Biology subjects

Zeng, J.

Publications and source records attributed to Zeng, J..

23 records · Page 2Linked to original sources

bioRxiv2017

TIDE: predicting translation initiation sites by deep learning

MotivationTranslation initiation is a key step in the regulation of gene expression. In addition to the annotated translation initiation sites (TISs), the translation process may also start at multiple alternative TISs (including both AUG and non-AUG codons), which makes it challenging to predict TISs and study the underlying regulatory mechanisms. Meanwhile, the advent of several high-throughput sequencing techniques for profiling initiating ribosomes at single-nucleotide resolution, e.g., GTI-seq and QTI-seq, provides abundant data for systematically studying the general principles of translation initiation and the development of computational method for TIS identification.\n\nMethodsWe have developed a deep learning based framework, named TITER, for accurately predicting TISs on a genome-wide scale based on QTI-seq data. TITER extracts the sequence features of translation initiation from the surrounding sequence contexts of TISs using a hybrid neural network and further integrates the prior preference of TIS codon composition into a unified prediction framework.\n\nResultsExtensive tests demonstrated that TITER can greatly outperform the state-of-the-art prediction methods in identifying TISs. In addition, TITER was able to identify important sequence signatures for individual types of TIS codons, including a Kozak-sequence-like motif for AUG start codon. Furthermore, the TITER prediction score can be related to the strength of translation initiation in various biological scenarios, including the repressive effect of the upstream open reading frames (uORFs) on gene expression and the mutational effects influencing translation initiation efficiency.\n\nAvailabilityTITER is available as an open-source software and can be downloaded from https://github.com/zhangsaithu/titer\n\nContactlzhang20@mail.tsinghua.edu.cn and zengjy321@tsinghua.edu.cn

bioinformatics↗

bioRxiv2017

Multiple-trait Bayesian Regression Methods with Mixture Priors for Genomic Prediction

Bayesian multiple-regression methods incorporating different mixture priors for marker effects are widely used in genomic prediction. Improvement in prediction accuracies from using those methods, such as BayesB, BayesC and BayesC{pi}, have been shown in single-trait analyses with both simulated data and real data. These methods have been extended to multi-trait analyses, but only under a specific limited circumstance that assumes a locus affects all the traits or none of them. In this paper, we develop and implement the most general multi-trait BayesC{Pi} and BayesB methods allowing a broader range of mixture priors. Further, we compare them to single-trait methods and the \"restricted\" multi-trait formulation using real data. In those data analyses, significant higher prediction accuracies were sometimes observed from these new broad-based multi-trait Bayesian multiple-regression methods. The software tool JWAS offers routines to perform the analyses.

genetics↗

bioRxiv2017

A Network Integration Approach for Drug-Target Interaction Prediction and Computational Drug Repositioning from Heterogeneous Information

The emergence of large-scale genomic, chemical and pharmacological data provides new opportunities for drug discovery and repositioning. Systematic integration of these heterogeneous data not only serves as a promising tool for identifying new drug-target interactions (DTIs), which is an important step in drug development, but also provides a more complete understanding of the molecular mechanisms of drug action. In this work, we integrate diverse drug-related information, including drugs, proteins, diseases and side-effects, together with their interactions, associations or similarities, to construct a heterogeneous network with 12,015 nodes and 1,895,445 edges. We then develop a new computational pipeline, called DTINet, to predict novel drug-target interactions from the constructed heterogeneous network. Specifically, DTINet focuses on learning a low-dimensional vector representation of features for each node, which accurately explains the topological properties of individual nodes in the heterogeneous network, and then predicts the likelihood of a new DTI based on these representations via a vector space projection scheme. DTINet achieves substantial performance improvement over other state-of-the-art methods for DTI prediction. Moreover, we have experimentally validated the novel interactions between three drugs and the cyclooxygenase (COX) protein family predicted by DTINet, and demonstrated the new potential applications of these identified COX inhibitors in preventing inflammatory diseases. These results indicate that DTINet can provide a practically useful tool for integrating heterogeneous information to predict new drug-target interactions and repurpose existing drugs. The source code of DTINet and the input heterogeneous network data can be downloaded from http://github.com/luoyunan/DTINet.

bioinformatics↗

bioRxiv2016

A Deep Boosting Based Approach for Capturing the Sequence Binding Preferences of RNA-Binding Proteins from High-Throughput CLIP-Seq Data

Characterizing the binding behaviors of RNA-binding proteins (RBPs) is important for understanding their functional roles in gene expression regulation. However, current high-throughput experimental methods for identifying RBP targets, such as CLIP-seq and RNAcompete, usually suffer from the false positive and false negative issues. Here, we develop a deep boosting based machine learning approach, called DeBooster, to accurately model the binding sequence preferences and identify the corresponding binding targets of RBPs from CLIP-seq data. Comprehensive validation tests have shown that DeBooster can outperform other state-of-the-art approaches in predicting RBP targets and recover false negatives that are common in current CLIP-seq data. In addition, we have demonstrated several new potential applications of DeBooster in understanding the regulatory functions of RBPs, including the binding effects of the RNA helicase MOV10 on mRNA degradation, the influence of different binding behaviors of the ADAR proteins on RNA editing, as well as the antagonizing effect of RBP binding on miRNA repression. Moreover, DeBooster may provide an effective index to investigate the effect of pathogenic mutations in RBP binding sites, especially those related to splicing events. We expect that DeBooster will be widely applied to analyze large-scale CLIP-seq experimental data and can provide a practically useful tool for novel biological discoveries in understanding the regulatory mechanisms of RBPs. The scource code of DeBooster can be downloaded from http://github.com/dongfanghong/deepboost.

bioinformatics↗

bioRxiv2016

Deep learning with feature embedding for compound-proteininteraction prediction

Accurately identifying compound-protein interactions in silico can deepen our understanding of the mechanisms of drug action and significantly facilitate the drug discovery and development process. Traditional similarity-based computational models for compound-protein interaction prediction rarely exploit the latent features from current available large-scale unlabelled compound and protein data, and often limit their usage on relatively small-scale datasets. We propose a new scheme that combines feature embedding (a technique of representation learning) with deep learning for predicting compound-protein interactions. Our method automatically learns the low-dimensional implicit but expressive features for compounds and proteins from the massive amount of unlabelled data. Combining effective feature embedding with powerful deep learning techniques, our method provides a general computational pipeline for accurate compound-protein interaction prediction, even when the interaction knowledge of compounds and proteins is entirely unknown. Evaluations on current large-scale databases of the measured compound-protein affinities, such as ChEMBL and BindingDB, as well as known drug-target interactions from DrugBank have demonstrated the superior prediction performance of our method, and suggested that it can offer a useful tool for drug development and drug repositioning.

bioinformatics↗