Analyzing domain features of small proteins using a machine-learning method.

Small proteins (SPs) are a unique group of proteins that play crucial roles in many important biological processes. Exploring the biological function of SPs is necessary. In this study, the InterPro tool and the maximum correlation method were utilized to analyze functional domains of SPs. The purpose was to identify important functional domains that can indicate the essential differences between small and large protein sequences. First, the small and large proteins were represented by their functional domains via a one-hot scheme. Then, the MaxRel method was adopted to evaluate the relationships between each domain and the target variable, indicating small or large protein. The top 36 domain features were selected for further investigation. Among them, 14 were deemed to be highly related to SPs because they were annotated to SPs more frequently than large proteins. We found the involvement of functional domains, such as ubiquitin-conjugating enzyme/RWD-like, nuclear transport factor 2 domain, and alpha subunit of guanine nucleotide-binding protein (G-protein) in regulating the biological function of SPs. The involvement of these domains has been confirmed by other recent studies. Our findings indicate that protein functional domains may regulate small protein-related functions and predict their biological activity.

Advancing targeted combination chemotherapy in triple negative breast cancer: nucleolin aptamer-mediated controlled drug release.

BACKGROUND: Triple-negative breast cancer (TNBC) is a recurrent, heterogeneous, and invasive form of breast cancer. The treatment of TNBC patients with paclitaxel and fluorouracil in a sequential manner has shown promising outcomes. However, it is challenging to deliver these chemotherapeutic agents sequentially to TNBC tumors. We aim to explore a precision therapy strategy for TNBC through the sequential delivery of paclitaxel and fluorouracil. METHODS: We developed a dual chemo-loaded aptamer with redox-sensitive caged paclitaxel for rapid release and non-cleavable caged fluorouracil for slow release. The binding affinity to the target protein was validated using Enzyme-linked oligonucleotide assays and Surface plasmon resonance assays. The targeting and internalization abilities into tumors were confirmed using Flow cytometry assays and Confocal microscopy assays. The inhibitory effects on TNBC progression were evaluated by pharmacological studies in vitro and in vivo. RESULTS: Various redox-responsive aptamer-paclitaxel conjugates were synthesized. Among them, AS1411-paclitaxel conjugate with a thioether linker (ASP) exhibited high anti-proliferation ability against TNBC cells, and its targeting ability was further improved through fluorouracil modification. The fluorouracil modified AS1411-paclitaxel conjugate with a thioether linker (FASP) exhibited effective targeting of TNBC cells and significantly improved the inhibitory effects on TNBC progression in vitro and in vivo. CONCLUSIONS: This study successfully developed fluorouracil-modified AS1411-paclitaxel conjugates with a thioether linker for targeted combination chemotherapy in TNBC. These conjugates demonstrated efficient recognition of TNBC cells, enabling targeted delivery and controlled release of paclitaxel and fluorouracil. This approach resulted in synergistic antitumor effects and reduced toxicity in vivo. However, challenges related to stability, immunogenicity, and scalability need to be further investigated for future translational applications.

Alcohol drives S-nitrosylation and redox activation of protein phosphatase 1, causing bovine airway cilia dysfunction.

Individuals with alcohol (ethanol)-use disorders are at increased risk for lung infections, in part, due to defective mucociliary clearance driven by motile cilia in the airways. We recently reported that isolated, demembranated bovine cilia (axonemes) are capable of producing nitric oxide (∙NO) when exposed to biologically relevant concentrations of alcohol. This increased presence of ∙NO can lead to protein S-nitrosylation, a posttranslational modification signaling mechanism involving reversible adduction of nitrosonium cations or ∙NO to thiolate or thiyl radicals, respectively, of proteins forming S-nitrosothiols (SNOs). We quantified and compared SNO content between isolated, demembranated axonemes extracted from bovine tracheae, with or without in situ alcohol exposure (100 mM × 24 h). We demonstrate that relevant concentrations of alcohol exposure shift the S-nitrosylation status of key cilia regulatory proteins, including 20-fold increases in S-nitrosylation of proteins that include protein phosphatase 1 (PP1). With the use of an ATP-reactivated axoneme motility system, we demonstrate that alcohol-driven S-nitrosylation of PP1 is associated with PP1 activation and dysfunction of axoneme motility. These new data demonstrate that alcohol can shift the S-nitrothiol balance at the level of the cilia organelle and highlight S-nitrosylation as a novel signaling mechanism to regulate PP1 and cilia motility.

Quantitative phosphoproteomics analysis reveals broad regulatory role of heparan sulfate on endothelial signaling.

Heparan sulfate (HS) is a linear, abundant, highly sulfated polysaccharide that expresses in the vasculature. Recent genetic studies documented that HS critically modulates various endothelial cell functions. However, elucidation of the underlying molecular mechanism has been challenging because of the presence of a large number of HS-binding ligands found in the examined experimental conditions. In this report, we used quantitative phosphoproteomics to examine the global HS-dependent signaling by comparing wild type and HS-deficient endothelial cells that were cultured in a serum-containing medium. A total of 7222 phosphopeptides, corresponding to 1179 proteins, were identified. Functional correlation analysis identified 25 HS-dependent functional networks, and the top five are related to cell morphology, cellular assembly and organization, cellular function and maintenance, cell-to-cell communication, inflammatory response and disorder, cell growth and proliferation, cell movement, and cellular survival and death. This is consistent with cell function studies showing that HS deficiency altered endothelial cell growth and mobility. Mining for the underlying molecular mechanisms further revealed that HS modulates signaling pathways critically related to cell adhesion, migration, and coagulation, including ILK, integrin, actin cytoskeleton organization, tight junction and thrombin signaling. Intriguingly, this analysis unexpectedly determined that the top HS-dependent signaling is the IGF-1 signaling pathway, which has not been known to be modulated by HS. In-depth analysis of growth factor signaling identified 22 HS-dependent growth factor/cytokine/growth hormone signaling pathways, including those both previously known, such as HGF and VEGF, and those unknown, such as IGF-1, erythropoietin, angiopoietin/Tie, IL-17A and growth hormones. Twelve of the identified 22 growth factor/cytokine/growth hormone signaling pathways, including IGF-1 and angiopoietin/Tie signaling, were alternatively confirmed in phospho-receptor tyrosine kinase array analysis. In summary, our SILAC-based quantitative phosphoproteomic analysis confirmed previous findings and also uncovered novel HS-dependent functional networks and signaling, revealing a much broader regulatory role of HS on endothelial signaling.

Functional proteomic analysis reveals the involvement of KIAA1199 in breast cancer growth, motility and invasiveness.

BACKGROUND: KIAA1199 is a recently identified novel gene that is up-regulated in human cancer with poor survival. Our proteomic study on signaling polarity in chemotactic cells revealed KIAA1199 as a novel protein target that may be involved in cellular chemotaxis and motility. In the present study, we examined the functional significance of KIAA1199 expression in breast cancer growth, motility and invasiveness. METHODS: We validated the previous microarray observation by tissue microarray immunohistochemistry using a TMA slide containing 12 breast tumor tissue cores and 12 corresponding normal tissues. We performed the shRNA-mediated knockdown of KIAA1199 in MDA-MB-231 and HS578T cells to study the role of this protein in cell proliferation, migration and apoptosis in vitro. We studied the effects of KIAA1199 knockdown in vivo in two groups of mice (n = 5). We carried out the SILAC LC-MS/MS based proteomic studies on the involvement of KIAA1199 in breast cancer. RESULTS: KIAA1199 mRNA and protein was significantly overexpressed in breast tumor specimens and cell lines as compared with non-neoplastic breast tissues from large-scale microarray and studies of breast cancer cell lines and tumors. To gain deeper insights into the novel role of KIAA1199 in breast cancer, we modulated KIAA1199 expression using shRNA-mediated knockdown in two breast cancer cell lines (MDA-MB-231 and HS578T), expressing higher levels of KIAA1199. The KIAA1199 knockdown cells showed reduced motility and cell proliferation in vitro. Moreover, when the knockdown cells were injected into the mammary fat pads of female athymic nude mice, there was a significant decrease in tumor incidence and growth. In addition, quantitative proteomic analysis revealed that knockdown of KIAA1199 in breast cancer (MDA-MB-231) cells affected a broad range of cellular functions including apoptosis, metabolism and cell motility. CONCLUSIONS: Our findings indicate that KIAA1199 may play an important role in breast tumor growth and invasiveness, and that it may represent a novel target for biomarker development and a novel therapeutic target for breast cancer.

ISPTM: an iterative search algorithm for systematic identification of post-translational modifications from complex proteome mixtures.

Identifying protein post-translational modifications (PTMs) from tandem mass spectrometry data of complex proteome mixtures is a highly challenging task. Here we present a new strategy, named iterative search for identifying PTMs (ISPTM), for tackling this challenge. The ISPTM approach consists of a basic search with no variable modification, followed by iterative searches of many PTMs using a small number of them (usually two) in each search. The performance of the ISPTM approach was evaluated on mixtures of 70 synthetic peptides with known modifications, on an 18-protein standard mixture with unknown modifications and on real, complex biological samples of mouse nuclear matrix proteins with unknown modifications. ISPTM revealed that many chemical PTMs were introduced by urea and iodoacetamide during sample preparation and many biological PTMs, including dimethylation of arginine and lysine, were significantly activated by Adriamycin treatment in nuclear matrix associated proteins. ISPTM increased the MS/MS spectral identification rate substantially, displayed significantly better sensitivity for systematic PTM identification compared with that of the conventional all-in-one search approach, and offered PTM identification results that were complementary to InsPecT and MODa, both of which are established PTM identification algorithms. In summary, ISPTM is a new and powerful tool for unbiased identification of many different PTMs with high confidence from complex proteome mixtures.

Quantitative proteomics reveals that miR-155 regulates the PI3K-AKT pathway in diffuse large B-cell lymphoma.

The aberrant expression of microRNA-155 (miR-155), which has emerged as having a significant impact on the biological characteristics of lymphocytes, plays important roles in B-cell malignancies, such as diffuse large B-cell lymphoma (DLBCL). DLBCL is the most common non-Hodgkin's lymphoma in the adult population, accounting for approximately 40% of newly diagnosed non-Hodgkin's lymphoma cases globally. To determine the specific function of miR-155, a quantitative proteomics approach was applied to examine the inhibitory effects of miR-155 on protein synthesis in DLBCL cells. PIK3R1 (p85α), a negative regulator of the phosphatidylinositol 3-kinase (PI3K)-AKT pathway, was identified as a direct target of miR-155. A luciferase reporter was repressed through the direct interaction of miR-155 and the p85α 3'-untranslated region, and overexpression of miR-155 down-regulated both the transcription and translation of p85α. The PI3K-AKT signaling pathway was highly activated by the sustained overexpression of miR-155 in DHL16 cells, whereas knockdown of miR-155 in OCI-Ly3 cells diminished AKT activity. Taken together, our results reveal a novel target involved in miR-155 biological characteristics and provide a molecular link between the overexpression of miR-155 and the activation of PI3K-AKT in DLBCL.

Quantitative proteomic analysis of mouse embryonic fibroblasts and induced pluripotent stem cells using 16O/18O labeling.

Induced pluripotent stem cells (iPSC) hold great promise for regenerative medicine as well as for investigations into the pathogenesis and treatment of various diseases. Understanding of key intracellular signaling pathways and protein targets that control development of iPSC from somatic cells is essential for designing new approaches to improve reprogramming efficiency. Here, we report the development and application of an integrated quantitative proteomics platform for investigating differences in protein expressions between mouse embryonic fibroblasts (MEF) and MEF-derived iPSC. This platform consists of 16O/18O labeling, multidimensional peptide separation coupled with tandem mass spectrometry, and data analysis with UNiquant software. With this platform, a total of 2481 proteins were identified and quantified from the 16O/18O-labeled MEF-iPSC proteome mixtures with a false discovery rate of 0.01. Among them, 218 proteins were significantly upregulated, while 247 proteins were significantly downregulated in iPSC compared to MEF. Many nuclear proteins, including Hdac1, Dnmt1, Pcna, Ccnd1, Smarcc1, and subunits in DNA replication and RNA polymerase II complex, were found to be enhanced in iPSC. Protein network analysis revealed that Pcna functions as a hub orchestrating complicated mechanisms including DNA replication, epigenetic inheritance (Dnmt1), and chromatin remodeling (Smarcc1) to reprogram MEF and maintain stemness of iPSC.

Histone acetyltransferase p300 acetylates Pax5 and strongly enhances Pax5-mediated transcriptional activity.

Pax5/B cell lineage specific activator protein (BSAP) is a B lineage-specific regulator that controls the B lineage-specific gene expression program and immunoglobulin gene V(H) to DJ(H) recombination. Despite extensive studies on its multiple functions, little is known about how the activity of Pax5 is regulated. Here, we show that co-expression of histone acetyltransferase E1A binding protein p300 dramatically enhances Pax5-mediated transcriptional activation. The p300-mediated enhancement is dependent on its intrinsic histone acetyltransferase activity. Moreover, p300 interacts with the C terminus of Pax5 and acetylates multiple lysine residues within the paired box DNA binding domain of Pax5. Mutations of lysine residues 67 and 87/89 to alanine within Pax5 abolish p300-mediated enhancement of Pax5-induced Luc-CD19 reporter expression in HEK293 cells and prevent Pax5 to activate endogenous Cd19 and Blnk expression in Pax5(-/-) murine pro B cells. These results uncover a novel level of regulation of Pax5 function by p300-mediated acetylation.

Development and application of site-specific proteomic approach for study protein S-nitrosylation.

Protein S-nitrosylation is the covalent redox-related modification of cysteine sulfhydryl groups with nitric oxide, creating a regulatory impact similar to phosphorylation. Recent studies have reported a growing number of proteins to be S-nitrosylated in vivo resulting in altered functions. These studies support S-nitrosylation as a critical regulatory mechanism, fine-tuning protein activities within diverse cellular processes and biochemical pathways. In addition, S-nitrosylation appears to have key roles in the etiology of a broad range of human diseases. In this review, we discuss recent advances in proteomic approaches for the enrichment, identification, and quantitation of cysteine S-nitrosylated proteins and peptides. These advances have provided analytical tools with the power to interpret the impact of S-nitrosylation at the system level, providing a new platform for drug discovery and the identification of diagnostic markers for human diseases.

Proteomic analysis of the organ of corti using nanoscale liquid chromatography coupled with tandem mass spectrometry.

The organ of Corti (OC) in the cochlea plays an essential role in auditory signal transduction in the inner ear. For its minute size and trace amount of proteins, the identification of the molecules in pathophysiologic processes in the bone-encapsulated OC requires both delicate separation and a highly sensitive analytical tool. Previously, we reported the development of a high resolution metal-free nanoscale liquid chromatography system for highly sensitive phosphoproteomic analysis. Here this system was coupled with a LTQ-Orbitrap XL mass spectrometer to investigate the OC proteome from normal hearing FVB/N male mice. A total of 628 proteins were identified from six replicates of single LC-MS/MS analysis, with a false discovery rate of 1% using the decoy database approach by the OMSSA search engine. This is currently the largest proteome dataset for the OC. A total of 11 proteins, including cochlin, myosin VI, and myosin IX, were identified that when defective are associated with hearing impairment or loss. This study demonstrated the effectiveness of our nanoLC-MS/MS platform for sensitive identification of hearing loss-associated proteins from minute amount of tissue samples.

Subcellular Localization Prediction of Human Proteins Using Multifeature Selection Methods.

Subcellular localization attempts to assign proteins to one of the cell compartments that performs specific biological functions. Finding the link between proteins, biological functions, and subcellular localization is an effective way to investigate the general organization of living cells in a systematic manner. However, determining the subcellular localization of proteins by traditional experimental approaches is difficult. Here, protein-protein interaction networks, functional enrichment on gene ontology and pathway, and a set of proteins having confirmed subcellular localization were applied to build prediction models for human protein subcellular localizations. To build an effective predictive model, we employed a variety of robust machine learning algorithms, including Boruta feature selection, minimum redundancy maximum relevance, Monte Carlo feature selection, and LightGBM. Then, the incremental feature selection method with random forest and support vector machine was used to discover the essential features. Furthermore, 38 key features were determined by integrating results of different feature selection methods, which may provide critical insights into the subcellular location of proteins. Their biological functions of subcellular localizations were discussed according to recent publications. In summary, our computational framework can help advance the understanding of subcellular localization prediction techniques and provide a new perspective to investigate the patterns of protein subcellular localization and their biological importance.

Identification of methylation signatures and rules for predicting the severity of SARS-CoV-2 infection with machine learning methods.

Patients infected with SARS-CoV-2 at various severities have different clinical manifestations and treatments. Mild or moderate patients usually recover with conventional medical treatment, but severe patients require prompt professional treatment. Thus, stratifying infected patients for targeted treatment is meaningful. A computational workflow was designed in this study to identify key blood methylation features and rules that can distinguish the severity of SARS-CoV-2 infection. First, the methylation features in the expression profile were deeply analyzed by a Monte Carlo feature selection method. A feature list was generated. Next, this ranked feature list was fed into the incremental feature selection method to determine the optimal features for different classification algorithms, thereby further building optimal classifiers. These selected key features were analyzed by functional enrichment to detect their biofunctional information. Furthermore, a set of rules were set up by a white-box algorithm, decision tree, to uncover different methylation patterns on various severity of SARS-CoV-2 infection. Some genes (PARP9, MX1, IRF7), corresponding to essential methylation sites, and rules were validated by published academic literature. Overall, this study contributes to revealing potential expression features and provides a reference for patient stratification. The physicians can prioritize and allocate health and medical resources for COVID-19 patients based on their predicted severe clinical outcomes.

Functional and embedding feature analysis for pan-cancer classification.

With the increasing number of people suffering from cancer, this illness has become a major health problem worldwide. Exploring the biological functions and signaling pathways of carcinogenesis is essential for cancer detection and research. In this study, a mutation dataset for eleven cancer types was first obtained from a web-based resource called cBioPortal for Cancer Genomics, followed by extracting 21,049 features from three aspects: relationship to GO and KEGG (enrichment features), mutated genes learned by word2vec (text features), and protein-protein interaction network analyzed by node2vec (network features). Irrelevant features were then excluded using the Boruta feature filtering method, and the retained relevant features were ranked by four feature selection methods (least absolute shrinkage and selection operator, minimum redundancy maximum relevance, Monte Carlo feature selection and light gradient boosting machine) to generate four feature-ranked lists. Incremental feature selection was used to determine the optimal number of features based on these feature lists to build the optimal classifiers and derive interpretable classification rules. The results of four feature-ranking methods were integrated to identify key functional pathways, such as olfactory transduction (hsa04740) and colorectal cancer (hsa05210), and the roles of these functional pathways in cancers were discussed in reference to literature. Overall, this machine learning-based study revealed the altered biological functions of cancers and provided a reference for the mechanisms of different cancers.

Detecting Blood Methylation Signatures in Response to Childhood Cancer Radiotherapy via Machine Learning Methods.

Radiotherapy is a helpful treatment for cancer, but it can also potentially cause changes in many molecules, resulting in adverse effects. Among these changes, the occurrence of abnormal DNA methylation patterns has alarmed scientists. To explore the influence of region-specific radiotherapy on blood DNA methylation, we designed a computational workflow by using machine learning methods that can identify crucial methylation alterations related to treatment exposure. Irrelevant methylation features from the DNA methylation profiles of 2052 childhood cancer survivors were excluded via the Boruta method, and the remaining features were ranked using the minimum redundancy maximum relevance method to generate feature lists. These feature lists were then fed into the incremental feature selection method, which uses a combination of deep forest, k-nearest neighbor, random forest, and decision tree to find the most important methylation signatures and build the best classifiers and classification rules. Several methylation signatures and rules have been discovered and confirmed, allowing for a better understanding of methylation patterns in response to different treatment exposures.

Identification of Cell Markers and Their Expression Patterns in Skin Based on Single-Cell RNA-Sequencing Profiles.

Atopic dermatitis and psoriasis are members of a family of inflammatory skin disorders. Cellular immune responses in skin tissues contribute to the development of these diseases. However, their underlying immune mechanisms remain to be fully elucidated. We developed a computational pipeline for analyzing the single-cell RNA-sequencing profiles of the Human Cell Atlas skin dataset to investigate the pathological mechanisms of skin diseases. First, we applied the maximum relevance criterion and the Boruta feature selection method to exclude irrelevant gene features from the single-cell gene expression profiles of inflammatory skin disease samples and healthy controls. The retained gene features were ranked by using the Monte Carlo feature selection method on the basis of their importance, and a feature list was compiled. This list was then introduced into the incremental feature selection method that combined the decision tree and random forest algorithms to extract important cell markers and thus build excellent classifiers and decision rules. These cell markers and their expression patterns have been analyzed and validated in recent studies and are potential therapeutic and diagnostic targets for skin diseases because their expression affects the pathogenesis of inflammatory skin diseases.

Identification of DNA Methylation Signature and Rules for SARS-CoV-2 Associated with Age.

BACKGROUND: COVID-19 displays an increased mortality rate and higher risk of severe symptoms with increasing age, which is thought to be a result of the compromised immunity of elderly patients. However, the underlying mechanisms of aging-associated immunodeficiency against Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) remains unclear. Epigenetic modifications show considerable changes with age, causing altered gene regulations and cell functions during the aging process. The DNA methylation patterns among patients with coronavirus 2019 disease (COVID-19) who had different ages were compared to explore the effect of aging-associated methylation modifications in SARS-CoV-2 infection. METHODS: Patients with COVID-19 were divided into three groups according to age. Boruta was used on the DNA methylation profiles of the patients to remove irrelevant features and retain essential signature sites to identify substantial aging-associated DNA methylation changes in COVID-19. Next, these features were ranked using the minimum redundancy maximum relevance (mRMR) method, and the feature list generated by mRMR was processed into the incremental feature selection method with decision tree (DT), random forest, k-nearest neighbor, and support vector machine to obtain the key methylation sites, optimal classifier, and decision rules. RESULTS: Several key methylation sites that showed distinct patterns among the patients with COVID-19 who had different ages were identified, and these methylation modifications may play crucial roles in regulating immune cell functions. An optimal classifier was built based on selected methylation signatures, which can be useful to predict the aging-associated disease risk of COVID-19. CONCLUSIONS: Existing works and our predictions suggest that the methylation modifications of genes, such as NHLH2, ZEB2, NWD1, ELOVL2, FGGY, and FHL2, are closely associated with age in patients with COVID-19, and the 39 decision rules extracted with the optimal DT classifier provides quantitative context to the methylation modifications in elderly patients with COVID-19. Our findings contribute to the understanding of the epigenetic regulations of aging-associated COVID-19 symptoms and provide the potential methylation targets for intervention strategies in elderly patients.

Recognition of Immune Cell Markers of COVID-19 Severity with Machine Learning Methods.

COVID-19 is hypothesized to be linked to the host's excessive inflammatory immunological response to SARS-CoV-2 infection, which is regarded to be a major factor in disease severity and mortality. Numerous immune cells play a key role in immune response regulation, and gene expression analysis in these cells could be a useful method for studying disease states, assessing immunological responses, and detecting biomarkers. Here, we developed a machine learning procedure to find biomarkers that discriminate disease severity in individual immune cells (B cell, CD4+ cell, CD8+ cell, monocyte, and NK cell) using single-cell gene expression profiles of COVID-19. The gene features of each profile were first filtered and ranked using the Boruta feature selection method and mRMR, and the resulting ranked feature lists were then fed into the incremental feature selection method to determine the optimal number of features with decision tree and random forest algorithms. Meanwhile, we extracted the classification rules in each cell type from the optimal decision tree classifiers. The best gene sets discovered in this study were analyzed by GO and KEGG pathway enrichment, and some important biomarkers like TLR2, ITK, CX3CR1, IL1B, and PRDM1 were validated by recent literature. The findings reveal that the optimal gene sets for each cell type can accurately classify COVID-19 disease severity and provide insight into the molecular mechanisms involved in disease progression.

Identifying Key MicroRNA Signatures for Neurodegenerative Diseases With Machine Learning Methods.

Neurodegenerative diseases, including Alzheimer's disease (AD), Parkinson's disease, and many other disease types, cause cognitive dysfunctions such as dementia via the progressive loss of structure or function of the body's neurons. However, the etiology of these diseases remains unknown, and diagnosing less common cognitive disorders such as vascular dementia (VaD) remains a challenge. In this work, we developed a machine-leaning-based technique to distinguish between normal control (NC), AD, VaD, dementia with Lewy bodies, and mild cognitive impairment at the microRNA (miRNA) expression level. First, unnecessary miRNA features in the miRNA expression profiles were removed using the Boruta feature selection method, and the retained feature sets were sorted using minimum redundancy maximum relevance and Monte Carlo feature selection to provide two ranking feature lists. The incremental feature selection method was used to construct a series of feature subsets from these feature lists, and the random forest and PART classifiers were trained on the sample data consisting of these feature subsets. On the basis of the model performance of these classifiers with different number of features, the best feature subsets and classifiers were identified, and the classification rules were retrieved from the optimal PART classifiers. Finally, the link between candidate miRNA features, including hsa-miR-3184-5p, has-miR-6088, and has-miR-4649, and neurodegenerative diseases was confirmed using recently published research, laying the groundwork for more research on miRNAs in neurodegenerative diseases for the diagnosis of cognitive impairment and the understanding of potential pathogenic mechanisms.

Identification of COVID-19 severity biomarkers based on feature selection on single-cell RNA-Seq data of CD8+ T cells.

The global outbreak of the COVID-19 epidemic has become a major public health problem. COVID-19 virus infection triggers a complex immune response. CD8+ T cells, in particular, play an essential role in controlling the severity of the disease. However, the mechanism of the regulatory role of CD8+ T cells on COVID-19 remains poorly investigated. In this study, single-cell gene expression profiles from three CD8+ T cell subtypes (effector, memory, and naive T cells) were downloaded. Each cell subtype included three disease states, namely, acute COVID-19, convalescent COVID-19, and unexposed individuals. The profiles on each cell subtype were individually analyzed in the same way. Irrelevant features in the profiles were first excluded by the Boruta method. The remaining features for each CD8+ T cells subtype were further analyzed by Max-Relevance and Min-Redundancy, Monte Carlo feature selection, and light gradient boosting machine methods to obtain three feature lists. These lists were then brought into the incremental feature selection method to determine the optimal features for each cell subtype. Their corresponding genes may be latent biomarkers to determine COVID-19 severity. Genes, such as ZFP36, DUSP1, TCR, and IL7R, can be confirmed to play an immune regulatory role in COVID-19 infection and recovery. The results of functional enrichment analysis revealed that these important genes may be associated with immune functions, such as response to cAMP, response to virus, T cell receptor complex, T cell activation, and T cell differentiation. This study further set up different gene expression pattens, represented by classification rules, on three states of COVID-19 and constructed several efficient classifiers to distinguish COVID-19 severity. The findings of this study provided new insights into the biological processes of CD8+ T cells in regulating the immune response.