CACHE

CRITICAL ASSESSMENT OF COMPUTATIONAL HIT-FINDING EXPERIMENTS

DONATE

  • About
    • WHAT IS CACHE
    • Conferences
  • CACHE News
  • CHALLENGES
    • Challenge #1
      • Announcement
      • Computation methods
      • Preliminary results
      • Final results
    • Challenge #2
      • Announcement
      • Computation methods
      • Preliminary results
      • Final Results
    • Challenge #3
      • Announcement
      • Computation methods
      • Preliminary results
      • Final Results
    • Challenge #4
      • Announcement
      • Computation methods
      • Preliminary results
    • Challenge #5
      • Announcement
      • Computation methods
    • Challenge #6
      • Announcement
    • FAQ
  • PUBLICATIONS
  • CONTACT

Challenge #1

Hit Identification
Method type (check all that applies)
Deep learning
High-throughput docking
Machine learning
Description of your approach (min 200 and max 800 words)

Our goal with this competition is to evaluate our released tools (rather than new methods). Pharmit (http://pharmit.csb.pitt.edu) will be used to perform pharmacophore screens of purchasable compounds. Pharmacophores will be constructed in a mostly manual process through inspection of known binders and docked fragments. We will screen all the commercial libraries in Pharmit (MolPort, MCULE, Chemspace, LabNetwork). Hit compounds will be pose optimized and ranked using the default deep learning scoring function of gnina (https://github.com/gnina). Multiple receptor structures will be used for pose optimization and ranking. Molecular dynamics simulations may be used to generate an ensemble of receptor structures. Consensus ranked hits will be clustered by chemical similarity to maximize the diversity of scaffolds and filtered by desirable properties (e.g. solubility, molecular weight, rotatable bonds). We also check that proposed compounds still have advertised availability from their vendors. Time permitting we may also do a high-throughput "blind" docking of the target using gnina. Default options will be used. Most likely this screen will be limited to the MolPort library and use only a single rigid receptor structure. We will merge the ranked lists from Pharmit and blind docking, but also ensure that compounds from both methods are selected.

Method Name
Pharmit+gnina
Free software packages used

Pharmit, gnina

Relevant publications of previous uses by your group of this software/method

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4987880/ https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8191141/ https://www.mdpi.com/1420-3049/26/23/7369

Virtual screening of merged selections
Method type (check all that applies)
Deep learning
High-throughput docking
Machine learning
Description of your approach (min 200 and max 800 words)

For the merged screen blind docking with gnina will be used. Top poses will be ranked by CNNaffinity.

Method Name
gnina
Free software packages used

gnina

Relevant publications of previous uses by your group of this software/method

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8191141/ https://www.mdpi.com/1420-3049/26/23/7369

Hit Optimization Methods
Method type (check all that applies)
Deep learning
High-throughput docking
Machine learning
Description of your approach (min 200 and max 800 words)

The exact method of hit optimization will depend on the nature of the hits. Assuming they present a consistent and compelling structural hypothesis for ligand binding, the most likely approach will be to perform template docking using all compounds with similar scaffolds from the relevant made-to-order library. Template docked compounds will be optimized and ranked using gnina as described for hit identification. For this step we may utilize neural network scoring functions designed for ΔΔG prediction that currently aren't part of the gnina release (although they might be by the time the work is performed). If hits do not suggest a compelling structural hypothesis (e.g. lack of consistency in binding modes/interactions), we will endeavor to construct such a hypothesis through enhanced sampling techniques that include receptor flexibility (both docking and simulation based) and generally banging our heads against the problem until we have multiple reasonable structural hypotheses that are mostly consistent with the data. Template docking will then be performed to suggest compounds compatible with each hypothesis. During selection of final compounds will try to maximize the informativeness of the resulting SAR. For example, we will also endeavor to select "activity cliff" compounds where a small chemical change is expected to remove activity as this would help validate/reject the structural hypothesis of ligand binding. We will also select a diversity of modifications (e.g. not just target one R group).

Method Name
template+gnina
Free software packages used

gnina

Relevant publications of previous uses by your group of this software/method

https://www.mlsb.io/papers_2021/MLSB2021_Exploring_%E2%88%86%E2%88%86G_prediction_with.pdf

Cache

All rights reserved
v5.47.19.49

Footer first

  • Login
  • Applicant Login
  • Terms of Participation
  • Privacy Policy
  • FAQ
  • Docs
This website is licensed under CC-BY 4.0

Toronto website development by Rebel Trail