Browse
Submit Data
Databases
API
Help

Dataset Information

24 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Effective prediction of short hydrogen bonds in proteins via machine learning method.

ABSTRACT: Short hydrogen bonds (SHBs), whose donor and acceptor heteroatoms lie within 2.7 Å, exhibit prominent quantum mechanical characters and are connected to a wide range of essential biomolecular processes. However, exact determination of the geometry and functional roles of SHBs requires a protein to be at atomic resolution. In this work, we analyze 1260 high-resolution peptide and protein structures from the Protein Data Bank and develop a boosting based machine learning model to predict the formation of SHBs between amino acids. This model, which we name as machine learning assisted prediction of short hydrogen bonds (MAPSHB), takes into account 21 structural, chemical and sequence features and their interaction effects and effectively categorizes each hydrogen bond in a protein to a short or normal hydrogen bond. The MAPSHB model reveals that the type of the donor amino acid plays a major role in determining the class of a hydrogen bond and that the side chain Tyr-Asp pair demonstrates a significant probability of forming a SHB. Combining electronic structure calculations and energy decomposition analysis, we elucidate how the interplay of competing intermolecular interactions stabilizes the Tyr-Asp SHBs more than other commonly observed combinations of amino acid side chains. The MAPSHB model, which is freely available on our web server, allows one to accurately and efficiently predict the presence of SHBs given a protein structure with moderate or low resolution and will facilitate the experimental and computational refinement of protein structures.

SUBMITTER: Zhou S

PROVIDER: S-EPMC8748993 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

Prediction of Breast Cancer Estrogen Receptor Status using Machine Learning

Project description:Gene expression profiles were generated from 199 primary breast cancer patients. Samples 1-176 were used in another study, GEO Series GSE22820, and form the training data set in this study. Sample numbers 200-222 form a validation set. This data is used to model a machine learning classifier for Estrogen Receptor Status. RNA was isolated from 199 primary breast cancer patients. A machine learning classifier was built to predict ER status using only three gene features.

2013-01-01 | E-GEOD-29210 | biostudies-arrayexpress

Short strong hydrogen bonds in proteins: a case study of rhamnogalacturonan acetylesterase.

Project description:An extremely low-field signal (at approximately 18 p.p.m.) in the (1)H NMR spectrum of rhamnogalacturonan acetylesterase (RGAE) shows the presence of a short strong hydrogen bond in the structure. This signal was also present in the mutant RGAE D192N, in which Asp192, which is part of the catalytic triad, has been replaced with Asn. A careful analysis of wild-type RGAE and RGAE D192N was conducted with the purpose of identifying possible candidates for the short hydrogen bond with the 18 p.p.m. deshielded proton. Theoretical calculations of chemical shift values were used in the interpretation of the experimental (1)H NMR spectra. The crystal structure of RGAE D192N was determined to 1.33 A resolution and refined to an R value of 11.6% for all data. The structure is virtually identical to the high-resolution (1.12 A) structure of the wild-type enzyme except for the interactions involving the mutation and a disordered loop. Searches of the Cambridge Structural Database were conducted to obtain information on the donor-acceptor distances of different types of hydrogen bonds. The short hydrogen-bond interactions found in RGAE have equivalents in small-molecule structures. An examination of the short hydrogen bonds in RGAE, the calculated pK(a) values and solvent-accessibilities identified a buried carboxylic acid carboxylate hydrogen bond between Asp75 and Asp87 as the likely origin of the 18 p.p.m. signal. Similar hydrogen-bond interactions between two Asp or Glu carboxy groups were found in 16% of a homology-reduced set of high-quality structures extracted from the PDB. The shortest hydrogen bonds in RGAE are all located close to the active site and short interactions between Ser and Thr side-chain OH groups and backbone carbonyl O atoms seem to play an important role in the stability of the protein structure. These results illustrate the significance of short strong hydrogen bonds in proteins.

| S-EPMC2483496 | biostudies-literature

Predicting hydrogen storage in MOFs via machine learning.

Project description:The H2 capacities of a diverse set of 918,734 metal-organic frameworks (MOFs) sourced from 19 databases is predicted via machine learning (ML). Using only 7 structural features as input, ML identifies 8,282 MOFs with the potential to exceed the capacities of state-of-the-art materials. The identified MOFs are predominantly hypothetical compounds having low densities (<0.31 g cm-3) in combination with high surface areas (>5,300 m2 g-1), void fractions (∼0.90), and pore volumes (>3.3 cm3 g-1). The relative importance of the input features are characterized, and dependencies on the ML algorithm and training set size are quantified. The most important features for predicting H2 uptake are pore volume (for gravimetric capacity) and void fraction (for volumetric capacity). The ML models are available on the web, allowing for rapid and accurate predictions of the hydrogen capacities of MOFs from limited structural data; the simplest models require only a single crystallographic feature.

| S-EPMC8276024 | biostudies-literature

A Machine Learning Method for Drug Combination Prediction.

Project description:Drug combination is now a hot research topic in the pharmaceutical industry, but experiment-based methodologies are extremely costly in time and money. Many computational methods have been proposed to address these problems by starting from existing drug combinations. However, in most cases, only molecular structure information is included, which covers too limited a set of drug characteristics to efficiently screen drug combinations. Here, we integrated similarity-based multifeature drug data to improve the prediction accuracy by using the neighbor recommender method combined with ensemble learning algorithms. By conducting feature assessment analysis, we selected the most useful drug features and achieved 0.964 AUC in the ensemble models. The comparison results showed that the ensemble models outperform traditional machine learning algorithms such as support vector machine (SVM), naïve Bayes (NB), and logistic regression (GLM). Furthermore, we predicted 7 candidate drug combinations for a specific drug, paclitaxel, and successfully verified that the two of the predicted combinations have promising effects.

| S-EPMC7477631 | biostudies-literature

Prediction and real-time compensation of qubit decoherence via machine learning.

Project description:The wide-ranging adoption of quantum technologies requires practical, high-performance advances in our ability to maintain quantum coherence while facing the challenge of state collapse under measurement. Here we use techniques from control theory and machine learning to predict the future evolution of a qubit's state; we deploy this information to suppress stochastic, semiclassical decoherence, even when access to measurements is limited. First, we implement a time-division multiplexed approach, interleaving measurement periods with periods of unsupervised but stabilised operation during which qubits are available, for example, in quantum information experiments. Second, we employ predictive feedback during sequential but time delayed measurements to reduce the Dick effect as encountered in passive frequency standards. Both experiments demonstrate significant improvements in qubit-phase stability over 'traditional' measurement-based feedback approaches by exploiting time domain correlations in the noise processes. This technique requires no additional hardware and is applicable to all two-level quantum systems where projective measurements are possible.

| S-EPMC5241809 | biostudies-other

Perturbation of Short Hydrogen Bonds in Photoactive Yellow Protein via Noncanonical Amino Acid Incorporation.

Project description:Photoactive yellow protein (PYP) is a small photoreceptor protein that has two unusually short hydrogen bonds between the deprotonated p-coumaric acid chromophore and two amino acids, a tyrosine and a glutamic acid. This has led to considerable debate as to whether the glutamic acid-chromophore hydrogen bond is a low barrier hydrogen bond, with conflicting results in the literature. We have modified the p Ka of the tyrosine by amber suppression and of the chromophore by chemical substitution. X-ray crystal structures of these modified proteins are nearly identical to the wild-type protein, so the heavy atom distance between proton donor and acceptor is maintained, even though these modifications change the relative proton affinity between donor and acceptor. Despite a considerable change in relative proton affinity, the NMR chemical shifts of the hydrogen-bonded protons are only moderately affected. QM/MM calculations were used to explore the protons' potential energy surface and connect the calculated proton position with empirically measured proton chemical shifts. The results are inconsistent with a low barrier hydrogen bond but in all cases are consistent with a localized proton, suggesting an ionic hydrogen bond rather than a low barrier hydrogen bond.

| S-EPMC7061054 | biostudies-literature

Prediction of DNA i-motifs via machine learning.

Project description:i-Motifs (iMs), are secondary structures formed in cytosine-rich DNA sequences and are involved in multiple functions in the genome. Although putative iM forming sequences are widely distributed in the human genome, the folding status and strength of putative iMs vary dramatically. Much previous research on iM has focused on assessing the iM folding properties using biophysical experiments. However, there are no dedicated computational tools for predicting the folding status and strength of iM structures. Here, we introduce a machine learning pipeline, iM-Seeker, to predict both folding status and structural stability of DNA iMs. The programme iM-Seeker incorporates a Balanced Random Forest classifier trained on genome-wide iMab antibody-based CUT&Tag sequencing data to predict the folding status and an Extreme Gradient Boosting regressor to estimate the folding strength according to both literature biophysical data and our in-house biophysical experiments. iM-Seeker predicts DNA iM folding status with a classification accuracy of 81% and estimates the folding strength with coefficient of determination (R2) of 0.642 on the test set. Model interpretation confirms that the nucleotide composition of the C-rich sequence significantly affects iM stability, with a positive correlation with sequences containing cytosine and thymine and a negative correlation with guanine and adenine.

| S-EPMC10954440 | biostudies-literature

A quantum crystallographic approach to short hydrogen bonds.

Project description:In this work we use high-resolution synchrotron X-ray diffraction for electron density mapping, in conjunction with ab initio modelling, to study short O-H⋯O and O+-H⋯O- hydrogen bonds whose behaviour is known to be tuneable by temperature. The short hydrogen bonds have donor-acceptor distances in the region of 2.45 Å and are formed in substituted urea and organic acid molecular complexes of N,N'-dimethylurea oxalic acid 2 : 1 (1), N,N-dimethylurea 2,4-dinitrobenzoate 1 : 1 (2) and N,N-dimethylurea 3,5-dinitrobenzoic acid 2 : 2 (3). From the combined analyses, these complexes are found to fall within the salt-cocrystal continuum and exhibit short hydrogen bonds that can be characterised as both strong and electrostatic (1, 3) or very strong with a significant covalent contribution (2). An additional charge assisted component is found to be important in distinguishing the relatively uncommon O-H⋯O pseudo-covalent interaction from a typical strong hydrogen bond. The electron density is found to be sensitive to the extent of static proton transfer, presenting it as a useful parameter in the study of the salt-cocrystal continuum. From complementary calculated hydrogen atom potentials, we attribute changes in proton position to the molecular environment. Calculated potentials also show zero barrier to proton migration, forming an 'energy slide' between the donor and acceptor atoms. The better fundamental understanding of the short hydrogen bond in the 'zone of fluctuation' presented in a salt-cocrystal continuum, enabled by studies like this, provide greater insight into their related properties and can have implications in the regulation of pharmaceutical materials.

| S-EPMC8436739 | biostudies-literature

Short hydrogen bonds enhance nonaromatic protein-related fluorescence.

Project description:Fluorescence in biological systems is usually associated with the presence of aromatic groups. Here, by employing a combined experimental and computational approach, we show that specific hydrogen bond networks can significantly affect fluorescence. In particular, we reveal that the single amino acid L-glutamine, by undergoing a chemical transformation leading to the formation of a short hydrogen bond, displays optical properties that are significantly enhanced compared with L-glutamine itself. Ab initio molecular dynamics simulations highlight that these short hydrogen bonds prevent the appearance of a conical intersection between the excited and the ground states and thereby significantly decrease nonradiative transition probabilities. Our findings open the door to the design of new photoactive materials with biophotonic applications.

| S-EPMC8166056 | biostudies-literature

Prediction of Phage Virion Proteins Using Machine Learning Methods.

Project description:Antimicrobial resistance (AMR) is a major problem and an immediate alternative to antibiotics is the need of the hour. Research on the possible alternative products to tackle bacterial infections is ongoing worldwide. One of the most promising alternatives to antibiotics is the use of bacteriophages (phage) or phage-driven antibacterial drugs to cure bacterial infections caused by AMR bacteria. Phage-driven proteins, including holins, endolysins, and exopolysaccharides, have shown great potential in the development of antibacterial drugs. Likewise, phage virion proteins (PVPs) might also play an important role in the development of antibacterial drugs. Here, we have developed a machine learning-based prediction method to predict PVPs using phage protein sequences. We have employed well-known basic and ensemble machine learning methods with protein sequence composition features for the prediction of PVPs. We found that the gradient boosting classifier (GBC) method achieved the best accuracy of 80% on the training dataset and an accuracy of 83% on the independent dataset. The performance on the independent dataset is better than other existing methods. A user-friendly web server developed by us is freely available to all users for the prediction of PVPs from phage protein sequences. The web server might facilitate the large-scale prediction of PVPs and hypothesis-driven experimental study design.

| S-EPMC10004995 | 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