Deep learning in omics: a survey and guideline

Ensemble Deep Learning Based on Multi-level Information Enhancement and Greedy Fuzzy Decision for Plant miRNA-lncRNA Interaction Prediction

MicroRNAs (miRNAs) and long non-coding RNAs (lncRNAs) are both non-coding RNAs (ncRNAs) and their interactions play important roles in biological processes. Computational methods, such as machine learning and various bioinformatics tools, can predict potential miRNA-lncRNA interactions, which is significant for studying their mechanisms and biological functions. A growing number of RNA interaction predictors for animal have been reported, but they are unreliable for plant due to the differences of ncRNAs in animal and plant. It is urgent to build a reliable plant predictor, especially for cross-species. This paper proposes an ensemble deep learning model based on multi-level information enhancement and greedy fuzzy decision (PmliPEMG) for plant miRNA-lncRNA interaction prediction. The fusion complex features, multi-scale convolutional long short-term memory networks, and attention mechanism are adopted to enhance the sample information at the feature, scale, and model levels, respectively. An ensemble deep learning model is built based on a novel method (greedy fuzzy decision) which greatly improves the efficiency. The multi-level information enhancement and greedy fuzzy decision are verified to have the positive effects on prediction performance. PmliPEMG can be applied to the cross-species prediction. It shows better performance and stronger generalization ability than state-of-the-art predictors and may provide valuable references for related research.

Performance Comparison of Deep Learning Autoencoders for Cancer Subtype Detection Using Multi-Omics Data

A heterogeneous disease such as cancer is activated through multiple pathways and different perturbations. Depending upon the activated pathway(s), the survival of the patients varies significantly and shows different efficacy to various drugs. Therefore, cancer subtype detection using genomics level data is a significant research problem. Subtype detection is often a complex problem, and in most cases, needs multi-omics data fusion to achieve accurate subtyping. Different data fusion and subtyping approaches have been proposed over the years, such as kernel-based fusion, matrix factorization, and deep learning autoencoders. In this paper, we compared the performance of different deep learning autoencoders for cancer subtype detection. We performed cancer subtype detection on four different cancer types from The Cancer Genome Atlas (TCGA) datasets using four autoencoder implementations. We also predicted the optimal number of subtypes in a cancer type using the silhouette score and found that the detected subtypes exhibit significant differences in survival profiles. Furthermore, we compared the effect of feature selection and similarity measures for subtype detection. For further evaluation, we used the Glioblastoma multiforme (GBM) dataset and identified the differentially expressed genes in each of the subtypes. The results obtained are consistent with other genomic studies and can be corroborated with the involved pathways and biological functions. Thus, it shows that the results from the autoencoders, obtained through the interaction of different datatypes of cancer, can be used for the prediction and characterization of patient subgroups and survival profiles.

miTAR: a hybrid deep learning-based approach for predicting miRNA targets

BACKGROUND

microRNAs (miRNAs) have been shown to play essential roles in a wide range of biological processes. Many computational methods have been developed to identify targets of miRNAs. However, the majority of these methods depend on pre-defined features that require considerable efforts and resources to compute and often prove suboptimal at predicting miRNA targets.

RESULTS

We developed a novel hybrid deep learning-based (DL-based) approach that is capable of predicting miRNA targets at a higher accuracy. This approach integrates convolutional neural networks (CNNs) that excel in learning spatial features and recurrent neural networks (RNNs) that discern sequential features. Therefore, our approach has the advantages of learning both the intrinsic spatial and sequential features of miRNA:target. The inputs for our approach are raw sequences of miRNAs and genes that can be obtained effortlessly. We applied our approach on two human datasets from recently miRNA target prediction studies and trained two models. We demonstrated that the two models consistently outperform the previous methods according to evaluation metrics on test datasets. Comparing our approach with currently available alternatives on independent datasets shows that our approach delivers substantial improvements in performance. We also show with multiple evidences that our approach is more robust than other methods on small datasets. Our study is the first study to perform comparisons across multiple existing DL-based approaches on miRNA target prediction. Furthermore, we examined the contribution of a Max pooling layer in between the CNN and RNN and demonstrated that it improves the performance of all our models. Finally, a unified model was developed that is robust on fitting different input datasets.

CONCLUSIONS

We present a new DL-based approach for predicting miRNA targets and demonstrate that our approach outperforms the current alternatives. We supplied an easy-to-use tool, miTAR, at https://github.com/tjgu/miTAR . Furthermore, our analysis results support that Max Pooling generally benefits the hybrid models and potentially prevents overfitting for hybrid models.

Multi-omics integration in biomedical research - A metabolomics-centric review

Recent advances in high-throughput technologies have enabled the profiling of multiple layers of a biological system, including DNA sequence data (genomics), RNA expression levels (transcriptomics), and metabolite levels (metabolomics). This has led to the generation of vast amounts of biological data that can be integrated in so-called multi-omics studies to examine the complex molecular underpinnings of health and disease. Integrative analysis of such datasets is not straightforward and is particularly complicated by the high dimensionality and heterogeneity of the data and by the lack of universal analysis protocols. Previous reviews have discussed various strategies to address the challenges of data integration, elaborating on specific aspects, such as network inference or feature selection techniques. Thereby, the main focus has been on the integration of two omics layers in their relation to a phenotype of interest. In this review we provide an overview over a typical multi-omics workflow, focusing on integration methods that have the potential to combine metabolomics data with two or more omics. We discuss multiple integration concepts including data-driven, knowledge-based, simultaneous and step-wise approaches. We highlight the application of these methods in recent multi-omics studies, including large-scale integration efforts aiming at a global depiction of the complex relationships within and between different biological layers without focusing on a particular phenotype.

"Omics" in traumatic brain injury: novel approaches to a complex disease

BACKGROUND

To date, there is neither any pharmacological treatment with efficacy in traumatic brain injury (TBI) nor any method to halt the disease progress. This is due to an incomplete understanding of the vast complexity of the biological cascades and failure to appreciate the diversity of secondary injury mechanisms in TBI. In recent years, techniques for high-throughput characterization and quantification of biological molecules that include genomics, proteomics, and metabolomics have evolved and referred to as omics.

METHODS

In this narrative review, we highlight how omics technology can be applied to potentiate diagnostics and prognostication as well as to advance our understanding of injury mechanisms in TBI.

RESULTS

The omics platforms provide possibilities to study function, dynamics, and alterations of molecular pathways of normal and TBI disease states. Through advanced bioinformatics, large datasets of molecular information from small biological samples can be analyzed in detail and provide valuable knowledge of pathophysiological mechanisms, to include in prognostic modeling when connected to clinically relevant data. In such a complex disease as TBI, omics enables broad categories of studies from gene compositions associated with susceptibility to secondary injury or poor outcome, to potential alterations in metabolites following TBI.

CONCLUSION

The field of omics in TBI research is rapidly evolving. The recent data and novel methods reviewed herein may form the basis for improved precision medicine approaches, development of pharmacological approaches, and individualization of therapeutic efforts by implementing mathematical "big data" predictive modeling in the near future.

Predicting Thermophilic Proteins by Machine Learning

Background:

Thermophilic proteins can maintain good activity under high temperature, therefore, it is important to study thermophilic proteins for the thermal stability of proteins.

Objective:

In order to solve the problem of low precision and low efficiency in predicting thermophilic proteins, a prediction method based on feature fusion and machine learning was proposed in this paper.

Methods:

For the selected thermophilic data sets, firstly, the thermophilic protein sequence was characterized based on feature fusion by the combination of g-gap dipeptide, entropy density and autocorrelation coefficient. Then, Kernel Principal Component Analysis (KPCA) was used to reduce the dimension of the expressed protein sequence features in order to reduce the training time and improve efficiency. Finally, the classification model was designed by using the classification algorithm.

Results:

A variety of classification algorithms was used to train and test on the selected thermophilic dataset. By comparison, the accuracy of the Support Vector Machine (SVM) under the jackknife method was over 92%. The combination of other evaluation indicators also proved that the SVM performance was the best.

Conclusion:

Because of choosing an effectively feature representation method and a robust classifier, the proposed method is suitable for predicting thermophilic proteins and is superior to most reported methods.

A gene prioritization method based on a swine multi-omics knowledgebase and a deep learning model

The analyses of multi-omics data have revealed candidate genes for objective traits. However, they are integrated poorly, especially in non-model organisms, and they pose a great challenge for prioritizing candidate genes for follow-up experimental verification. Here, we present a general convolutional neural network model that integrates multi-omics information to prioritize the candidate genes of objective traits. By applying this model to Sus scrofa, which is a non-model organism, but one of the most important livestock animals, the model precision was 72.9%, recall 73.5%, and F1-Measure 73.4%, demonstrating a good prediction performance compared with previous studies in Arabidopsis thaliana and Oryza sativa. Additionally, to facilitate the use of the model, we present ISwine (http://iswine.iomics.pro/), which is an online comprehensive knowledgebase in which we incorporated almost all the published swine multi-omics data. Overall, the results suggest that the deep learning strategy will greatly facilitate analyses of multi-omics integration in the future.

Yuhua Fu et al. develop a CNN model that integrates multi-omics information to prioritize candidate genes of objective traits. Their model performs well when applied to important livestock non-model animals like Sus scrofa. Finally, the authors present ISwine, an online comprehensive knowledgebase which includes all published swine omics data to facilitate the integration of heterogeneous data.

A bird's-eye view of deep learning in bioimage analysis

Deep learning of artificial neural networks has become the de facto standard approach to solving data analysis problems in virtually all fields of science and engineering. Also in biology and medicine, deep learning technologies are fundamentally transforming how we acquire, process, analyze, and interpret data, with potentially far-reaching consequences for healthcare. In this mini-review, we take a bird's-eye view at the past, present, and future developments of deep learning, starting from science at large, to biomedical imaging, and bioimage analysis in particular.

Remarks on Computational Method for Identifying Acid and Alkaline Enzymes

The catalytic efficiency of the enzyme is thousands of times higher than that of ordinary catalysts. Thus, they are widely used in industrial and medical fields. However, enzymes with protein structure can be destroyed and inactivated in high temperature, over acid or over alkali environment. It is well known that most of enzymes work well in an environment with pH of 6-8, while some special enzymes remain active only in an alkaline environment with pH > 8 or an acidic environment with pH < 6. Therefore, the identification of acidic and alkaline enzymes has become a key task for industrial production. Because of the wide varieties of enzymes, it is hard work to determine the acidity and alkalinity of the enzyme by experimental methods, and even this task cannot be achieved. Converting protein sequences into digital features and building computational models can efficiently and accurately identify the acidity and alkalinity of enzymes. This review summarized the progress of the digital features to express proteins and computational methods to identify acidic and alkaline enzymes. We hope that this paper will provide more convenience, ideas, and guides for computationally classifying acid and alkaline enzymes.

Machine learning approaches to drug response prediction: challenges and recent progress

Cancer is a leading cause of death worldwide. Identifying the best treatment using computational models to personalize drug response prediction holds great promise to improve patient's chances of successful recovery. Unfortunately, the computational task of predicting drug response is very challenging, partially due to the limitations of the available data and partially due to algorithmic shortcomings. The recent advances in deep learning may open a new chapter in the search for computational drug response prediction models and ultimately result in more accurate tools for therapy response. This review provides an overview of the computational challenges and advances in drug response prediction, and focuses on comparing the machine learning techniques to be of utmost practical use for clinicians and machine learning non-experts. The incorporation of new data modalities such as single-cell profiling, along with techniques that rapidly find effective drug combinations will likely be instrumental in improving cancer care.

Exploring Neural Networks and Related Visualization Techniques in Gene Expression Data

Over the past decade, neural networks have become one of the cutting-edge methods in various research fields, outshining specifically in complex classification problems. In this paper, we propose two main contributions: first, we conduct a methodological study of neural network modeling for classifying biological traits based on structured gene expression data. Then, we suggest an innovative approach for utilizing deep learning visualization techniques in order to reveal the specific genes important for the correct classification of each trait within the trained models. Our data suggests that this approach have great potential for becoming a standard feature importance tool used in complex medical research problems, and that it can further be generalized to various structured data classification problems outside the biological domain.

Is There Any Sequence Feature in the RNA Pseudouridine Modification Prediction Problem?

Pseudouridine (Ψ) is the most abundant RNA modification and has been found in many kinds of RNAs, including snRNA, rRNA, tRNA, mRNA, and snoRNA. Thus, Ψ sites play a significant role in basic research and drug development. Although some experimental techniques have been developed to identify Ψ sites, they are expensive and time consuming, especially in the post-genomic era with the explosive growth of known RNA sequences. Thus, highly accurate computational methods are urgently required to quickly detect the Ψ sites on uncharacterized RNA sequences. Several predictors have been proposed using multifarious features, but their evaluated performances are still unsatisfactory. In this study, we first identified Ψ sites for H. sapiens, S. cerevisiae, and M. musculus using the sequence features from the bi-profile Bayes (BPB) method based on the random forest (RF) and support vector machine (SVM) algorithms, where the performances were evaluated using 5-fold cross-validation and independent tests. It was found that the SVM-based accuracies were 3.55% and 5.09% lower than the iPseU-CUU predictor for the H_990 and S_628 datasets, respectively. Almost the same-level results were obtained for M_994 and an independent H_200 dataset, even showing a 5.0% improvement for S_200. Then, three different kinds of features, including basic Kmer, general parallel correlation pseudo-dinucleotide composition (PC-PseDNC-General), and nucleotide chemical property (NCP) and nucleotide density (ND) from the iRNA-PseU method, were combined with BPB to show their comprehensive performances, where the effective features are selected by the max-relevance-max-distance (MRMD) method. The best evaluated accuracies of the combined features for the S_628 and M_994 datasets were achieved at 70.54% and 72.45%, which were 2.39% and 0.65% higher than iPseU-CUU. For the S_200 dataset, it was also improved 8% from 69% to 77%. However, there was no obvious improvement for H. sapiens, which was evaluated as approximately 63.23% and 72.0% for the H_990 and H_200 datasets, respectively. The overall performances for Ψ identification using BPB features as well as the combined features were not obviously improved. Although some kinds of feature extraction methods based on the RNA sequence information have been applied to construct the predictors in previous studies, the corresponding accuracies are generally in the range of 60%-70%. Thus, researchers need to reconsider whether there is any sequence feature in the RNA Ψ modification prediction problem.

Probing lncRNA-Protein Interactions: Data Repositories, Models, and Algorithms

Identifying lncRNA-protein interactions (LPIs) is vital to understanding various key biological processes. Wet experiments found a few LPIs, but experimental methods are costly and time-consuming. Therefore, computational methods are increasingly exploited to capture LPI candidates. We introduced relevant data repositories, focused on two types of LPI prediction models: network-based methods and machine learning-based methods. Machine learning-based methods contain matrix factorization-based techniques and ensemble learning-based techniques. To detect the performance of computational methods, we compared parts of LPI prediction models on Leave-One-Out cross-validation (LOOCV) and fivefold cross-validation. The results show that SFPEL-LPI obtained the best performance of AUC. Although computational models have efficiently unraveled some LPI candidates, there are many limitations involved. We discussed future directions to further boost LPI predictive performance.

Accurate classification of membrane protein types based on sequence and evolutionary information using deep learning

Background

Membrane proteins play an important role in the life activities of organisms. Knowing membrane protein types provides clues for understanding the structure and function of proteins. Though various computational methods for predicting membrane protein types have been developed, the results still do not meet the expectations of researchers.

Results

We propose two deep learning models to process sequence information and evolutionary information, respectively. Both models obtained better results than traditional machine learning models. Furthermore, to improve the performance of the sequence information model, we also provide a new vector representation method to replace the one-hot encoding, whose overall success rate improved by 3.81% and 6.55% on two datasets. Finally, a more effective model is obtained by fusing the above two models, whose overall success rate reached 95.68% and 92.98% on two datasets.

Conclusion

The final experimental results show that our method is more effective than existing methods for predicting membrane protein types, which can help laboratory researchers to identify the type of novel membrane proteins.

Fold-LTR-TCP: protein fold recognition based on triadic closure principle

As an important task in protein structure and function studies, protein fold recognition has attracted more and more attention. The existing computational predictors in this field treat this task as a multi-classification problem, ignoring the relationship among proteins in the dataset. However, previous studies showed that their relationship is critical for protein homology analysis. In this study, the protein fold recognition is treated as an information retrieval task. The Learning to Rank model (LTR) was employed to retrieve the query protein against the template proteins to find the template proteins in the same fold with the query protein in a supervised manner. The triadic closure principle (TCP) was performed on the ranking list generated by the LTR to improve its accuracy by considering the relationship among the query protein and the template proteins in the ranking list. Finally, a predictor called Fold-LTR-TCP was proposed. The rigorous test on the LE benchmark dataset showed that the Fold-LTR-TCP predictor achieved an accuracy of 73.2%, outperforming all the other competing methods.

Convolutional neural network-based annotation of bacterial type IV secretion system effectors with enhanced accuracy and reduced false discovery

The type IV bacterial secretion system (SS) is reported to be one of the most ubiquitous SSs in nature and can induce serious conditions by secreting type IV SS effectors (T4SEs) into the host cells. Recent studies mainly focus on annotating new T4SE from the huge amount of sequencing data, and various computational tools are therefore developed to accelerate T4SE annotation. However, these tools are reported as heavily dependent on the selected methods and their annotation performance need to be further enhanced. Herein, a convolution neural network (CNN) technique was used to annotate T4SEs by integrating multiple protein encoding strategies. First, the annotation accuracies of nine encoding strategies integrated with CNN were assessed and compared with that of the popular T4SE annotation tools based on independent benchmark. Second, false discovery rates of various models were systematically evaluated by (1) scanning the genome of Legionella pneumophila subsp. ATCC 33152 and (2) predicting the real-world non-T4SEs validated using published experiments. Based on the above analyses, the encoding strategies, (a) position-specific scoring matrix (PSSM), (b) protein secondary structure & solvent accessibility (PSSSA) and (c) one-hot encoding scheme (Onehot), were identified as well-performing when integrated with CNN. Finally, a novel strategy that collectively considers the three well-performing models (CNN-PSSM, CNN-PSSSA and CNN-Onehot) was proposed, and a new tool (CNN-T4SE, https://idrblab.org/cnnt4se/) was constructed to facilitate T4SE annotation. All in all, this study conducted a comprehensive analysis on the performance of a collection of encoding strategies when integrated with CNN, which could facilitate the suppression of T4SS in infection and limit the spread of antimicrobial resistance.

SNNRice6mA: A Deep Learning Method for Predicting DNA N6-Methyladenine Sites in Rice Genome

DNA N6-methyladenine (6mA) is an important epigenetic modification, which is involved in many biology regulation processes. An accurate and reliable method for 6mA identification can help us gain a better insight into the regulatory mechanism of the modification. Although many experimental techniques have been proposed to identify 6mA sites genome-wide, these techniques are time consuming and laborious. Recently, several machine learning methods have been developed to identify 6mA sites genome-wide. However, there is room for the improvement on their performance for predicting 6mA sites in rice genome. In this paper, we developed a simple and lightweight deep learning model to identify DNA 6mA sites in rice genome. Our model needs no prior knowledge of 6mA or manually crafted sequence feature. We built our model based on two rice 6mA benchmark datasets. Our method got an average prediction accuracy of ∼93% and ∼92% on the two datasets we used. We compared our method with existing 6mA prediction tools. The comparison results show that our model outperforms the state-of-the-art methods.

AOPs-SVM: A Sequence-Based Classifier of Antioxidant Proteins Using a Support Vector Machine

Antioxidant proteins play important roles in countering oxidative damage in organisms. Because it is time-consuming and has a high cost, the accurate identification of antioxidant proteins using biological experiments is a challenging task. For these reasons, we proposed a model using machine-learning algorithms that we named AOPs-SVM, which was developed based on sequence features and a support vector machine. Using a testing dataset, we conducted a jackknife cross-validation test with the proposed AOPs-SVM classifier and obtained 0.68 in sensitivity, 0.985 in specificity, 0.942 in average accuracy, 0.741 in MCC, and 0.832 in AUC. This outperformed existing classifiers. The experiment results demonstrate that the AOPs-SVM is an effective classifier and contributes to the research related to antioxidant proteins. A web server was built at http://server.malab.cn/AOPs-SVM/index.jsp to provide open access.

A Random Forest Sub-Golgi Protein Classifier Optimized via Dipeptide and Amino Acid Composition Features

To gain insight into the malfunction of the Golgi apparatus and its relationship to various genetic and neurodegenerative diseases, the identification of sub-Golgi proteins, both cis-Golgi and trans-Golgi proteins, is of great significance. In this study, a state-of-art random forests sub-Golgi protein classifier, rfGPT, was developed. The rfGPT used 2-gap dipeptide and split amino acid composition for the feature vectors and was combined with the synthetic minority over-sampling technique (SMOTE) and an analysis of variance (ANOVA) feature selection method. The rfGPT was trained on a sub-Golgi protein sequence data set (137 sequences), with sequence identity less than 25%. For the optimal rfGPT classifier with 93 features, the accuracy (ACC) was 90.5%; the Matthews correlation coefficient (MCC) was 0.811; the sensitivity (Sn) was 92.6%; and the specificity (Sp) was 88.4%. The independent testing scores for the rfGPT were ACC = 90.6%; MCC = 0.696; Sn = 96.1%; and Sp = 69.2%. Although the independent testing accuracy was 4.4% lower than that for the best reported sub-Golgi classifier trained on a data set with 40% sequence identity (304 sequences), the rfGPT is currently the top sub-Golgi protein predictor utilizing feature vectors without any position-specific scoring matrix and its derivative features. Therefore, the rfGPT is a more practical tool, because no sequence alignment is required with tens of millions of protein sequences. To date, the rfGPT is the Golgi classifier with the best independent testing scores, optimized by training on smaller benchmark data sets. Feature importance analysis proves that the non-polar and aliphatic residues composition, the (aromatic residues) + (non-polar, aliphatic residues) dipeptide and aromatic residues composition between NH2-termial and COOH-terminal of protein sequences are the three top biological features for distinguishing the sub-Golgi proteins.

Protein functional annotation of simultaneously improved stability, accuracy and false discovery rate achieved by a sequence-based deep learning

Functional annotation of protein sequence with high accuracy has become one of the most important issues in modern biomedical studies, and computational approaches of significantly accelerated analysis process and enhanced accuracy are greatly desired. Although a variety of methods have been developed to elevate protein annotation accuracy, their ability in controlling false annotation rates remains either limited or not systematically evaluated. In this study, a protein encoding strategy, together with a deep learning algorithm, was proposed to control the false discovery rate in protein function annotation, and its performances were systematically compared with that of the traditional similarity-based and de novo approaches. Based on a comprehensive assessment from multiple perspectives, the proposed strategy and algorithm were found to perform better in both prediction stability and annotation accuracy compared with other de novo methods. Moreover, an in-depth assessment revealed that it possessed an improved capacity of controlling the false discovery rate compared with traditional methods. All in all, this study not only provided a comprehensive analysis on the performances of the newly proposed strategy but also provided a tool for the researcher in the fields of protein function annotation.

Deep Splicing Code: Classifying Alternative Splicing Events Using Deep Learning

Alternative splicing (AS) is the process of combining different parts of the pre-mRNA to produce diverse transcripts and eventually different protein products from a single gene. In computational biology field, researchers try to understand AS behavior and regulation using computational models known as “Splicing Codes”. The final goal of these algorithms is to make an in-silico prediction of AS outcome from genomic sequence. Here, we develop a deep learning approach, called Deep Splicing Code (DSC), for categorizing the well-studied classes of AS namely alternatively skipped exons, alternative 5’ss, alternative 3’ss, and constitutively spliced exons based only on the sequence of the exon junctions. The proposed approach significantly improves the prediction and the obtained results reveal that constitutive exons have distinguishable local characteristics from alternatively spliced exons. Using the motif visualization technique, we show that the trained models learned to search for competitive alternative splice sites as well as motifs of important splicing factors with high precision. Thus, the proposed approach greatly expands the opportunities to improve alternative splicing modeling. In addition, a web-server for AS events prediction has been developed based on the proposed method.

iProEP: A Computational Predictor for Predicting Promoter

Promoter is a fundamental DNA element located around the transcription start site (TSS) and could regulate gene transcription. Promoter recognition is of great significance in determining transcription units, studying gene structure, analyzing gene regulation mechanisms, and annotating gene functional information. Many models have already been proposed to predict promoters. However, the performances of these methods still need to be improved. In this work, we combined pseudo k-tuple nucleotide composition (PseKNC) with position-correlation scoring function (PCSF) to formulate promoter sequences of Homo sapiens (H. sapiens), Drosophila melanogaster (D. melanogaster), Caenorhabditis elegans (C. elegans), Bacillus subtilis (B. subtilis), and Escherichia coli (E. coli). Minimum Redundancy Maximum Relevance (mRMR) algorithm and increment feature selection strategy were then adopted to find out optimal feature subsets. Support vector machine (SVM) was used to distinguish between promoters and non-promoters. In the 10-fold cross-validation test, accuracies of 93.3%, 93.9%, 95.7%, 95.2%, and 93.1% were obtained for H. sapiens, D. melanogaster, C. elegans, B. subtilis, and E. coli, with the areas under receiver operating curves (AUCs) of 0.974, 0.975, 0.981, 0.988, and 0.976, respectively. Comparative results demonstrated that our method outperforms existing methods for identifying promoters. An online web server was established that can be freely accessed (http://lin-group.cn/server/iProEP/).

Machine Learning SNP Based Prediction for Precision Medicine

In the past decade, precision genomics based medicine has emerged to provide tailored and effective healthcare for patients depending upon their genetic features. Genome Wide Association Studies have also identified population based risk genetic variants for common and complex diseases. In order to meet the full promise of precision medicine, research is attempting to leverage our increasing genomic understanding and further develop personalized medical healthcare through ever more accurate disease risk prediction models. Polygenic risk scoring and machine learning are two primary approaches for disease risk prediction. Despite recent improvements, the results of polygenic risk scoring remain limited due to the approaches that are currently used. By contrast, machine learning algorithms have increased predictive abilities for complex disease risk. This increase in predictive abilities results from the ability of machine learning algorithms to handle multi-dimensional data. Here, we provide an overview of polygenic risk scoring and machine learning in complex disease risk prediction. We highlight recent machine learning application developments and describe how machine learning approaches can lead to improved complex disease prediction, which will help to incorporate genetic features into future personalized healthcare. Finally, we discuss how the future application of machine learning prediction models might help manage complex disease by providing tissue-specific targets for customized, preventive interventions.

SALMON: Survival Analysis Learning With Multi-Omics Neural Networks on Breast Cancer

Improved cancer prognosis is a central goal for precision health medicine. Though many models can predict differential survival from data, there is a strong need for sophisticated algorithms that can aggregate and filter relevant predictors from increasingly complex data inputs. In turn, these models should provide deeper insight into which types of data are most relevant to improve prognosis. Deep Learning-based neural networks offer a potential solution for both problems because they are highly flexible and account for data complexity in a non-linear fashion. In this study, we implement Deep Learning-based networks to determine how gene expression data predicts Cox regression survival in breast cancer. We accomplish this through an algorithm called SALMON (Survival Analysis Learning with Multi-Omics Neural Networks), which aggregates and simplifies gene expression data and cancer biomarkers to enable prognosis prediction. The results revealed improved performance when more omics data were used in model construction. Rather than use raw gene expression values as model inputs, we innovatively use eigengene modules from the result of gene co-expression network analysis. The corresponding high impact co-expression modules and other omics data are identified by feature selection technique, then examined by conducting enrichment analysis and exploiting biological functions, escalated the interpretation of input feature from gene level to co-expression modules level. Our study shows the feasibility of discovering breast cancer related co-expression modules, sketch a blueprint of future endeavors on Deep Learning-based survival analysis. SALMON source code is available at https://github.com/huangzhii/SALMON/.

Gene2vec: gene subsequence embedding for prediction of mammalian N6-methyladenosine sites from mRNA

N⁶-Methyladenosine (m⁶A) refers to methylation modification of the adenosine nucleotide acid at the nitrogen-6 position. Many conventional computational methods for identifying N⁶-methyladenosine sites are limited by the small amount of data available. Taking advantage of the thousands of m⁶A sites detected by high-throughput sequencing, it is now possible to discover the characteristics of m⁶A sequences using deep learning techniques. To the best of our knowledge, our work is the first attempt to use word embedding and deep neural networks for m⁶A prediction from mRNA sequences. Using four deep neural networks, we developed a model inferred from a larger sequence shifting window that can predict m⁶A accurately and robustly. Four prediction schemes were built with various RNA sequence representations and optimized convolutional neural networks. The soft voting results from the four deep networks were shown to outperform all of the state-of-the-art methods. We evaluated these predictors mentioned above on a rigorous independent test data set and proved that our proposed method outperforms the state-of-the-art predictors. The training, independent, and cross-species testing data sets are much larger than in previous studies, which could help to avoid the problem of overfitting. Furthermore, an online prediction web server implementing the four proposed predictors has been built and is available at http://server.malab.cn/Gene2vec/.

Recent Advances on the Machine Learning Methods in Identifying DNA Replication Origins in Eukaryotic Genomics

The initiate site of DNA replication is called origins of replication (ORI) which is regulated by a set of regulatory proteins and plays important roles in the basic biochemical process during cell growth and division in all living organisms. Therefore, the study of ORIs is essential for understanding the cell-division cycle and gene expression regulation so that scholars can develop a new strategy against genetic diseases by using the knowledge of DNA replication. Thus, the accurate identification of ORIs will provide key clues for DNA replication research and clinical medicine. Although, the conventional experiments could provide accurate results, they are time-consuming and cost ineffective. On the contrary, bioinformatics-based methods can overcome these shortcomings. Especially, with the emergence of DNA sequences in the post-genomic era, it is highly expected to develop high throughput tools to identify ORIs based on sequence information. In this review, we will summarize the current progress in computational prediction of eukaryotic ORIs including the collection of benchmark dataset, the application of machine learning-based techniques, the results obtained by these methods, and the construction of web servers. Finally, we gave the future perspectives on ORIs prediction. The review provided readers with a whole background of ORIs prediction based on machine learning methods, which will be helpful for researchers to study DNA replication in-depth and drug therapy of genetic defect.