iMPT-FDNPL: Identification of Membrane Protein Types with Functional Domains and a Natural Language Processing Approach

PredictEFC: a fast and efficient multi-label classifier for predicting enzyme family classes

BACKGROUND

Enzymes play an irreplaceable and important role in maintaining the lives of living organisms. The Enzyme Commission (EC) number of an enzyme indicates its essential functions. Correct identification of the first digit (family class) of the EC number for a given enzyme is a hot topic in the past twenty years. Several previous methods adopted functional domain composition to represent enzymes. However, it would lead to dimension disaster, thereby reducing the efficiency of the methods. On the other hand, most previous methods can only deal with enzymes belonging to one family class. In fact, several enzymes belong to two or more family classes.

RESULTS

In this study, a fast and efficient multi-label classifier, named PredictEFC, was designed. To construct this classifier, a novel feature extraction scheme was designed for processing functional domain information of enzymes, which counting the distribution of each functional domain entry across seven family classes in the training dataset. Based on this scheme, each training or test enzyme was encoded into a 7-dimenion vector by fusing its functional domain information and above statistical results. Random k-labelsets (RAKEL) was adopted to build the classifier, where random forest was selected as the base classification algorithm. The two tenfold cross-validation results on the training dataset shown that the accuracy of PredictEFC can reach 0.8493 and 0.8370. The independent test on two datasets indicated the accuracy values of 0.9118 and 0.8777.

CONCLUSION

The performance of PredictEFC was slightly lower than the classifier directly using functional domain composition. However, its efficiency was sharply improved. The running time was less than one-tenth of the time of the classifier directly using functional domain composition. In additional, the utility of PredictEFC was superior to the classifiers using traditional dimensionality reduction methods and some previous methods, and this classifier can be transplanted for predicting enzyme family classes of other species. Finally, a web-server available at http://124.221.158.221/ was set up for easy usage.

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.

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.

Machine learning in computational modelling of membrane protein sequences and structures: From methodologies to applications

Membrane proteins mediate a wide spectrum of biological processes, such as signal transduction and cell communication. Due to the arduous and costly nature inherent to the experimental process, membrane proteins have long been devoid of well-resolved atomic-level tertiary structures and, consequently, the understanding of their functional roles underlying a multitude of life activities has been hampered. Currently, computational tools dedicated to furthering the structure-function understanding are primarily focused on utilizing intelligent algorithms to address a variety of site-wise prediction problems (e.g., topology and interaction sites), but are scattered across different computing sources. Moreover, the recent advent of deep learning techniques has immensely expedited the development of computational tools for membrane protein-related prediction problems. Given the growing number of applications optimized particularly by manifold deep neural networks, we herein provide a review on the current status of computational strategies mainly in membrane protein type classification, topology identification, interaction site detection, and pathogenic effect prediction. Meanwhile, we provide an overview of how the entire prediction process proceeds, including database collection, data pre-processing, feature extraction, and method selection. This review is expected to be useful for developing more extendable computational tools specific to membrane proteins.

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.

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 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.

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.

Identification of methylation signatures associated with CAR T cell in B-cell acute lymphoblastic leukemia and non-hodgkin’s lymphoma

CD19-targeted CAR T cell immunotherapy has exceptional efficacy for the treatment of B-cell malignancies. B-cell acute lymphocytic leukemia and non-Hodgkin’s lymphoma are two common B-cell malignancies with high recurrence rate and are refractory to cure. Although CAR T-cell immunotherapy overcomes the limitations of conventional treatments for such malignancies, failure of treatment and tumor recurrence remain common. In this study, we searched for important methylation signatures to differentiate CAR-transduced and untransduced T cells from patients with acute lymphoblastic leukemia and non-Hodgkin’s lymphoma. First, we used three feature ranking methods, namely, Monte Carlo feature selection, light gradient boosting machine, and least absolute shrinkage and selection operator, to rank all methylation features in order of their importance. Then, the incremental feature selection method was adopted to construct efficient classifiers and filter the optimal feature subsets. Some important methylated genes, namely, SERPINB6, ANK1, PDCD5, DAPK2, and DNAJB6, were identified. Furthermore, the classification rules for distinguishing different classes were established, which can precisely describe the role of methylation features in the classification. Overall, we applied advanced machine learning approaches to the high-throughput data, investigating the mechanism of CAR T cells to establish the theoretical foundation for modifying CAR T cells.

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.

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.

Screening gene signatures for clinical response subtypes of lung transplantation

Lung is the most important organ in the human respiratory system, whose normal functions are quite essential for human beings. Under certain pathological conditions, the normal lung functions could no longer be maintained in patients, and lung transplantation is generally applied to ease patients' breathing and prolong their lives. However, several risk factors exist during and after lung transplantation, including bleeding, infection, and transplant rejections. In particular, transplant rejections are difficult to predict or prevent, leading to the most dangerous complications and severe status in patients undergoing lung transplantation. Given that most common monitoring and validation methods for lung transplantation rejections may take quite a long time and have low reproducibility, new technologies and methods are required to improve the efficacy and accuracy of rejection monitoring after lung transplantation. Recently, one previous study set up the gene expression profiles of patients who underwent lung transplantation. However, it did not provide a tool to predict lung transplantation responses. Here, a further deep investigation was conducted on such profiling data. A computational framework, incorporating several machine learning algorithms, such as feature selection methods and classification algorithms, was built to establish an effective prediction model distinguishing patient into different clinical subgroups, corresponding to different rejection responses after lung transplantation. Furthermore, the framework also screened essential genes with functional enrichments and create quantitative rules for the distinction of patients with different rejection responses to lung transplantation. The outcome of this contribution could provide guidelines for clinical treatment of each rejection subtype and contribute to the revealing of complicated rejection mechanisms of lung transplantation.

Analysis of Lymphoma-Related Genes with Gene Ontology and Kyoto Encyclopedia of Genes and Genomes Enrichment

Lymphoma is a serious malignant tumor that contains more than 70 different types and seriously endangers the body's lymphatic system. The lymphatic system is the regulatory center of the immune system and is important in the immune response to foreign antigens and tumors. Studies showed that multiple genetic variants are associated with lymphoma but determining the pathogenic mechanisms remains a challenge. In the present study, we first applied the Gene Ontology (GO) and KEGG pathway enrichment analyses of lymphoma-associated and lymphoma-nonassociated genes. Next, the Boruta and max-relevance and min-redundancy feature selection methods were performed to filter and rank features. Then, features preselected and ranked using the incremental feature selection method were applied for the decision tree model to identify the best GO terms and KEGG pathways and extract classification rules. Results indicate that our predicted features, such as B-cell activation, negative regulation of protein processing, negative regulation of mast cell cytokine production, and natural killer cell-mediated cytotoxicity, are associated with the biological process of lymphoma, consistent with those of recent publications. This study provides a new perspective for future research on the molecular mechanisms of lymphoma.

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.

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 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.

Identifying COVID-19 Severity-Related SARS-CoV-2 Mutation Using a Machine Learning Method

SARS-CoV-2 shows great evolutionary capacity through a high frequency of genomic variation during transmission. Evolved SARS-CoV-2 often demonstrates resistance to previous vaccines and can cause poor clinical status in patients. Mutations in the SARS-CoV-2 genome involve mutations in structural and nonstructural proteins, and some of these proteins such as spike proteins have been shown to be directly associated with the clinical status of patients with severe COVID-19 pneumonia. In this study, we collected genome-wide mutation information of virulent strains and the severity of COVID-19 pneumonia in patients varying depending on their clinical status. Important protein mutations and untranslated region mutations were extracted using machine learning methods. First, through Boruta and four ranking algorithms (least absolute shrinkage and selection operator, light gradient boosting machine, max-relevance and min-redundancy, and Monte Carlo feature selection), mutations that were highly correlated with the clinical status of the patients were screened out and sorted in four feature lists. Some mutations such as D614G and V1176F were shown to be associated with viral infectivity. Moreover, previously unreported mutations such as A320V of nsp14 and I164ILV of nsp14 were also identified, which suggests their potential roles. We then applied the incremental feature selection method to each feature list to construct efficient classifiers, which can be directly used to distinguish the clinical status of COVID-19 patients. Meanwhile, four sets of quantitative rules were set up, which can help us to more intuitively understand the role of each mutation in differentiating the clinical status of COVID-19 patients. Identified key mutations linked to virologic properties will help better understand the mechanisms of infection and will aid in the development of antiviral treatments.

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.

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.

Drug-Drug Interactions Prediction Using Fingerprint Only

Combination drug therapy is an efficient way to treat complicated diseases. Drug-drug interaction (DDI) is an important research topic in this therapy as patient safety is a problem when two or more drugs are taken at the same time. Traditionally, in vitro experiments and clinical trials are common ways to determine DDIs. However, these methods cannot meet the requirements of large-scale tests. It is an alternative way to develop computational methods for predicting DDIs. Although several previous methods have been proposed, they always need several types of drug information, limiting their applications. In this study, we proposed a simple computational method to predict DDIs. In this method, drugs were represented by their fingerprint features, which are most widely used in investigating drug-related problems. These features were refined by three models, including addition, subtraction, and Hadamard models, to generate the representation of DDIs. The powerful classification algorithm, random forest, was picked up to build the classifier. The results of two types of tenfold cross-validation on the classifier indicated good performance for discovering novel DDIs among known drugs and acceptable performance for identifying DDIs between known drugs and unknown drugs or among unknown drugs. Although the classifier adopted a sample scheme to represent DDIs, it was still superior to other methods, which adopted features generated by some advanced computer algorithms. Furthermore, a user-friendly web-server, named DDIPF (http://106.14.164.77:5004/DDIPF/), was developed to implement the classifier.

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.

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.

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.

Exploring the Genomic Patterns in Human and Mouse Cerebellums Via Single-Cell Sequencing and Machine Learning Method

In mammals, the cerebellum plays an important role in movement control. Cellular research reveals that the cerebellum involves a variety of sub-cell types, including Golgi, granule, interneuron, and unipolar brush cells. The functional characteristics of cerebellar cells exhibit considerable differences among diverse mammalian species, reflecting a potential development and evolution of nervous system. In this study, we aimed to recognize the transcriptional differences between human and mouse cerebellum in four cerebellar sub-cell types by using single-cell sequencing data and machine learning methods. A total of 321,387 single-cell sequencing data were used. The 321,387 cells included 4 cell types, i.e., Golgi (5,048, 1.57%), granule (250,307, 77.88%), interneuron (60,526, 18.83%), and unipolar brush (5,506, 1.72%) cells. Our results showed that by using gene expression profiles as features, the optimal classification model could achieve very high even perfect performance for Golgi, granule, interneuron, and unipolar brush cells, respectively, suggesting a remarkable difference between the genomic profiles of human and mouse. Furthermore, a group of related genes and rules contributing to the classification was identified, which might provide helpful information for deepening the understanding of cerebellar cell heterogeneity and evolution.

Identification of protein functions in mouse with a label space partition method

Protein is very important for almost all living creatures because it participates in most complicated and essential biological processes. Determining the functions of given proteins is one of the most essential problems in protein science. Such determination can be conducted through traditional experiments. However, the experimental methods are always time-consuming and of high costs. In recent years, computational methods give useful aids for identification of protein functions. This study presented a new multi-label classifier for identifying functions of mouse proteins. Due to the number of functional types, which were termed as labels in the classification procedure, a label space partition method was employed to divide labels into some partitions. On each partition, a multi-label classifier was constructed. The classifiers based on all partitions were integrated in the proposed classifier. The cross-validation results proved that the proposed classifier was of good performance. Classifiers with label partition were superior to those without label partition or with random label partition.

Predicting Heart Cell Types by Using Transcriptome Profiles and a Machine Learning Method

The heart is an essential organ in the human body. It contains various types of cells, such as cardiomyocytes, mesothelial cells, endothelial cells, and fibroblasts. The interactions between these cells determine the vital functions of the heart. Therefore, identifying the different cell types and revealing the expression rules in these cell types are crucial. In this study, multiple machine learning methods were used to analyze the heart single-cell profiles with 11 different heart cell types. The single-cell profiles were first analyzed via light gradient boosting machine method to evaluate the importance of gene features on the profiling dataset, and a ranking feature list was produced. This feature list was then brought into the incremental feature selection method to identify the best features and build the optimal classifiers. The results suggested that the best decision tree (DT) and random forest classification models achieved the highest weighted F1 scores of 0.957 and 0.981, respectively. The selected features, such as NPPA, LAMA2, DLC1, and the classification rules extracted from the optimal DT classifier played a crucial role in cardiac structure and function in recent research and enrichment analysis. In particular, some lncRNAs (LINC02019, NEAT1) were found to be quite important for the recognition of different cardiac cell types. In summary, these findings provide a solid academic foundation for the development of molecular diagnostics and biomarker discovery for cardiac diseases.

Predicting RNA 5-Methylcytosine Sites by Using Essential Sequence Features and Distributions

Methylation is one of the most common and considerable modifications in biological systems mediated by multiple enzymes. Recent studies have shown that methylation has been widely identified in different RNA molecules. RNA methylation modifications have various kinds, such as 5-methylcytosine (m5C). However, for individual methylation sites, their functions still remain to be elucidated. Testing of all methylation sites relies heavily on high-throughput sequencing technology, which is expensive and labor consuming. Thus, computational prediction approaches could serve as a substitute. In this study, multiple machine learning models were used to predict possible RNA m5C sites on the basis of mRNA sequences in human and mouse. Each site was represented by several features derived from $k$ -mers of an RNA subsequence containing such site as center. The powerful max-relevance and min-redundancy (mRMR) feature selection method was employed to analyse these features. The outcome feature list was fed into incremental feature selection method, incorporating four classification algorithms, to build efficient models. Furthermore, the sites related to features used in the models were also investigated.

Predicting Human Protein Subcellular Locations by Using a Combination of Network and Function Features

Given the limitation of technologies, the subcellular localizations of proteins are difficult to identify. Predicting the subcellular localization and the intercellular distribution patterns of proteins in accordance with their specific biological roles, including validated functions, relationships with other proteins, and even their specific sequence characteristics, is necessary. The computational prediction of protein subcellular localizations can be performed on the basis of the sequence and the functional characteristics. In this study, the protein-protein interaction network, functional annotation of proteins and a group of direct proteins with known subcellular localization were used to construct models. To build efficient models, several powerful machine learning algorithms, including two feature selection methods, four classification algorithms, were employed. Some key proteins and functional terms were discovered, which may provide important contributions for determining protein subcellular locations. Furthermore, some quantitative rules were established to identify the potential subcellular localizations of proteins. As the first prediction model that uses direct protein annotation information (i.e., functional features) and STRING-based protein-protein interaction network (i.e., network features), our computational model can help promote the development of predictive technologies on subcellular localizations and provide a new approach for exploring the protein subcellular localization patterns and their potential biological importance.