Tutorial for stereoisomerism and QSAR #11
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
cwognum
approved these changes
Aug 20, 2024
There was a problem hiding this comment.
This is awesome, @zhu0619 ! Thanks for pulling this together! I actually learned a lot reading through this myself.
I'll leave some comment and questions I had while reading down below:
- Is the first cell actually tagged? If not, see here. You should use the one of these tags.
# Note: Cell is tagged to not show up in the mkdocs build
- What is the difference in spatial arrangement for enantiomers ? Could we visualize this in 3D as well to explain?
- In addition to
dm.same_mol, could we add a little bit more context on the value of different equality tests? E.g. will InCHI keys detect stereochemistry? Are there cases where you don't need to (or even shouldn't) account for stereochemistry? - Similar question for E/Z isomers. I don't see these in the (very helpful! 🔥 ) figure at the top either?
- I would briefly introduce
molfeat. - I would briefly introduce the task you're modeling and explain why 3D features are important for this task.
- I would hide the long output of cell
[33]. You can keep the logs, but hide it in the docs by tagging the cell withremove_output. - Could you provide more info on the importance of predicting ACs to contextualize the results, e.g. by giving one example in which you care about accurately predicting ACs and one example where you care more about overall performance?
|
@cwognum Haven't thought you will review so quickly. |
|
I'm working with Lu to correct some aspects of the document and add one additional edge case (mixed defined, undefined stereochemistry), as well as remake the figure from Wikipedia since it is horrible and actually has a couple of mistakes LOL |
zhu0619
changed the title
|
@Fransu86 It's ready for your review. :) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Changelogs
This PR adds a tutorial that explains the significance of stereoisomers exhibiting activity cliffs in a dataset and their impact on QSAR modeling.
This notebook covers exploration of different types of stereoisomerization, how stereochemical information can be captured through molecular representations. We also examine the impact of stereoisomers that exhibit significant activity cliffs (ACs) in QSAR modeling.