BL/6 strain, age 16-20 weeks) underwent single-cell RNA sequencing library preparation, sequencing, and analysis with Seurat, Monocle 3, and CellChat packages in R. Pathway analysis used Qiagen Ingenuity Pathway Analysis software. Immunostaining confirmed cell distribution.

Results

We identified 14 distinct immune cell clusters (56% myeloid and 44% lymphoid). Myeloid populations included resident macrophages, conventional dendritic cells (cDC2s), Langerhans cells, neutrophils, monocytes, and mast cells. Additionally, lymphocyte subsets (B, CD8, CD4, γδT, natural killer, natural killer T, and group 2 innate lymphoid cells) were found. We also found three new subtypes of resident macrophages in the cornea. Trajectory analysis suggested a differentiation pathway from monocytes to conventional dendritic cells, resident macrophages, and LCs. Intercellular communication network analysis using cord diagram identified amyloid precursor protein, chemokine (C-C motif) ligands (2, 3, 4, 6, 7, 9, and 12), Cxcl2, Mif, Tnf, Tgfb1, Igf1, and Il10 as prominent ligands involved in these interactions. Sexually dimorphic gene expression patterns were observed, with male myeloid cells expressing genes linked to immune regulation (Egr1, Foxp1, Mrc1, and Il1rn) and females showing higher expression of antigen presentation genes (Clic1, Psmb8, and Psmb9). Finally, immunostaining confirmed the spatial distribution of these cell populations within the cornea.

Conclusions

This study unveils a diverse immune landscape in the mouse cornea, with evidence for cell differentiation and sex-based differences. Immunostaining validates the spatial distribution of these populations, furthering our knowledge of corneal immune function.

Cancer marker TNFRSF1A: From single‑cell heterogeneity of renal cell carcinoma to functional validation

During the progression of renal cell carcinoma (RCC), tumor growth, metastasis and treatment response heterogeneity are regulated by both the tumor itself and the tumor microenvironment (TME). The aim of the present study was to investigate the role of the TME in RCC and construct a crosstalk network for clear cell RCC (ccRCC). An additional aim was to evaluate whether TNF receptor superfamily member 1A (TNFRSF1A) is a potential therapeutic target for ccRCC. Single-cell data analysis of RCC was performed using the GSE152938 dataset, focusing on key cellular components and their involvement in the ccRCC TME. Additionally, cell-cell communication was analyzed to elucidate the complex network of the ccRCC microenvironment. Analyses of data from The Cancer Genome Atlas and Clinical Proteomic Tumor Analysis Consortium databases were performed to further mine the key TNF receptor genes, with a particular focus on the prediction and assessment of the cancer-associated features of TNFRSF1A. In addition, following the silencing of TNFRSF1A using small interfering RNA in the 786-O ccRCC cell line, a number of in vitro experiments were conducted to further investigate the cancer-promoting characteristics of TNFRSF1A. These included 5-ethynyl-2'-deoxyuridine incorporation, Cell Counting Kit-8, colony formation, Transwell, cell cycle and apoptosis assays. The TNF signaling pathway was found to have a critical role in the development of ccRCC. Based on the specific crosstalk identified between TNF and TNFRSF1A, the communication of this signaling pathway within the TME was elucidated. The results of the cellular phenotype experiments indicated that TNFRSF1A promotes the proliferation, migration and invasion of ccRCC cells. Consequently, it is proposed that targeting TNFRSF1A may disrupt tumor progression and serve as a therapeutic strategy. In conclusion, by understanding the TME and identifying significant crosstalk within the TNF signaling pathway, the potential of TNFRSF1A as a therapeutic target is highlighted. This may facilitate an advance in precision medicine and improve the prognosis for patients with RCC.

scGPT: toward building a foundation model for single-cell multi-omics using generative AI

Generative pretrained models have achieved remarkable success in various domains such as language and computer vision. Specifically, the combination of large-scale diverse datasets and pretrained transformers has emerged as a promising approach for developing foundation models. Drawing parallels between language and cellular biology (in which texts comprise words; similarly, cells are defined by genes), our study probes the applicability of foundation models to advance cellular biology and genetic research. Using burgeoning single-cell sequencing data, we have constructed a foundation model for single-cell biology, scGPT, based on a generative pretrained transformer across a repository of over 33 million cells. Our findings illustrate that scGPT effectively distills critical biological insights concerning genes and cells. Through further adaptation of transfer learning, scGPT can be optimized to achieve superior performance across diverse downstream applications. This includes tasks such as cell type annotation, multi-batch integration, multi-omic integration, perturbation response prediction and gene network inference.

Single-Cell RNA Sequencing and Its Applications in Pituitary Research

BACKGROUND

Mounting evidence underscores the significance of cellular diversity within the endocrine system and the intricate interplay between different cell types and tissues, essential for preserving physiological balance and influencing disease trajectories. The pituitary gland, a central player in the endocrine orchestra, exemplifies this complexity with its assortment of hormone-secreting and nonsecreting cells.

SUMMARY

The pituitary gland houses several types of cells responsible for hormone production, alongside nonsecretory cells like fibroblasts and endothelial cells, each playing a crucial role in the gland's function and regulatory mechanisms. Despite the acknowledged importance of these cellular interactions, the detailed mechanisms by which they contribute to pituitary gland physiology and pathology remain largely uncharted. The last decade has seen the emergence of groundbreaking technologies such as single-cell RNA sequencing, offering unprecedented insights into cellular heterogeneity and interactions. However, the application of this advanced tool in exploring the pituitary gland's complexities has been scant. This review provides an overview of this methodology, highlighting its strengths and limitations, and discusses future possibilities for employing it to deepen our understanding of the pituitary gland and its dysfunction in disease states.

KEY MESSAGE

Single-cell RNA sequencing technology offers an unprecedented means to study the heterogeneity and interactions of pituitary cells, though its application has been limited thus far. Further utilization of this tool will help uncover the complex physiological and pathological mechanisms of the pituitary, advancing research and treatment of pituitary diseases.

HyperCell: Advancing Cell Type Classification with Hyperdimensional Computing

Single-cell RNA sequencing (scRNA-seq) has revolutionized genomics, enabling the exploration of cellular heterogeneity at an unprecedented resolution. However, scRNA-seq data poses challenges, including high dimensionality, inherent noise, and sparse gene expression. In this paper, we propose a novel approach, utilizing hyperdimensional computing, to enhance cell type classification accuracy in scRNA-seq datasets. We use the QuantHD method for high-dimensional hypervector encoding and iterative training. Experiments on diverse datasets subjected to both split by batch and random split settings demonstrate the superiority of our proposed model in handling noise and outperforming established classification methods such as XGBoost, Seurat reference mapping, and scANVI. Our findings highlight the potential of hyperdimensional computing to advance single-cell data analysis, yielding deep insights into cellular dynamics, tissue functions, and disease mechanisms. This work paves the way for more accurate cell type annotation and brings new opportunities for biomedical research and personalized medicine.

Applications of single‑cell omics and spatial transcriptomics technologies in gastric cancer (Review)

Gastric cancer (GC) is a prominent contributor to global cancer-related mortalities, and a deeper understanding of its molecular characteristics and tumor heterogeneity is required. Single-cell omics and spatial transcriptomics (ST) technologies have revolutionized cancer research by enabling the exploration of cellular heterogeneity and molecular landscapes at the single-cell level. In the present review, an overview of the advancements in single-cell omics and ST technologies and their applications in GC research is provided. Firstly, multiple single-cell omics and ST methods are discussed, highlighting their ability to offer unique insights into gene expression, genetic alterations, epigenomic modifications, protein expression patterns and cellular location in tissues. Furthermore, a summary is provided of key findings from previous research on single-cell omics and ST methods used in GC, which have provided valuable insights into genetic alterations, tumor diagnosis and prognosis, tumor microenvironment analysis, and treatment response. In summary, the application of single-cell omics and ST technologies has revealed the levels of cellular heterogeneity and the molecular characteristics of GC, and holds promise for improving diagnostics, personalized treatments and patient outcomes in GC.

From cancer big data to treatment: Artificial intelligence in cancer research

In recent years, developing the idea of "cancer big data" has emerged as a result of the significant expansion of various fields such as clinical research, genomics, proteomics and public health records. Advances in omics technologies are making a significant contribution to cancer big data in biomedicine and disease diagnosis. The increasingly availability of extensive cancer big data has set the stage for the development of multimodal artificial intelligence (AI) frameworks. These frameworks aim to analyze high-dimensional multi-omics data, extracting meaningful information that is challenging to obtain manually. Although interpretability and data quality remain critical challenges, these methods hold great promise for advancing our understanding of cancer biology and improving patient care and clinical outcomes. Here, we provide an overview of cancer big data and explore the applications of both traditional machine learning and deep learning approaches in cancer genomic and proteomic studies. We briefly discuss the challenges and potential of AI techniques in the integrated analysis of omics data, as well as the future direction of personalized treatment options in cancer.

A machine learning one-class logistic regression model to predict stemness for single cell transcriptomics and spatial omics

Cell annotation is a crucial methodological component to interpreting single cell and spatial omics data. These approaches were developed for single cell analysis but are often biased, manually curated and yet unproven in spatial omics. Here we apply a stemness model for assessing oncogenic states to single cell and spatial omic cancer datasets. This one-class logistic regression machine learning algorithm is used to extract transcriptomic features from non-transformed stem cells to identify dedifferentiated cell states in tumors. We found this method identifies single cell states in metastatic tumor cell populations without the requirement of cell annotation. This machine learning model identified stem-like cell populations not identified in single cell or spatial transcriptomic analysis using existing methods. For the first time, we demonstrate the application of a ML tool across five emerging spatial transcriptomic and proteomic technologies to identify oncogenic stem-like cell types in the tumor microenvironment.

Machine Learning Analysis of Alzheimer's Disease Single-Cell RNA-Sequencing Data across Cortex and Hippocampus Regions

Advancements in molecular biology have revolutionized our understanding of complex diseases, with Alzheimer's disease being a prime example. Single-cell sequencing, currently the most suitable technology, facilitates profoundly detailed disease analysis at the cellular level. Prior research has established that the pathology of Alzheimer's disease varies across different brain regions and cell types. In parallel, only machine learning has the capacity to address the myriad challenges presented by such studies, where the integration of large-scale data and numerous experiments is required to extract meaningful knowledge. Our methodology utilizes single-cell RNA sequencing data from healthy and Alzheimer's disease (AD) samples, focused on the cortex and hippocampus regions in mice. We designed three distinct case studies and implemented an ensemble feature selection approach through machine learning, also performing an analysis of distinct age-related datasets to unravel age-specific effects, showing differential gene expression patterns within each condition. Important evidence was reported, such as enrichment in central nervous system development and regulation of oligodendrocyte differentiation between the hippocampus and cortex of 6-month-old AD mice as well as regulation of epinephrine secretion and dendritic spine morphogenesis in 15-month-old AD mice. Our outcomes from all three of our case studies illustrate the capacity of machine learning strategies when applied to single-cell data, revealing critical insights into Alzheimer's disease.

Yeast cell detection using fuzzy automatic contrast enhancement (FACE) and you only look once (YOLO)

In contemporary biomedical research, the accurate automatic detection of cells within intricate microscopic imagery stands as a cornerstone for scientific advancement. Leveraging state-of-the-art deep learning techniques, this study introduces a novel amalgamation of Fuzzy Automatic Contrast Enhancement (FACE) and the You Only Look Once (YOLO) framework to address this critical challenge of automatic cell detection. Yeast cells, representing a vital component of the fungi family, hold profound significance in elucidating the intricacies of eukaryotic cells and human biology. The proposed methodology introduces a paradigm shift in cell detection by optimizing image contrast through optimal fuzzy clustering within the FACE approach. This advancement mitigates the shortcomings of conventional contrast enhancement techniques, minimizing artifacts and suboptimal outcomes. Further enhancing contrast, a universal contrast enhancement variable is ingeniously introduced, enriching image clarity with automatic precision. Experimental validation encompasses a diverse range of yeast cell images subjected to rigorous quantitative assessment via Root-Mean-Square Contrast and Root-Mean-Square Deviation (RMSD). Comparative analyses against conventional enhancement methods showcase the superior performance of the FACE-enhanced images. Notably, the integration of the innovative You Only Look Once (YOLOv5) facilitates automatic cell detection within a finely partitioned grid system. This leads to the development of two models-one operating on pristine raw images, the other harnessing the enriched landscape of FACE-enhanced imagery. Strikingly, the FACE enhancement achieves exceptional accuracy in automatic yeast cell detection by YOLOv5 across both raw and enhanced images. Comprehensive performance evaluations encompassing tenfold accuracy assessments and confidence scoring substantiate the robustness of the FACE-YOLO model. Notably, the integration of FACE-enhanced images serves as a catalyst, significantly elevating the performance of YOLOv5 detection. Complementing these efforts, OpenCV lends computational acumen to delineate precise yeast cell contours and coordinates, augmenting the precision of cell detection.

Challenges and Opportunities in Building a Global Representative Single-Cell and Spatial Atlas in Cancer

SUMMARY

Cancer health disparities are complex and a mixture of factors that need to be accounted for in both our planning, implementation, and execution across all researchers, especially in single-cell and spatial technologies, which have a higher burden for adoption in low- and middle-income countries. This commentary tackles the hurdles these technologies face in creating a diverse, representative atlas of cancer and is a call to arms for a strategic plan toward inclusivity across all global populations.

LVPT: Lazy Velocity Pseudotime Inference Method

The emergence of RNA velocity has enriched our understanding of the dynamic transcriptional landscape within individual cells. In light of this breakthrough, we embarked on integrating RNA velocity with cellular pseudotime inference, aiming to improve the prediction of cell orders along biological trajectories beyond existing methods. Here, we developed LVPT, a novel method for pseudotime and trajectory inference. LVPT introduces a lazy probability to indicate the probability that the cell stays in the original state and calculates the transition matrix based on RNA velocity to provide the probability and direction of cell differentiation. LVPT shows better and comparable performance of pseudotime inference compared with other existing methods on both simulated datasets with different structures and real datasets. The validation results were consistent with prior knowledge, indicating that LVPT is an accurate and efficient method for pseudotime inference.

Computational approaches in rheumatic diseases - Deciphering complex spatio-temporal cell interactions

Inflammatory arthritis, including rheumatoid (RA), and psoriatic (PsA) arthritis, are clinically and immunologically heterogeneous diseases with no identified cure. Chronic inflammation of the synovial tissue ushers loss of function of the joint that severely impacts the patient's quality of life, eventually leading to disability and life-threatening comorbidities. The pathogenesis of synovial inflammation is the consequence of compounded immune and stromal cell interactions influenced by genetic and environmental factors. Deciphering the complexity of the synovial cellular landscape has accelerated primarily due to the utilisation of bulk and single cell RNA sequencing. Particularly the capacity to generate cell-cell interaction networks could reveal evidence of previously unappreciated processes leading to disease. However, there is currently a lack of universal nomenclature as a result of varied experimental and technological approaches that discombobulates the study of synovial inflammation. While spatial transcriptomic analysis that combines anatomical information with transcriptomic data of synovial tissue biopsies promises to provide more insights into disease pathogenesis, in vitro functional assays with single-cell resolution will be required to validate current bioinformatic applications. In order to provide a comprehensive approach and translate experimental data to clinical practice, a combination of clinical and molecular data with machine learning has the potential to enhance patient stratification and identify individuals at risk of arthritis that would benefit from early therapeutic intervention. This review aims to provide a comprehensive understanding of the effect of computational approaches in deciphering synovial inflammation pathogenesis and discuss the impact that further experimental and novel computational tools may have on therapeutic target identification and drug development.

The biological significance of cuproptosis-key gene MTF1 in pan-cancer and its inhibitory effects on ROS-mediated cell death of liver hepatocellular carcinoma

Metal regulatory transcription factor 1 (MTF1) has been reported to be correlated with several human diseases, especially like cancers. Exploring the underlying mechanisms and biological functions of MTF1 could provide novel strategies for clinical diagnosis and therapy of cancers. In this study, we conducted the comprehensive analysis to evaluate the profiles of MTF1 in pan-cancer. For example, TIMER2.0, TNMplot and GEPIA2.0 were employed to analyze the expression values of MTF1 in pan-cancer. The methylation levels of MTF1 were evaluated via UALCAN and DiseaseMeth version 2.0 databases. The mutation profiles of MTF1 in pan-cancers were analyzed using cBioPortal. GEPIA2.0, Kaplan-Meier plotter and cBioPortal were also used to explore the roles of MTF1 in cancer prognosis. We found that high MTF1 expression was related to poor prognosis of liver hepatocellular carcinoma (LIHC) and brain lower grade glioma (LGG). Also, high expression level of MTF1 was associated with good prognosis of kidney renal clear cell carcinoma (KIRC), lung cancer, ovarian cancer and breast cancer. We investigated the genetic alteration and methylation levels of MTF1 between the primary tumor and normal tissues. The relationship between MTF1 expression and several immune cells was analyzed, including T cell CD8 + and dendritic cells (DC). Mechanically, MTF1-interacted molecules might participate in the regulation of metabolism-related pathways, such as peptidyl-serine phosphorylation, negative regulation of cellular amide metabolic process and peptidyl-threonine phosphorylation. Single cell sequencing indicated that MTF1 was associated with angiogenesis, DNA repair and cell invasion. In addition, in vitro experiment indicated knockdown of MTF1 resulted in the suppressed cell proliferation, increased reactive oxygen species (ROS) and promoted cell death in LIHC cells HepG2 and Huh7. Taken together, this pan-cancer analysis of MTF1 has implicated that MTF1 could play an essential role in the progression of various human cancers.

Single-Cell Analysis in the Omics Era: Technologies and Applications in Cancer

Cancer molecular profiling obtained with conventional bulk sequencing describes average alterations obtained from the entire cellular population analyzed. In the era of precision medicine, this approach is unable to track tumor heterogeneity and cannot be exploited to unravel the biological processes behind clonal evolution. In the last few years, functional single-cell omics has improved our understanding of cancer heterogeneity. This approach requires isolation and identification of single cells starting from an entire population. A cell suspension obtained by tumor tissue dissociation or hematological material can be manipulated using different techniques to separate individual cells, employed for single-cell downstream analysis. Single-cell data can then be used to analyze cell-cell diversity, thus mapping evolving cancer biological processes. Despite its unquestionable advantages, single-cell analysis produces massive amounts of data with several potential biases, stemming from cell manipulation and pre-amplification steps. To overcome these limitations, several bioinformatic approaches have been developed and explored. In this work, we provide an overview of this entire process while discussing the most recent advances in the field of functional omics at single-cell resolution.

Variability of fluorescence intensity distribution measured by flow cytometry is influenced by cell size and cell cycle progression

The distribution of fluorescence signals measured with flow cytometry can be influenced by several factors, including qualitative and quantitative properties of the used fluorochromes, optical properties of the detection system, as well as the variability within the analyzed cell population itself. Most of the single cell samples prepared from in vitrocultures or clinical specimens contain a variable cell cycle component. Cell cycle, together with changes in the cell size, are two of the factors that alter the functional properties of analyzed cells and thus affect the interpretation of obtained results. Here, we describe the association between cell cycle status and cell size, and the variability in the distribution of fluorescence intensity as determined with flow cytometry, at population scale. We show that variability in the distribution of background and specific fluorescence signals is related to the cell cycle state of the selected population, with the 10% low fluorescence signal fraction enriched mainly in cells in their G0/G1 cell cycle phase, and the 10% high fraction containing cells mostly in the G2/M phase. Therefore we advise using caution and additional experimental validation when comparing populations defined by fractions at both ends of fluorescence signal distribution to avoid biases caused by the effect of cell cycle and cell size.

Artificial Intelligence-Assisted Transcriptomic Analysis to Advance Cancer Immunotherapy

The emergence of immunotherapy has dramatically changed the cancer treatment paradigm and generated tremendous promise in precision medicine. However, cancer immunotherapy is greatly limited by its low response rates and immune-related adverse events. Transcriptomics technology is a promising tool for deciphering the molecular underpinnings of immunotherapy response and therapeutic toxicity. In particular, applying single-cell RNA-seq (scRNA-seq) has deepened our understanding of tumor heterogeneity and the microenvironment, providing powerful help for developing new immunotherapy strategies. Artificial intelligence (AI) technology in transcriptome analysis meets the need for efficient handling and robust results. Specifically, it further extends the application scope of transcriptomic technologies in cancer research. AI-assisted transcriptomic analysis has performed well in exploring the underlying mechanisms of drug resistance and immunotherapy toxicity and predicting therapeutic response, with profound significance in cancer treatment. In this review, we summarized emerging AI-assisted transcriptomic technologies. We then highlighted new insights into cancer immunotherapy based on AI-assisted transcriptomic analysis, focusing on tumor heterogeneity, the tumor microenvironment, immune-related adverse event pathogenesis, drug resistance, and new target discovery. This review summarizes solid evidence for immunotherapy research, which might help the cancer research community overcome the challenges faced by immunotherapy.

Identification of Human Cell Cycle Phase Markers Based on Single-Cell RNA-Seq Data by Using Machine Learning Methods

The cell cycle is composed of a series of ordered, highly regulated processes through which a cell grows and duplicates its genome and eventually divides into two daughter cells. According to the complex changes in cell structure and biosynthesis, the cell cycle is divided into four phases: gap 1 (G1), DNA synthesis (S), gap 2 (G2), and mitosis (M). Determining which cell cycle phases a cell is in is critical to the research of cancer development and pharmacy for targeting cell cycle. However, current detection methods have the following problems: (1) they are complicated and time consuming to perform, and (2) they cannot detect the cell cycle on a large scale. Rapid developments in single-cell technology have made dissecting cells on a large scale possible with unprecedented resolution. In the present research, we construct efficient classifiers and identify essential gene biomarkers based on single-cell RNA sequencing data through Boruta and three feature ranking algorithms (e.g., mRMR, MCFS, and SHAP by LightGBM) by utilizing four advanced classification algorithms. Meanwhile, we mine a series of classification rules that can distinguish different cell cycle phases. Collectively, we have provided a novel method for determining the cell cycle and identified new potential cell cycle-related genes, thereby contributing to the understanding of the processes that regulate the cell cycle.

Comprehensive analyses of PDHA1 that serves as a predictive biomarker for immunotherapy response in cancer

Recent studies have proposed that pyruvate dehydrogenase E1 component subunit alpha (PDHA1), a cuproptosis-key gene, is crucial to the glucose metabolism reprogram of tumor cells. However, the functional roles and regulated mechanisms of PDHA1 in multiple cancers are largely unknown. The Cancer Genome Atlas (TCGA), GEPIA2, and cBioPortal databases were utilized to elucidate the function of PDHA1 in 33 tumor types. We found that PDHA1 was aberrantly expressed in most cancer types. Lung adenocarcinoma (LUAD) patients with high PDHA1 levels were significantly correlated with poor prognosis of overall survival (OS) and first progression (FP). Kidney renal clear cell carcinoma (KIRC) patients with low PDHA1 levels displayed poor OS and disease-free survival (DFS). However, for stomach adenocarcinoma (STAD), the downregulated PDHA1 expression predicted a good prognosis in patients. Moreover, we evaluated the mutation diversity of PDHA1 in cancers and their association with prognosis. We also analyzed the protein phosphorylation and DNA methylation of PDHA1 in various tumors. The PDHA1 expression was negatively correlated with tumor-infiltrating immune cells, such as myeloid dendritic cells (DCs), B cells, and T cells in pan-cancers. Mechanically, we used single-cell sequencing to discover that the PDHA1 expression had a close link with several cancer-associated signaling pathways, such as DNA damage, cell invasion, and angiogenesis. At last, we conducted a co-expressed enrichment analysis and showed that aberrantly expressed PDHA1 participated in the regulation of mitochondrial signaling pathways, including oxidative phosphorylation, cellular respiration, and electron transfer activity. In summary, PDHA1 could be a prognostic and immune-associated biomarker in multiple cancers.

Panoramic Manifold Projection (Panoramap) for Single-Cell Data Dimensionality Reduction and Visualization

Nonlinear dimensionality reduction (NLDR) methods such as t-Distributed Stochastic Neighbour Embedding (t-SNE) and Uniform Manifold Approximation and Projection (UMAP) have been widely used for biological data exploration, especially in single-cell analysis. However, the existing methods have drawbacks in preserving data's geometric and topological structures. A high-dimensional data analysis method, called Panoramic manifold projection (Panoramap), was developed as an enhanced deep learning framework for structure-preserving NLDR. Panoramap enhances deep neural networks by using cross-layer geometry-preserving constraints. The constraints constitute the loss for deep manifold learning and serve as geometric regularizers for NLDR network training. Therefore, Panoramap has better performance in preserving global structures of the original data. Here, we apply Panoramap to single-cell datasets and show that Panoramap excels at delineating the cell type lineage/hierarchy and can reveal rare cell types. Panoramap can facilitate trajectory inference and has the potential to aid in the early diagnosis of tumors. Panoramap gives improved and more biologically plausible visualization and interpretation of single-cell data. Panoramap can be readily used in single-cell research domains and other research fields that involve high dimensional data analysis.

Set Norm and Equivariant Skip Connections: Putting the Deep in Deep Sets

Permutation invariant neural networks are a promising tool for making predictions from sets. However, we show that existing permutation invariant architectures, Deep Sets and Set Transformer, can suffer from vanishing or exploding gradients when they are deep. Additionally, layer norm, the normalization of choice in Set Transformer, can hurt performance by removing information useful for prediction. To address these issues, we introduce the "clean path principle" for equivariant residual connections and develop set norm (sn), a normalization tailored for sets. With these, we build Deep Sets++ and Set Transformer++, models that reach high depths with better or comparable performance than their original counterparts on a diverse suite of tasks. We additionally introduce Flow-RBC, a new single-cell dataset and real-world application of permutation invariant prediction. We open-source our data and code here: https://github.com/rajesh-lab/deep_permutation_invariant.

Temporal Regulation of Gene Expression in Post-Mitotic Cells is Revealed from a Synchronized Population of C. elegans Larvae

Unsupervised Uniform Manifold Approximation and Projection (UMAP) plots of single cell sequencing data from synchronized Caenorhabditis elegans larvae yield tissue-specific data clusters, some of which are plotted as elongated archipelagos. These archipelagos likely represent a single cell type. I show that the pharyngeal archipelagos express a myriad of asynchronous temporally regulated genes, which likely accounts for their elongated topology. With one archipelago, I show that there is a high correlation between a) the base pair distance between the binding sites of an archipelago-specific transcription factor (HLH-6) and the transcriptional start site of the targeted genes and b) the timing of peak gene expression of those genes that are expressed in an archipelago-specific manner. Despite the correlation being made with only four genes, it prompts the hypothesis that the physical distance between a transcription factor and the relevant transcription start site may be an important factor in determining the temporal onset of transcription and transcript abundance.

DNA sequencing: an overview of solid-state and biological nanopore-based methods

The field of sequencing is a topic of significant interest since its emergence and has become increasingly important over time. Impressive achievements have been obtained in this field, especially in relations to DNA and RNA sequencing. Since the first achievements by Sanger and colleagues in the 1950s, many sequencing techniques have been developed, while others have disappeared. DNA sequencing has undergone three generations of major evolution. Each generation has its own specifications that are mentioned briefly. Among these generations, nanopore sequencing has its own exciting characteristics that have been given more attention here. Among pioneer technologies being used by the third-generation techniques, nanopores, either biological or solid-state, have been experimentally or theoretically extensively studied. All sequencing technologies have their own advantages and disadvantages, so nanopores are not free from this general rule. It is also generally pointed out what research has been done to overcome the obstacles. In this review, biological and solid-state nanopores are elaborated on, and applications of them are also discussed briefly.

Machine learning-assisted imaging analysis of a human epiblast model

The human embryo is a complex structure that emerges and develops as a result of cell-level decisions guided by both intrinsic genetic programs and cell-cell interactions. Given limited accessibility and associated ethical constraints of human embryonic tissue samples, researchers have turned to the use of human stem cells to generate embryo models to study specific embryogenic developmental steps. However, to study complex self-organizing developmental events using embryo models, there is a need for computational and imaging tools for detailed characterization of cell-level dynamics at the single cell level. In this work, we obtained live cell imaging data from a human pluripotent stem cell (hPSC)-based epiblast model that can recapitulate the lumenal epiblast cyst formation soon after implantation of the human blastocyst. By processing imaging data with a Python pipeline that incorporates both cell tracking and event recognition with the use of a CNN-LSTM machine learning model, we obtained detailed temporal information of changes in cell state and neighborhood during the dynamic growth and morphogenesis of lumenal hPSC cysts. The use of this tool combined with reporter lines for cell types of interest will drive future mechanistic studies of hPSC fate specification in embryo models and will advance our understanding of how cell-level decisions lead to global organization and emergent phenomena. Insight, innovation, integration: Human pluripotent stem cells (hPSCs) have been successfully used to model and understand cellular events that take place during human embryogenesis. Understanding how cell-cell and cell-environment interactions guide cell actions within a hPSC-based embryo model is a key step in elucidating the mechanisms driving system-level embryonic patterning and growth. In this work, we present a robust video analysis pipeline that incorporates the use of machine learning methods to fully characterize the process of hPSC self-organization into lumenal cysts to mimic the lumenal epiblast cyst formation soon after implantation of the human blastocyst. This pipeline will be a useful tool for understanding cellular mechanisms underlying key embryogenic events in embryo models.

LR Hunting: A Random Forest Based Cell-Cell Interaction Discovery Method for Single-Cell Gene Expression Data

Cell–cell interactions (CCIs) and cell–cell communication (CCC) are critical for maintaining complex biological systems. The availability of single-cell RNA sequencing (scRNA-seq) data opens new avenues for deciphering CCIs and CCCs through identifying ligand-receptor (LR) gene interactions between cells. However, most methods were developed to examine the LR interactions of individual pairs of genes. Here, we propose a novel approach named LR hunting which first uses random forests (RFs)-based data imputation technique to link the data between different cell types. To guarantee the robustness of the data imputation procedure, we repeat the computation procedures multiple times to generate aggregated imputed minimal depth index (IMDI). Next, we identify significant LR interactions among all combinations of LR pairs simultaneously using unsupervised RFs. We demonstrated LR hunting can recover biological meaningful CCIs using a mouse cellular indexing of transcriptomes and epitopes by sequencing (CITE-seq) dataset and a triple-negative breast cancer scRNA-seq dataset.

Analyzing Modern Biomolecules: The Revolution of Nucleic-Acid Sequencing - Review

Recent developments have revolutionized the study of biomolecules. Among them are molecular markers, amplification and sequencing of nucleic acids. The latter is classified into three generations. The first allows to sequence small DNA fragments. The second one increases throughput, reducing turnaround and pricing, and is therefore more convenient to sequence full genomes and transcriptomes. The third generation is currently pushing technology to its limits, being able to sequence single molecules, without previous amplification, which was previously impossible. Besides, this represents a new revolution, allowing researchers to directly sequence RNA without previous retrotranscription. These technologies are having a significant impact on different areas, such as medicine, agronomy, ecology and biotechnology. Additionally, the study of biomolecules is revealing interesting evolutionary information. That includes deciphering what makes us human, including phenomena like non-coding RNA expansion. All this is redefining the concept of gene and transcript. Basic analyses and applications are now facilitated with new genome editing tools, such as CRISPR. All these developments, in general, and nucleic-acid sequencing, in particular, are opening a new exciting era of biomolecule analyses and applications, including personalized medicine, and diagnosis and prevention of diseases for humans and other animals.