Mikhail Kviatkovskii

Results 27 issues of Mikhail Kviatkovskii

**Is your feature request related to a problem? Please describe.** A clear and concise description of what the problem is. Ex. I'm always frustrated when [...] **Describe the solution you'd...

Improvement
Core
Technical

There is famous [Lipinski's rule of five](https://en.wikipedia.org/wiki/Lipinski%27s_rule_of_five), that allows to quickly estimate "druglikeliness" of the molecule. We need to implement method that checks if a compound satisfies all 5 criterias...

Indigo API
High priority
python

Blocked by https://github.com/epam/Indigo/issues/659 and https://github.com/epam/Indigo/issues/628 After we create a couple of useful presets of featurisers, it could be useful to try to improve GCN architecture to achieve better predicting results....

python

Blocked by https://github.com/epam/Indigo/issues/659 and https://github.com/epam/Indigo/issues/628 After we create a couple of useful presets of featurisers, it could be useful to try to improve GAT architecture to achieve better predicting results....

ML

Blocked by https://github.com/epam/Indigo/issues/659 and https://github.com/epam/Indigo/issues/628 After we create a couple of useful presets of featurisers, it could be useful to try to improve AttentiveFP architecture to achieve better predicting results....

High priority
ML

Blocked by https://github.com/epam/Indigo/issues/659. After we create a couple of useful presets of featurisers, it could be useful to try to improve MPNN architecture to achieve better predicting results. **ToDo** Tune...

High priority
ML

We have slightly outdated version of Adrenergic dataset, it was created in 2019. Probably some new activities data arrived to CheMBL, we need to check it and probably prepare a...

ML

Currently we have multiple atom, bond and molecule featurisers. We need to create a preset of featurisers that will allow us to achieve good prediction results. **ToDo** * Test different...

High priority
python
ML

Blocked by #602. Add GMPP main function that: 1. Takes GNN model type (like MPNN or GAT) and optionally some kwargs parameters for it. 2. Takes featurisers preset (for atoms...

High priority
python
ML