DeeReCT-PolyA: a robust and generic deep learning method for PAS identification

Big data and deep learning for RNA biology

The exponential growth of big data in RNA biology (RB) has led to the development of deep learning (DL) models that have driven crucial discoveries. As constantly evidenced by DL studies in other fields, the successful implementation of DL in RB depends heavily on the effective utilization of large-scale datasets from public databases. In achieving this goal, data encoding methods, learning algorithms, and techniques that align well with biological domain knowledge have played pivotal roles. In this review, we provide guiding principles for applying these DL concepts to various problems in RB by demonstrating successful examples and associated methodologies. We also discuss the remaining challenges in developing DL models for RB and suggest strategies to overcome these challenges. Overall, this review aims to illuminate the compelling potential of DL for RB and ways to apply this powerful technology to investigate the intriguing biology of RNA more effectively.

Context-Aware Poly(A) Signal Prediction Model via Deep Spatial-Temporal Neural Networks

Polyadenylation [Poly(A)] is an essential process during messenger RNA (mRNA) maturation in biological eukaryote systems. Identifying Poly(A) signals (PASs) from the genome level is the key to understanding the mechanism of translation regulation and mRNA metabolism. In this work, we propose a deep dual-dynamic context-aware Poly(A) signal prediction model, called multiscale convolution with self-attention networks (MCANet), to adaptively uncover the spatial-temporal contextual dependence information. Specifically, the model automatically learns and strengthens informative features from the temporalwise and the spatialwise dimension. The identity connectivity performs contextual feature maps of Poly(A) data by direct connections from previous layers to subsequent layers. Then, a fully parametric rectified linear unit (FP-RELU) with dual-dynamic coefficients is devised to make the training of the model easier and enhance the generalization ability. A cross-entropy loss (CL) function is designed to make the model focus on samples that are easy to misclassify. Experiments on different Poly(A) signals demonstrate the superior performance of the proposed MCANet, and an ablation study shows the effectiveness of the network design for the feature learning and prediction of Poly(A) signals.

Applications of deep learning in understanding gene regulation

Gene regulation is a central topic in cell biology. Advances in omics technologies and the accumulation of omics data have provided better opportunities for gene regulation studies than ever before. For this reason deep learning, as a data-driven predictive modeling approach, has been successfully applied to this field during the past decade. In this article, we aim to give a brief yet comprehensive overview of representative deep-learning methods for gene regulation. Specifically, we discuss and compare the design principles and datasets used by each method, creating a reference for researchers who wish to replicate or improve existing methods. We also discuss the common problems of existing approaches and prospectively introduce the emerging deep-learning paradigms that will potentially alleviate them. We hope that this article will provide a rich and up-to-date resource and shed light on future research directions in this area.

Annotating TSSs in Multiple Cell Types Based on DNA Sequence and RNA-seq Data via DeeReCT-TSS

The accurate annotation of transcription start sites (TSSs) and their usage are critical for the mechanistic understanding of gene regulation in different biological contexts. To fulfill this, specific high-throughput experimental technologies have been developed to capture TSSs in a genome-wide manner, and various computational tools have also been developed for in silico prediction of TSSs solely based on genomic sequences. Most of these computational tools cast the problem as a binary classification task on a balanced dataset, thus resulting in drastic false positive predictions when applied on the genome scale. Here, we present DeeReCT-TSS, a deep learning-based method that is capable of identifying TSSs across the whole genome based on both DNA sequence and conventional RNA sequencing data. We show that by effectively incorporating these two sources of information, DeeReCT-TSS significantly outperforms other solely sequence-based methods on the precise annotation of TSSs used in different cell types. Furthermore, we develop a meta-learning-based extension for simultaneous TSS annotations on 10 cell types, which enables the identification of cell type-specific TSSs. Finally, we demonstrate the high precision of DeeReCT-TSS on two independent datasets by correlating our predicted TSSs with experimentally defined TSS chromatin states. The source code for DeeReCT-TSS is available at https://github.com/JoshuaChou2018/DeeReCT-TSS_release and https://ngdc.cncb.ac.cn/biocode/tools/BT007316.

A Survey on Methods for Predicting Polyadenylation Sites from DNA Sequences, Bulk RNA-seq, and Single-cell RNA-seq

Alternative polyadenylation (APA) plays important roles in modulating mRNA stability, translation, and subcellular localization, and contributes extensively to shaping eukaryotic transcriptome complexity and proteome diversity. Identification of poly(A) sites (pAs) on a genome-wide scale is a critical step toward understanding the underlying mechanism of APA-mediated gene regulation. A number of established computational tools have been proposed to predict pAs from diverse genomic data. Here we provided an exhaustive overview of computational approaches for predicting pAs from DNA sequences, bulk RNA sequencing (RNA-seq) data, and single-cell RNA sequencing (scRNA-seq) data. Particularly, we examined several representative tools using bulk RNA-seq and scRNA-seq data from peripheral blood mononuclear cells and put forward operable suggestions on how to assess the reliability of pAs predicted by different tools. We also proposed practical guidelines on choosing appropriate methods applicable to diverse scenarios. Moreover, we discussed in depth the challenges in improving the performance of pA prediction and benchmarking different methods. Additionally, we highlighted outstanding challenges and opportunities using new machine learning and integrative multi-omics techniques, and provided our perspective on how computational methodologies might evolve in the future for non-3' untranslated region, tissue-specific, cross-species, and single-cell pA prediction.

DeepGenGrep: a general deep learning-based predictor for multiple genomic signals and regions

MOTIVATION

Accurate annotation of different genomic signals and regions (GSRs) from DNA sequences is fundamentally important for understanding gene structure, regulation and function. Numerous efforts have been made to develop machine learning-based predictors for in silico identification of GSRs. However, it remains a great challenge to identify GSRs as the performance of most existing approaches is unsatisfactory. As such, it is highly desirable to develop more accurate computational methods for GSRs prediction.

RESULTS

In this study, we propose a general deep learning framework termed DeepGenGrep, a general predictor for the systematic identification of multiple different GSRs from genomic DNA sequences. DeepGenGrep leverages the power of hybrid neural networks comprising a three-layer convolutional neural network and a two-layer long short-term memory to effectively learn useful feature representations from sequences. Benchmarking experiments demonstrate that DeepGenGrep outperforms several state-of-the-art approaches on identifying polyadenylation signals, translation initiation sites and splice sites across four eukaryotic species including Homo sapiens, Mus musculus, Bos taurus and Drosophila melanogaster. Overall, DeepGenGrep represents a useful tool for the high-throughput and cost-effective identification of potential GSRs in eukaryotic genomes.

AVAILABILITY AND IMPLEMENTATION

The webserver and source code are freely available at http://bigdata.biocie.cn/deepgengrep/home and Github (https://github.com/wx-cie/DeepGenGrep/).

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Investigating the Genomic Background of CRISPR-Cas Genomes for CRISPR-Based Antimicrobials

CRISPR-Cas systems are an adaptive immunity that protects prokaryotes against foreign genetic elements. Genetic templates acquired during past infection events enable DNA-interacting enzymes to recognize foreign DNA for destruction. Due to the programmability and specificity of these genetic templates, CRISPR-Cas systems are potential alternative antibiotics that can be engineered to self-target antimicrobial resistance genes on the chromosome or plasmid. However, several fundamental questions remain to repurpose these tools against drug-resistant bacteria. For endogenous CRISPR-Cas self-targeting, antimicrobial resistance genes and functional CRISPR-Cas systems have to co-occur in the target cell. Furthermore, these tools have to outplay DNA repair pathways that respond to the nuclease activities of Cas proteins, even for exogenous CRISPR-Cas delivery. Here, we conduct a comprehensive survey of CRISPR-Cas genomes. First, we address the co-occurrence of CRISPR-Cas systems and antimicrobial resistance genes in the CRISPR-Cas genomes. We show that the average number of these genes varies greatly by the CRISPR-Cas type, and some CRISPR-Cas types (IE and IIIA) have over 20 genes per genome. Next, we investigate the DNA repair pathways of these CRISPR-Cas genomes, revealing that the diversity and frequency of these pathways differ by the CRISPR-Cas type. The interplay between CRISPR-Cas systems and DNA repair pathways is essential for the acquisition of new spacers in CRISPR arrays. We conduct simulation studies to demonstrate that the efficiency of these DNA repair pathways may be inferred from the time-series patterns in the RNA structure of CRISPR repeats. This bioinformatic survey of CRISPR-Cas genomes elucidates the necessity to consider multifaceted interactions between different genes and systems, to design effective CRISPR-based antimicrobials that can specifically target drug-resistant bacteria in natural microbial communities.

DeeReCT-APA: Prediction of Alternative Polyadenylation Site Usage Through Deep Learning

Alternative polyadenylation (APA) is a crucial step in post-transcriptional regulation. Previous bioinformatic studies have mainly focused on the recognition of polyadenylation sites (PASs) in a given genomic sequence, which is a binary classification problem. Recently, computational methods for predicting the usage level of alternative PASs in the same gene have been proposed. However, all of them cast the problem as a non-quantitative pairwise comparison task and do not take the competition among multiple PASs into account. To address this, here we propose a deep learning architecture, Deep Regulatory Code and Tools for Alternative Polyadenylation (DeeReCT-APA), to quantitatively predict the usage of all alternative PASs of a given gene. To accommodate different genes with potentially different numbers of PASs, DeeReCT-APA treats the problem as a regression task with a variable-length target. Based on a convolutional neural network-long short-term memory (CNN-LSTM) architecture, DeeReCT-APA extracts sequence features with CNN layers, uses bidirectional LSTM to explicitly model the interactions among competing PASs, and outputs percentage scores representing the usage levels of all PASs of a gene. In addition to the fact that only our method can quantitatively predict the usage of all the PASs within a gene, we show that our method consistently outperforms other existing methods on three different tasks for which they are trained: pairwise comparison task, highest usage prediction task, and ranking task. Finally, we demonstrate that our method can be used to predict the effect of genetic variations on APA patterns and sheds light on future mechanistic understanding in APA regulation. Our code and data are available at https://github.com/lzx325/DeeReCT-APA-repo.

Identification of alternative splicing-derived cancer neoantigens for mRNA vaccine development

Messenger RNA (mRNA) vaccines have shown great potential for anti-tumor therapy due to the advantages in safety, efficacy and industrial production. However, it remains a challenge to identify suitable cancer neoantigens that can be targeted for mRNA vaccines. Abnormal alternative splicing occurs in a variety of tumors, which may result in the translation of abnormal transcripts into tumor-specific proteins. High-throughput technologies make it possible for systematic characterization of alternative splicing as a source of suitable target neoantigens for mRNA vaccine development. Here, we summarized difficulties and challenges for identifying alternative splicing-derived cancer neoantigens from RNA-seq data and proposed a conceptual framework for designing personalized mRNA vaccines based on alternative splicing-derived cancer neoantigens. In addition, several points were presented to spark further discussion toward improving the identification of alternative splicing-derived cancer neoantigens.

From shallow to deep: some lessons learned from application of machine learning for recognition of functional genomic elements in human genome

Identification of genomic signals as indicators for functional genomic elements is one of the areas that received early and widespread application of machine learning methods. With time, the methods applied grew in variety and generally exhibited a tendency to improve their ability to identify some major genomic and transcriptomics signals. The evolution of machine learning in genomics followed a similar path to applications of machine learning in other fields. These were impacted in a major way by three dominant developments, namely an enormous increase in availability and quality of data, a significant increase in computational power available to machine learning applications, and finally, new machine learning paradigms, of which deep learning is the most well-known example. It is not easy in general to distinguish factors leading to improvements in results of applications of machine learning. This is even more so in the field of genomics, where the advent of next-generation sequencing and the increased ability to perform functional analysis of raw data have had a major effect on the applicability of machine learning in OMICS fields. In this paper, we survey the results from a subset of published work in application of machine learning in the recognition of genomic signals and regions in human genome and summarize some lessons learnt from this endeavor. There is no doubt that a significant progress has been made both in terms of accuracy and reliability of models. Questions remain however whether the progress has been sufficient and what these developments bring to the field of genomics in general and human genomics in particular. Improving usability, interpretability and accuracy of models remains an important open challenge for current and future research in application of machine learning and more generally of artificial intelligence methods in genomics.

Protein-RNA interaction prediction with deep learning: structure matters

Protein-RNA interactions are of vital importance to a variety of cellular activities. Both experimental and computational techniques have been developed to study the interactions. Because of the limitation of the previous database, especially the lack of protein structure data, most of the existing computational methods rely heavily on the sequence data, with only a small portion of the methods utilizing the structural information. Recently, AlphaFold has revolutionized the entire protein and biology field. Foreseeably, the protein-RNA interaction prediction will also be promoted significantly in the upcoming years. In this work, we give a thorough review of this field, surveying both the binding site and binding preference prediction problems and covering the commonly used datasets, features and models. We also point out the potential challenges and opportunities in this field. This survey summarizes the development of the RNA-binding protein-RNA interaction field in the past and foresees its future development in the post-AlphaFold era.

Predicting environmentally responsive transgenerational differential DNA methylated regions (epimutations) in the genome using a hybrid deep-machine learning approach

BACKGROUND

Deep learning is an active bioinformatics artificial intelligence field that is useful in solving many biological problems, including predicting altered epigenetics such as DNA methylation regions. Deep learning (DL) can learn an informative representation that addresses the need for defining relevant features. However, deep learning models are computationally expensive, and they require large training datasets to achieve good classification performance.

RESULTS

One approach to addressing these challenges is to use a less complex deep learning network for feature selection and Machine Learning (ML) for classification. In the current study, we introduce a hybrid DL-ML approach that uses a deep neural network for extracting molecular features and a non-DL classifier to predict environmentally responsive transgenerational differential DNA methylated regions (DMRs), termed epimutations, based on the extracted DL-based features. Various environmental toxicant induced epigenetic transgenerational inheritance sperm epimutations were used to train the model on the rat genome DNA sequence and use the model to predict transgenerational DMRs (epimutations) across the entire genome.

CONCLUSION

The approach was also used to predict potential DMRs in the human genome. Experimental results show that the hybrid DL-ML approach outperforms deep learning and traditional machine learning methods.

Using Convolutional Neural Networks to Measure the Physiological Age of Caenorhabditis elegans

Caenorhabditis elegans (C. elegans) is a popular and excellent model for studies of aging due to its short lifespan. Methods for precisely measuring the physiological age of C. elegans are critically needed, especially for antiaging drug screening and genetic screening studies. The effects of various antiaging interventions on the rate of aging in the early stage of the aging process can be determined based on the quantification of physiological age. However, in general, the age of C. elegans is evaluated via human visual inspection of morphological changes based on personal experience and subjective judgment. For example, the rate of motor activity decay has been used to predict lifespan in early- to mid-stage aging. Using image processing, the physiological age of C. elegans can be measured and then classified into periods or classes from childhood to elderhood (e.g., 3 periods comprising days 0-2, 4-6 and 10-12) by using texture entropy (Shamir, L. et al., 2009). Our dataset consists of 913 microscopic images of C. elegans, with approximately 60 images per day from day 1 to day 14 of adulthood. We present quantitative methods to measure the physiological age of C. elegans with convolution neural networks (CNNs), which can measure age with a granularity of days rather than periods. The methods achieved a mean absolute error (MAE) of less than 1 day for the measured age of C. elegans. In our experiments, we found that after training and testing our dataset, 5 popular CNN models, 50-layer residual network (ResNet50), InceptionV3, InceptionResNetV2, 16-layer Visual Geometry Group network (VGG16) and MobileNet, measured the physiological age of C. elegans with an average testing MAE of 1.58 days. Furthermore, based on the results, we propose two models, one model for linear regression analysis and the other model for logistic regression, that combine a CNN model and a new attribute: curved_or_straight. The linear regression analysis model achieved a test MAE of 0.94 days; the logistic regression model achieved an accuracy of 84.78 percent with an error tolerance of 1 day.

AI applications in functional genomics

We review the current applications of artificial intelligence (AI) in functional genomics. The recent explosion of AI follows the remarkable achievements made possible by "deep learning", along with a burst of "big data" that can meet its hunger. Biology is about to overthrow astronomy as the paradigmatic representative of big data producer. This has been made possible by huge advancements in the field of high throughput technologies, applied to determine how the individual components of a biological system work together to accomplish different processes. The disciplines contributing to this bulk of data are collectively known as functional genomics. They consist in studies of: i) the information contained in the DNA (genomics); ii) the modifications that DNA can reversibly undergo (epigenomics); iii) the RNA transcripts originated by a genome (transcriptomics); iv) the ensemble of chemical modifications decorating different types of RNA transcripts (epitranscriptomics); v) the products of protein-coding transcripts (proteomics); and vi) the small molecules produced from cell metabolism (metabolomics) present in an organism or system at a given time, in physiological or pathological conditions. After reviewing main applications of AI in functional genomics, we discuss important accompanying issues, including ethical, legal and economic issues and the importance of explainability.

Foretelling the Phenotype of a Genomic Sequence

Estimating phenotypic features (physical and biochemical traits) in a biological organism from their genomic sequence alone and/or environmental conditions has major applications in anthropological paleontology and criminal forensics, for example. To what extent do genomic sequences generally and causally determine phenotypic features of organisms, environmental conditions aside? We present results of two studies, one in blackfly (Insecta:Diptera:Simuliidae) larvae in two species (Simulium ignescens and S. tunja) with four phenotypic features, including the area and spot pattern of the cephalic apotome (in the form of a latin cross on the dorsal side of the head), the postgenal cleft (area under the head on the ventral side) and general body color in larva specimens; the second in strains of Arabidopsis thaliana. They establish that a substantial component of these phenotypic features (over 75 percent) are at least logically inferable, if not causally determined, by genomic fragments alone, despite the fact that these phenotypic features are not 100 percent determined entirely by genetic traits. These results suggest that it is possible to infer the genetic contribution in the determination of specific phenotypic features of a biological organism, without recourse to the causal chain of metabolomics and proteomic events leading to them from genomic sequences.

QAUST: Protein Function Prediction Using Structure Similarity, Protein Interaction, and Functional Motifs

The number of available protein sequences in public databases is increasing exponentially. However, a significant percentage of these sequences lack functional annotation, which is essential for the understanding of how biological systems operate. Here, we propose a novel method, Quantitative Annotation of Unknown STructure (QAUST), to infer protein functions, specifically Gene Ontology (GO) terms and Enzyme Commission (EC) numbers. QAUST uses three sources of information: structure information encoded by global and local structure similarity search, biological network information inferred by protein–protein interaction data, and sequence information extracted from functionally discriminative sequence motifs. These three pieces of information are combined by consensus averaging to make the final prediction. Our approach has been tested on 500 protein targets from the Critical Assessment of Functional Annotation (CAFA) benchmark set. The results show that our method provides accurate functional annotation and outperforms other prediction methods based on sequence similarity search or threading. We further demonstrate that a previously unknown function of human tripartite motif-containing 22 (TRIM22) protein predicted by QAUST can be experimentally validated.

Poly(A)-DG: A deep-learning-based domain generalization method to identify cross-species Poly(A) signal without prior knowledge from target species

In eukaryotes, polyadenylation (poly(A)) is an essential process during mRNA maturation. Identifying the cis-determinants of poly(A) signal (PAS) on the DNA sequence is the key to understand the mechanism of translation regulation and mRNA metabolism. Although machine learning methods were widely used in computationally identifying PAS, the need for tremendous amounts of annotation data hinder applications of existing methods in species without experimental data on PAS. Therefore, cross-species PAS identification, which enables the possibility to predict PAS from untrained species, naturally becomes a promising direction. In our works, we propose a novel deep learning method named Poly(A)-DG for cross-species PAS identification. Poly(A)-DG consists of a Convolution Neural Network-Multilayer Perceptron (CNN-MLP) network and a domain generalization technique. It learns PAS patterns from the training species and identifies PAS in target species without re-training. To test our method, we use four species and build cross-species training sets with two of them and evaluate the performance of the remaining ones. Moreover, we test our method against insufficient data and imbalanced data issues and demonstrate that Poly(A)-DG not only outperforms state-of-the-art methods but also maintains relatively high accuracy when it comes to a smaller or imbalanced training set.

SANPolyA: a deep learning method for identifying Poly(A) signals

MOTIVATION

Polyadenylation plays a regulatory role in transcription. The recognition of polyadenylation signal (PAS) motif sequence is an important step in polyadenylation. In the past few years, some statistical machine learning-based and deep learning-based methods have been proposed for PAS identification. Although these methods predict PAS with success, there is room for their improvement on PAS identification.

RESULTS

In this study, we proposed a deep neural network-based computational method, called SANPolyA, for identifying PAS in human and mouse genomes. SANPolyA requires no manually crafted sequence features. We compared our method SANPolyA with several previous PAS identification methods on several PAS benchmark datasets. Our results showed that SANPolyA outperforms the state-of-art methods. SANPolyA also showed good performance on leave-one-motif-out evaluation.

AVAILABILITY AND IMPLEMENTATION

https://github.com/yuht4/SANPolyA.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

DeepPASTA: deep neural network based polyadenylation site analysis

MOTIVATION

Alternative polyadenylation (polyA) sites near the 3' end of a pre-mRNA create multiple mRNA transcripts with different 3' untranslated regions (3' UTRs). The sequence elements of a 3' UTR are essential for many biological activities such as mRNA stability, sub-cellular localization, protein translation, protein binding and translation efficiency. Moreover, numerous studies in the literature have reported the correlation between diseases and the shortening (or lengthening) of 3' UTRs. As alternative polyA sites are common in mammalian genes, several machine learning tools have been published for predicting polyA sites from sequence data. These tools either consider limited sequence features or use relatively old algorithms for polyA site prediction. Moreover, none of the previous tools consider RNA secondary structures as a feature to predict polyA sites.

RESULTS

In this paper, we propose a new deep learning model, called DeepPASTA, for predicting polyA sites from both sequence and RNA secondary structure data. The model is then extended to predict tissue-specific polyA sites. Moreover, the tool can predict the most dominant (i.e. frequently used) polyA site of a gene in a specific tissue and relative dominance when two polyA sites of the same gene are given. Our extensive experiments demonstrate that DeepPASTA signisficantly outperforms the existing tools for polyA site prediction and tissue-specific relative and absolute dominant polyA site prediction.

AVAILABILITY AND IMPLEMENTATION

https://github.com/arefeen/DeepPASTA.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Using a Heat Diffusion Model to Detect Potential Drug Resistance Genes of Mycobacterium tuberculosis

BACKGROUND

Tuberculosis (TB), caused by Mycobacterium tuberculosis (Mtb), is one of the oldest known and most dangerous diseases. Although the spread of TB was controlled in the early 20th century using antibiotics and vaccines, TB has again become a threat because of increased drug resistance. There is still a lack of effective treatment regimens for a person who is already infected with multidrug-resistant Mtb (MDR-Mtb) or extensively drug-resistant Mtb (XDRMtb). In the past decades, many research groups have explored the drug resistance profiles of Mtb based on sequence data by GWAS, which identified some mutations that were significantly linked with drug resistance, and attempted to explain the resistance mechanisms. However, they mainly focused on several significant mutations in drug targets (e.g. rpoB, katG). Some genes which are potentially associated with drug resistance may be overlooked by the GWAS analysis.

OBJECTIVE

In this article, our motivation is to detect potential drug resistance genes of Mtb using a heat diffusion model.

METHODS

All sequencing data, which contained 127 samples of Mtb, i.e. 34 ethambutol-, 65 isoniazid-, 53 rifampicin- and 45 streptomycin-resistant strains. The raw sequence data were preprocessed using Trimmomatic software and aligned to the Mtb H37Rv reference genome using Bowtie2. From the resulting alignments, SAMtools and VarScan were used to filter sequences and call SNPs. The GWAS was performed by the PLINK package to obtain the significant SNPs, which were mapped to genes. The P-values of genes calculated by GWAS were transferred into a heat vector. The heat vector and the Mtb protein-protein interactions (PPI) derived from the STRING database were inputted into the heat diffusion model to obtain significant subnetworks by HotNet2. Finally, the most significant (P < 0.05) subnetworks associated with different phenotypes were obtained. To verify the change of binding energy between the drug and target before and after mutation, the method of molecular dynamics simulation was performed using the AMBER software.

RESULTS

We identified significant subnetworks in rifampicin-resistant samples. Excitingly, we found rpoB and rpoC, which are drug targets of rifampicin. From the protein structure of rpoB, the mutation location was extremely close to the drug binding site, with a distance of only 3.97 Å. Molecular dynamics simulation revealed that the binding energy of rpoB and rifampicin decreased after D435V mutation. To a large extent, this mutation can influence the affinity of drug-target binding. In addition, topA and pyrG were reported to be linked with drug resistance, and might be new TB drug targets. Other genes that have not yet been reported are worth further study.

CONCLUSION

Using a heat diffusion model in combination with GWAS results and protein-protein interactions, the significantly mutated subnetworks in rifampicin-resistant samples were found. The subnetwork not only contained the known targets of rifampicin (rpoB, rpoC), but also included topA and pyrG, which are potentially associated with drug resistance. Together, these results offer deeper insights into drug resistance of Mtb, and provides potential drug targets for finding new antituberculosis drugs.

Precise Prediction of Calpain Cleavage Sites and Their Aberrance Caused by Mutations in Cancer

As a widespread post-translational modification of proteins, calpain-mediated cleavage regulates a broad range of cellular processes, including proliferation, differentiation, cytoskeletal reorganization, and apoptosis. The identification of proteins that undergo calpain cleavage in a site-specific manner is the necessary foundation for understanding the exact molecular mechanisms and regulatory roles of calpain-mediated cleavage. In contrast with time-consuming and labor-intensive experimental methods, computational approaches for detecting calpain cleavage sites have attracted wide attention due to their efficiency and convenience. In this study, we established a novel computational tool named DeepCalpain (http://deepcalpain.cancerbio.info/) for predicting the potential calpain cleavage sites by adopting deep neural network and the particle swarm optimization algorithm. Through critical evaluation and comparison, DeepCalpain exhibited superior performance against other existing tools. Meanwhile, we found that protein interactions could enrich the calpain-substrate regulatory relationship. Since calpain-mediated cleavage was critical for cancer development and progression, we comprehensively analyzed the calpain cleavage associated mutations across 11 cancers with the help of DeepCalpain, which demonstrated that the calpain-mediated cleavage events were affected by mutations and heavily implicated in the regulation of cancer cells. These prediction and analysis results might provide helpful information to reveal the regulatory mechanism of calpain cleavage in biological pathways and different cancer types, which might open new avenues for the diagnosis and treatment of cancers.

A deep dense inception network for protein beta-turn prediction

Beta-turn prediction is useful in protein function studies and experimental design. Although recent approaches using machine-learning techniques such as support vector machine (SVM), neural networks, and K nearest neighbor have achieved good results for beta-turn prediction, there is still significant room for improvement. As previous predictors utilized features in a sliding window of 4-20 residues to capture interactions among sequentially neighboring residues, such feature engineering may result in incomplete or biased features and neglect interactions among long-range residues. Deep neural networks provide a new opportunity to address these issues. Here, we proposed a deep dense inception network (DeepDIN) for beta-turn prediction, which takes advantage of the state-of-the-art deep neural network design of dense networks and inception networks. A test on a recent BT6376 benchmark data set shows that DeepDIN outperformed the previous best tool BetaTPred3 significantly in both the overall prediction accuracy and the nine-type beta-turn classification accuracy. A tool, called MUFold-BetaTurn, was developed, which is the first beta-turn prediction tool utilizing deep neural networks. The tool can be downloaded at http://dslsrv8.cs.missouri.edu/~cf797/MUFoldBetaTurn/download.html.

Hybrid model for efficient prediction of poly(A) signals in human genomic DNA

Polyadenylation signals (PAS) are found in most protein-coding and some non-coding genes in eukaryotes. Their accurate recognition improves understanding gene regulation mechanisms and recognition of the 3'-end of transcribed gene regions where premature or alternate transcription ends may lead to various diseases. Although different methods and tools for in-silico prediction of genomic signals have been proposed, the correct identification of PAS in genomic DNA remains challenging due to a vast number of non-relevant hexamers identical to PAS hexamers. In this study, we developed a novel method for PAS recognition. The method is implemented in a hybrid PAS recognition model (HybPAS), which is based on deep neural networks (DNNs) and logistic regression models (LRMs). One of such models is developed for each of the 12 most frequent human PAS hexamers. DNN models appeared the best for eight PAS types (including the two most frequent PAS hexamers), while LRM appeared best for the remaining four PAS types. The new models use different combinations of signal processing-based, statistical, and sequence-based features as input. The results obtained on human genomic data show that HybPAS outperforms the well-tuned state-of-the-art Omni-PolyA models, reducing the classification error for different PAS hexamers by up to 57.35% for 10 out of 12 PAS types, with Omni-PolyA models being better for two PAS types. For the most frequent PAS types, 'AATAAA' and 'ATTAAA', HybPAS reduced the error rate by 35.14% and 34.48%, respectively. On average, HybPAS reduces the error by 30.29%. HybPAS is implemented partly in Python and in MATLAB available at https://github.com/EMANG-KAUST/PolyA_Prediction_LRM_DNN.

mlDEEPre: Multi-Functional Enzyme Function Prediction With Hierarchical Multi-Label Deep Learning

As a great challenge in bioinformatics, enzyme function prediction is a significant step toward designing novel enzymes and diagnosing enzyme-related diseases. Existing studies mainly focus on the mono-functional enzyme function prediction. However, the number of multi-functional enzymes is growing rapidly, which requires novel computational methods to be developed. In this paper, following our previous work, DEEPre, which uses deep learning to annotate mono-functional enzyme's function, we propose a novel method, mlDEEPre, which is designed specifically for predicting the functionalities of multi-functional enzymes. By adopting a novel loss function, associated with the relationship between different labels, and a self-adapted label assigning threshold, mlDEEPre can accurately and efficiently perform multi-functional enzyme prediction. Extensive experiments also show that mlDEEPre can outperform the other methods in predicting whether an enzyme is a mono-functional or a multi-functional enzyme (mono-functional vs. multi-functional), as well as the main class prediction across different criteria. Furthermore, due to the flexibility of mlDEEPre and DEEPre, mlDEEPre can be incorporated into DEEPre seamlessly, which enables the updated DEEPre to handle both mono-functional and multi-functional predictions without human intervention.