scholarly journals DeepKinZero: zero-shot learning for predicting kinase–phosphosite associations involving understudied kinases

2020 ◽  
Vol 36 (12) ◽  
pp. 3652-3661 ◽  
Author(s):  
Iman Deznabi ◽  
Busra Arabaci ◽  
Mehmet Koyutürk ◽  
Oznur Tastan
Keyword(s):  
Protein Function ◽  
Large Body ◽  
Supplementary Information ◽  
Baseline Model ◽  
Source Codes ◽  
Target Sites ◽  
Specific Manner ◽  
Proteome Level ◽  
A Site ◽  
Experimental Challenge

Abstract Motivation Protein phosphorylation is a key regulator of protein function in signal transduction pathways. Kinases are the enzymes that catalyze the phosphorylation of other proteins in a target-specific manner. The dysregulation of phosphorylation is associated with many diseases including cancer. Although the advances in phosphoproteomics enable the identification of phosphosites at the proteome level, most of the phosphoproteome is still in the dark: more than 95% of the reported human phosphosites have no known kinases. Determining which kinase is responsible for phosphorylating a site remains an experimental challenge. Existing computational methods require several examples of known targets of a kinase to make accurate kinase-specific predictions, yet for a large body of kinases, only a few or no target sites are reported. Results We present DeepKinZero, the first zero-shot learning approach to predict the kinase acting on a phosphosite for kinases with no known phosphosite information. DeepKinZero transfers knowledge from kinases with many known target phosphosites to those kinases with no known sites through a zero-shot learning model. The kinase-specific positional amino acid preferences are learned using a bidirectional recurrent neural network. We show that DeepKinZero achieves significant improvement in accuracy for kinases with no known phosphosites in comparison to the baseline model and other methods available. By expanding our knowledge on understudied kinases, DeepKinZero can help to chart the phosphoproteome atlas. Availability and implementation The source codes are available at https://github.com/Tastanlab/DeepKinZero. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals DeepKinZero: Zero-Shot Learning for Predicting Kinase-Phosphosite Associations Involving Understudied Kinases

2019 ◽  
Author(s):  
Iman Deznabi ◽  
Busra Arabaci ◽  
Mehmet Koyutürk ◽  
Oznur Tastan
Keyword(s):  
Protein Function ◽  
Large Body ◽  
Signal Transduction Pathways ◽  
Learning Approach ◽  
Baseline Model ◽  
Target Sites ◽  
Specific Manner ◽  
Proteome Level ◽  
A Site ◽  
Experimental Challenge

AbstractProtein phosphorylation is a key regulator of protein function in signal transduction pathways. Kinases are the enzymes that catalyze the phosphorylation of other proteins in a target specific manner. The dysregulation of phosphorylation is associated with many diseases including cancer. Although the advances in phosphoproteomics enable the identification of phosphosites at the proteome level, most of the phosphoproteome is still in the dark: more than 95% of the reported human phosphosites have no known kinases. Determining which kinase is responsible for phosphorylating a site remains an experimental challenge. Existing computational methods require several examples of known targets of a kinase to make accurate kinase specific predictions, yet for a large body of kinases, only a few or no target sites are reported. We present DeepKinZero, the first zero-shot learning approach to predict the kinase acting on a phosphosite for kinases with no known phosphosite information. DeepKinZero transfers knowledge from kinases with many known target phosphosites to those kinases with no known sites through a zero-shot learning model. The kinase specific positional amino acid preferences are learned using a bidirectional recurrent neural network. We show that DeepKinZero achieves significant improvement in accuracy for kinases with no known phosphosites in comparison to the baseline model and other methods available. By expanding our knowledge on understudied kinases, DeepKinZero can help to chart the phosphoproteome atlas.

scholarly journals CRISPRitz: rapid, high-throughput and variant-aware in silico off-target site identification for CRISPR genome editing

2019 ◽  
Vol 36 (7) ◽  
pp. 2001-2008 ◽  
Author(s):  
Samuele Cancellieri ◽  
Matthew C Canver ◽  
Nicola Bombieri ◽  
Rosalba Giugno ◽  
Luca Pinello
Keyword(s):  
In Silico ◽  
Supplementary Information ◽  
Guide Rnas ◽  
Computational Performance ◽  
Search Mechanism ◽  
Genomic Annotation ◽  
Target Sites ◽  
Dna Elements ◽  
Efficient Data ◽  
A Site

ABSTRACT Motivation Clustered regularly interspaced short palindromic repeats (CRISPR) technologies allow for facile genomic modification in a site-specific manner. A key step in this process is the in silico design of single guide RNAs to efficiently and specifically target a site of interest. To this end, it is necessary to enumerate all potential off-target sites within a given genome that could be inadvertently altered by nuclease-mediated cleavage. Currently available software for this task is limited by computational efficiency, variant support or annotation, and assessment of the functional impact of potential off-target effects. Results To overcome these limitations, we have developed CRISPRitz, a suite of software tools to support the design and analysis of CRISPR/CRISPR-associated (Cas) experiments. Using efficient data structures combined with parallel computation, we offer a rapid, reliable, and exhaustive search mechanism to enumerate a comprehensive list of putative off-target sites. As proof-of-principle, we performed a head-to-head comparison with other available tools on several datasets. This analysis highlighted the unique features and superior computational performance of CRISPRitz including support for genomic searching with DNA/RNA bulges and mismatches of arbitrary size as specified by the user as well as consideration of genetic variants (variant-aware). In addition, graphical reports are offered for coding and non-coding regions that annotate the potential impact of putative off-target sites that lie within regions of functional genomic annotation (e.g. insulator and chromatin accessible sites from the ENCyclopedia Of DNA Elements [ENCODE] project). Availability and implementation The software is freely available at: https://github.com/pinellolab/CRISPRitzhttps://github.com/InfOmics/CRISPRitz. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals SubMito-XGBoost: predicting protein submitochondrial localization by fusing multiple feature information and eXtreme gradient boosting

2019 ◽  
Vol 36 (4) ◽  
pp. 1074-1081 ◽  
Author(s):  
Bin Yu ◽  
Wenying Qiu ◽  
Cheng Chen ◽  
Anjun Ma ◽  
Jing Jiang ◽  
...  
Keyword(s):  
Drug Design ◽  
Protein Function ◽  
Predictive Performance ◽  
Supplementary Information ◽  
Gradient Boosting ◽  
Source Codes ◽  
Extreme Gradient Boosting ◽  
Auto Correlation Function ◽  
Abnormal Mitochondria ◽  
Leave One Out

Abstract Motivation Mitochondria are an essential organelle in most eukaryotes. They not only play an important role in energy metabolism but also take part in many critical cytopathological processes. Abnormal mitochondria can trigger a series of human diseases, such as Parkinson's disease, multifactor disorder and Type-II diabetes. Protein submitochondrial localization enables the understanding of protein function in studying disease pathogenesis and drug design. Results We proposed a new method, SubMito-XGBoost, for protein submitochondrial localization prediction. Three steps are included: (i) the g-gap dipeptide composition (g-gap DC), pseudo-amino acid composition (PseAAC), auto-correlation function (ACF) and Bi-gram position-specific scoring matrix (Bi-gram PSSM) are employed to extract protein sequence features, (ii) Synthetic Minority Oversampling Technique (SMOTE) is used to balance samples, and the ReliefF algorithm is applied for feature selection and (iii) the obtained feature vectors are fed into XGBoost to predict protein submitochondrial locations. SubMito-XGBoost has obtained satisfactory prediction results by the leave-one-out-cross-validation (LOOCV) compared with existing methods. The prediction accuracies of the SubMito-XGBoost method on the two training datasets M317 and M983 were 97.7% and 98.9%, which are 2.8–12.5% and 3.8–9.9% higher than other methods, respectively. The prediction accuracy of the independent test set M495 was 94.8%, which is significantly better than the existing studies. The proposed method also achieves satisfactory predictive performance on plant and non-plant protein submitochondrial datasets. SubMito-XGBoost also plays an important role in new drug design for the treatment of related diseases. Availability and implementation The source codes and data are publicly available at https://github.com/QUST-AIBBDRC/SubMito-XGBoost/. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals TALE: Transformer-based protein function Annotation with joint sequence–Label Embedding

2020 ◽  
Author(s):  
Yue Cao ◽  
Yang Shen
Keyword(s):  
High Throughput ◽  
Protein Function ◽  
Sequence Data ◽  
Sequence Similarity ◽  
Directed Graphs ◽  
Training Data ◽  
Supplementary Information ◽  
Function Annotation ◽  
Source Codes ◽  
Protein Function Annotation

AbstractMotivationFacing the increasing gap between high-throughput sequence data and limited functional insights, computational protein function annotation provides a high-throughput alternative to experimental approaches. However, current methods can have limited applicability while relying on data besides sequences, or lack generalizability to novel sequences, species and functions.ResultsTo overcome aforementioned barriers in applicability and generalizability, we propose a novel deep learning model, named Transformer-based protein function Annotation through joint sequence–Label Embedding (TALE). For generalizbility to novel sequences we use self attention-based transformers to capture global patterns in sequences. For generalizability to unseen or rarely seen functions, we also embed protein function labels (hierarchical GO terms on directed graphs) together with inputs/features (sequences) in a joint latent space. Combining TALE and a sequence similarity-based method, TALE+ outperformed competing methods when only sequence input is available. It even outperformed a state-of-the-art method using network information besides sequence, in two of the three gene ontologies. Furthermore, TALE and TALE+ showed superior generalizability to proteins of low homology and never/rarely annotated novel species or functions compared to training data, revealing deep insights into the protein sequence–function relationship. Ablation studies elucidated contributions of algorithmic components toward the accuracy and the generalizability.AvailabilityThe data, source codes and models are available at https://github.com/Shen-Lab/[email protected] informationSupplementary data are available at Bioinformatics online.

A novel method for data fusion over entity-relation graphs and its application to protein–protein interaction prediction

2021 ◽  
Author(s):  
Daniele Raimondi ◽  
Jaak Simm ◽  
Adam Arany ◽  
Yves Moreau
Keyword(s):  
Data Fusion ◽  
Protein Interactions ◽  
Protein Function ◽  
Scientific Progress ◽  
Supplementary Information ◽  
Sources Of Information ◽  
Protein Protein Interaction ◽  
Ppi Networks ◽  
Proteome Level ◽  
Clear Shift

Abstract Motivation Modern bioinformatics is facing increasingly complex problems to solve, and we are indeed rapidly approaching an era in which the ability to seamlessly integrate heterogeneous sources of information will be crucial for the scientific progress. Here, we present a novel non-linear data fusion framework that generalizes the conventional matrix factorization paradigm allowing inference over arbitrary entity-relation graphs, and we applied it to the prediction of protein–protein interactions (PPIs). Improving our knowledge of PPI networks at the proteome scale is indeed crucial to understand protein function, physiological and disease states and cell life in general. Results We devised three data fusion-based models for the proteome-level prediction of PPIs, and we show that our method outperforms state of the art approaches on common benchmarks. Moreover, we investigate its predictions on newly published PPIs, showing that this new data has a clear shift in its underlying distributions and we thus train and test our models on this extended dataset. Supplementary information Supplementary data are available at Bioinformatics online.

movAPA: modeling and visualization of dynamics of alternative polyadenylation across biological samples

2020 ◽  
Author(s):  
Wenbin Ye ◽  
Tao Liu ◽  
Hongjuan Fu ◽  
Congting Ye ◽  
Guoli Ji ◽  
...  
Keyword(s):  
Biological Samples ◽  
Tissue Specificity ◽  
Single Cells ◽  
Alternative Polyadenylation ◽  
R Package ◽  
Supplementary Information ◽  
Rna Seq ◽  
Mouse Sperm ◽  
High Scalability ◽  
A Site

Abstract Motivation Alternative polyadenylation (APA) has been widely recognized as a widespread mechanism modulated dynamically. Studies based on 3′ end sequencing and/or RNA-seq have profiled poly(A) sites in various species with diverse pipelines, yet no unified and easy-to-use toolkit is available for comprehensive APA analyses. Results We developed an R package called movAPA for modeling and visualization of dynamics of alternative polyadenylation across biological samples. movAPA incorporates rich functions for preprocessing, annotation and statistical analyses of poly(A) sites, identification of poly(A) signals, profiling of APA dynamics and visualization. Particularly, seven metrics are provided for measuring the tissue-specificity or usages of APA sites across samples. Three methods are used for identifying 3′ UTR shortening/lengthening events between conditions. APA site switching involving non-3′ UTR polyadenylation can also be explored. Using poly(A) site data from rice and mouse sperm cells, we demonstrated the high scalability and flexibility of movAPA in profiling APA dynamics across tissues and single cells. Availability and implementation https://github.com/BMILAB/movAPA. Supplementary information Supplementary data are available at Bioinformatics online.

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.

Personalization in the Information Era

2011 ◽  
pp. 3059-3064
Author(s):  
José Juan Pazos-Arias ◽  
Martín López-Nores
Keyword(s):  
Information Overload ◽  
Large Body ◽  
Communication Technologies ◽  
Digital Subscriber Line ◽  
New Paradigm ◽  
Entertainment Education ◽  
Open Problems ◽  
Amount Of Information ◽  
A Site ◽  
Watching Tv

We are witnessing the development of new communication technologies (e.g., DTV networks [digital TV], 3G [thirdgeneration] telephony, and DSL [digital subscriber line]) and a rapid growth in the amount of information available. In this scenario, users were supposed to benefit extensively from services delivering news, entertainment, education, commercial functionalities, and so forth. However, the current situation may be better referred to as information overload; as it frequently happens that users are faced with an overwhelming amount of information. A similar situation was noticeable in the 1990s with the exponential growth of the Internet, which made users feel disoriented among the myriad of contents available through their PCs. This gave birth to search engines (e.g., Google and Yahoo) that would retrieve relevant Web pages in response to user-entered queries. These tools proved effective, with millions of people using them to find pieces of information and services. However, the advent of new devices (DTV receivers, mobile phones, media players, etc.) introduces consumption and usage habits that render the search-engine paradigm insufficient. It is no longer realistic to think that users will bother to visit a site, enter queries describing what they want, and select particular contents from among those in a list. The reasons may relate to users adopting a predominantly passive role (e.g., while driving or watching TV), the absence of bidirectional communication (as in broadcasting environments), or users feeling uneasy with the interfaces provided. To tackle these issues, a large body of research is being devoted nowadays to the design and provision of personalized information services, with a new paradigm of recommender systems proactively selecting the contents that match the interests and needs of each individual at any time. This article describes the evolution of these services, followed by an overview of the functionalities available in diverse areas of application and a discussion of open problems. Background The development of personalized information

VisFeature: a stand-alone program for visualizing and analyzing statistical features of biological sequences

2019 ◽  
Author(s):  
Jun Wang ◽  
Pu-Feng Du ◽  
Xin-Yu Xue ◽  
Guang-Ping Li ◽  
Yuan-Ke Zhou ◽  
...  
Keyword(s):  
Sequence Data ◽  
Software Tool ◽  
Data Retrieval ◽  
Supplementary Information ◽  
Statistical Features ◽  
Biological Sequence ◽  
Sequence Alignments ◽  
Multiple Sequence ◽  
Source Codes ◽  
Multiple Sequence Alignments

Abstract Summary Many efforts have been made in developing bioinformatics algorithms to predict functional attributes of genes and proteins from their primary sequences. One challenge in this process is to intuitively analyze and to understand the statistical features that have been selected by heuristic or iterative methods. In this paper, we developed VisFeature, which aims to be a helpful software tool that allows the users to intuitively visualize and analyze statistical features of all types of biological sequence, including DNA, RNA and proteins. VisFeature also integrates sequence data retrieval, multiple sequence alignments and statistical feature generation functions. Availability and implementation VisFeature is a desktop application that is implemented using JavaScript/Electron and R. The source codes of VisFeature are freely accessible from the GitHub repository (https://github.com/wangjun1996/VisFeature). The binary release, which includes an example dataset, can be freely downloaded from the same GitHub repository (https://github.com/wangjun1996/VisFeature/releases). Contact [email protected] or [email protected] Supplementary information Supplementary data are available at Bioinformatics online.

Sign in / Sign up

Export Citation Format

Share Document