Home > Search Results: Divín, Prokop
Search:
 
Search Tips :: Simple Search
Search collections:
Sort by: Display results: Output format:
National Repository of Grey Literature 1 records found  Search took 0.00 seconds. 
Comparison of sequence and structure-based machine learning approaches for protein-ligand binding residues
 Divín, Prokop ; Hoksza, David (advisor) ; Škoda, Petr (referee)
The prediction of protein-ligand binding sites is an important task, allowing us to understand protein-ligand interactions, the understanding of which is essential in drug design and the development of certain areas of biology. Although machine learning tools for binding site prediction have been developed, the methods developed so far have only been interested in prediction from the 3D structure of the protein, which is unknown for most proteins. Therefore, in our work we are interested in prediction from knowl- edge of the mere sequence of residues representing the protein. Here we compare possi- ble approaches to solve this problem. We compare the representation of residues using their chemical and physical properties with a representation using methods from natural language recognition. Furthermore, we compare the chosen machine learning methods. Finally, we compare our results with the P2Rank method, as a state-of-the-art method using 3D structure to predict protein-ligand binding sites. 1
Detailed record

Interested in being notified about new results for this query?
Subscribe to the RSS feed.
Digital Repository :: Search :: Submit :: Personalize :: Help
Powered by Invenio v1.1.2
Maintained by admin.invenio@techlib.cz
This site is also available in the following languages:
Česky  English