Single-Cell Analysis Using Machine Learning Techniques and Its Application to Medical Research

Emerging artificial intelligence-driven precision therapies in tumor drug resistance: recent advances, opportunities, and challenges

Drug resistance is one of the main reasons for cancer treatment failure, leading to a rapid recurrence/disease progression of the cancer. Recently, artificial intelligence (AI) has empowered physicians to use its powerful data processing and pattern recognition capabilities to extract and mine valuable drug resistance information from large amounts of clinical or omics data, to study drug resistance mechanisms, to evaluate and predict drug resistance, and to develop innovative therapeutic strategies to reduce drug resistance. In this review, we proposed a feasible workflow for incorporating AI into tumor drug resistance research, highlighted current AI-driven tumor drug resistance applications, and discussed the opportunities and challenges encountered in the process. Based on a comprehensive literature analysis, we systematically summarized the role of AI in tumor drug resistance research, including drug development, resistance mechanism elucidation, drug sensitivity prediction, combination therapy optimization, resistance phenotype identification, and clinical biomarker discovery. With the continuous advancement of AI technology and rigorous validation of clinical data, AI models are expected to fuel the development of precision oncology by improving efficacy, guiding therapeutic decisions, and optimizing patient prognosis. In summary, by leveraging clinical and omics data, AI models are expected to pioneer new therapy strategies to mitigate tumor drug resistance, improve efficacy and patient survival, and provide novel perspectives and tools for oncology treatment.

RNA Metabolism and the Role of Small RNAs in Regulating Multiple Aspects of RNA Metabolism

RNA metabolism is focused on RNA molecules and encompasses all the crucial processes an RNA molecule may or will undergo throughout its life cycle. It is an essential cellular process that allows all cells to function effectively. The transcriptomic landscape of a cell is shaped by the processes such as RNA biosynthesis, maturation (RNA processing, folding, and modification), intra- and inter-cellular transport, transcriptional and post-transcriptional regulation, modification, catabolic decay, and retrograde signaling, all of which are interconnected and are essential for cellular RNA homeostasis. In eukaryotes, sRNAs, typically 20-31 nucleotides in length, are a class of ncRNAs found to function as nodes in various gene regulatory networks. sRNAs are known to play significant roles in regulating RNA population at the transcriptional, post-transcriptional, and translational levels. Along with sRNAs, such as miRNAs, siRNAs, and piRNAs, new categories of ncRNAs, i.e., lncRNAs and circRNAs, also contribute to RNA metabolism regulation in eukaryotes. In plants, various genetic screens have demonstrated that sRNA biogenesis mutants, as well as RNA metabolism pathway mutants, exhibit similar growth and development defects, misregulated primary and secondary metabolism, as well as impaired stress response. In addition, sRNAs are both the "products" and the "regulators" in broad RNA metabolism networks; gene regulatory networks involving sRNAs form autoregulatory loops that affect the expression of both sRNA and the respective target. This review examines the interconnected aspects of RNA metabolism with sRNA regulatory pathways in plants. It also explores the potential conservation of these pathways across different kingdoms, particularly in plants and animals. Additionally, the review highlights how cellular RNA homeostasis directly impacts adaptive responses to environmental changes as well as different developmental aspects in plants.

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.

Enhancing single-cell biology through advanced AI-powered microfluidics

Microfluidic technology has largely benefited both fundamental biological research and translational clinical diagnosis with its advantages in high-throughput, single-cell resolution, high integrity, and wide-accessibility. Despite the merits we obtained from microfluidics in the last two decades, the current requirement of intelligence in biomedicine urges the microfluidic technology to process biological big data more efficiently and intelligently. Thus, the current readout technology based on the direct detection of the signals in either optics or electrics was not able to meet the requirement. The implementation of artificial intelligence (AI) in microfluidic technology matches up with the large-scale data usually obtained in the high-throughput assays of microfluidics. At the same time, AI is able to process the multimodal datasets obtained from versatile microfluidic devices, including images, videos, electric signals, and sequences. Moreover, AI provides the microfluidic technology with the capability to understand and decipher the obtained datasets rather than simply obtaining, which eventually facilitates fundamental and translational research in many areas, including cell type discovery, cell signaling, single-cell genetics, and diagnosis. In this Perspective, we will highlight the recent advances in employing AI for single-cell biology and present an outlook on the future direction with more advanced AI algorithms.

Identification of immune subtypes of melanoma based on single-cell and bulk RNA sequencing data

The tumor microenvironment plays a crucial role in melanoma. In this study, the abundance of immune cells in melanoma samples was assessed and analyzed using single sample gene set enrichment analysis (ssGSEA), and the predictive value of immune cells was assessed using univariate COX regression analysis. The Least Absolute Shrinkage and Selection Operator (LASSO)-Cox regression analysis was applied to construct an immune cell risk score (ICRS) model with a high predictive value for identifying the immune profile of melanoma patients. The pathway enrichment between the different ICRS groups was also elucidated. Next, five hub genes for diagnosing the prognosis of melanoma were screened by two machine learning algorithms, LASSO and random forest. The distribution of hub genes in immune cells was analyzed on account of Single-cell RNA sequencing (scRNA-seq), and the interaction between genes and immune cells was elucidated by cellular communication. Ultimately, the ICRS model on account of two types of immune cells (Activated CD8 T cell and Immature B cell) was constructed and validated, which can determine melanoma prognosis. In addition, five hub genes were identified as potential therapeutic targets affecting the prognosis of melanoma patients.

Research progress of single-cell transcriptome sequencing in autoimmune diseases and autoinflammatory disease: A review

Autoimmunity refers to the phenomenon that the body's immune system produces antibodies or sensitized lymphocytes to its own tissues to cause an immune response. Immune disorders caused by autoimmunity can mediate autoimmune diseases. Autoimmune diseases have complicated pathogenesis due to the many types of cells involved, and the mechanism is still unclear. The emergence of single-cell research technology can solve the problem that ordinary transcriptome technology cannot be accurate to cell type. It provides unbiased results through independent analysis of cells in tissues and provides more mRNA information for identifying cell subpopulations, which provides a novel approach to study disruption of immune tolerance and disturbance of pro-inflammatory pathways on a cellular basis. It may fundamentally change the understanding of molecular pathways in the pathogenesis of autoimmune diseases and develop targeted drugs. Single-cell transcriptome sequencing (scRNA-seq) has been widely applied in autoimmune diseases, which provides a powerful tool for demonstrating the cellular heterogeneity of tissues involved in various immune inflammations, identifying pathogenic cell populations, and revealing the mechanism of disease occurrence and development. This review describes the principles of scRNA-seq, introduces common sequencing platforms and practical procedures, and focuses on the progress of scRNA-seq in 41 autoimmune diseases, which include 9 systemic autoimmune diseases and autoinflammatory diseases (rheumatoid arthritis, systemic lupus erythematosus, etc.) and 32 organ-specific autoimmune diseases (5 Skin diseases, 3 Nervous system diseases, 4 Eye diseases, 2 Respiratory system diseases, 2 Circulatory system diseases, 6 Liver, Gallbladder and Pancreas diseases, 2 Gastrointestinal system diseases, 3 Muscle, Bones and joint diseases, 3 Urinary system diseases, 2 Reproductive system diseases). This review also prospects the molecular mechanism targets of autoimmune diseases from the multi-molecular level and multi-dimensional analysis combined with single-cell multi-omics sequencing technology (such as scRNA-seq, Single cell ATAC-seq and single cell immune group library sequencing), which provides a reference for further exploring the pathogenesis and marker screening of autoimmune diseases and autoimmune inflammatory diseases in the future.

Introducing AI to the molecular tumor board: one direction toward the establishment of precision medicine using large-scale cancer clinical and biological information

Since U.S. President Barack Obama announced the Precision Medicine Initiative in his New Year's State of the Union address in 2015, the establishment of a precision medicine system has been emphasized worldwide, particularly in the field of oncology. With the advent of next-generation sequencers specifically, genome analysis technology has made remarkable progress, and there are active efforts to apply genome information to diagnosis and treatment. Generally, in the process of feeding back the results of next-generation sequencing analysis to patients, a molecular tumor board (MTB), consisting of experts in clinical oncology, genetic medicine, etc., is established to discuss the results. On the other hand, an MTB currently involves a large amount of work, with humans searching through vast databases and literature, selecting the best drug candidates, and manually confirming the status of available clinical trials. In addition, as personalized medicine advances, the burden on MTB members is expected to increase in the future. Under these circumstances, introducing cutting-edge artificial intelligence (AI) technology and information and communication technology to MTBs while reducing the burden on MTB members and building a platform that enables more accurate and personalized medical care would be of great benefit to patients. In this review, we introduced the latest status of elemental technologies that have potential for AI utilization in MTB, and discussed issues that may arise in the future as we progress with AI implementation.

Application of non-negative matrix factorization in oncology: one approach for establishing precision medicine

The increase in the expectations of artificial intelligence (AI) technology has led to machine learning technology being actively used in the medical field. Non-negative matrix factorization (NMF) is a machine learning technique used for image analysis, speech recognition, and language processing; recently, it is being applied to medical research. Precision medicine, wherein important information is extracted from large-scale medical data to provide optimal medical care for every individual, is considered important in medical policies globally, and the application of machine learning techniques to this end is being handled in several ways. NMF is also introduced differently because of the characteristics of its algorithms. In this review, the importance of NMF in the field of medicine, with a focus on the field of oncology, is described by explaining the mathematical science of NMF and the characteristics of the algorithm, providing examples of how NMF can be used to establish precision medicine, and presenting the challenges of NMF. Finally, the direction regarding the effective use of NMF in the field of oncology is also discussed.

Cochlear Development; New Tools and Approaches

The sensory epithelium of the mammalian cochlea, the organ of Corti, is comprised of at least seven unique cell types including two functionally distinct types of mechanosensory hair cells. All of the cell types within the organ of Corti are believed to develop from a population of precursor cells referred to as prosensory cells. Results from previous studies have begun to identify the developmental processes, lineage restrictions and signaling networks that mediate the specification of many of these cell types, however, the small size of the organ and the limited number of each cell type has hampered progress. Recent technical advances, in particular relating to the ability to capture and characterize gene expression at the single cell level, have opened new avenues for understanding cellular specification in the organ of Corti. This review will cover our current understanding of cellular specification in the cochlea, discuss the most commonly used methods for single cell RNA sequencing and describe how results from a recent study using single cell sequencing provided new insights regarding cellular specification.

Intercellular Communication-Related Molecular Subtypes and a Gene Signature Identified by the Single-Cell RNA Sequencing Combined with a Transcriptomic Analysis

Background. The tumor microenvironment (TME) of lung adenocarcinoma (LUAD) comprise various cell types that communicate with each other through ligand-receptor interactions. This study focused on the identification of cell types in LUAD by single-cell RNA sequencing (scRNA-seq) data and screening of intercellular communication-related genes. Methods. The Gene Expression Omnibus (GEO) database (https://www.ncbi.nlm.nih.gov/geo) provided the RNA-seq data of LUAD patients in the GSE149655, GSE31210, and GSE72094 datasets. Quality control of the scRNA-seq data in GSE149655 was performed by the Seurat package (http://seurat.r-forge.r-project.org) for identifying highly variable genes for principal component analysis (PCA) and cell clustering. The CellPhoneDB (http://www.cellphonedb.org) was used for filtering intercellular communication-related ligand-receptor pairs. According to ligand and receptor expressions, LUAD samples were clustered using ConsensusClusterPlus (https://www.bioconductor.org/packages/release/bioc/html/ConsensusClusterPlus). Additionally, the identification of prognosis-related ligand and receptor genes was conducted along with the development of a risk prediction model by the least absolute shrinkage and selection operator (LASSO) Cox regression analysis. Results. This study identified twelve cell types in 8170 cells of LUAD tissues along with 219 ligand and receptor genes. LUAD was classified into three different molecular subtypes, among which cluster 3 (C3) had the longest overall survival (OS) time and cluster (C1) had the shortest OS time. In comparison with the other two molecular subtypes, it was observed that C1 had a higher rate of somatic mutations and lower levels of infiltrating immune cells and immune scores. Ten genes were screened from the total ligand and receptor genes to construct a risk model, which showed a strong prediction power in the prognosis of patients with LUAD. Conclusion. The results of this study revealed cell types specific to LUAD, which were classified into different molecular subtypes according to intercellular communication-related genes. A novel prognostic risk model was developed in this study, providing new insights into prognostic assessment models for LUAD.

Automated Endocardial Border Detection and Left Ventricular Functional Assessment in Echocardiography Using Deep Learning

Endocardial border detection is a key step in assessing left ventricular systolic function in echocardiography. However, this process is still not sufficiently accurate, and manual retracing is often required, causing time-consuming and intra-/inter-observer variability in clinical practice. To address these clinical issues, more accurate and normalized automatic endocardial border detection would be valuable. Here, we develop a deep learning-based method for automated endocardial border detection and left ventricular functional assessment in two-dimensional echocardiographic videos. First, segmentation of the left ventricular cavity was performed in the six representative projections for a cardiac cycle. We employed four segmentation methods: U-Net, UNet++, UNet3+, and Deep Residual U-Net. UNet++ and UNet3+ showed a sufficiently high performance in the mean value of intersection over union and Dice coefficient. The accuracy of the four segmentation methods was then evaluated by calculating the mean value for the estimation error of the echocardiographic indexes. UNet++ was superior to the other segmentation methods, with the acceptable mean estimation error of the left ventricular ejection fraction of 10.8%, global longitudinal strain of 8.5%, and global circumferential strain of 5.8%, respectively. Our method using UNet++ demonstrated the best performance. This method may potentially support examiners and improve the workflow in echocardiography.