FUpred: detecting protein domains through deep-learning-based contact map prediction

Abstract Motivation Protein domains are subunits that can fold and function independently. Correct domain boundary assignment is thus a critical step toward accurate protein structure and function analyses. There is, however, no efficient algorithm available for accurate domain prediction from sequence. The problem is particularly challenging for proteins with discontinuous domains, which consist of domain segments that are separated along the sequence. Results We developed a new algorithm, FUpred, which predicts protein domain boundaries utilizing contact maps created by deep residual neural networks coupled with coevolutionary precision matrices. The core idea of the algorithm is to retrieve domain boundary locations by maximizing the number of intra-domain contacts, while minimizing the number of inter-domain contacts from the contact maps. FUpred was tested on a large-scale dataset consisting of 2549 proteins and generated correct single- and multi-domain classifications with a Matthew’s correlation coefficient of 0.799, which was 19.1% (or 5.3%) higher than the best machine learning (or threading)-based method. For proteins with discontinuous domains, the domain boundary detection and normalized domain overlapping scores of FUpred were 0.788 and 0.521, respectively, which were 17.3% and 23.8% higher than the best control method. The results demonstrate a new avenue to accurately detect domain composition from sequence alone, especially for discontinuous, multi-domain proteins. Availability and implementation https://zhanglab.ccmb.med.umich.edu/FUpred. Supplementary information Supplementary data are available at Bioinformatics online.

Download Full-text

DNN-Dom: predicting protein domain boundary from sequence alone by deep neural network

Bioinformatics ◽

10.1093/bioinformatics/btz464 ◽

2019 ◽

Vol 35 (24) ◽

pp. 5128-5136 ◽

Cited By ~ 3

Author(s):

Qiang Shi ◽

Weiya Chen ◽

Siqi Huang ◽

Fanglin Jin ◽

Yinghao Dong ◽

...

Keyword(s):

Neural Network ◽

Machine Learning ◽

Structure Prediction ◽

Domain Boundary ◽

Protein Domain ◽

Supplementary Information ◽

High Dimensions ◽

Long Range Interactions ◽

Domain Boundary Prediction ◽

And Function

Abstract Motivation Accurate delineation of protein domain boundary plays an important role for protein engineering and structure prediction. Although machine-learning methods are widely used to predict domain boundary, these approaches often ignore long-range interactions among residues, which have been proven to improve the prediction performance. However, how to simultaneously model the local and global interactions to further improve domain boundary prediction is still a challenging problem. Results This article employs a hybrid deep learning method that combines convolutional neural network and gate recurrent units’ models for domain boundary prediction. It not only captures the local and non-local interactions, but also fuses these features for prediction. Additionally, we adopt balanced Random Forest for classification to deal with high imbalance of samples and high dimensions of deep features. Experimental results show that our proposed approach (DNN-Dom) outperforms existing machine-learning-based methods for boundary prediction. We expect that DNN-Dom can be useful for assisting protein structure and function prediction. Availability and implementation The method is available as DNN-Dom Server at http://isyslab.info/DNN-Dom/. Supplementary information Supplementary data are available at Bioinformatics online.

Download Full-text

ConDo: protein domain boundary prediction using coevolutionary information

Bioinformatics ◽

10.1093/bioinformatics/bty973 ◽

2018 ◽

Vol 35 (14) ◽

pp. 2411-2417 ◽

Cited By ~ 2

Author(s):

Seung Hwan Hong ◽

Keehyoung Joo ◽

Jooyoung Lee

Keyword(s):

Long Range ◽

Domain Boundary ◽

Prediction Method ◽

Protein Domain ◽

Supplementary Information ◽

Sequence Information ◽

Multiple Sequence ◽

Domain Boundary Prediction ◽

Correlation Information ◽

And Function

AbstractMotivationDomain boundary prediction is one of the most important problems in the study of protein structure and function. Many sequence-based domain boundary prediction methods are either template-based or machine learning (ML) based. ML-based methods often perform poorly due to their use of only local (i.e. short-range) features. These conventional features such as sequence profiles, secondary structures and solvent accessibilities are typically restricted to be within 20 residues of the domain boundary candidate.ResultsTo address the performance of ML-based methods, we developed a new protein domain boundary prediction method (ConDo) that utilizes novel long-range features such as coevolutionary information in addition to the aforementioned local window features as inputs for ML. Toward this purpose, two types of coevolutionary information were extracted from multiple sequence alignment using direct coupling analysis: (i) partially aligned sequences, and (ii) correlated mutation information. Both the partially aligned sequence information and the modularity of residue–residue couplings possess long-range correlation information.Availability and implementationhttps://github.com/gicsaw/ConDo.gitSupplementary informationSupplementary data are available at Bioinformatics online.

Download Full-text

Large-scale structure prediction by improved contact predictions and model quality assessment

10.1101/128231 ◽

2017 ◽

Cited By ~ 2

Author(s):

Mirco Michel ◽

David Menéndez Hurtado ◽

Karolis Uziela ◽

Arne Elofsson

Keyword(s):

Structure Prediction ◽

Large Scale ◽

Supplementary Information ◽

Model Quality ◽

Contact Maps ◽

Folding Algorithm ◽

Unknown Structure ◽

Supplementary Material ◽

Direct Coupling Analysis ◽

Contact Predictions

AbstractMotivationAccurate contact predictions can be used for predicting the structure of proteins. Until recently these methods were limited to very big protein families, decreasing their utility. However, recent progress by combining direct coupling analysis with machine learning methods has made it possible to predict accurate contact maps for smaller families. To what extent these predictions can be used to produce accurate models of the families is not known.ResultsWe present the PconsFold2 pipeline that uses contact predictions from PconsC3, the CONFOLD folding algorithm and model quality estimations to predict the structure of a protein. We show that the model quality estimation significantly increases the number of models that reliably can be identified. Finally, we apply PconsFold2 to 6379 Pfam families of unknown structure and find that PconsFold2 can, with an estimated 90% specificity, predict the structure of up to 558 Pfam families of unknown structure. Out of these 415 have not been reported before.AvailabilityDatasets as well as models of all the 558 Pfam families are available at http://c3.pcons.net/. All programs used here are freely [email protected] informationNo supplementary data

Download Full-text

genuMet: distinguish genuine untargeted metabolic features without quality control samples

10.1101/837260 ◽

2019 ◽

Cited By ~ 1

Author(s):

L Cao ◽

C Clish ◽

FB Hu ◽

MA Martínez-González ◽

C Razquin ◽

...

Keyword(s):

Quality Control ◽

Large Scale ◽

Control Method ◽

R Package ◽

True Positive Rate ◽

Supplementary Information ◽

True Negative ◽

True Negative Rate ◽

Positive Rate ◽

Measurement Artifacts

AbstractMotivationLarge-scale untargeted metabolomics experiments lead to detection of thousands of novel metabolic features as well as false positive artifacts. With the incorporation of pooled QC samples and corresponding bioinformatics algorithms, those measurement artifacts can be well quality controlled. However, it is impracticable for all the studies to apply such experimental design.ResultsWe introduce a post-alignment quality control method called genuMet, which is solely based on injection order of biological samples to identify potential false metabolic features. In terms of the missing pattern of metabolic signals, genuMet can reach over 95% true negative rate and 85% true positive rate with suitable parameters, compared with the algorithm utilizing pooled QC samples. genu-Met makes it possible for studies without pooled QC samples to reduce false metabolic signals and perform robust statistical analysis.Availability and implementationgenuMet is implemented in a R package and available on https://github.com/liucaomics/genuMet under GPL-v2 license.ContactLiming Liang: [email protected] informationSupplementary data are available at ….

Download Full-text

Large-Scale Evolutionary Patterns of Protein Domain Distributions in Eukaryotes

10.1101/142182 ◽

2017 ◽

Cited By ~ 1

Author(s):

Arli A. Parikesit ◽

Peter F. Stadler ◽

Sonja J. Prohaska

Keyword(s):

Large Scale ◽

Gene Prediction ◽

Protein Domains ◽

Protein Domain ◽

Medical Sciences ◽

Evolutionary Patterns ◽

Important Indicator ◽

Domain Annotation ◽

Species Specific ◽

High Level

AbstractThe genomic inventory of protein domains is an important indicator of an organism’s regulatory and metabolic capabilities. Existing gene annotations, however, can be plagued by substantial ascertainment biases that make it difficult to obtain and compare quantitative domain data. We find that quantitative trends across the Eukarya can be investigated based on a combination of gene prediction and standard domain annotation pipelines. Species-specific training is required, however, to account for the genomic peculiarities in many lineages. In contrast to earlier studies we find wide-spread statistically significant avoidance of protein domains associated with distinct functional high-level gene-ontology terms.1998 ACM Subject Classification J.3 Life and Medical Sciences

Download Full-text

Large-scale sequence similarity analysis reveals the scope of sequence and function divergence in PilZ domain proteins

10.1101/2020.02.11.943704 ◽

2020 ◽

Author(s):

Qing Wei Cheang ◽

Shuo Sheng ◽

Linghui Xu ◽

Zhao-Xun Liang

Keyword(s):

Large Scale ◽

Sequence Similarity ◽

Protein Domain ◽

Divergent Evolution ◽

Cellular Functions ◽

Vast Number ◽

Future Studies ◽

Function Relationship ◽

And Function ◽

Scale Sequence

AbstractPilZ domain-containing proteins constitute a superfamily of widely distributed bacterial signalling proteins. Although studies have established the canonical PilZ domain as an adaptor protein domain evolved to specifically bind the second messenger c-di-GMP, mounting evidence suggest that the PilZ domain has undergone enormous divergent evolution to generate a superfamily of proteins that are characterized by a wide range of c-di-GMP-binding affinity, binding partners and cellular functions. The divergent evolution has even generated families of non-canonical PilZ domains that completely lack c-di-GMP binding ability. In this study, we performed a large-scale sequence analysis on more than 28,000 single- and di-domain PilZ proteins using the sequence similarity networking tool created originally to analyse functionally diverse enzyme superfamilies. The sequence similarity networks (SSN) generated by the analysis feature a large number of putative isofunctional protein clusters, and thus, provide an unprecedented panoramic view of the sequence-function relationship and function diversification in PilZ proteins. Some of the protein clusters in the networks are considered as unexplored clusters that contain proteins with completely unknown biological function; whereas others contain one, two or a few functionally known proteins, and therefore, enabling us to infer the cellular function of uncharacterized homologs or orthologs. With the ultimate goal of elucidating the diverse roles played by PilZ proteins in bacterial signal transduction, the work described here will facilitate the annotation of the vast number of PilZ proteins encoded by bacterial genome and help to prioritize functionally unknown PilZ proteins for future studies.ImportanceAlthough PilZ domain is best known as the protein domain evolved specifically for the binding of the second messenger c-di-GMP, divergent evolution has generated a superfamily of PilZ proteins with a diversity of ligand or protein-binding properties and cellular functions. We analysed the sequences of more than 28,000 PilZ proteins using the sequence similarity networking (SSN) tool to yield a global view of the sequence-function relationship and function diversification in PilZ proteins. The results will facilitate the annotation of the vast number of PilZ proteins encoded by bacterial genomes and help us prioritize PilZ proteins for future studies.

Download Full-text

HiCSR: a Hi-C super-resolution framework for producing highly realistic contact maps

10.1101/2020.02.24.961714 ◽

2020 ◽

Author(s):

Michael C. Dimmick ◽

Leo J. Lee ◽

Brendan J. Frey

Keyword(s):

High Resolution ◽

Super Resolution ◽

Cell Types ◽

Supplementary Information ◽

Low Resolution ◽

Generative Adversarial Network ◽

High Resolution Data ◽

Contact Maps ◽

Adversarial Network ◽

And Function

AbstractMotivationHi-C data has enabled the genome-wide study of chromatin folding and architecture, and has led to important discoveries in the structure and function of chromatin conformation. Here, high resolution data plays a particularly important role as many chromatin substructures such as Topologically Associating Domains (TADs) and chromatin loops cannot be adequately studied with low resolution contact maps. However, the high sequencing costs associated with the generation of high resolution Hi-C data has become an experimental barrier. Data driven machine learning models, which allow low resolution Hi-C data to be computationally enhanced, offer a promising avenue to address this challenge.ResultsBy carefully examining the properties of Hi-C maps and integrating various recent advances in deep learning, we developed a Hi-C Super-Resolution (HiCSR) framework capable of accurately recovering the fine details, textures, and substructures found in high resolution contact maps. This was achieved using a novel loss function tailored to the Hi-C enhancement problem which optimizes for an adversarial loss from a Generative Adversarial Network (GAN), a feature reconstruction loss derived from the latent representation of a denoising autoencoder, and a pixel-wise loss. Not only can the resulting framework generate enhanced Hi-C maps more visually similar to the original high resolution maps, it also excels on a suite of reproducibility metrics produced by members of the ENCODE Consortium compared to existing approaches, including HiCPlus, HiCNN, hicGAN and DeepHiC. Finally, we demonstrate that HiCSR is capable of enhancing Hi-C data across sequencing depth, cell types, and species, recovering biologically significant contact domain boundaries.AvailabilityWe make our implementation available for download at: https://github.com/PSI-Lab/[email protected] informationAvailable Online

Download Full-text

The evolution of protein domain families

Biochemical Society Transactions ◽

10.1042/bst0370751 ◽

2009 ◽

Vol 37 (4) ◽

pp. 751-755 ◽

Cited By ~ 68

Author(s):

Marija Buljan ◽

Alex Bateman

Keyword(s):

Domain Architecture ◽

Protein Domains ◽

Protein Domain ◽

Cell Surface Receptor ◽

Immunoglobulin Superfamily ◽

Insertion And Deletion ◽

Variable Domains ◽

Surface Receptor ◽

Duplication Events ◽

And Function

Protein domains are the common currency of protein structure and function. Over 10000 such protein families have now been collected in the Pfam database. Using these data along with animal gene phylogenies from TreeFam allowed us to investigate the gain and loss of protein domains. Most gains and losses of domains occur at protein termini. We show that the nature of changes is similar after speciation or duplication events. However, changes in domain architecture happen at a higher frequency after gene duplication. We suggest that the bias towards protein termini is largely because insertion and deletion of domains at most positions in a protein are likely to disrupt the structure of existing domains. We can also use Pfam to trace the evolution of specific families. For example, the immunoglobulin superfamily can be traced over 500 million years during its expansion into one of the largest families in the human genome. It can be shown that this protein family has its origins in basic animals such as the poriferan sponges where it is found in cell-surface-receptor proteins. We can trace how the structure and sequence of this family diverged during vertebrate evolution into constant and variable domains that are found in the antibodies of our immune system as well as in neural and muscle proteins.

Download Full-text

Cancer mutational signatures representation by large-scale context embedding

Bioinformatics ◽

10.1093/bioinformatics/btaa433 ◽

2020 ◽

Vol 36 (Supplement_1) ◽

pp. i309-i316 ◽

Cited By ~ 1

Author(s):

Yang Zhang ◽

Yunxuan Xiao ◽

Muyu Yang ◽

Jian Ma

Keyword(s):

Breast Cancer ◽

Large Scale ◽

Somatic Mutations ◽

Genome Structure ◽

Superior Performance ◽

Supplementary Information ◽

Patient Specific ◽

Cancer Subtypes ◽

Cancer Heterogeneity ◽

And Function

Abstract Motivation The accumulation of somatic mutations plays critical roles in cancer development and progression. However, the global patterns of somatic mutations, especially non-coding mutations, and their roles in defining molecular subtypes of cancer have not been well characterized due to the computational challenges in analysing the complex mutational patterns. Results Here, we develop a new algorithm, called MutSpace, to effectively extract patient-specific mutational features using an embedding framework for larger sequence context. Our method is motivated by the observation that the mutation rate at megabase scale and the local mutational patterns jointly contribute to distinguishing cancer subtypes, both of which can be simultaneously captured by MutSpace. Simulation evaluations show that MutSpace can effectively characterize mutational features from known patient subgroups and achieve superior performance compared with previous methods. As a proof-of-principle, we apply MutSpace to 560 breast cancer patient samples and demonstrate that our method achieves high accuracy in subtype identification. In addition, the learned embeddings from MutSpace reflect intrinsic patterns of breast cancer subtypes and other features of genome structure and function. MutSpace is a promising new framework to better understand cancer heterogeneity based on somatic mutations. Availability and implementation Source code of MutSpace can be accessed at: https://github.com/ma-compbio/MutSpace. Supplementary information Supplementary data are available at Bioinformatics online.

Download Full-text

Ribosome occupancy profiles are conserved between structurally and evolutionarily related yeast domains

Bioinformatics ◽

10.1093/bioinformatics/btab020 ◽

2021 ◽

Author(s):

Daniel A Nissley ◽

Anna Carbery ◽

Mark Chonofsky ◽

Charlotte M Deane

Keyword(s):

Amino Acid ◽

Large Scale ◽

Sequence Similarity ◽

Ribosome Profiling ◽

Supplementary Information ◽

Rare Codon ◽

Homologous Proteins ◽

Translation Speed ◽

And Function ◽

Related Proteins

Abstract Motivation Protein synthesis is a non-equilibrium process, meaning that the speed of translation can influence the ability of proteins to fold and function. Assuming that structurally similar proteins fold by similar pathways, the profile of translation speed along an mRNA should be evolutionarily conserved between related proteins to direct correct folding and downstream function. The only evidence to date for such conservation of translation speed between homologous proteins has used codon rarity as a proxy for translation speed. There are, however, many other factors including mRNA structure and the chemistry of the amino acids in the A- and P-sites of the ribosome that influence the speed of amino acid addition. Results Ribosome profiling experiments provide a signal directly proportional to the underlying translation times at the level of individual codons. We compared ribosome occupancy profiles (extracted from five different large-scale yeast ribosome profiling studies) between related protein domains to more directly test if their translation schedule was conserved. Our analysis reveals that the ribosome occupancy profiles of paralogous domains tend to be significantly more similar to one another than to profiles of non-paralogous domains. This trend does not depend on domain length, structural classes, amino acid composition or sequence similarity. Our results indicate that entire ribosome occupancy profiles and not just rare codon locations are conserved between even distantly related domains in yeast, providing support for the hypothesis that translation schedule is conserved between structurally related domains to retain folding pathways and facilitate efficient folding. Availability and implementation Python3 code is available on GitHub at https://github.com/DanNissley/Compare-ribosome-occupancy. Supplementary information Supplementary data are available at Bioinformatics online.

Download Full-text