|
|
System for Searching of Chemical Structures
Ševčík, Ivan ; Rychlý, Marek (referee) ; Křivka, Zbyněk (advisor)
This thesis deals with the problem of searching of structures in large chemical compounds databases. The aim is to design and implement an efficient system that supports two basic types of search, which are identity and substructure search. This task is complicated not only by the large number of entries in databases but also by graph representation of chemical structures, for which many algorithms are hard to solve. The thesis will introduce concepts which will prove useful in solving these problems. A web service is also created as a part of the thesis in order to make the database searching available to the users.
|
|
|
Representation of chemical compounds and its utilization in similarity search
Škoda, Petr ; Hoksza, David (advisor) ; Brezovský, Jan (referee) ; Modrák, Martin (referee)
Virtual screening is a well-established part of computer-aided drug design, which heavily employs similarity search and similarity modeling methods. Most of the popular methods are target agnostic, leaving space for design of new methods that would take into account the specifics of the particular molecular target. Additionally, newly developed methods suffer from two related issues: benchmarking and availability. Benchmarking in the domain often suffers from the use of inappropriate reference methods, lack of reproducibility, and the use of nonstandard benchmark datasets. Although there have been several benchmarking studies in the domain that aim at addressing these issues, mainly by offering a standardized comparison, they often suffer from similar drawbacks. For these reasons, new methods fail to gain trust and therefore fail to become a part of the standard toolbox, which thus consists mostly of older methods. In this work, we address the above-described issues. First, we introduce new adaptive methods for virtual screening. Then, to make our and other newly developed methods readily available, we have designed and implemented a virtual screening tool. To address the benchmarking issue, we have compiled a publicly available collection of benchmarking datasets and proposed a platform offering a...
|
|
|
System for Searching of Chemical Structures
Ševčík, Ivan ; Rychlý, Marek (referee) ; Křivka, Zbyněk (advisor)
This thesis deals with the problem of searching of structures in large chemical compounds databases. The aim is to design and implement an efficient system that supports two basic types of search, which are identity and substructure search. This task is complicated not only by the large number of entries in databases but also by graph representation of chemical structures, for which many algorithms are hard to solve. The thesis will introduce concepts which will prove useful in solving these problems. A web service is also created as a part of the thesis in order to make the database searching available to the users.
|
|
|
Využití simulovaného žíhání pro optimalizaci molekulárních otisků ve virtuálním screeningu
Filandr, Adam ; Hoksza, David (advisor) ; Kratochvíl, Miroslav (referee)
Ligand based virtual screening can be realised with various molecular rep- resentations. Fragment-feature representation represents the molecules as a set of fragments, where each fragment receives a set of descriptors. First goal of this thesis is to find suitable similarity function for such represen- tation. This representation can also be improved by assigning a weight for each descriptor, which gives it a priority in a given similarity function. The second goal of this thesis is to examine simulated annealing as an algorithm used to find the weights. We experimentally analysed the influence of various fragment types, descriptor types, similarity functions, correlated descriptors, fragment noise and parameters of simulated annealing. Because the experi- ments are computationally demanding, we also created a tool for large scale computations. 1
|
guest ::
