A Comprehensive Evaluation of Cross-Omics Blood-Based Biomarkers for Neuropsychiatric Disorders

The identification of peripheral multi-omics biomarkers of brain disorders has long been hindered by insufficient sample size and confounder influence. This study aimed to compare biomarker potential for different molecules and diseases. We leveraged summary statistics of five blood quantitative trait loci studies (N = 1980 to 22,609) and genome-wide association studies (N = 9725 to 500,199) from 14 different brain disorders, such as Schizophrenia (SCZ) and Alzheimer’s Disease (AD). We applied summary-based and two-sample Mendelian Randomization to estimate the associations between blood molecules and brain disorders. We identified 524 RNA, 807 methylation sites, 29 proteins, seven cytokines, and 22 metabolites having a significant association with at least one of 14 brain disorders. Simulation analyses indicated that a cross-omics combination of biomarkers had better performance for most disorders, and different disorders could associate with different omics. We identified an 11-methylation-site model for SCZ diagnosis (Area Under Curve, AUC = 0.74) by analyzing selected candidate markers in published datasets (total N = 6098). Moreover, we constructed an 18-methylation-sites model that could predict the prognosis of elders with mild cognitive impairment (hazard ratio = 2.32). We provided an association landscape between blood cross-omic biomarkers and 14 brain disorders as well as a suggestion guide for future clinical discovery and application.

Establishment of a 5 DNA Methylation Site Prognostic Signature Associated with N6-Methyladenosine in Lung Adenocarcinoma

Background: There is a high incidence of lung adenocarcinoma (LUAD). Even with surgery, targeted therapy and immunotherapy, the survival rate of LUAD patients is still low. N6-methyladenosine (m6A) and DNA methylation markers can help with the diagnosis and treatment of LUAD patients. Therefore, it is necessary to identify a novel m6A-related DNA methylation sites signature to predict the survival of patients with LUAD. Methods: In this study, we screened 15 m6A-related genes and their 217 methylation sites. RNA sequencing data of 15 genes and the clinicopathological parameters of TCGA-LUAD were obtained from the TCGA database (http://cancergenome.nih.gov/). The LUAD-DNA CpG site information was obtained from the Illumina Human Methylation 450 BeadChip (Illumina, San Diego, CA, United States). The methylation sites related to prognosis were screened using univariate COX analysis, and the independent predictors of LUAD patients were identified using multivariate COX analysis of least absolute shrinkage and selection operator (LASSO) Cox regression analysis. Finally, a model with 5 methylation sites as the main body to predict the prognosis of OS in patients with LUAD was obtained. According to the risk grouping of the prediction model, Kaplan-Meier curve and the receiver operating characteristic (ROC) curve were performed in the test and training sets to assess the predicted capacity of the model. In addition, a nomogram constructed by combining the risk score of methylation group and other related clinicopathological factors to verify the reliability of our model.Results: We constructed a m6A-related 5-DNA methylation site model to predict OS in LUAD patients. According to the results of the Kaplan-Meier curve, both the test set and the training set, the high-risk group showed a worse prognosis. The AUCs of the 5 DNA methylation signature at 1, 5 and 10 years in test datasets were 0.730, 0.649 and 0.726, respectively, and 0.679, 0.656 and 0.732 in training datasets. Finally, we constructed a nomogram to further verify the reliability of the model.Conclusion: In this study, we analyzed the methylation sites of m6A-related genes and established a m6A-related 5-DNA methylation site model to predict OS in LUAD patients.

SSMFN: a fused spatial and sequential deep learning model for methylation site prediction

Background Conventional in vivo methods for post-translational modification site prediction such as spectrophotometry, Western blotting, and chromatin immune precipitation can be very expensive and time-consuming. Neural networks (NN) are one of the computational approaches that can predict effectively the post-translational modification site. We developed a neural network model, namely the Sequential and Spatial Methylation Fusion Network (SSMFN), to predict possible methylation sites on protein sequences. Method We designed our model to be able to extract spatial and sequential information from amino acid sequences. Convolutional neural networks (CNN) is applied to harness spatial information, while long short-term memory (LSTM) is applied for sequential data. The latent representation of the CNN and LSTM branch are then fused. Afterwards, we compared the performance of our proposed model to the state-of-the-art methylation site prediction models on the balanced and imbalanced dataset. Results Our model appeared to be better in almost all measurement when trained on the balanced training dataset. On the imbalanced training dataset, all of the models gave better performance since they are trained on more data. In several metrics, our model also surpasses the PRMePred model, which requires a laborious effort for feature extraction and selection. Conclusion Our models achieved the best performance across different environments in almost all measurements. Also, our result suggests that the NN model trained on a balanced training dataset and tested on an imbalanced dataset will offer high specificity and low sensitivity. Thus, the NN model for methylation site prediction should be trained on an imbalanced dataset. Since in the actual application, there are far more negative samples than positive samples.

EDLm6APred: ensemble deep learning approach for mRNA m6A site prediction

Background As a common and abundant RNA methylation modification, N6-methyladenosine (m6A) is widely spread in various species' transcriptomes, and it is closely related to the occurrence and development of various life processes and diseases. Thus, accurate identification of m6A methylation sites has become a hot topic. Most biological methods rely on high-throughput sequencing technology, which places great demands on the sequencing library preparation and data analysis. Thus, various machine learning methods have been proposed to extract various types of features based on sequences, then occupied conventional classifiers, such as SVM, RF, etc., for m6A methylation site identification. However, the identification performance relies heavily on the extracted features, which still need to be improved. Results This paper mainly studies feature extraction and classification of m6A methylation sites in a natural language processing way, which manages to organically integrate the feature extraction and classification simultaneously, with consideration of upstream and downstream information of m6A sites. One-hot, RNA word embedding, and Word2vec are adopted to depict sites from the perspectives of the base as well as its upstream and downstream sequence. The BiLSTM model, a well-known sequence model, was then constructed to discriminate the sequences with potential m6A sites. Since the above-mentioned three feature extraction methods focus on different perspectives of m6A sites, an ensemble deep learning predictor (EDLm6APred) was finally constructed for m6A site prediction. Experimental results on human and mouse data sets show that EDLm6APred outperforms the other single ones, indicating that base, upstream, and downstream information are all essential for m6A site detection. Compared with the existing m6A methylation site prediction models without genomic features, EDLm6APred obtains 86.6% of the area under receiver operating curve on the human data sets, indicating the effectiveness of sequential modeling on RNA. To maximize user convenience, a webserver was developed as an implementation of EDLm6APred and made publicly available at www.xjtlu.edu.cn/biologicalsciences/EDLm6APred. Conclusions Our proposed EDLm6APred method is a reliable predictor for m6A methylation sites.

IGF-2 modified by the m6A demethylation enzyme ALKBH5 in the ossification of the ligamentum flavum

Abstract Background: Ossification of the ligamentum flavum (OLF) is a pathological heterotopic ossification of the paravertebral ligament. However, the specific pathophysiology mechanism of this disease is still unknown. The m 6 A methylation and its potential functions in OLF remain to be unexplored. Method: In this study, we performed a transcriptome-wide methylation analysis using the OLF and normal ligaments to explore the mechanism of OLF. Common and region-specific methylation have different preferences for methylation site selection and thereby different impacts on their biological functions. We screened out the methylase-ALKBH5, and by promoting or inhibiting its expression, observing the content of m 6 A, and measuring the ossification of ligaments, and then measuring IGF expression situation by alizarin red staining, alkaline phosphatase, immunofluorescence, immunohistochemistry, etc. Result: MeRIP-seq and qPCR showed that the m6A methylation level of OLF group was usually higher than that of control group. In addition, we found that ALKBH5 is an important demethyltransferase in OLF, which promotes the expression of m 6 A. ALKBH5 promotes the expression of IGF-2, which in turn promotes osteogenesis in OLF. Conclusion: Overall, we provided a region-specific map of m 6 A methylation and characterized the distinct features of specific and common methylation in OLF, and we proved that IGF-2 can be regulated by ALKBH5 to promote the process of OLF.

IGF-2 Modified by the m6A Demethylation Enzyme ALKBH5 in the Ossification of the Ligamentum Flavum

Background: Ossification of the ligamentum flavum (OLF) is a pathological heterotopic ossification of the paravertebral ligament. However, the specific pathophysiology mechanism of this disease is still unknown. The m6A methylation and its potential functions in OLF remain to be unexplored. Method: In this study, we performed a transcriptome-wide methylation analysis using the OLF and normal ligaments to explore the mechanism of OLF. Common and region-specific methylation have different preferences for methylation site selection and thereby different impacts on their biological functions. We screened out the methylase-ALKBH5, and by promoting or inhibiting its expression, observing the content of m6A, and measuring the ossification of ligaments, and then measuring IGF expression situation by alizarin red staining, alkaline phosphatase, immunofluorescence, immunohistochemistry, etc. Result: MeRIP-seq and qPCR showed that the m6A methylation level of OLF group was usually higher than that of control group. In addition, we found that ALKBH5 is an important demethyltransferase in OLF, which promotes the expression of m6A. ALKBH5 promotes the expression of IGF-2, which in turn promotes osteogenesis in OLF.Conclusion: Overall, we provided a region-specific map of m6A methylation and characterized the distinct features of specific and common methylation in OLF, and we proved that IGF-2 can be regulated by ALKBH5 to promote the process of OLF.

Identification of 2’-O-methylation Site by Investigating Multi-feature Extracting Techniques

Background: RNA methylation is a reversible post-transcriptional modification involving numerous biological processes. Ribose 2'-O-methylation is part of RNA methylation. It has shown that ribose 2'-O-methylation plays an important role in immune recognition and other pathogenesis. Objective: We aim to design a computational method to identify 2'-O-methylation. Methods: Different from the experimental method, we propose a computational workflow to identify the methylation site based on the multi-feature extracting algorithm. Results: With a voting procedure based on 7 best feature-classifier combinations, we achieved Accuracy of 76.5% in 10-fold cross-validation. Furthermore, we optimized features and input the optimized features into SVM. As a result, the AUC reached to 0.813. Conclusion: The RNA sample, especially the negative samples, used in this study are more objective and strict, so we obtained more representative results than state-of-arts studies.

Edge sparse PCA based on gene network for correcting cell type heterogeneity in epigenome-wide association studies

Background: In epigenome-wide association studies (EWAS), the mixed methylation expression caused by the combination of different cell types may lead the researchers to find the false methylation site related to the phenotype of interest. In order to fix this problem, researchers have proposed some non-reference methods based on sparse principle component analysis (PCA) to correct the EWAS false discovery. However, the existing model assumes that all methylation site have the same a priori probability in each PC load, but it is known that there already has network structure in the genetic variable corresponding to the methylation site. In this paper, we show that the results of the existing EWAS correction model are still not good enough. If we can integrate the existing methylation network as prior knowledge into the sparse PCA model, we can effectively improve the correction ability of the existing model. Result: Based on the above ideas, we propose GN-ReFAEWAS, a model which uses the prior methylation gene network structure into the PCA framework for feature extraction. This model can be used to correct the false discovery in EWAS. GN-ReFAEWAS model does not need cell counting data and can estimate cell type composition through methylation principal component data. The key of this model is to solve a sparse regularize problem of methylation network. This paper uses regularize and random sampling algorithm to solve this problem. We used one simulated data set and three real data sets for experiments and compared four existing EWAS calibration models. The experimental results show that the GN-ReFAEWAS model is superior to existing models. Conclusion: The result proved that GN-ReFAEWAS model can provide a better estimation of cell-type composition and reduce the false positives in EWAS.