Skip to main content

Setup your Fragment Growing generator with a reference Chemical Space

Updated

Thank you for answering our questionnaire! Based on your answers, we have provided our team's recommendations to help you properly set up Makya for your project. 

Your answers

  1. I want to modify one or both extremity(es) of my molecule, keeping the scaffold fixed.
  2. I want to stay close to a reference molecule or dataset
  3. No, I don't have data yet, I am starting a new project 

Given the requirements of your project, we recommend setting up a Fragment Growing generator guided by a reference chemical space.

 

1. Selection of the generator 

The Fragment Growing generator can be used for generating compounds by proposing new branches to grow a molecular fragment. It is purely chemistry-driven so a good understanding of organic chemistry is required. The exit vectors (reactive centers where the chemistry will take place) can be defined by the user or automatically calculated by Makya; the generator will then search for commercial building blocks which can react in this (/these) position(s). 

For example, given a building block and one of its reaction centers (exit vectors), a boronic acid function, the fragment growing generator will propose novel compounds by attaching new branches at this center while keeping the rest of the fragment intact.

 

2. Construction of a Chemical Space

Chemical spaces are used in Makya to guide molecule generation in a direction of the user’s choice. Generators that are given a reference chemical space optimize the Tanimoto similarity of generated compounds to the chemical space. Playing with the input space can strongly influence the generator’s outcome. In particular, not only can you include data from your project or from the literature (such as a chemical series that you wish to expand), but you can also include your own ideas and designs.

 

3. Step by Step setup

Step 1: upload your reference chemical space in Makya

Note: this step is not necessary; you can also create your custom chemical space during the generator set-up, and even use the sketcher to draw your molecules (see Step 2, Chemical Space).

 

  • Prepare a .csv or .sdf file with a SMILES column that lists all the molecules you want to remain close to.
  • To upload your reference dataset, follow the steps described in the documentation: Datasets.
  • Requirements: your dataset should not contain columns without any values or without a column title. 
  • Note: Makya automatically cleans the dataset. In particular, chirality is removed. For more information, see the documentation. 

 

Step 2: set up your Fragment Growing generator

A description of the Fragment Growing generator and of the setting-up steps is provided in the documentation: Fragment Growing generator. You can also find examples in our use-cases: for example, Growing around a fragment using a 3D reference molecule.

 

  • Create a new Fragment Growing generator in the Generation tab of your project. The generator set-up page appears. 
  • In the Exit Vectors tab, enter the molecular fragment you want to grow from. 
    • The fragment should not contain any charged atoms, as protonation is performed directly inside Makya.
    • It is important to input fragments that are suitable building blocks for chemical synthesis (for example, brominated or chlorinated fragments, or molecules with an OH to form an ester), as the Fragment Growing generator is a chemistry-based generator trained on chemical reactions. 
  • After having entered your fragment, you can either specify the exit vectors from which the generator should grow new molecules, or let the algorithm determine appropriate exit vectors.
    • To specify exit vector(s), click on Set and input the atoms ID. 
    • Make sure to select all the atoms that will be involved in the reaction.
  • In the Chemical Space tab, select the dataset of your project.
    • If you have not uploaded a dataset in the previous step, you can also create your own chemical space here: click on Create Chemical Space and write your SMILES, or draw your molecule using the sketcher (pen icon).
    • The similarity to this chemical space will be an element of the overall fitness function that will be optimized during molecule generation. It ensures that you will stay close to your project molecules. 

 

These are the minimal steps needed to fit the requirements of your project. If you want to add more constraints on the generation, you can do so during the set-up of your generator. For example, you can add scorers with RDKit descriptors. They will score your molecules post generation and help you filter the results. You can also set up 3D ligand-based parameters so as to generate molecules that are close to one of your reference molecules in 3D.

 

Step 3: run the generator and analyze your results

  • To run your generator, go back to the Generation tab and click on Run.
  • You can see the first generated molecules while the generation is still running. Check that there is no error in your set-up and that the generated molecules look conform to the requirements of your problem.

 

Once you have enough molecules, you can use the Parallel Coordinates to filter the molecules based on scores such as the Iktos Ranking or Similarity to your chemical space. For more information on the visualization, analysis and export of your results, check the documentation: Visualisation and Analysis of Generated Molecules.

 

For any questions, contact your Application scientist. 

Powered by Zendesk