Browse
Submit Data
Databases
API
Help

Dataset Information

0 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

The transformative power of transformers in protein structure prediction.

ABSTRACT: Transformer neural networks have revolutionized structural biology with the ability to predict protein structures at unprecedented high accuracy. Here, we report the predictive modeling performance of the state-of-the-art protein structure prediction methods built on transformers for 69 protein targets from the recently concluded 15th Critical Assessment of Structure Prediction (CASP15) challenge. Our study shows the power of transformers in protein structure modeling and highlights future areas of improvement.

SUBMITTER: Moussad B

PROVIDER: S-EPMC10410766 | biostudies-literature | 2023 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Publications

The transformative power of transformers in protein structure prediction.

Moussad Bernard B Roche Rahmatullah R Bhattacharya Debswapna D

Proceedings of the National Academy of Sciences of the United States of America 20230731 32

Transformer neural networks have revolutionized structural biology with the ability to predict protein structures at unprecedented high accuracy. Here, we report the predictive modeling performance of the state-of-the-art protein structure prediction methods built on transformers for 69 protein targets from the recently concluded 15th Critical Assessment of Structure Prediction (CASP15) challenge. Our study shows the power of transformers in protein structure modeling and highlights future areas ...[more]

PMID: 37523536

Similar Datasets

ADOPT: intrinsic protein disorder prediction through deep bidirectional transformers.

Project description:Intrinsically disordered proteins (IDPs) are important for a broad range of biological functions and are involved in many diseases. An understanding of intrinsic disorder is key to develop compounds that target IDPs. Experimental characterization of IDPs is hindered by the very fact that they are highly dynamic. Computational methods that predict disorder from the amino acid sequence have been proposed. Here, we present ADOPT (Attention DisOrder PredicTor), a new predictor of protein disorder. ADOPT is composed of a self-supervised encoder and a supervised disorder predictor. The former is based on a deep bidirectional transformer, which extracts dense residue-level representations from Facebook's Evolutionary Scale Modeling library. The latter uses a database of nuclear magnetic resonance chemical shifts, constructed to ensure balanced amounts of disordered and ordered residues, as a training and a test dataset for protein disorder. ADOPT predicts whether a protein or a specific region is disordered with better performance than the best existing predictors and faster than most other proposed methods (a few seconds per sequence). We identify the features that are relevant for the prediction performance and show that good performance can already be gained with <100 features. ADOPT is available as a stand-alone package at https://github.com/PeptoneLtd/ADOPT and as a web server at https://adopt.peptone.io/.

| S-EPMC10150328 | biostudies-literature

ProteinNPT: Improving Protein Property Prediction and Design with Non-Parametric Transformers.

Project description:Protein design holds immense potential for optimizing naturally occurring proteins, with broad applications in drug discovery, material design, and sustainability. However, computational methods for protein engineering are confronted with significant challenges, such as an expansive design space, sparse functional regions, and a scarcity of available labels. These issues are further exacerbated in practice by the fact most real-life design scenarios necessitate the simultaneous optimization of multiple properties. In this work, we introduce ProteinNPT, a non-parametric transformer variant tailored to protein sequences and particularly suited to label-scarce and multi-task learning settings. We first focus on the supervised fitness prediction setting and develop several cross-validation schemes which support robust performance assessment. We subsequently reimplement prior top-performing baselines, introduce several extensions of these baselines by integrating diverse branches of the protein engineering literature, and demonstrate that ProteinNPT consistently outperforms all of them across a diverse set of protein property prediction tasks. Finally, we demonstrate the value of our approach for iterative protein design across extensive in silico Bayesian optimization and conditional sampling experiments.

| S-EPMC10723423 | biostudies-literature

An enhanced protection scheme for power transformers integrating alpha plane analysis.

Project description:Power transformers play a critical role in electric power systems by facilitating connections between subsystems with different voltage levels. Ensuring their reliable operation and protection against faults is essential for maintaining network stability. Percentage differential (PD) protection, commonly used in transformer protection relays, faces limitations such as dealing with current transformer (CT) saturation during external faults and difficulty in detecting certain fault types. This paper proposes an enhanced transformer protection scheme by integrating the alpha plane (AP) concept, traditionally used in transmission line protection, to improve transformer differential protection. This entails redefining AP restraint and operating zones based on transformer current behavior under various operating and fault conditions, in addition to introducing a novel algorithm utilizing a new mathematical approach to compute the alpha-plane complex ratio. The proposed methodology along with the PD approach are evaluated through MATLAB/SIMULINK on an autotransformer within a simulated real power system, supplemented by experimental evaluation. The results demonstrate the proposed scheme offers higher sensitivity to high impedance ground faults, maintains stability during border range of CT saturation under external faults, and delivers faster tripping times compared to the traditional PD method. This approach provides a robust and reliable solution to overcome the inherent challenges of conventional transformer protection techniques.

| S-EPMC11906808 | biostudies-literature

A developed DQ control method for shunt active power filter to improve power quality in transformers.

Project description:Power transformers are the most important component in power system. Exposing these transformers to the harmonic distortions causes additional heat losses, insulation stress, decrease in lifetime of insulation, and reduced power factor with decrease in efficiency of the system. The lifespan of distribution transformers is influenced by the fragility of power quality in power networks. Harmonic mitigation filters with robust control technique are required to reduce the harmonic effects on power transformer. Traditionally, synchronous reference frame (DQ) is employed to control the shunt active power filter (APF) for mitigation of harmonics in power transformers. DQ control of Shunt APF lacks merits of fast response, delayed operation due to phased lock loop under abnormal grid conditions leading to insufficient harmonic elimination. A developed DQ method based on detecting the positive and negative sequence components is proposed to precisely control the shunt APF for reliable operation of power transformer. This detection technique improves the response time, mitigate the harmonics effecting the operation of transformer and overall power factor. The proposed control system is evaluated under different abnormal operating scenarios and compared with traditional DQ method. The results and analysis confirm the efficacy of the developed DQ method in improving the power transformer performance.

| S-EPMC11257387 | biostudies-literature

Algebraic graph-assisted bidirectional transformers for molecular property prediction.

Project description:The ability of molecular property prediction is of great significance to drug discovery, human health, and environmental protection. Despite considerable efforts, quantitative prediction of various molecular properties remains a challenge. Although some machine learning models, such as bidirectional encoder from transformer, can incorporate massive unlabeled molecular data into molecular representations via a self-supervised learning strategy, it neglects three-dimensional (3D) stereochemical information. Algebraic graph, specifically, element-specific multiscale weighted colored algebraic graph, embeds complementary 3D molecular information into graph invariants. We propose an algebraic graph-assisted bidirectional transformer (AGBT) framework by fusing representations generated by algebraic graph and bidirectional transformer, as well as a variety of machine learning algorithms, including decision trees, multitask learning, and deep neural networks. We validate the proposed AGBT framework on eight molecular datasets, involving quantitative toxicity, physical chemistry, and physiology datasets. Extensive numerical experiments have shown that AGBT is a state-of-the-art framework for molecular property prediction.

| S-EPMC8192505 | biostudies-literature

Protein language model-embedded geometric graphs power inter-protein contact prediction.

Project description:Accurate prediction of contacting residue pairs between interacting proteins is very useful for structural characterization of protein-protein interactions. Although significant improvement has been made in inter-protein contact prediction recently, there is still a large room for improving the prediction accuracy. Here we present a new deep learning method referred to as PLMGraph-Inter for inter-protein contact prediction. Specifically, we employ rotationally and translationally invariant geometric graphs obtained from structures of interacting proteins to integrate multiple protein language models, which are successively transformed by graph encoders formed by geometric vector perceptrons and residual networks formed by dimensional hybrid residual blocks to predict inter-protein contacts. Extensive evaluation on multiple test sets illustrates that PLMGraph-Inter outperforms five top inter-protein contact prediction methods, including DeepHomo, GLINTER, CDPred, DeepHomo2, and DRN-1D2D_Inter, by large margins. In addition, we also show that the prediction of PLMGraph-Inter can complement the result of AlphaFold-Multimer. Finally, we show leveraging the contacts predicted by PLMGraph-Inter as constraints for protein-protein docking can dramatically improve its performance for protein complex structure prediction.

| S-EPMC10987090 | biostudies-literature

Energy consumption analysis of power grid distribution transformers based on an improved genetic algorithm

Project description: Not available

| S-EPMC10703079 | biostudies-literature

A Classification Method for Select Defects in Power Transformers Based on the Acoustic Signals.

Project description:Effective, accurate and adequately early detection of any potential defects in power transformers is still a challenging issue. As the acoustic method is known as one of the noninvasive and nondestructive testing methods, this paper proposes a new approach of the classification method for defect identification in power transformers based on the acoustic measurements. Typical application of acoustic emission (AE) method is the detection of partial discharges (PD); however, during PD measurements other defects may also be identified in the transformer. In this research, a database of various signal sources recorded during acoustic PD measurements in real-life power transformers over several years was gathered. Furthermore, all of the signals are divided into two groups (PD/other) and in the second step into eight classes of various defects. Based on these, selected classification models including machine learning algorithms were applied to training and validation. Energy patterns based on the discrete wavelet transform (DWT) were used as model inputs. As a result, the presented method allows one to identify with high accuracy, not only the selected kind of PD (1st step), but other kinds of faults or anomalies within the transformer being tested (2nd step). The proposed two-step classification method may be applied as a supplementary part of a technical condition assessment system or decision support system for management of power transformers.

| S-EPMC6929177 | biostudies-literature

DeepTGIN: a novel hybrid multimodal approach using transformers and graph isomorphism networks for protein-ligand binding affinity prediction.

Project description:Predicting protein-ligand binding affinity is essential for understanding protein-ligand interactions and advancing drug discovery. Recent research has demonstrated the advantages of sequence-based models and graph-based models. In this study, we present a novel hybrid multimodal approach, DeepTGIN, which integrates transformers and graph isomorphism networks to predict protein-ligand binding affinity. DeepTGIN is designed to learn sequence and graph features efficiently. The DeepTGIN model comprises three modules: the data representation module, the encoder module, and the prediction module. The transformer encoder learns sequential features from proteins and protein pockets separately, while the graph isomorphism network extracts graph features from the ligands. To evaluate the performance of DeepTGIN, we compared it with state-of-the-art models using the PDBbind 2016 core set and PDBbind 2013 core set. DeepTGIN outperforms these models in terms of R, RMSE, MAE, SD, and CI metrics. Ablation studies further demonstrate the effectiveness of the ligand features and the encoder module. The code is available at: https://github.com/zhc-moushang/DeepTGIN . SCIENTIFIC CONTRIBUTION: DeepTGIN is a novel hybrid multimodal deep learning model for predict protein-ligand binding affinity. The model combines the Transformer encoder to extract sequence features from protein and protein pocket, while integrating graph isomorphism networks to capture features from the ligand. This model addresses the limitations of existing methods in exploring protein pocket and ligand features.

| S-EPMC11684089 | biostudies-literature

PeptideBERT: A Language Model Based on Transformers for Peptide Property Prediction.

Project description:Recent advances in language models have enabled the protein modeling community with a powerful tool that uses transformers to represent protein sequences as text. This breakthrough enables a sequence-to-property prediction for peptides without relying on explicit structural data. Inspired by the recent progress in the field of large language models, we present PeptideBERT, a protein language model specifically tailored for predicting essential peptide properties such as hemolysis, solubility, and nonfouling. The PeptideBERT utilizes the ProtBERT pretrained transformer model with 12 attention heads and 12 hidden layers. Through fine-tuning the pretrained model for the three downstream tasks, our model is state of the art (SOTA) in predicting hemolysis, which is crucial for determining a peptide's potential to induce red blood cells as well as nonfouling properties. Leveraging primarily shorter sequences and a data set with negative samples predominantly associated with insoluble peptides, our model showcases remarkable performance.

| S-EPMC10683064 | 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