Ankit Kumar (अंकित कुमार)

It will only update inline code block. To select all triple ticks the code blocks: `.light .readme pre code table`.

@backspaces is the issue resolved?

@miquelduranfrigola Here are some molecules generated by the ‘reinvent 4 mol2mol_medium_similarity.prior’.       To view more you can visit: 1. https://github.com/ankitskvmdam/eos694w/blob/main/notebook/Playground.ipynb and...

Hi @miquelduranfrigola , Yes it makes sense. I have updated the code, now we are only saving unique molecules. I have also created a notebook to test the performance: ~~https://github.com/ankitskvmdam/eos694w/blob/main/notebook/TestPerformance.ipynb~~...

Hi, @miquelduranfrigola, Other Reinvent4 Models: 1. LibInvent: This model helps you find R-groups that can be attached to specific scaffolds. It requires one scaffold per line and each scaffold marked...

Sure, I will explore them.

Hi @miquelduranfrigola, here is the [notebook](https://github.com/ankitskvmdam/eos694w/blob/explore-different-prior/notebook/Playground.ipynb) in which I explore `mol2mol_medium_similarity.prior` (for reference), `mol2mol_scaffold.prior` and `mol2mol_scaffold_generic.prior` Performance: |Model|Input Smile|Unique Model Generated|Loss|Time (in seconds)| |-|-|-|-|-| |`mol2mol_medium_similarity`|3|287|13|144| |`mol2mol_scaffold`|3|280|20|46| |`mol2mol_scaffold_generic`|3|257|43|43|

Hi @miquelduranfrigola, I have generated some molecules using `libinvent.prior`. On average it takes around 10 seconds to generate ~438 molecules (loss 62).     

@DhanshreeA Reinvent4 has one more interesting model/prior which we want to incorporate. So far we have added/created pr to incorporate three models/priors. So, I think we can keep this open...

@miquelduranfrigola, I am exploring his approach to find the scaffold. The above shared result I got but explicitly providing attachment points. I am using this notebook to explore how to...