Identification of Colon Immune Cell Marker Genes Using Machine Learning Methods.

Immune cell infiltration that occurs at the site of colon tumors influences the course of cancer. Different immune cell compositions in the microenvironment lead to different immune responses and different therapeutic effects. This study analyzed single-cell RNA sequencing data in a normal colon with the aim of screening genetic markers of 25 candidate immune cell types and revealing quantitative differences between them. The dataset contains 25 classes of immune cells, 41,650 cells in total, and each cell is expressed by 22,164 genes at the expression level. They were fed into a machine learning-based stream. The five feature ranking algorithms (last absolute shrinkage and selection operator, light gradient boosting machine, Monte Carlo feature selection, minimum redundancy maximum relevance, and random forest) were first used to analyze the importance of gene features, yielding five feature lists. Then, incremental feature selection and two classification algorithms (decision tree and random forest) were combined to filter the most important genetic markers from each list. For different immune cell subtypes, their marker genes, such as KLRB1 in CD4 T cells, RPL30 in B cell IGA plasma cells, and JCHAIN in IgG producing B cells, were identified. They were confirmed to be differentially expressed in different immune cells and involved in immune processes. In addition, quantitative rules were summarized by using the decision tree algorithm to distinguish candidate immune cell types. These results provide a reference for exploring the cell composition of the colon cancer microenvironment and for clinical immunotherapy.

Characterizations of microRNAs involved in the molecular mechanisms underlying the therapeutic effects of noni (Morinda citrifolia L.) fruit juice on hyperuricemia in mice.

Background: Hyperuricemia is generally defined as the high level of serum uric acid and is well known as an important risk factor for the development of various medical disorders. However, the medicinal treatment of hyperuricemia is frequently associated with multiple side-effects. Methods: The therapeutic effect of noni (Morinda citrifolia L.) fruit juice on hyperuricemia and the underlying molecular mechanisms were investigated in mouse model of hyperuricemia induced by potassium oxonate using biochemical and high-throughput RNA sequencing analyses. Results: The levels of serum uric acid (UA) and xanthine oxidase (XOD) in mice treated with noni fruit juice were significantly decreased, suggesting that the noni fruit juice could alleviate hyperuricemia by inhibiting the XOD activity and reducing the level of serum UA. The contents of both serum creatinine and blood urine nitrogen of the noni fruit juice group were significantly lower than those of the model group, suggesting that noni fruit juice promoted the excretion of UA without causing deleterious effect on the renal functions in mice. The differentially expressed microRNAs involved in the pathogenesis of hyperuricemia in mice were identified by RNA sequencing with their target genes further annotated based on both Gene Ontology and Kyoto Encyclopedia of Genes and Genomes databases to explore the metabolic pathways and molecular mechanisms underlying the therapeutic effect on hyperuricemia by noni fruit juice. Conclusion: Our study provided strong experimental evidence to support the further investigations of the potential application of noni fruit juice in the treatment of hyperuricemia.

Molecular and biochemical investigations of the anti-fatigue effects of tea polyphenols and fruit extracts of Lycium ruthenicum Murr. on mice with exercise-induced fatigue.

Background: The molecular mechanisms regulating the therapeutic effects of plant-based ingredients on the exercise-induced fatigue (EIF) remain unclear. The therapeutic effects of both tea polyphenols (TP) and fruit extracts of Lycium ruthenicum (LR) on mouse model of EIF were investigated. Methods: The variations in the fatigue-related biochemical factors, i.e., lactate dehydrogenase (LDH), superoxide dismutase (SOD), tumor necrosis factor-α (TNF-α), interleukin-1ß (IL-1ß), interleukin-2 (IL-2), and interleukin-6 (IL-6), in mouse models of EIF treated with TP and LR were determined. The microRNAs involved in the therapeutic effects of TP and LR on the treatment of mice with EIF were identified using the next-generation sequencing technology. Results: Our results revealed that both TP and LR showed evident anti-inflammatory effect and reduced oxidative stress. In comparison with the control groups, the contents of LDH, TNF-α, IL-6, IL-1ß, and IL-2 were significantly decreased and the contents of SOD were significantly increased in the experimental groups treated with either TP or LR. A total of 23 microRNAs (21 upregulated and 2 downregulated) identified for the first time by the high-throughput RNA sequencing were involved in the molecular response to EIF in mice treated with TP and LR. The regulatory functions of these microRNAs in the pathogenesis of EIF in mice were further explored based on Gene Ontology (GO) annotation and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses with a total of over 20,000-30,000 target genes annotated and 44 metabolic pathways enriched in the experimental groups based on GO and KEGG databases, respectively. Conclusion: Our study revealed the therapeutic effects of TP and LR and identified the microRNAs involved in the molecular mechanisms regulating the EIF in mice, providing strong experimental evidence to support further agricultural development of LR as well as the investigations and applications of TP and LR in the treatment of EIF in humans, including the professional athletes.

Immune responses of different COVID-19 vaccination strategies by analyzing single-cell RNA sequencing data from multiple tissues using machine learning methods.

Multiple types of COVID-19 vaccines have been shown to be highly effective in preventing SARS-CoV-2 infection and in reducing post-infection symptoms. Almost all of these vaccines induce systemic immune responses, but differences in immune responses induced by different vaccination regimens are evident. This study aimed to reveal the differences in immune gene expression levels of different target cells under different vaccine strategies after SARS-CoV-2 infection in hamsters. A machine learning based process was designed to analyze single-cell transcriptomic data of different cell types from the blood, lung, and nasal mucosa of hamsters infected with SARS-CoV-2, including B and T cells from the blood and nasal cavity, macrophages from the lung and nasal cavity, alveolar epithelial and lung endothelial cells. The cohort was divided into five groups: non-vaccinated (control), 2*adenovirus (two doses of adenovirus vaccine), 2*attenuated (two doses of attenuated virus vaccine), 2*mRNA (two doses of mRNA vaccine), and mRNA/attenuated (primed by mRNA vaccine, boosted by attenuated vaccine). All genes were ranked using five signature ranking methods (LASSO, LightGBM, Monte Carlo feature selection, mRMR, and permutation feature importance). Some key genes that contributed to the analysis of immune changes, such as RPS23, DDX5, PFN1 in immune cells, and IRF9 and MX1 in tissue cells, were screened. Afterward, the five feature sorting lists were fed into the feature incremental selection framework, which contained two classification algorithms (decision tree [DT] and random forest [RF]), to construct optimal classifiers and generate quantitative rules. Results showed that random forest classifiers could provide relative higher performance than decision tree classifiers, whereas the DT classifiers provided quantitative rules that indicated special gene expression levels under different vaccine strategies. These findings may help us to develop better protective vaccination programs and new vaccines.

Electronic Beam Steering Metamaterial Antenna with Dual-Tuned Mode of Liquid Crystal Material.

In this study, a dual-tuned mode of liquid crystal (LC) material was proposed and adopted on reconfigurable metamaterial antennas to expand the fixed-frequency beam-steering range. The novel dual-tuned mode of the LC is composed of double LC layers combined with composite right/left-handed (CRLH) transmission line theory. Through a multi-separated metal layer, the double LC layers can be loaded with controllable bias voltage independently. Therefore, the LC material exhibits four extreme states, among which the permittivity of LC can be varied linearly. On the strength of the dual-tuned mode of LC, a CRLH unit cell is elaborately designed on three-layer substrates with balanced dispersion values under arbitrary LC state. Then five CRLH unit cells are cascaded to form an electronically controlled beam-steering CRLH metamaterial antenna on a downlink Ku satellite communication band with dual-tuned characteristics. The simulated results demonstrate that the metamaterial antenna features' continuous electronic beam-steering capacity from broadside to -35° at 14.4 GHz. Furthermore, the beam-steering properties are implemented in a broad frequency band from 13.8 GHz to 17 GHz, with good impedance matching. The proposed dual-tuned mode can make the regulation of LC material more flexible and enlarge the beam-steering range simultaneously.

Plasmon-Determined Selectivity in Photocatalytic Transformations on Gold and Gold-Palladium Nanostructures.

Noble metal nanostructures absorb light producing coherent oscillations of the metal's electrons, so-called localized surface plasmon resonances (LSPRs). LSPRs can decay generating hot carriers, highly energetic species that trigger chemical transformations in the molecules located on the metal surfaces. The number of chemical reactions can be expanded by coupling noble and catalytically active metals. However, it remains unclear whether such mono- and bimetallic nanostructures possess any sensitivity toward one or another chemical reaction if both of them can take place in one molecular analyte. In this study, we utilize tip-enhanced Raman spectroscopy (TERS), an emerging analytical technique that has single-molecule sensitivity and sub-nanometer spatial resolution, to investigate plasmon-driven reactivity of 2-nitro-5-thiolobenzoic acid (2-N-5TBA) on gold and gold@palladium nanoplates (AuNPs and Au@PdNPs). This molecular analyte possesses both nitro and carboxyl groups, which can be reduced or removed by hot carriers. We found that on AuNPs, 2-N-5TBA dimerized forming 4,4'-dimethylazobenzene (DMAB), the bicarbonyl derivative of DMAB, as well as 4-nitrobenzenethiol (4-NBT). Our accompanying theoretical investigation based on density functional theory (DFT) and time-dependent density functional theory (TDDFT) confirmed these findings. The theoretical analysis shows that 2-N-5TBA first dimerized forming the bicarbonyl derivative of DMAB, which then decarboxylated forming DMAB. Finally, DMAB can be further reduced leading to 4-NBT. This reaction mechanism is supported by TERS-determined yields on these three molecules on AuNPs. We also found that on Au@PdNPs, 2-N-5TBA first formed the bicarbonyl derivative of DMAB, which is then reduced to both bihydroxyl-DMAB and 4-amino-3-mercaptobenzoic acid. The yield of these reaction products on Au@PdNPs strictly follows the free-energy potential of these molecules on the metallic surfaces.

Role of Plasmonic Antenna in Hot Carrier-Driven Reactions on Bimetallic Nanostructures.

Noble metal nanostructures can efficiently harvest electromagnetic radiation, which, in turn, is used to generate localized surface plasmon resonances. Surface plasmons decay, producing hot carriers, that is, short-lived species that can trigger chemical reactions on metallic surfaces. However, noble metal nanostructures catalyze only a very small number of chemical reactions. This limitation can be overcome by coupling such nanostructures with catalytic-active metals. Although the role of such catalytically active metals in plasmon-driven catalysis is well-understood, the mechanistics of a noble metal antenna in such chemistry remains unclear. In this study, we utilize tip-enhanced Raman spectroscopy, an innovative nanoscale imaging technique, to investigate the rates and yields of plasmon-driven reactions on mono- and bimetallic gold- and silver-based nanostructures. We found that silver nanoplates (AgNPs) demonstrate a significantly higher yield of 4-nitrobenzenehtiol to p,p'-dimercaptoazobisbenzene (DMAB) reduction than gold nanoplates (AuNPs). We also observed substantially greater yields of DMAB on silver-platinum and silver-palladium nanoplates (Ag@PtNPs and Ag@PdNPs) compared to their gold analogues, Au@PtNPs and Au@PdNPs. Furthermore, Ag@PtNPs exhibited enhanced reactivity in 4-mercatophenylmethanol to 4-mercaptobenzoic acid oxidation compared to Au@PtNPs. These results showed that silver-based bimetallic nanostructures feature much greater reactivity compared to their gold-based analogues.

Characterization of spleen and lymph node cell types via CITE-seq and machine learning methods.

The spleen and lymph nodes are important functional organs for human immune system. The identification of cell types for spleen and lymph nodes is helpful for understanding the mechanism of immune system. However, the cell types of spleen and lymph are highly diverse in the human body. Therefore, in this study, we employed a series of machine learning algorithms to computationally analyze the cell types of spleen and lymph based on single-cell CITE-seq sequencing data. A total of 28,211 cell data (training vs. test = 14,435 vs. 13,776) involving 24 cell types were collected for this study. For the training dataset, it was analyzed by Boruta and minimum redundancy maximum relevance (mRMR) one by one, resulting in an mRMR feature list. This list was fed into the incremental feature selection (IFS) method, incorporating four classification algorithms (deep forest, random forest, K-nearest neighbor, and decision tree). Some essential features were discovered and the deep forest with its optimal features achieved the best performance. A group of related proteins (CD4, TCRb, CD103, CD43, and CD23) and genes (Nkg7 and Thy1) contributing to the classification of spleen and lymph nodes cell types were analyzed. Furthermore, the classification rules yielded by decision tree were also provided and analyzed. Above findings may provide helpful information for deepening our understanding on the diversity of cell types.

Identification of protein-protein interaction associated functions based on gene ontology and KEGG pathway.

Protein-protein interactions (PPIs) are extremely important for gaining mechanistic insights into the functional organization of the proteome. The resolution of PPI functions can help in the identification of novel diagnostic and therapeutic targets with medical utility, thus facilitating the development of new medications. However, the traditional methods for resolving PPI functions are mainly experimental methods, such as co-immunoprecipitation, pull-down assays, cross-linking, label transfer, and far-Western blot analysis, that are not only expensive but also time-consuming. In this study, we constructed an integrated feature selection scheme for the large-scale selection of the relevant functions of PPIs by using the Gene Ontology and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway annotations of PPI participants. First, we encoded the proteins in each PPI with their gene ontologies and KEGG pathways. Then, the encoded protein features were refined as features of both positive and negative PPIs. Subsequently, Boruta was used for the initial filtering of features to obtain 5684 features. Three feature ranking algorithms, namely, least absolute shrinkage and selection operator, light gradient boosting machine, and max-relevance and min-redundancy, were applied to evaluate feature importance. Finally, the top-ranked features derived from multiple datasets were comprehensively evaluated, and the intersection of results mined by three feature ranking algorithms was taken to identify the features with high correlation with PPIs. Some functional terms were identified in our study, including cytokine-cytokine receptor interaction (hsa04060), intrinsic component of membrane (GO:0031224), and protein-binding biological process (GO:0005515). Our newly proposed integrated computational approach offers a novel perspective of the large-scale mining of biological functions linked to PPI.

A case report on mixed pulmonary infection of Nocardia nova, Mycobacterium tuberculosis, and Aspergillus fumigatus based on metagenomic next-generation sequencing.

Background: Pulmonary infection is one of the common complications of long-term use of glucocorticoids. Severe infections not only increase the length of hospital stay and treatment costs but also cause progression or recurrence of the primary disease. Case description: Herein, we reported a case of mixed pulmonary infection secondary to glucocorticoid use. Rare pathogens such as Nocardia nova, Mycobacterium tuberculosis, Aspergillus fumigatus, and cytomegalovirus were detected by metagenomic next-generation sequencing (mNGS) of bronchoalveolar lavage fluid and lung puncture tissue. Combining the results of conventional pathogen detection and clinical symptoms, the patient was diagnosed with mixed pulmonary infection by multiple pathogens. After timely targeted medication, the patient was finally discharged with a good prognosis. Conclusion: To our knowledge, this is the first case report on mixed pulmonary infection with pathogens including Nocardia nova, Mycobacterium tuberculosis, Aspergillus fumigatus, and human cytomegalovirus. As a new clinical diagnostic method, mNGS has great advantages in diagnosis of diseases such as mixed infections.

Modified Bu-Fei decoction inhibits lung metastasis via suppressing angiopoietin-like 4.

BACKGROUND: Modified Bu-Fei decoction (MBFD), a formula of traditional Chinese medicine, is used for treating lung cancer in clinic. The actions and mechanisms of MBFD on modulating lung microenvironment is not clear. PURPOSE: Lung microenvironment is rich in vascular endothelial cells (ECs). This study is aimed to examine the actions of MBFD on tumor biology, and to uncover the underlying mechanisms by focusing on pulmonary ECs. METHODS: The Lewis lung carcinoma (LLC) xenograft model and the metastatic cancer model were used to determine the efficacy of MBFD on inhibiting tumor growth and metastasis. Flow cytometry and trans-well analysis were used to determine the role of ECs in anti-metastatic actions of MBFD. The in silico analysis and function assays were used to identify the mechanisms of MBFD in retarding lung metastasis. Plasma from lung cancer patients were used to verify the effects of MBFD on angiogenin-like protein 4 (ANGPTL4) in clinical conditions. RESULTS: MBFD significantly suppressed spontaneous lung metastasis of LLC tumors, but not tumor growth, at clinically relevant concentrations. The anti-metastatic effects of MBFD were verified in metastatic cancer models created by intravenous injection of LLC or 4T1 cells. MBFD inhibited lung infiltration of circulating tumor cells, without reducing tumor cell proliferations in lung. In vitro, MBFD dose-dependently inhibited trans-endothelial migrations of tumor cells. RNA-seq assay and verification experiments confirmed that MBFD potently depressed endothelial ANGPTL4 which is able to broke endothelial barrier and protect tumor cells from anoikis. Database analysis revealed that high ANGPTL4 levels is negatively correlated with overall survival of cancer patients. Importantly, MBFD therapy reduced plasma levels of ANGPTL4 in lung cancer patients. Finally, MBFD was revealed to inhibit ANGPTL4 expressions in a hypoxia inducible factor-1α (HIF-1α)-dependent manner, based on results from specific signaling inhibitors and network pharmacology analysis. CONCLUSION: MBFD, at clinically relevant concentrations, inhibits cancer lung metastasis via suppressing endothelial ANGPTL4. These results revealed novel effects and mechanisms of MBFD in treating cancer, and have a significant clinical implication of MBFD therapy in combating metastasis.

Can Light Alter the Yield of Plasmon-Driven Reactions on Gold and Gold-Palladium Nanoplates?

Noble-metal nanostructures, as well as their bimetallic analogues, catalyze a broad spectrum of plasmon-driven reactions. Catalytic properties of such nanostructures arise from light-generated surface plasmon resonances that decay forming transient hot electrons and holes. Hot carriers with "slower" dissipation rates accumulate on nanostructures generating an electrostatic potential. In this study, we examine whether light intensity can alter the electrostatic potential of mono- and bimetallic nanostructures changing yields of plasmon-driven reactions. Using tip-enhanced Raman spectroscopy (TERS), we quantified the yield of plasmon-driven transformations of 4-nitrobenzenethiol (4-NBT) and 3-mercaptobenzoic acid (3-MBA) on gold and gold-palladium nanoplates (AuNPs and Au@PdNPs, respectively). We found that on AuNPs 3-MBA decarboxylated forming thiophenol (TP), whereas 4-NBT was reduced to DMAB. The yield of both TP and DMAB gradually increased with increasing light intensity. On Au@PdNPs, 3-MBA could be reduced to 3-mercaptophenylmethanol (3-MPM), the yield of which was also directly dependent on the light intensity.

Identification of cortical interneuron cell markers in mouse embryos based on machine learning analysis of single-cell transcriptomics.

Mammalian cortical interneurons (CINs) could be classified into more than two dozen cell types that possess diverse electrophysiological and molecular characteristics, and participate in various essential biological processes in the human neural system. However, the mechanism to generate diversity in CINs remains controversial. This study aims to predict CIN diversity in mouse embryo by using single-cell transcriptomics and the machine learning methods. Data of 2,669 single-cell transcriptome sequencing results are employed. The 2,669 cells are classified into three categories, caudal ganglionic eminence (CGE) cells, dorsal medial ganglionic eminence (dMGE) cells, and ventral medial ganglionic eminence (vMGE) cells, corresponding to the three regions in the mouse subpallium where the cells are collected. Such transcriptomic profiles were first analyzed by the minimum redundancy and maximum relevance method. A feature list was obtained, which was further fed into the incremental feature selection, incorporating two classification algorithms (random forest and repeated incremental pruning to produce error reduction), to extract key genes and construct powerful classifiers and classification rules. The optimal classifier could achieve an MCC of 0.725, and category-specified prediction accuracies of 0.958, 0.760, and 0.737 for the CGE, dMGE, and vMGE cells, respectively. The related genes and rules may provide helpful information for deepening the understanding of CIN diversity.

Identification of COVID-19-Specific Immune Markers Using a Machine Learning Method.

Notably, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has a tight relationship with the immune system. Human resistance to COVID-19 infection comprises two stages. The first stage is immune defense, while the second stage is extensive inflammation. This process is further divided into innate and adaptive immunity during the immune defense phase. These two stages involve various immune cells, including CD4+ T cells, CD8+ T cells, monocytes, dendritic cells, B cells, and natural killer cells. Various immune cells are involved and make up the complex and unique immune system response to COVID-19, providing characteristics that set it apart from other respiratory infectious diseases. In the present study, we identified cell markers for differentiating COVID-19 from common inflammatory responses, non-COVID-19 severe respiratory diseases, and healthy populations based on single-cell profiling of the gene expression of six immune cell types by using Boruta and mRMR feature selection methods. Some features such as IFI44L in B cells, S100A8 in monocytes, and NCR2 in natural killer cells are involved in the innate immune response of COVID-19. Other features such as ZFP36L2 in CD4+ T cells can regulate the inflammatory process of COVID-19. Subsequently, the IFS method was used to determine the best feature subsets and classifiers in the six immune cell types for two classification algorithms. Furthermore, we established the quantitative rules used to distinguish the disease status. The results of this study can provide theoretical support for a more in-depth investigation of COVID-19 pathogenesis and intervention strategies.

Identifying Functions of Proteins in Mice With Functional Embedding Features.

In current biology, exploring the biological functions of proteins is important. Given the large number of proteins in some organisms, exploring their functions one by one through traditional experiments is impossible. Therefore, developing quick and reliable methods for identifying protein functions is necessary. Considerable accumulation of protein knowledge and recent developments on computer science provide an alternative way to complete this task, that is, designing computational methods. Several efforts have been made in this field. Most previous methods have adopted the protein sequence features or directly used the linkage from a protein-protein interaction (PPI) network. In this study, we proposed some novel multi-label classifiers, which adopted new embedding features to represent proteins. These features were derived from functional domains and a PPI network via word embedding and network embedding, respectively. The minimum redundancy maximum relevance method was used to assess the features, generating a feature list. Incremental feature selection, incorporating RAndom k-labELsets to construct multi-label classifiers, used such list to construct two optimum classifiers, corresponding to two key measurements: accuracy and exact match. These two classifiers had good performance, and they were superior to classifiers that used features extracted by traditional methods.

Identifying In Vitro Cultured Human Hepatocytes Markers with Machine Learning Methods Based on Single-Cell RNA-Seq Data.

Cell transplantation is an effective method for compensating for the loss of liver function and improve patient survival. However, given that hepatocytes cultivated in vitro have diverse developmental processes and physiological features, obtaining hepatocytes that can properly function in vivo is difficult. In the present study, we present an advanced computational analysis on single-cell transcriptional profiling to resolve the heterogeneity of the hepatocyte differentiation process in vitro and to mine biomarkers at different periods of differentiation. We obtained a batch of compressed and effective classification features with the Boruta method and ranked them using the Max-Relevance and Min-Redundancy method. Some key genes were identified during the in vitro culture of hepatocytes, including CD147, which not only regulates terminally differentiated cells in the liver but also affects cell differentiation. PPIA, which encodes a CD147 ligand, also appeared in the identified gene list, and the combination of the two proteins mediated multiple biological pathways. Other genes, such as TMSB10, TMEM176B, and CD63, which are involved in the maturation and differentiation of hepatocytes and assist different hepatic cell types in performing their roles were also identified. Then, several classifiers were trained and evaluated to obtain optimal classifiers and optimal feature subsets, using three classification algorithms (random forest, k-nearest neighbor, and decision tree) and the incremental feature selection method. The best random forest classifier with a 0.940 Matthews correlation coefficient was constructed to distinguish different hepatic cell types. Finally, classification rules were created for quantitatively describing hepatic cell types. In summary, This study provided potential targets for cell transplantation associated liver disease treatment strategies by elucidating the process and mechanism of hepatocyte development at both qualitative and quantitative levels.

Identification of Type 2 Diabetes Biomarkers From Mixed Single-Cell Sequencing Data With Feature Selection Methods.

Diabetes is the most common disease and a major threat to human health. Type 2 diabetes (T2D) makes up about 90% of all cases. With the development of high-throughput sequencing technologies, more and more fundamental pathogenesis of T2D at genetic and transcriptomic levels has been revealed. The recent single-cell sequencing can further reveal the cellular heterogenicity of complex diseases in an unprecedented way. With the expectation on the molecular essence of T2D across multiple cell types, we investigated the expression profiling of more than 1,600 single cells (949 cells from T2D patients and 651 cells from normal controls) and identified the differential expression profiling and characteristics at the transcriptomics level that can distinguish such two groups of cells at the single-cell level. The expression profile was analyzed by several machine learning algorithms, including Monte Carlo feature selection, support vector machine, and repeated incremental pruning to produce error reduction (RIPPER). On one hand, some T2D-associated genes (MTND4P24, MTND2P28, and LOC100128906) were discovered. On the other hand, we revealed novel potential pathogenic mechanisms in a rule manner. They are induced by newly recognized genes and neglected by traditional bulk sequencing techniques. Particularly, the newly identified T2D genes were shown to follow specific quantitative rules with diabetes prediction potentials, and such rules further indicated several potential functional crosstalks involved in T2D.

Identifying Methylation Signatures and Rules for COVID-19 With Machine Learning Methods.

The occurrence of coronavirus disease 2019 (COVID-19) has become a serious challenge to global public health. Definitive and effective treatments for COVID-19 are still lacking, and targeted antiviral drugs are not available. In addition, viruses can regulate host innate immunity and antiviral processes through the epigenome to promote viral self-replication and disease progression. In this study, we first analyzed the methylation dataset of COVID-19 using the Monte Carlo feature selection method to obtain a feature list. This feature list was subjected to the incremental feature selection method combined with a decision tree algorithm to extract key biomarkers, build effective classification models and classification rules that can remarkably distinguish patients with or without COVID-19. EPSTI1, NACAP1, SHROOM3, C19ORF35, and MX1 as the essential features play important roles in the infection and immune response to novel coronavirus. The six significant rules extracted from the optimal classifier quantitatively explained the expression pattern of COVID-19. Therefore, these findings validated that our method can distinguish COVID-19 at the methylation level and provide guidance for the diagnosis and treatment of COVID-19.

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.

Detecting Brain Structure-Specific Methylation Signatures and Rules for Alzheimer's Disease.

Alzheimer's disease (AD) is a progressive disease that leads to irreversible behavioral changes, erratic emotions, and loss of motor skills. These conditions make people with AD hard or almost impossible to take care of. Multiple internal and external pathological factors may affect or even trigger the initiation and progression of AD. DNA methylation is one of the most effective regulatory roles during AD pathogenesis, and pathological methylation alterations may be potentially different in the various brain structures of people with AD. Although multiple loci associated with AD initiation and progression have been identified, the spatial distribution patterns of AD-associated DNA methylation in the brain have not been clarified. According to the systematic methylation profiles on different structural brain regions, we applied multiple machine learning algorithms to investigate such profiles. First, the profile on each brain region was analyzed by the Boruta feature filtering method. Some important methylation features were extracted and further analyzed by the max-relevance and min-redundancy method, resulting in a feature list. Then, the incremental feature selection method, incorporating some classification algorithms, adopted such list to identify candidate AD-associated loci at methylation with structural specificity, establish a group of quantitative rules for revealing the effects of DNA methylation in various brain regions (i.e., four brain structures) on AD pathogenesis. Furthermore, some efficient classifiers based on essential methylation sites were proposed to identify AD samples. Results revealed that methylation alterations in different brain structures have different contributions to AD pathogenesis. This study further illustrates the complex pathological mechanisms of AD.