Prediction of thermophilic proteins using feature selection technique
1Key Laboratory for NeuroInformation of Ministry of Education, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu 610054, China. hlin@uestc.edu.cn
Journal of Microbiological Methods
|November 4, 2010
Summary
We developed a computational method to predict thermophilic proteins, aiding in protein engineering and design. This machine learning model accurately identifies stable proteins for creating robust enzymes.
Area of Science:
- Computational Biology
- Protein Engineering
- Bioinformatics
Background:
- Protein thermostability is crucial for enzyme engineering applications.
- Identifying mesophilic proteins computationally can advance protein design.
- Current methods may lack accuracy in predicting protein stability.
Purpose of the Study:
- To develop a computational method for predicting thermophilic proteins.
- To utilize amino acid distribution and pair information for prediction.
- To support protein engineering and design efforts with accurate stability predictions.
Main Methods:
- Developed a support vector machine (SVM) based prediction model.
- Used amino acid distribution and selected amino acid pair information as features.
- Constructed a benchmark dataset of 915 thermophilic and 793 non-thermophilic proteins.
Main Results:
- Achieved high prediction accuracy using jackknife cross-validation.
- Successfully predicted 93.8% of thermophilic proteins.
- Successfully predicted 92.7% of non-thermophilic proteins.
Conclusions:
- The developed SVM model demonstrates high predictive success for protein thermostability.
- This computational method can be effectively applied to protein engineering and design.
- The model facilitates the design of more stable proteins for various applications.
Related Concept Videos
01:29Diversity of Archaea IV
Hyperthermophilic archaea are a group of extremophiles thriving at temperatures above 80°C, often in hydrothermal vents and volcanic soils where conditions surpass the boiling point of water. At such temperatures, proteins, membranes, and DNA in most organisms degrade, but hyperthermophiles have evolved remarkable adaptations to maintain stability and function.Unique Cellular FeaturesHyperthermophilic membranes are composed of a monolayer of biphytanyl tetraether lipids, which resist thermal...
01:21Hyperthermophilic Bacteria
Domain Bacteria includes some unique hyperthermophilic species. They exhibit remarkable adaptations that enable survival in extreme environments.Thermotoga species are rod-shaped, gram-negative, non-sporulating hyperthermophiles that form a sheath-like envelope called a toga. They ferment sugars or starch, producing lactate, acetate, CO₂, and H₂, and can also grow via anaerobic respiration using H₂ and ferric iron. Found in hot springs and hydrothermal vents, over 20% of their genes show strong...
01:30Diversity of Archaea I
Archaea, a domain of single-celled microorganisms, are classified into five major phyla based on genetic and biochemical characteristics: Euryarchaeota, Crenarchaeota, Thaumarchaeota, Korarchaeota, and Nanoarchaeota. Among these, the phylum Euryarchaeota is notable for its remarkable diversity in morphology, metabolism, and ecological adaptations.Morphological and Metabolic DiversityMembers of Euryarchaeota exhibit a variety of cellular shapes, including rods and cocci. Their metabolic pathways...
01:27Diversity of Archaea III
Crenarchaeota, a prominent phylum of Archaea, is remarkable for its ability to thrive in extreme environments characterized by high temperatures and acidity. These microorganisms inhabit sulfuric hot springs, volcanic systems, and submarine hydrothermal vents, where temperatures often exceed 100°C. The unique adaptations of Crenarchaeota not only allow survival under such extreme conditions but also provide insights into the mechanisms of life in primordial Earth-like environments.Morphological...
01:27Factors Influencing Microbial Growth: Temperature
Microorganisms display remarkable adaptations, enabling them to thrive in diverse ecological niches across a wide range of temperatures. Temperature profoundly influences microbial growth by affecting enzymatic activity, membrane fluidity, and other cellular processes.Each microorganism operates within a specific temperature range defined by three cardinal points: minimum, optimum, and maximum. Below the minimum temperature, membranes lose fluidity, halting transport processes. Above the...
02:47Protein Families
Protein families are groups of homologous proteins; that is, they have similarities in amino acid sequences and three-dimensional structures. Protein families usually occur because of gene duplication, where an additional copy of a gene is inserted into the genome of an organism. Mutations that change the amino acids but still allow the protein to be properly synthesized, will lead to new protein family members. If these new proteins contain similar amino acids in key locations, protein...