Related Experiment Video
Updated: Jul 6, 2026
09:57
Examining Proteasome Assembly with Recombinant Archaeal Proteasomes and Nondenaturing PAGE: The Case for a Combined Approach
Published on: December 17, 2016
Predicting proteolytic sites in extracellular proteins: only halfway there
Yossef Kliger1, Eyal Gofer, Assaf Wool
1Compugen Ltd, 72 Pinchas Rosen, Tel Aviv, Israel. kliger@compugen.co.il
Bioinformatics (Oxford, England)
|March 7, 2008
Summary
Researchers developed a machine learning approach to identify unannotated proteolytic sites in secreted proteins. This method is crucial for understanding protein maturation and function, especially for the majority of sites lacking current annotation.
Area of Science:
- Biochemistry
- Computational Biology
- Proteomics
Background:
- Secretory proteins often exist as inactive precursors requiring post-translational proteolysis for maturation and activation.
- Identifying these proteolytic cleavage sites is essential for understanding protein function and biological pathways.
- Current annotation of extracellular proteolytic sites is incomplete, leaving many sites undiscovered.
Purpose of the Study:
- To develop and apply a machine learning model for the sequence-based discovery of proteolytic sites in secreted proteins.
- To address the challenge of identifying both known and novel proteolytic cleavage sites.
- To improve the understanding of protein maturation processes through computational prediction.
Main Methods:
- Utilized machine learning algorithms for sequence-based prediction of proteolytic sites.
- Analyzed and categorized unannotated proteolytic sites based on similarity to known sites.
- Validated the model's applicability using the Fibroblast Growth Factor (FGF) family.
Main Results:
- Over 3600 extracellular proteolytic sites remain unannotated, representing a significant gap in current knowledge.
- Only 6% of unannotated sites share similarity with known sites, while 94% are novel.
- The machine learning classifier achieved high precision for known sites but a lower precision (22%) for novel sites, highlighting different computational challenges.
- Physiologically relevant proteolytic sites were confirmed in homologous FGF proteins, demonstrating the classifier's utility.
Conclusions:
- A significant number of extracellular proteolytic sites are currently unannotated, necessitating advanced discovery methods.
- Machine learning offers a powerful tool for identifying novel proteolytic sites, though challenges remain for dissimilar sites.
- The developed classifier has practical applications in verifying conserved proteolytic sites within protein families like FGF.
More Related Videos
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...
01:39Mitochondrial Precursor Proteins
Mitochondrial precursors are partially unfolded or loosely folded polypeptide chains. Newly synthesized precursors are inhibited from spontaneously folding into their native conformation by the cytosolic chaperones, heat shock proteins 70 (Hsp70), and mitochondrial import stimulation factors (MSFs). Precursors bound to MSFs are guided to the TOM70-TOM37 receptors, while precursors bound to Hsp70 chaperones are targetted to TOM20-TOM22 receptor complexes.
Most of the mitochondrial precursors...
Most of the mitochondrial precursors...
01:19Translocation of Proteins into the Mitochondria
Mitochondrial precursors are translocated to the internal subcompartments via independent mechanisms involving distinct protein machineries called translocases.
Sorting of outer membrane proteins:
Mitochondrial outer membrane proteins are of two types: the transmembrane, beta-barrel porins, and the membrane-anchored, alpha-helical proteins. Beta-barrel porin precursors are translocated by the TOM complex and inserted into the outer mitochondrial membrane by the SAM complex. In contrast,...
Sorting of outer membrane proteins:
Mitochondrial outer membrane proteins are of two types: the transmembrane, beta-barrel porins, and the membrane-anchored, alpha-helical proteins. Beta-barrel porin precursors are translocated by the TOM complex and inserted into the outer mitochondrial membrane by the SAM complex. In contrast,...
02:18The Proteasome
Eukaryotic cells can degrade proteins through several pathways. One of the most important amongst these is the ubiquitin-proteasome pathway. It helps the cell eliminate the misfolded, damaged, or unwarranted cytoplasmic proteins in a highly specific manner.
In this pathway, the target proteins are first tagged with small proteins called ubiquitin. A series of enzymes carry out the ubiquitination of the target proteins - E1 (ubiquitin-activating enzyme), E2 (ubiquitin-conjugating enzyme), and E3...
In this pathway, the target proteins are first tagged with small proteins called ubiquitin. A series of enzymes carry out the ubiquitination of the target proteins - E1 (ubiquitin-activating enzyme), E2 (ubiquitin-conjugating enzyme), and E3...
01:13The Proteasome
Eukaryotic cells can degrade proteins through several pathways. One of the most important among these is the ubiquitin-proteasome pathway. It helps the cell eliminate the misfolded, damaged, or unwarranted cytoplasmic proteins in a highly specific manner.
In this pathway, the target proteins are first tagged with small proteins called ubiquitin. This involves participation of a series of enzymes including— E1 (ubiquitin-activating enzyme), E2 (ubiquitin-conjugating enzyme), and E3 (ubiquitin...
In this pathway, the target proteins are first tagged with small proteins called ubiquitin. This involves participation of a series of enzymes including— E1 (ubiquitin-activating enzyme), E2 (ubiquitin-conjugating enzyme), and E3 (ubiquitin...
01:26Insertion of Single-pass Transmembrane Proteins in the RER
Integral membrane proteins are proteins adhered to the lipid bilayer of a cell organelle or membrane. They can be of two types: transmembrane integral proteins that span the lipid bilayer and monotopic proteins that are attached to either side of the membrane but do not pass through it.
Integral transmembrane proteins possess transmembrane and extra membrane domains. The transmembrane domains are primarily made of 20-25 hydrophobic amino acids arranged in a helical secondary confirmation. These...
Integral transmembrane proteins possess transmembrane and extra membrane domains. The transmembrane domains are primarily made of 20-25 hydrophobic amino acids arranged in a helical secondary confirmation. These...