Related Experiment Video
Updated: May 14, 2026
07:08
Optimization of Synthetic Proteins: Identification of Interpositional Dependencies Indicating Structurally and/or Functionally Linked Residues
Published on: July 14, 2015
Sequence-only evolutionary and predicted structural features for the prediction of stability changes in protein
Lukas Folkman1, Bela Stantic, Abdul Sattar
1Institute for Integrated and Intelligent Systems, Griffith University, Brisbane, Australia. lukas.folkman@griffithuni.edu.au
BMC Bioinformatics
|February 2, 2013
Summary
Predicting protein stability changes requires combining evolutionary and predicted structural features. Our machine learning approach effectively uses these features, improving prediction accuracy using only protein sequence data.
Area of Science:
- Biochemistry and Molecular Biology
- Computational Biology
- Bioinformatics
Background:
- Single amino acid substitutions can drastically alter protein stability, structure, and function.
- Computational prediction of protein stability changes from sequence is crucial in the post-genomic era.
- Existing methods lack effective evolutionary features and exploration of predicted structural features for stability prediction.
Purpose of the Study:
- To propose and analyze novel evolutionary and predicted structural features for protein stability change prediction.
- To evaluate the performance of machine learning models using these features.
- To explore the utility of predicted structural features when protein structures are unavailable.
Main Methods:
- Development and application of machine learning models trained on experimentally measured stability changes.
- Integration of evolutionary features (mutation likelihood, SIFT score) and predicted structural features (secondary structure, accessible surface area).
- Evaluation of prediction accuracy for both stability change direction and actual values.
Main Results:
- The combination of mutation likelihood, SIFT score, and secondary structure yielded the best performance for predicting the direction of stability change.
- The combination of mutation likelihood, SIFT score, and accessible surface area minimized error in predicting actual stability change values.
- The proposed method demonstrated improved prediction performance compared to similar existing studies.
Conclusions:
- A combination of evolutionary and predicted structural features significantly enhances prediction accuracy for protein stability changes.
- Even features performing poorly individually can be beneficial when integrated with evolutionary features.
- High prediction accuracy is achievable using only protein sequence data through the appropriate combination of structural and evolutionary features.
Related Concept Videos
01:49Conserved Binding Sites
Many proteins’ biological role depends on their interactions with their ligands, small molecules that bind to specific locations on the protein known as ligand-binding sites. Ligand-binding sites are often conserved among homologous proteins as these sites are critical for protein function.
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally analyses the...
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally analyses the...
01:49Conserved Binding Sites
Many proteins’ biological role depends on their interactions with their ligands, small molecules that bind to specific locations on the protein known as ligand-binding sites. Ligand-binding sites are often conserved among homologous proteins as these sites are critical for protein function.
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally analyses the...
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally analyses the...
01:22Protein Folding
Overview
01:25Protein Folding
Proteins are chains of amino acids linked together by peptide bonds. Upon synthesis, a protein folds into a three-dimensional conformation, critical to its biological function. Interactions between its constituent amino acids guide protein folding, and hence the protein structure is primarily dependent on its amino acid sequence.
Protein Structure Is Critical to Its Biological Function
Proteins perform a wide range of biological functions such as catalyzing chemical reactions, providing...
Protein Structure Is Critical to Its Biological Function
Proteins perform a wide range of biological functions such as catalyzing chemical reactions, providing...
01:22Protein Folding
Overview
02:26Conservation of Protein Domains Over Different Proteins
Protein domains are small structurally independent units that are part of a single amino acid chain. Although these domains are often structurally independent, they may rely on synergistic effects to perform their functions as part of a larger protein. Protein domains may be conserved within the same organism, as well as across different organisms.
A limited set of protein domains often duplicate and recombine during evolution. These domains can be organized in different combinations to form...
A limited set of protein domains often duplicate and recombine during evolution. These domains can be organized in different combinations to form...