The primary aim of the group is development of new chemoinformatic approaches, implementation of computational pipelines and their application to drug design. The group has expertise in molecular docking and molecular dynamics, pharmacophore modelling, machine learning and artificial intelligence. We develop approaches and software for de novo structure generation, hit/lead optimization and virtual screening and apply them and state-of-the-art tools to discover new hits and optimize compound properties. The group is partially involved in support of internal institutional databases of chemical compounds.
Development of chemoinformatic approaches, their software implementation and application of the developed and state-of-the-art tools to solve practical tasks related to drug design. In particular, we are focused on approaches to de novo design and structure optimization, machine learning and artificial intelligence.
Within this project we develop the framework of chemically reasonable mutations (CReM) for fragment-based structure generation which have a unique feature to generate synthetically accessible compounds. On top of CReM we develop multiple tools to address different practical tasks related to chemical space exploration: de novo hit generation, multi-objective hit/lead optimization, scaffold decoration and analogues enumeration. These tools use molecular docking, 3D pharmacophores and machine learning models to guide the search.
https://github.com/DrrDom/crem
We develop a framework of representation of 3D pharmacophores, which provides fast identification of identical or similar pharmacophores and calculation of 3D pharmacophore hashes, descriptors and fingerprints. These abilities are used in development of ligand-based pharmacophore models, retrieve pharmacophores from molecular dynamic simulations of protein-ligand complexes, virtual screening using pharmacophores and development of machine learning models to search for new promising hits.
https://github.com/DrrDom/pmapper
We are working on development of approaches to interpret and retrieve knowledge from machine learning and AI models, study applicability of different interpretation approaches and benchmark them. The major goal is to shed light on AI models, which are usually considered “black boxes”, and better understand their decisions. This should raise the trust to these models from medicinal chemists and the retrieved structure-property relationships can be used to guide optimization of compound properties.
https://github.com/DrrDom/spci
https://github.com/ci-lab-cz/ibenchmark
We develop a framework and implement algorithms of multiple instance learning which allows to represent a single compound by multiple instances (e.g. conformers, tautomers, protomers, etc) that greatly improves predictive performance of models. Using the novel neural network models we are able not only to predict a target property value but also to retrieve key instances, for example bioactive conformers, that helps better understanding of the modelling property and allow rational optimization of compound properties. This is a collaborative project with Strasbourg University and Kazan Federal University.
https://github.com/cimm-kzn/3D-MIL-QSAR
We support and participate in various drug design projects, in particular, currently we work on: i) lead optimization of tubulin inhibitors as anticancer agents, ii) de novo design of anti-tuberculosis compounds, iii) scaffold hopping and searching for new MARK4 inhibitors as potential anti-Alzheimer agents. Within these projects we collaborate with internal and external groups of researchers.
| Project: | In silico design of compounds with desired properties |
|---|---|
| Supervisors: | Polishchuk Pavlo Ph.D., M.Sc. |
| Available: | 2 |
| Intended for: | Doctoral training |
| Summary: |
One of the main goals of chemoinformatics is development of new compounds with desired properties or activities. Many de novo design approaches were suggested so far. The designed compounds should satisfy multiple criteria, e.g. synthetic accessibility, novelty, diversity, selectivity, etc. Generators of chemical structures satisfying these criteria are a core of all de novo design approaches. Available approaches often result in synthetically hardly accessible structures or limit their diversity and novelty. Within this study a new fragment-based approach for structure generation will be implemented which will result in chemically valid structures and will provide flexible control over their diversity, novelty and synthetic accessibility. This will be used for development of de novo design approaches based on molecular docking, pharmacophore modeling to generate compounds which will be able to fit to a binding site of a given protein. This can be used for development of novel compounds and for optimization of structures of available ligands. Developed approaches should be implemented in open-source software tools. |
| Project: | Development of 3D pharmacophore signatures and their applications to drug design |
|---|---|
| Supervisors: | Polishchuk Pavlo Ph.D., M.Sc. |
| Available: | 1 |
| Intended for: | Doctoral training |
| Summary: |
Pharmacophore modeling is a powerful approach to encode possible protein-ligand interactions and searching of new promising compounds in large libraries. So far, almost all available software for pharmacophore modeling is proprietary and implemented approaches have some limitations to efficiently work with big data. Within this study a new approach to represent 3D pharmacophores as hashes will be implemented. This representation will make it possible to quickly identify similar pharmacophores in large data sets. This property can be used to develop a new alignment free approach to ligand-based pharmacophore modeling. The developed 3D pharmacophore hashes will help to identify representative pharmacophores retrieved from molecular dynamic simulation of protein-ligand complexes. These developments will increase success rates of future screening campaigns and should be implemented in open-source software. |
| Project: | Development of 3D pharmacophore signatures and their application in the design of anticancer drugs |
|---|---|
| Supervisors: | Polishchuk Pavlo Ph.D., M.Sc. |
| Available: | 1 |
| Intended for: | Doctoral training |
| Summary: |
1 place in the face-to-face form of study |
| Project: | Computationally guided optimization of compound properties |
|---|---|
| Supervisors: | Polishchuk Pavlo Ph.D., M.Sc. |
| Available: | 1 |
| Intended for: | Master training |
| Project: | Fragment-based de novo design using pharmacophore models |
|---|---|
| Supervisors: | Polishchuk Pavlo Ph.D., M.Sc. |
| Available: | 1 |
| Intended for: | Master training |
| Project: | Novel 3D pharmacophore representation for machine learning |
|---|---|
| Supervisors: | Polishchuk Pavlo Ph.D., M.Sc. |
| Available: | 1 |
| Intended for: | Master training |
| Project: | Applicability domains in machine learning modeling |
|---|---|
| Supervisors: | Polishchuk Pavlo Ph.D., M.Sc. |
| Available: | 1 |
| Intended for: | Master training |
