scholarly journals Graph neural representational learning of RNA secondary structures for predicting RNA-protein interactions

2020 ◽  
Vol 36 (Supplement_1) ◽  
pp. i276-i284 ◽  
Author(s):  
Zichao Yan ◽  
William L Hamilton ◽  
Mathieu Blanchette
Keyword(s):  
Protein Interactions ◽  
Graph Representation ◽  
Supplementary Information ◽  
Neural Network Approach ◽  
Rna Molecules ◽  
Significant Performance ◽  
Protein Interaction Prediction ◽  
Performance Gains ◽  
Post Transcriptional Regulation ◽  
Sequence Bias

Abstract Motivation RNA-protein interactions are key effectors of post-transcriptional regulation. Significant experimental and bioinformatics efforts have been expended on characterizing protein binding mechanisms on the molecular level, and on highlighting the sequence and structural traits of RNA that impact the binding specificity for different proteins. Yet our ability to predict these interactions in silico remains relatively poor. Results In this study, we introduce RPI-Net, a graph neural network approach for RNA-protein interaction prediction. RPI-Net learns and exploits a graph representation of RNA molecules, yielding significant performance gains over existing state-of-the-art approaches. We also introduce an approach to rectify an important type of sequence bias caused by the RNase T1 enzyme used in many CLIP-Seq experiments, and we show that correcting this bias is essential in order to learn meaningful predictors and properly evaluate their accuracy. Finally, we provide new approaches to interpret the trained models and extract simple, biologically interpretable representations of the learned sequence and structural motifs. Availability and implementation Source code can be accessed at https://www.github.com/HarveyYan/RNAonGraph. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Graph neural representational learning of RNA secondary structures for predicting RNA-protein interactions

2020 ◽  
Author(s):  
Zichao Yan ◽  
William L. Hamilton ◽  
Mathieu Blanchette
Keyword(s):  
Protein Interactions ◽  
Graph Representation ◽  
Data Sets ◽  
Neural Network Approach ◽  
Rna Molecules ◽  
Significant Performance ◽  
Protein Interaction Prediction ◽  
Performance Gains ◽  
Post Transcriptional Regulation ◽  
Sequence Bias

AbstractMotivationRNA-protein interactions are key effectors of post-transcriptional regulation. Significant experimental and bioinformatics efforts have been expended on characterizing protein binding mechanisms on the molecular level, and on highlighting the sequence and structural traits of RNA that impact the binding specificity for different proteins. Yet our ability to predict these interactions in silico remains relatively poor.ResultsIn this study, we introduce RPI-Net, a graph neural network approach for RNA-protein interaction prediction. RPI-Net learns and exploits a graph representation of RNA molecules, yielding significant performance gains over existing state-of-the-art approaches. We also introduce an approach to rectify particular type of sequence bias present in many CLIP-Seq data sets, and we show that correcting this bias is essential in order to learn meaningful predictors and properly evaluate their accuracy. Finally, we provide new approaches to interpret the trained models and extract simple, biologically-interpretable representations of the learned sequence and structural motifs.AvailabilitySource code can be accessed at https://www.github.com/HarveyYan/[email protected], [email protected]

scholarly journals CROSSalive: a web server for predicting the in vivo structure of RNA molecules

2019 ◽  
Author(s):  
Riccardo Delli Ponti ◽  
Alexandros Armaos ◽  
Andrea Vandelli ◽  
Gian Gaetano Tartaglia
Keyword(s):  
Protein Interactions ◽  
Rna Structure ◽  
Cross Validation ◽  
Supplementary Information ◽  
Supplementary Data ◽  
High Confidence ◽  
Rna Molecules ◽  
Non Coding Rna ◽  
Long Non Coding Rna

Abstract Motivation RNA structure is difficult to predict in vivo due to interactions with enzymes and other molecules. Here we introduce CROSSalive, an algorithm to predict the single- and double-stranded regions of RNAs in vivo using predictions of protein interactions. Results Trained on icSHAPE data in presence (m6a+) and absence of N6 methyladenosine modification (m6a-), CROSSalive achieves cross-validation accuracies between 0.70 and 0.88 in identifying high-confidence single- and double-stranded regions. The algorithm was applied to the long non-coding RNA Xist (17 900 nt, not present in the training) and shows an Area under the ROC curve of 0.83 in predicting structured regions. Availability and implementation CROSSalive webserver is freely accessible at http://service.tartaglialab.com/new_submission/crossalive Contact [email protected] Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals RAPPPID: Towards Generalisable Protein Interaction Prediction with AWD-LSTM Twin Networks

2021 ◽  
Author(s):  
Joseph Szymborski ◽  
Amin Emad
Keyword(s):  
Protein Interaction ◽  
Protein Interactions ◽  
Information Leakage ◽  
Supplementary Information ◽  
Protein Protein Interactions ◽  
Training Time ◽  
Interaction Prediction ◽  
Protein Protein Interaction ◽  
Protein Interaction Prediction ◽  
Time To Learn

Motivation: Computational methods for the prediction of protein-protein interactions, while important tools for researchers, are plagued by challenges in generalising to unseen proteins. Datasets used for modelling protein-protein predictions are particularly predisposed to information leakage and sampling biases. Results: In this study, we introduce RAPPPID, a method for the Regularised Automatic Prediction of Protein-Protein Interactions using Deep Learning. RAPPPID is a twin AWD-LSTM network which employs multiple regularisation methods during training time to learn generalised weights. Testing on stringent interaction datasets composed of proteins not seen during training, RAPPPID outperforms state-of-the-art methods. Further experiments show that RAPPPID's performance holds regardless of the particular proteins in the testing set and its performance is higher for biologically supported edges. This study serves to demonstrate that appropriate regularisation is an important component of overcoming the challenges of creating models for protein-protein interaction prediction that generalise to unseen proteins. Availability and Implementation: Code and datasets are freely available at https://github.com/jszym/rapppid. Contact: [email protected] Supplementary Information: Online-only supplementary data is available at the journal's website.

Structure-aware protein–protein interaction site prediction using deep graph convolutional network

2021 ◽  
Author(s):  
Qianmu Yuan ◽  
Jianwen Chen ◽  
Huiying Zhao ◽  
Yaoqi Zhou ◽  
Yuedong Yang
Keyword(s):  
Protein Interactions ◽  
Spatial Information ◽  
Screening Tools ◽  
Supplementary Information ◽  
Protein Protein Interactions ◽  
Convolutional Network ◽  
Source Codes ◽  
Site Prediction ◽  
Protein Protein Interaction ◽  
Mapping Techniques

Abstract Motivation Protein–protein interactions (PPI) play crucial roles in many biological processes, and identifying PPI sites is an important step for mechanistic understanding of diseases and design of novel drugs. Since experimental approaches for PPI site identification are expensive and time-consuming, many computational methods have been developed as screening tools. However, these methods are mostly based on neighbored features in sequence, and thus limited to capture spatial information. Results We propose a deep graph-based framework deep Graph convolutional network for Protein–Protein-Interacting Site prediction (GraphPPIS) for PPI site prediction, where the PPI site prediction problem was converted into a graph node classification task and solved by deep learning using the initial residual and identity mapping techniques. We showed that a deeper architecture (up to eight layers) allows significant performance improvement over other sequence-based and structure-based methods by more than 12.5% and 10.5% on AUPRC and MCC, respectively. Further analyses indicated that the predicted interacting sites by GraphPPIS are more spatially clustered and closer to the native ones even when false-positive predictions are made. The results highlight the importance of capturing spatially neighboring residues for interacting site prediction. Availability and implementation The datasets, the pre-computed features, and the source codes along with the pre-trained models of GraphPPIS are available at https://github.com/biomed-AI/GraphPPIS. The GraphPPIS web server is freely available at https://biomed.nscc-gz.cn/apps/GraphPPIS. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals miRador: a fast and precise tool for the prediction of plant miRNAs

2021 ◽  
Author(s):  
Reza K Hammond ◽  
Parth Patel ◽  
Pallavi Gupta ◽  
Blake C. Meyers
Keyword(s):  
Stress Responses ◽  
Target Prediction ◽  
Accurate Identification ◽  
Rna Molecules ◽  
Prediction Tools ◽  
Novel Mirna ◽  
Precise Tool ◽  
Computationally Intensive ◽  
And Function ◽  
Post Transcriptional Regulation

Plant microRNAs (miRNAs) are short, non-coding RNA molecules that restrict gene expression via post-transcriptional regulation and function in several essential pathways including development, growth, and stress responses. Accurately identifying miRNAs in populations of small RNA (sRNA) sequencing libraries is a computationally intensive process which has resulted in the misidentification of inaccurately annotated miRNA sequences. In recent years, criteria for miRNA annotation have been refined to reduce these misannotations. Here, we describe miRador, a novel miRNA identification tool that utilizes the most up-to-date, community-established criteria for accurate identification of miRNAs in plants. We combine target prediction and Parallel Analysis of RNA Ends (PARE) data to assess the precision of the miRNAs identified by miRador. We compare miRador to other commonly used miRNA prediction tools and we find that miRador is at least as precise as other prediction tools while being significantly faster than other tools.

scholarly journals LPI-HyADBS: a hybrid framework for lncRNA-protein interaction prediction integrating feature selection and classification

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Liqian Zhou ◽  
Qi Duan ◽  
Xiongfei Tian ◽  
He Xu ◽  
Jianxin Tang ◽  
...  
Keyword(s):  
Feature Selection ◽  
Protein Interactions ◽  
Cross Validation ◽  
Rna Binding ◽  
Rna Binding Proteins ◽  
Biological Information ◽  
Hybrid Framework ◽  
Protein Interaction Prediction ◽  
Single Dataset ◽  
Feature Selection Approach

Abstract Background Long noncoding RNAs (lncRNAs) have dense linkages with a plethora of important cellular activities. lncRNAs exert functions by linking with corresponding RNA-binding proteins. Since experimental techniques to detect lncRNA-protein interactions (LPIs) are laborious and time-consuming, a few computational methods have been reported for LPI prediction. However, computation-based LPI identification methods have the following limitations: (1) Most methods were evaluated on a single dataset, and researchers may thus fail to measure their generalization ability. (2) The majority of methods were validated under cross validation on lncRNA-protein pairs, did not investigate the performance under other cross validations, especially for cross validation on independent lncRNAs and independent proteins. (3) lncRNAs and proteins have abundant biological information, how to select informative features need to further investigate. Results Under a hybrid framework (LPI-HyADBS) integrating feature selection based on AdaBoost, and classification models including deep neural network (DNN), extreme gradient Boost (XGBoost), and SVM with a penalty Coefficient of misclassification (C-SVM), this work focuses on finding new LPIs. First, five datasets are arranged. Each dataset contains lncRNA sequences, protein sequences, and an LPI network. Second, biological features of lncRNAs and proteins are acquired based on Pyfeat. Third, the obtained features of lncRNAs and proteins are selected based on AdaBoost and concatenated to depict each LPI sample. Fourth, DNN, XGBoost, and C-SVM are used to classify lncRNA-protein pairs based on the concatenated features. Finally, a hybrid framework is developed to integrate the classification results from the above three classifiers. LPI-HyADBS is compared to six classical LPI prediction approaches (LPI-SKF, LPI-NRLMF, Capsule-LPI, LPI-CNNCP, LPLNP, and LPBNI) on five datasets under 5-fold cross validations on lncRNAs, proteins, lncRNA-protein pairs, and independent lncRNAs and independent proteins. The results show LPI-HyADBS has the best LPI prediction performance under four different cross validations. In particular, LPI-HyADBS obtains better classification ability than other six approaches under the constructed independent dataset. Case analyses suggest that there is relevance between ZNF667-AS1 and Q15717. Conclusions Integrating feature selection approach based on AdaBoost, three classification techniques including DNN, XGBoost, and C-SVM, this work develops a hybrid framework to identify new linkages between lncRNAs and proteins.

scholarly journals Coevolution-based prediction of protein–protein interactions in polyketide biosynthetic assembly lines

2020 ◽  
Vol 36 (19) ◽  
pp. 4846-4853 ◽  
Author(s):  
Yan Wang ◽  
Miguel Correa Marrero ◽  
Marnix H Medema ◽  
Aalt D J van Dijk
Keyword(s):  
Protein Interactions ◽  
Antitumor Agents ◽  
Acyl Carrier Protein ◽  
Specific Protein ◽  
Combinatorial Biosynthesis ◽  
Supplementary Information ◽  
Protein Protein Interactions ◽  
Assembly Lines ◽  
Specific Order ◽  
Encoding Genes

Abstract Motivation Polyketide synthases (PKSs) are enzymes that generate diverse molecules of great pharmaceutical importance, including a range of clinically used antimicrobials and antitumor agents. Many polyketides are synthesized by cis-AT modular PKSs, which are organized in assembly lines, in which multiple enzymes line up in a specific order. This order is defined by specific protein–protein interactions (PPIs). The unique modular structure and catalyzing mechanism of these assembly lines makes their products predictable and also spurred combinatorial biosynthesis studies to produce novel polyketides using synthetic biology. However, predicting the interactions of PKSs, and thereby inferring the order of their assembly line, is still challenging, especially for cases in which this order is not reflected by the ordering of the PKS-encoding genes in the genome. Results Here, we introduce PKSpop, which uses a coevolution-based PPI algorithm to infer protein order in PKS assembly lines. Our method accurately predicts protein orders (93% accuracy). Additionally, we identify new residue pairs that are key in determining interaction specificity, and show that coevolution of N- and C-terminal docking domains of PKSs is significantly more predictive for PPIs than coevolution between ketosynthase and acyl carrier protein domains. Availability and implementation The code is available on http://www.bif.wur.nl/ (under ‘Software’). Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Chemical–protein interaction extraction via Gaussian probability distribution and external biomedical knowledge

2020 ◽  
Vol 36 (15) ◽  
pp. 4323-4330 ◽  
Author(s):  
Cong Sun ◽  
Zhihao Yang ◽  
Leilei Su ◽  
Lei Wang ◽  
Yin Zhang ◽  
...  
Keyword(s):  
Probability Distribution ◽  
Protein Interactions ◽  
Local Structure ◽  
Relation Extraction ◽  
Biomedical Literature ◽  
Supplementary Information ◽  
Biomedical Knowledge ◽  
Proposed Model ◽  
Gaussian Probability Distribution ◽  
Extraction Performance

Abstract Motivation The biomedical literature contains a wealth of chemical–protein interactions (CPIs). Automatically extracting CPIs described in biomedical literature is essential for drug discovery, precision medicine, as well as basic biomedical research. Most existing methods focus only on the sentence sequence to identify these CPIs. However, the local structure of sentences and external biomedical knowledge also contain valuable information. Effective use of such information may improve the performance of CPI extraction. Results In this article, we propose a novel neural network-based approach to improve CPI extraction. Specifically, the approach first employs BERT to generate high-quality contextual representations of the title sequence, instance sequence and knowledge sequence. Then, the Gaussian probability distribution is introduced to capture the local structure of the instance. Meanwhile, the attention mechanism is applied to fuse the title information and biomedical knowledge, respectively. Finally, the related representations are concatenated and fed into the softmax function to extract CPIs. We evaluate our proposed model on the CHEMPROT corpus. Our proposed model is superior in performance as compared with other state-of-the-art models. The experimental results show that the Gaussian probability distribution and external knowledge are complementary to each other. Integrating them can effectively improve the CPI extraction performance. Furthermore, the Gaussian probability distribution can effectively improve the extraction performance of sentences with overlapping relations in biomedical relation extraction tasks. Availability and implementation Data and code are available at https://github.com/CongSun-dlut/CPI_extraction. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals DDxNet: a deep learning model for automatic interpretation of electronic health records, electrocardiograms and electroencephalograms

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Jayaraman J. Thiagarajan ◽  
Deepta Rajan ◽  
Sameeksha Katoch ◽  
Andreas Spanias
Keyword(s):  
Electronic Health Records ◽  
Rapid Development ◽  
Benchmark Problems ◽  
Health Records ◽  
Automatic Interpretation ◽  
Deep Architecture ◽  
Significant Performance ◽  
Electronic Health ◽  
Improving Accuracy ◽  
Performance Gains

Abstract Effective patient care mandates rapid, yet accurate, diagnosis. With the abundance of non-invasive diagnostic measurements and electronic health records (EHR), manual interpretation for differential diagnosis has become time-consuming and challenging. This has led to wide-spread adoption of AI-powered tools, in pursuit of improving accuracy and efficiency of this process. While the unique challenges presented by each modality and clinical task demand customized tools, the cumbersome process of making problem-specific choices has triggered the critical need for a generic solution to enable rapid development of models in practice. In this spirit, we develop DDxNet, a deep architecture for time-varying clinical data, which we demonstrate to be well-suited for diagnostic tasks involving different modalities (ECG/EEG/EHR), required level of characterization (abnormality detection/phenotyping) and data fidelity (single-lead ECG/22-channel EEG). Using multiple benchmark problems, we show that DDxNet produces high-fidelity predictive models, and sometimes even provides significant performance gains over problem-specific solutions.

Sign in / Sign up

Export Citation Format

Share Document