4.5 Article

DeepPPThermo: A Deep Learning Framework for Predicting Protein Thermostability Combining Protein-Level and Amino Acid-Level Features

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Biochemistry & Molecular Biology

DeepTP: A Deep Learning Model for Thermophilic Protein Prediction

Jianjun Zhao et al.

Summary: Thermophilic proteins are valuable in biopharmaceuticals and enzyme engineering. To address the limitations of existing prediction models, a deep learning model called DeepTP was proposed, which utilized self-attention and multiple-channel feature fusion. DeepTP outperformed existing methods in performance comparison, achieving AUC values of 0.944 and 0.801 in independent balanced test set and validation set, respectively. In the unbalanced test set, DeepTP had an average precision (AP) of 0.536. The tool is freely available.

INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES (2023)

Article Biochemical Research Methods

Pfeature: A Tool for Computing Wide Range of Protein Features and Building Prediction Models

Akshara Pande et al.

Summary: In the past 30 years, numerous protein features have been discovered for protein annotation. To integrate these features, we developed a method called Pfeature, which can compute over 200,000 features for predicting protein function, residue-level annotation, and chemically modified peptides. Pfeature includes six major modules: composition, binary profiles, evolutionary information, structural features, patterns, and model building.

JOURNAL OF COMPUTATIONAL BIOLOGY (2023)

Article Biochemistry & Molecular Biology

BacDive in 2022: the knowledge base for standardized bacterial and archaeal data

Lorenz Christian Reimer et al.

Summary: BacDive, the bacterial metadatabase, has become a leading database for standardized prokaryotic data on strain level, offering a wealth of information for bacterial and archaeal strains. The database has seen a 30% increase in data over the past three years, with new features such as a query builder tool and an interactive dashboard for statistical overview. Improved genomic sequence data and integration with other databases further enhance the usability and accessibility of the data.

NUCLEIC ACIDS RESEARCH (2022)

Article Biochemical Research Methods

BridgeDPI: a novel Graph Neural Network for predicting drug-protein interactions

Yifan Wu et al.

Summary: This article introduces a novel method called BridgeDPl, which predicts drug-protein interactions (DPI) by constructing a learnable drug-protein association network and combining network-level information with learning-based methods, achieving significant improvements.

BIOINFORMATICS (2022)

Article Biology

SAPPHIRE: A stacking-based ensemble learning framework for accurate prediction of thermophilic proteins

Phasit Charoenkwan et al.

Summary: This study presents a novel computational method, SAPPHIRE, for accurately identifying thermophilic proteins (TPPs) using sequence information. The method combines different feature encodings and machine learning algorithms to train baseline models and extract key information of TPPs. SAPPHIRE outperforms existing methods in terms of predictive performance and achieves higher accuracy and correlation coefficient.

COMPUTERS IN BIOLOGY AND MEDICINE (2022)

Article Biochemistry & Molecular Biology

A Statistical Analysis of the Sequence and Structure of Thermophilic and Non-Thermophilic Proteins

Zahoor Ahmed et al.

Summary: The study found that polar amino acids, short bond length, wide DHA angle, and aromatic amino acids play important roles in the thermostability of proteins through statistical analysis on pairs of thermophilic proteins and their non-thermophilic orthologous.

INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES (2022)

Article Biochemical Research Methods

kmer2vec: A Novel Method for Comparing DNA Sequences by word2vec Embedding

Ruohan Ren et al.

Summary: In this study, a novel k-mer contextual alignment-free method called kmer2vec is proposed, which converts DNA/RNA sequences into points in a word2vec high-dimensional space for comparison. This method is significant in genomics analysis as it can extract structural information and accurately reflect relationships between sequences.

JOURNAL OF COMPUTATIONAL BIOLOGY (2022)

Review Biochemical Research Methods

Application of deep learning methods in biological networks

Shuting Jin et al.

Summary: The increase in biological data and the formation of biomolecule interaction databases have led to the emergence of diverse biological networks, providing valuable resources for understanding biological systems, complex disease discovery, and drug research. However, the complexity of biological networks analysis has also increased with the rise in data volume, necessitating algorithms like deep learning to handle large, heterogeneous, and complex data. Deep learning, with its ability to extract abstract features and process complex graph data structures, is increasingly being used in mining valuable information from network data.

BRIEFINGS IN BIOINFORMATICS (2021)

Article Biochemistry & Molecular Biology

Structural, thermodynamic and functional studies of human 71 kDa heat shock cognate protein (HSPA8/hHsc70)

Noeli Soares Melo Silva et al.

Summary: The study reveals that rHSPA8 shares structural and functional similarities with other human Hsp70s, interacts with adenosine nucleotides, has lower ATPase activity compared to HSPA5/hGrp78/hBiP but higher than recombinant HSPA1A/hHsp70-1A, and shows capacity in preventing the aggregation of client proteins.

BIOCHIMICA ET BIOPHYSICA ACTA-PROTEINS AND PROTEOMICS (2021)

Review Biochemistry & Molecular Biology

Structural foundations of sticholysin functionality

Juan Palacios-Ortega et al.

Summary: Actinoporins are a family of pore-forming toxins produced by sea anemones, which exert their activity by specifically recognizing sphingomyelin at their target membranes and killing cells. This review examines the structural features of actinoporins down to the residue level, focusing on the roles of specific amino acids in their function and fold. The membrane requirements for pore formation, the effect of lipid composition, and the process of pore formation are also discussed in light of the latest findings in the field.

BIOCHIMICA ET BIOPHYSICA ACTA-PROTEINS AND PROTEOMICS (2021)

Article Biochemistry & Molecular Biology

iLearnPlus: a comprehensive and automated machine-learning platform for nucleic acid and protein sequence analysis, prediction and visualization

Zhen Chen et al.

Summary: iLearnPlus is the first machine-learning platform with graphical- and web-based interfaces for analysis and predictions using nucleic acid and protein sequences, providing a comprehensive set of algorithms and automating sequence-based feature extraction and analysis. It caters to experienced bioinformaticians and biologists with no programming background, showcasing its capabilities through case studies on lncRNA prediction and crotonylation site prediction.

NUCLEIC ACIDS RESEARCH (2021)

Article Multidisciplinary Sciences

A novel sequence-based predictor for identifying and characterizing thermophilic proteins using estimated propensity scores of dipeptides

Phasit Charoenkwan et al.

Summary: A novel sequence-based thermophilic protein predictor SCMTPP was developed by combining the scoring card method (SCM) with estimated propensity scores of g-gap dipeptides, showing improved predictability and interpretability. SCMTPP outperformed commonly used machine learning models and the state-of-the-art approach ThermoPred, with high accuracy and MCC in benchmarking experiments. This predictor is expected to be a powerful tool for identifying thermophilic proteins on a large scale and guiding experimental characterization efforts.

SCIENTIFIC REPORTS (2021)

Article Biochemistry & Molecular Biology

AbsoluRATE: An in-silico method to predict the aggregation kinetics of native proteins

Puneet Rawat et al.

Summary: Understanding protein aggregation kinetics is crucial for predicting disease progression, accumulation in biotherapeutics, and engineering nano-biomaterials. A regression model was developed to predict absolute rates of protein and peptide aggregation, achieving a correlation coefficient of 0.72 with MAE of 0.91. The model considers experimental conditions and sequence-based properties, revealing important sequence attributes associated with aggregation kinetics and mechanism.

BIOCHIMICA ET BIOPHYSICA ACTA-PROTEINS AND PROTEOMICS (2021)

Article Multidisciplinary Sciences

Structure-based protein function prediction using graph convolutional networks

Vladimir Gligorijevic et al.

Summary: DeepFRI is a graph convolutional network for predicting protein functions by leveraging sequence features from a protein language model and protein structures. It outperforms other methods and supports large-scale sequence repositories.

NATURE COMMUNICATIONS (2021)

Article Biochemical Research Methods

GoVec: Gene Ontology Representation Learning Using Weighted Heterogeneous Graph and Meta-Path

Esmaeil Nourani

Summary: GoVec is a representation learning method for biomedical knowledge graphs that seamlessly generates representations for both ontologies and biological entities in a heterogeneous graph, which can be used in various bioinformatics applications.

JOURNAL OF COMPUTATIONAL BIOLOGY (2021)

Article Biochemical Research Methods

Comprehensive Study on Enhancing Low-Quality Position-Specific Scoring Matrix with Deep Learning for Accurate Protein Structure Property Prediction: Using Bagging Multiple Sequence Alignment Learning

Yuzhi Guo et al.

Summary: The study proposes an enhancing scheme for protein structure property prediction, utilizing Bagging MSA method to calculate PSSM features and integrating them using deep learning networks, which leads to improved prediction accuracy. Empirical evaluation shows that this method generates more informative PSSM features for structure property prediction.

JOURNAL OF COMPUTATIONAL BIOLOGY (2021)

Article Biochemical Research Methods

A Novel Multi-Ensemble Method for Identifying Essential Proteins

Wei Dai et al.

Summary: In this article, a novel multi-ensemble method is proposed to integrate different base classifiers by continually adding samples that are predicted correctly by other base classifiers. The experimental results show that this approach achieved better performance in yeast data and Escherichia coli data compared to individual classifiers and other ensemble learning methods.

JOURNAL OF COMPUTATIONAL BIOLOGY (2021)

Article Biochemical Research Methods

EPTool: A New Enhancing PSSM Tool for Protein Secondary Structure Prediction

Yuzhi Guo et al.

Summary: EPTool is a tool for training and evaluating the enhancing PSSM model using Bagging MSA Learning, improving PSSM quality for proteins with insufficient homologous sequences, and equipped with convenient applications for PSSM features calculation and visualization.

JOURNAL OF COMPUTATIONAL BIOLOGY (2021)

Article Biochemical Research Methods

Predicting Protein Functions Based on Differential Co-expression and Neighborhood Analysis

Jael Sanyanda Wekesa et al.

Summary: The CNPFP method integrates various data sources and uses a global iterative approach and genomic features to predict protein functions through differential co-expression analysis and neighbor-voting algorithm. It identifies yeast cell cycle-specific proteins and selects the most relevant feature subset. The method achieves high performance metrics in protein function prediction, demonstrating the importance of exploiting intrinsic protein relationships.

JOURNAL OF COMPUTATIONAL BIOLOGY (2021)

Article Biochemical Research Methods

Amino acid encoding for deep learning applications

Hesham ElAbd et al.

BMC BIOINFORMATICS (2020)

Article Biotechnology & Applied Microbiology

Discrimination of Thermophilic Proteins and Non-thermophilic Proteins Using Feature Dimension Reduction

Zifan Guo et al.

FRONTIERS IN BIOENGINEERING AND BIOTECHNOLOGY (2020)

Article Chemistry, Medicinal

Convolution Neural Network-Based Prediction of Protein Thermostability

Xingrong Fang et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2019)

Article Biochemical Research Methods

Unified rational protein engineering with sequence-based deep representation learning

Ethan C. Alley et al.

NATURE METHODS (2019)

Article Biochemistry & Molecular Biology

Thermophilic Adaptation in Prokaryotes Is Constrained by Metabolic Costs of Proteostasis

Sergey V. Venev et al.

MOLECULAR BIOLOGY AND EVOLUTION (2018)

Article Mathematical & Computational Biology

A two-step discriminated method to identify thermophilic proteins

Hua Tang et al.

INTERNATIONAL JOURNAL OF BIOMATHEMATICS (2017)

Review Biochemical Research Methods

A comprehensive overview and evaluation of circular RNA detection tools

Xiangxiang Zeng et al.

PLOS COMPUTATIONAL BIOLOGY (2017)

Article Multidisciplinary Sciences

Continuous Distributed Representation of Biological Sequences for Deep Proteomics and Genomics

Ehsaneddin Asgari et al.

PLOS ONE (2015)

Article Biochemistry & Molecular Biology

Detecting thermophilic proteins through selecting amino acid and dipeptide composition features

Songyot Nakariyakul et al.

AMINO ACIDS (2012)

Article Biochemical Research Methods

Prediction of thermophilic proteins using feature selection technique

Hao Lin et al.

JOURNAL OF MICROBIOLOGICAL METHODS (2011)

Article Biochemistry & Molecular Biology

Distance-dependent statistical potentials for discriminating thermophilic and mesophilic proteins

Yunqi Li et al.

BIOCHEMICAL AND BIOPHYSICAL RESEARCH COMMUNICATIONS (2010)

Article Computer Science, Artificial Intelligence

An expert system to predict protein thermostability using decision tree

Li-Cheng Wu et al.

EXPERT SYSTEMS WITH APPLICATIONS (2009)

Article Multidisciplinary Sciences

Predictina protein-protein interactions based only on sequences information

Juwen Shen et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2007)

Article Biotechnology & Applied Microbiology

LogitBoost classifier for discriminating thermophilic and mesophilic proteins

Guangya Zhang et al.

JOURNAL OF BIOTECHNOLOGY (2007)

Article Biochemistry & Molecular Biology

Effective factors in thermostability of thermophilic proteins

M Sadeghi et al.

BIOPHYSICAL CHEMISTRY (2006)