Investigating the gene expression profiles of cells in seven embryonic stages with machine learning algorithms

TMPpred: A support vector machine-based thermophilic protein identifier

MOTIVATION

The thermostability of proteins will cause them to break the temperature binding and play more functions. Using machine learning, we explored the mechanism of and reasons for protein thermostability characteristics.

RESULTS

Different from other methods that only pursue the performance of models, we aim to find important features so as to provide a powerful reference for in vitro experiments. We transformed this problem into a binary classification problem, that is, the distinction between thermophilic proteins and nonthermophilic proteins. Using support vector machine-based model construction and analysis, we inferred that Gly, Ala, Ser and Thr may be the most important components at the residue level that determine the thermal stability of proteins. It is also noteworthy that our proposed model obtains an Sn of 0.892, an Sp of 0.857, an ACC of 0.87566 and an AUC of 0.874. To facilitate other researchers, we wrapped our model and deployed it as a web server, which is accessible at http://112.124.26.17:7000/TMPpred/index.html.

Machine learning-assisted imaging analysis of a human epiblast model

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

Identifying COVID-19-Specific Transcriptomic Biomarkers with Machine Learning Methods

COVID-19, a severe respiratory disease caused by a new type of coronavirus SARS-CoV-2, has been spreading all over the world. Patients infected with SARS-CoV-2 may have no pathogenic symptoms, i.e., presymptomatic patients and asymptomatic patients. Both patients could further spread the virus to other susceptible people, thereby making the control of COVID-19 difficult. The two major challenges for COVID-19 diagnosis at present are as follows: (1) patients could share similar symptoms with other respiratory infections, and (2) patients may not have any symptoms but could still spread the virus. Therefore, new biomarkers at different omics levels are required for the large-scale screening and diagnosis of COVID-19. Although some initial analyses could identify a group of candidate gene biomarkers for COVID-19, the previous work still could not identify biomarkers capable for clinical use in COVID-19, which requires disease-specific diagnosis compared with other multiple infectious diseases. As an extension of the previous study, optimized machine learning models were applied in the present study to identify some specific qualitative host biomarkers associated with COVID-19 infection on the basis of a publicly released transcriptomic dataset, which included healthy controls and patients with bacterial infection, influenza, COVID-19, and other kinds of coronavirus. This dataset was first analysed by Boruta, Max-Relevance and Min-Redundancy feature selection methods one by one, resulting in a feature list. This list was fed into the incremental feature selection method, incorporating one of the classification algorithms to extract essential biomarkers and build efficient classifiers and classification rules. The capacity of these findings to distinguish COVID-19 with other similar respiratory infectious diseases at the transcriptomic level was also validated, which may improve the efficacy and accuracy of COVID-19 diagnosis.

CWLy-RF: A novel approach for identifying cell wall lyases based on random forest classifier

Drug resistance of pathogenic bacteria has become increasingly serious due to the abuse of antibiotics in recent years. Researchers have found that cell wall lyases are effective antibacterial agents that can specifically recognize target bacteria and degrade bacterial peptidoglycan. Traditional wet experiments are usually expensive, time-consuming and laborious for the identification of lyases. Therefore, there is an urgent need to develop prediction tools based on computer methods to identify lyases quickly and accurately. In this paper, a new predictor, CWLy-RF, is proposed based on the random forest (RF) algorithm to identify cell wall lyases. In this method, we combined three features, namely, 400D, 188D and the composition of k-spaced amino acid group pairs, using mixed-feature representation methods. Afterward, we improved the feature representation ability with the selected top 100 features by using the information gain method and trained a predictive model using RF. The constructed prediction model is evaluated by using 10-fold cross-validation. The accuracy obtained was 96.09%, the AUC was 0.993, the MCC was 0.922, the sensitivity was 94.92%, and the specificity was 97.32%. We have proved that the proposed predictor CWLy-RF is superior to other latest models, and it will hopefully become an effective and useful tool for identifying lyases.

Analysis of the Sequence Characteristics of Antifreeze Protein

Antifreeze protein (AFP) is a proteinaceous compound with improved antifreeze ability and binding ability to ice to prevent its growth. As a surface-active material, a small number of AFPs have a tremendous influence on the growth of ice. Therefore, identifying novel AFPs is important to understand protein–ice interactions and create novel ice-binding domains. To date, predicting AFPs is difficult due to their low sequence similarity for the ice-binding domain and the lack of common features among different AFPs. Here, a computational engine was developed to predict the features of AFPs and reveal the most important 39 features for AFP identification, such as antifreeze-like/N-acetylneuraminic acid synthase C-terminal, insect AFP motif, C-type lectin-like, and EGF-like domain. With this newly presented computational method, a group of previously confirmed functional AFP motifs was screened out. This study has identified some potential new AFP motifs and contributes to understanding biological antifreeze mechanisms.

HelPredictor models single-cell transcriptome to predict human embryo lineage allocation

The in-depth understanding of cellular fate decision of human preimplantation embryos has prompted investigations on how changes in lineage allocation, which is far from trivial and remains a time-consuming task by experimental methods. It is desirable to develop a novel effective bioinformatics strategy to consider transitions of coordinated embryo lineage allocation and stage-specific patterns. There are rapidly growing applications of machine learning models to interpret complex datasets for identifying candidate development-related factors and lineage-determining molecular events. Here we developed the first machine learning platform, HelPredictor, that integrates three feature selection methods, namely, principal components analysis, F-score algorithm and squared coefficient of variation, and four classical machine learning classifiers that different combinations of methods and classifiers have independent outputs by increment feature selection method. With application to single-cell sequencing data of human embryo, HelPredictor not only achieved 94.9% and 90.9% respectively with cross-validation and independent test, but also fast classified different embryonic lineages and their development trajectories using less HelPredictor-predicted factors. The above-mentioned candidate lineage-specific genes were discussed in detail and were clustered for exploring transitions of embryonic heterogeneity. Our tool can fast and efficiently reveal potential lineage-specific and stage-specific biomarkers and provide insights into how advanced computational tools contribute to development research. The source code is available at https://github.com/liameihao/HelPredictor.

RFhy-m2G: Identification of RNA N2-methylguanosine modification sites based on random forest and hybrid features

N2-methylguanosine is a post-transcriptional modification of RNA that is found in eukaryotes and archaea. The biological function of m2G modification discovered so far is to control and stabilize the three-dimensional structure of tRNA and the dynamic barrier of reverse transcription. To discover additional biological functions of m2G, it is necessary to develop time-saving and labor-saving calculation tools to identify m2G. In this paper, based on hybrid features and a random forest, a novel predictor, RFhy-m2G, was developed to identify the m2G modification sites for three species. The hybrid feature used by the predictor is used to fuse the three features of ENAC, PseDNC, and NPPS. These three features include primary sequence derivation properties, physicochemical properties, and position-specific properties. Since there are redundant features in hybrid features, MRMD2.0 is used for optimal feature selection. Through feature analysis, it is found that the optimal hybrid features obtained still contain three kinds of properties, and the hybrid features can more accurately identify m2G modification sites and improve prediction performance. Based on five-fold cross-validation and independent testing to evaluate the prediction model, the accuracies obtained were 0.9982 and 0.9417, respectively. The robustness of the predictor is demonstrated by comparisons with other predictors.

Identification of Common Genes and Pathways in Eight Fibrosis Diseases

Acute and chronic inflammation often leads to fibrosis, which is also the common and final pathological outcome of chronic inflammatory diseases. To explore the common genes and pathogenic pathways among different fibrotic diseases, we collected all the reported genes of the eight fibrotic diseases: eye fibrosis, heart fibrosis, hepatic fibrosis, intestinal fibrosis, lung fibrosis, pancreas fibrosis, renal fibrosis, and skin fibrosis. We calculated the Kyoto Encyclopedia of Genes and Genomes (KEGG) and Gene Ontology (GO) enrichment scores of all fibrotic disease genes. Each gene was encoded using KEGG and GO enrichment scores, which reflected how much a gene can affect this function. For each fibrotic disease, by comparing the KEGG and GO enrichment scores between reported disease genes and other genes using the Monte Carlo feature selection (MCFS) method, the key KEGG and GO features were identified. We compared the gene overlaps among eight fibrotic diseases and connective tissue growth factor (CTGF) was finally identified as the common key molecule. The key KEGG and GO features of the eight fibrotic diseases were all screened by MCFS method. Moreover, we interestingly found overlaps of pathways between renal fibrosis and skin fibrosis, such as GO:1901890-positive regulation of cell junction assembly, as well as common regulatory genes, such as CTGF, which is the key molecule regulating fibrogenesis. We hope to offer a new insight into the cellular and molecular mechanisms underlying fibrosis and therefore help leading to the development of new drugs, which specifically delay or even improve the symptoms of fibrosis.

Multiple Feature Selection Strategies Identified Novel Cardiac Gene Expression Signature for Heart Failure

Heart failure (HF) is a serious condition in which the support of blood pumped by the heart is insufficient to meet the demands of body at a normal cardiac filling pressure. Approximately 26 million patients worldwide are suffering from heart failure and about 17–45% of patients with heart failure die within 1-year, and the majority die within 5-years admitted to a hospital. The molecular mechanisms underlying the progression of heart failure have been poorly studied. We compared the gene expression profiles between patients with heart failure (n = 177) and without heart failure (n = 136) using multiple feature selection strategies and identified 38 HF signature genes. The support vector machine (SVM) classifier based on these 38 genes evaluated with leave-one-out cross validation (LOOCV) achieved great performance with sensitivity of 0.983 and specificity of 0.963. The network analysis suggested that the hub gene SMOC2 may play important roles in HF. Other genes, such as FCN3, HMGN2, and SERPINA3, also showed great promises. Our results can facilitate the early detection of heart failure and can reveal its molecular mechanisms.

Distinguishing Glioblastoma Subtypes by Methylation Signatures

Glioblastoma, also called glioblastoma multiform (GBM), is the most aggressive cancer that initiates within the brain. GBM is produced in the central nervous system. Cancer cells in GBM are similar to stem cells. Several different schemes for GBM stratification exist. These schemes are based on intertumoral molecular heterogeneity, preoperative images, and integrated tumor characteristics. Although the formation of glioblastoma is remarkably related to gene methylation, GBM has been poorly classified by epigenetics. To classify glioblastoma subtypes on the basis of different degrees of genes' methylation, we adopted several powerful machine learning algorithms to identify numerous methylation features (sites) associated with the classification of GBM. The features were first analyzed by an excellent feature selection method, Monte Carlo feature selection (MCFS), resulting in a feature list. Then, such list was fed into the incremental feature selection (IFS), incorporating one classification algorithm, to extract essential sites. These sites can be annotated onto coding genes, such as CXCR4, TBX18, SP5, and TMEM22, and enriched in relevant biological functions related to GBM classification (e.g., subtype-specific functions). Representative functions, such as nervous system development, intrinsic plasma membrane component, calcium ion binding, systemic lupus erythematosus, and alcoholism, are potential pathogenic functions that participate in the initiation and progression of glioblastoma and its subtypes. With these sites, an efficient model can be built to classify the subtypes of glioblastoma.

Identification of Post-myocardial Infarction Blood Expression Signatures Using Multiple Feature Selection Strategies

Myocardial infarction (MI) is a type of serious heart attack in which the blood flow to the heart is suddenly interrupted, resulting in injury to the heart muscles due to a lack of oxygen supply. Although clinical diagnosis methods can be used to identify the occurrence of MI, using the changes of molecular markers or characteristic molecules in blood to characterize the early phase and later trend of MI will help us choose a more reasonable treatment plan. Previously, comparative transcriptome studies focused on finding differentially expressed genes between MI patients and healthy people. However, signature molecules altered in different phases of MI have not been well excavated. We developed a set of computational approaches integrating multiple machine learning algorithms, including Monte Carlo feature selection (MCFS), incremental feature selection (IFS), and support vector machine (SVM), to identify gene expression characteristics on different phases of MI. 134 genes were determined to serve as features for building optimal SVM classifiers to distinguish acute MI and post-MI. Subsequently, functional enrichment analyses followed by protein-protein interaction analysis on 134 genes identified several hub genes (IL1R1, TLR2, and TLR4) associated with progression of MI, which can be used as new diagnostic molecules for MI.

Identification and Analysis of Dysfunctional Genes and Pathways in CD8+ T Cells of Non-Small Cell Lung Cancer Based on RNA Sequencing

Lung cancer, the most common of malignant tumors, is typically of the non-small cell (NSCLC) type. T-cell-based immunotherapies are a promising and powerful approach to treating NSCLCs. To characterize the CD8⁺ T cells of non-small cell lung cancer, we re-analyzed the published RNA-Seq gene expression profiles of 36 CD8⁺ T cell isolated from tumor (TIL) samples and 32 adjacent uninvolved lung (NTIL) samples. With an advanced Monte Carlo method of feature selection, we identified the CD8⁺ TIL specific expression patterns. These patterns revealed the key dysfunctional genes and pathways in CD8⁺ TIL and shed light on the molecular mechanisms of immunity and use of immunotherapy.

The Serum MicroRNA Signatures for Pancreatic Cancer Detection and Operability Evaluation

Pancreatic cancer (PC) has high morbidity and mortality. It is the fourth leading cause of cancer death. Its diagnosis and treatment are difficult. Liquid biopsy makes early diagnosis of pancreatic cancer possible. We analyzed the expression profiles of 2,555 serum miRNAs in 100 pancreatic cancer patients and 150 healthy controls. With advanced feature selection methods, we identified 13 pancreatic cancer signature miRNAs that can classify the pancreatic cancer patients and healthy controls. For pancreatic cancer treatment, operation is still the first choice. But many pancreatic cancer patients are already inoperable. Therefore, we compared the 79 inoperable and 21 operable patients and identified 432 miRNAs that can predict whether a pancreatic cancer patient was operable. The functional analysis of the 13 pancreatic cancer signatures and the 432 operability miRNAs revealed the molecular mechanisms of pancreatic cancer and shield light on the diagnosis and therapy of pancreatic cancer in clinical practice.