Browse
Submit Data
Databases
API
Help

Dataset Information

23 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Structure-based deep learning for binding site detection in nucleic acid macromolecules.

ABSTRACT: Structure-based drug design (SBDD) targeting nucleic acid macromolecules, particularly RNA, is a gaining momentum research direction that already resulted in several FDA-approved compounds. Similar to proteins, one of the critical components in SBDD for RNA is the correct identification of the binding sites for putative drug candidates. RNAs share a common structural organization that, together with the dynamic nature of these molecules, makes it challenging to recognize binding sites for small molecules. Moreover, there is a need for structure-based approaches, as sequence information only does not consider conformation plasticity of nucleic acid macromolecules. Deep learning holds a great promise to resolve binding site detection problem, but requires a large amount of structural data, which is very limited for nucleic acids, compared to proteins. In this study we composed a set of ∼2000 nucleic acid-small molecule structures comprising ∼2500 binding sites, which is ∼40-times larger than previously used one, and demonstrated the first structure-based deep learning approach, BiteNet _N , to detect binding sites in nucleic acid structures. BiteNet _N operates with arbitrary nucleic acid complexes, shows the state-of-the-art performance, and can be helpful in the analysis of different conformations and mutant variants, as we demonstrated for HIV-1 TAR RNA and ATP-aptamer case studies.

SUBMITTER: Kozlovskii I

PROVIDER: S-EPMC8633674 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

Improved deep learning-based macromolecules structure classification from electron cryo-tomograms.

Project description:Cellular processes are governed by macromolecular complexes inside the cell. Study of the native structures of macromolecular complexes has been extremely difficult due to lack of data. With recent breakthroughs in Cellular Electron Cryo-Tomography (CECT) 3D imaging technology, it is now possible for researchers to gain accesses to fully study and understand the macro-molecular structures single cells. However, systematic recovery of macromolecular structures from CECT is very difficult due to high degree of structural complexity and practical imaging limitations. Specifically, we proposed a deep learning-based image classification approach for large-scale systematic macromolecular structure separation from CECT data. However, our previous work was only a very initial step toward exploration of the full potential of deep learning-based macromolecule separation. In this paper, we focus on improving classification performance by proposing three newly designed individual CNN models: an extended version of (Deep Small Receptive Field) DSRF3D, donated as DSRF3D-v2, a 3D residual block-based neural network, named as RB3D, and a convolutional 3D (C3D)-based model, CB3D. We compare them with our previously developed model (DSRF3D) on 12 datasets with different SNRs and tilt angle ranges. The experiments show that our new models achieved significantly higher classification accuracies. The accuracies are not only higher than 0.9 on normal datasets, but also demonstrate potentials to operate on datasets with high levels of noises and missing wedge effects presented.

| S-EPMC6738941 | biostudies-literature

Deep learning-based subdivision approach for large scale macromolecules structure recovery from electron cryo tomograms.

Project description:Cellular Electron CryoTomography (CECT) enables 3D visualization of cellular organization at near-native state and in sub-molecular resolution, making it a powerful tool for analyzing structures of macromolecular complexes and their spatial organizations inside single cells. However, high degree of structural complexity together with practical imaging limitations makes the systematic de novo discovery of structures within cells challenging. It would likely require averaging and classifying millions of subtomograms potentially containing hundreds of highly heterogeneous structural classes. Although it is no longer difficult to acquire CECT data containing such amount of subtomograms due to advances in data acquisition automation, existing computational approaches have very limited scalability or discrimination ability, making them incapable of processing such amount of data.To complement existing approaches, in this article we propose a new approach for subdividing subtomograms into smaller but relatively homogeneous subsets. The structures in these subsets can then be separately recovered using existing computation intensive methods. Our approach is based on supervised structural feature extraction using deep learning, in combination with unsupervised clustering and reference-free classification. Our experiments show that, compared with existing unsupervised rotation invariant feature and pose-normalization based approaches, our new approach achieves significant improvements in both discrimination ability and scalability. More importantly, our new approach is able to discover new structural classes and recover structures that do not exist in training data.Source code freely available at http://www.cs.cmu.edu/?mxu1/software .mxu1@cs.cmu.edu.Supplementary data are available at Bioinformatics online.

| S-EPMC5946875 | biostudies-literature

Binding site discovery from nucleic acid sequences by discriminative learning of hidden Markov models.

Project description:We present a discriminative learning method for pattern discovery of binding sites in nucleic acid sequences based on hidden Markov models. Sets of positive and negative example sequences are mined for sequence motifs whose occurrence frequency varies between the sets. The method offers several objective functions, but we concentrate on mutual information of condition and motif occurrence. We perform a systematic comparison of our method and numerous published motif-finding tools. Our method achieves the highest motif discovery performance, while being faster than most published methods. We present case studies of data from various technologies, including ChIP-Seq, RIP-Chip and PAR-CLIP, of embryonic stem cell transcription factors and of RNA-binding proteins, demonstrating practicality and utility of the method. For the alternative splicing factor RBM10, our analysis finds motifs known to be splicing-relevant. The motif discovery method is implemented in the free software package Discrover. It is applicable to genome- and transcriptome-scale data, makes use of available repeat experiments and aside from binary contrasts also more complex data configurations can be utilized.

| S-EPMC4245949 | biostudies-literature

EquiPNAS: improved protein-nucleic acid binding site prediction using protein-language-model-informed equivariant deep graph neural networks.

Project description:Protein language models (pLMs) trained on a large corpus of protein sequences have shown unprecedented scalability and broad generalizability in a wide range of predictive modeling tasks, but their power has not yet been harnessed for predicting protein-nucleic acid binding sites, critical for characterizing the interactions between proteins and nucleic acids. Here we present EquiPNAS, a new pLM-informed E(3) equivariant deep graph neural network framework for improved protein-nucleic acid binding site prediction. By combining the strengths of pLM and symmetry-aware deep graph learning, EquiPNAS consistently outperforms the state-of-the-art methods for both protein-DNA and protein-RNA binding site prediction on multiple datasets across a diverse set of predictive modeling scenarios ranging from using experimental input to AlphaFold2 predictions. Our ablation study reveals that the pLM embeddings used in EquiPNAS are sufficiently powerful to dramatically reduce the dependence on the availability of evolutionary information without compromising on accuracy, and that the symmetry-aware nature of the E(3) equivariant graph-based neural architecture offers remarkable robustness and performance resilience. EquiPNAS is freely available at https://github.com/Bhattacharya-Lab/EquiPNAS.

| S-EPMC10515942 | biostudies-literature

DeepDISE: DNA Binding Site Prediction Using a Deep Learning Method.

Project description:It is essential for future research to develop a new, reliable prediction method of DNA binding sites because DNA binding sites on DNA-binding proteins provide critical clues about protein function and drug discovery. However, the current prediction methods of DNA binding sites have relatively poor accuracy. Using 3D coordinates and the atom-type of surface protein atom as the input, we trained and tested a deep learning model to predict how likely a voxel on the protein surface is to be a DNA-binding site. Based on three different evaluation datasets, the results show that our model not only outperforms several previous methods on two commonly used datasets, but also demonstrates its robust performance to be consistent among the three datasets. The visualized prediction outcomes show that the binding sites are also mostly located in correct regions. We successfully built a deep learning model to predict the DNA binding sites on target proteins. It demonstrates that 3D protein structures plus atom-type information on protein surfaces can be used to predict the potential binding sites on a protein. This approach should be further extended to develop the binding sites of other important biological molecules.

| S-EPMC8197219 | biostudies-literature

Cold-Shock Domains-Abundance, Structure, Properties, and Nucleic-Acid Binding.

Project description:The cold-shock domain has a deceptively simple architecture but supports a complex biology. It is conserved from bacteria to man and has representatives in all kingdoms of life. Bacterial cold-shock proteins consist of a single cold-shock domain and some, but not all are induced by cold shock. Cold-shock domains in human proteins are often associated with natively unfolded protein segments and more rarely with other folded domains. Cold-shock proteins and domains share a five-stranded all-antiparallel ?-barrel structure and a conserved surface that binds single-stranded nucleic acids, predominantly by stacking interactions between nucleobases and aromatic protein sidechains. This conserved binding mode explains the cold-shock domains' ability to associate with both DNA and RNA strands and their limited sequence selectivity. The promiscuous DNA and RNA binding provides a rationale for the ability of cold-shock domain-containing proteins to function in transcription regulation and DNA-damage repair as well as in regulating splicing, translation, mRNA stability and RNA sequestration.

| S-EPMC7825780 | biostudies-literature

Structure and nucleic acid binding activity of the nucleoporin Nup157.

Project description:At the center of the nuclear pore complex (NPC) is a uniquely versatile central transport channel. Structural analyses of distinct segments ("protomers") of the three "channel" nucleoporins yielded a model for how this channel is constructed. Its principal feature is a midplane ring that can undergo regulated diameter changes of as much as an estimated 30 nm. To better understand how a family of "adaptor" nucleoporins--concentrically surrounding this channel--might cushion these huge structural changes, we determined the crystal structure of one adaptor nucleoporin, Nup157. Here, we show that a recombinant Saccharomyces cerevisiae Nup157 protomer, representing two-thirds of Nup157 (residues 70-893), folds into a seven-bladed β-propeller followed by an α-helical domain, which together form a C-shaped architecture. Notably, the structure contains a large patch of positively charged residues, most of which are evolutionarily conserved. Consistent with this surface feature, we found that Nup157(70-893) binds to nucleic acids, although in a sequence-independent manner. Nevertheless, this interaction supports a previously reported role of Nup157, and its paralogue Nup170, in chromatin organization. Based on its nucleic acid binding capacity, we propose a dual location and function of Nup157. Finally, modeling the remaining C-terminal portion of Nup157 shows that it projects as a superhelical stack from the compact C-shaped portion of the molecule. The predicted four hinge regions indicate an intrinsic flexibility of Nup157, which could contribute to structural plasticity within the NPC.

| S-EPMC3799309 | biostudies-literature

PNA-Pdx: Versatile Peptide Nucleic Acid-Based Detection of Nucleic Acids and SNPs.

Project description:Monitoring diseases caused by pathogens or by mutations in DNA sequences requires accurate, rapid, and sensitive tools to detect specific nucleic acid sequences. Here, we describe a new peptide nucleic acid (PNA)-based nucleic acid detection toolkit, termed PNA-powered diagnostics (PNA-Pdx). PNA-Pdx employs PNA probes that bind specifically to a target and are then detected in lateral flow assays. This can precisely detect a specific pathogen or genotype genomic sequence. PNA probes can also be designed to invade double-stranded DNAs (dsDNAs) to produce single-stranded DNAs for precise CRISPR-Cas12b-based detection of genomic SNPs without requiring the protospacer-adjacent motif (PAM), as Cas12b requires PAM sequences only for dsDNA targets. PNA-Pdx identified target nucleic acid sequences at concentrations as low as 2 copies/μL and precisely detected the SARS-CoV-2 genome in clinical samples in 40 min. Furthermore, the specific dsDNA invasion by the PNA coupled with CRISPR-Cas12b precisely detected genomic SNPs without PAM restriction. Overall, PNA-Pdx provides a novel toolkit for nucleic acid and SNP detection as well as highlights the benefits of engineering PNA probes for detecting nucleic acids.

| S-EPMC10535012 | biostudies-literature

Structural transformation induced by locked nucleic acid or 2'-O-methyl nucleic acid site-specific modifications on thrombin binding aptamer.

Project description:BackgroundLocked nucleic acid (LNA) and 2'-O-methyl nucleic acid (OMeNA) are two of the most extensively studied nucleotide derivatives in the last decades. However, how they affect DNA quadruplex structures remains largely unknown. To explore their possible biological affinities for quadruplexes, we investigated how LNA- or OMeNA-substitutions affect G-quadruplex structure formation using a thrombin binding aptamer (TBA), the most studied extracorporal G-quadruplex-forming DNA sequence, which is frequently modified to increase its analytical performance.ResultsThe experimental results showed that when two or more nucleotides were substituted with LNA or OMeNA, the anti-parallel TBA structure was transformed into an unstructured random conformation in a 50 mM K+ environment; OMeNA appeared to have greater power to induce this transformation. However, the native TBA was unstructured in a 50 mM Ca2+ environment, whereas four or more LNA- or OMeNA- substitutions could convert this unstructured TBA into a parallel quadruplex structure. PAGE mobility measurements suggested that these TBAs might be a dimeric form.ConclusionLNA or 2'-OMeNA site-specific modifications induced G-quadruplex structural transformation of TBA, which enriched our understanding of the intrinsic G-quadrupex forming property and affinity of LNA and OMeNA modifications. This study demonstrates possible applications in the regulation of gene expression (i.e. manual intervention of gene therapy), genetic analyses, molecular diagnosis and the construction of nano-scale biostructures.

| S-EPMC4000052 | biostudies-literature

Deep Learning for Image-Based Cassava Disease Detection.

Project description:Cassava is the third largest source of carbohydrates for human food in the world but is vulnerable to virus diseases, which threaten to destabilize food security in sub-Saharan Africa. Novel methods of cassava disease detection are needed to support improved control which will prevent this crisis. Image recognition offers both a cost effective and scalable technology for disease detection. New deep learning models offer an avenue for this technology to be easily deployed on mobile devices. Using a dataset of cassava disease images taken in the field in Tanzania, we applied transfer learning to train a deep convolutional neural network to identify three diseases and two types of pest damage (or lack thereof). The best trained model accuracies were 98% for brown leaf spot (BLS), 96% for red mite damage (RMD), 95% for green mite damage (GMD), 98% for cassava brown streak disease (CBSD), and 96% for cassava mosaic disease (CMD). The best model achieved an overall accuracy of 93% for data not used in the training process. Our results show that the transfer learning approach for image recognition of field images offers a fast, affordable, and easily deployable strategy for digital plant disease detection.

| S-EPMC5663696 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data