Sign in

Lukas Sigmund

@lukasmsigmund.bsky.social
79 followers 153 following 4 posts

PostDoc @ AstraZeneca | Computational Chemistry and Machine Learning

PostsRepliesMedia
Lukas Sigmund @lukasmsigmund.bsky.social · 13/04/2026
Do you need easy access to local atom or bond features? Then our new Python package BONAFIDE could be of interest to you. More than 550 descriptors are now just a few lines of simple Python code away. Check it out here: molecularai.github.io/atom-bond-fe...
molecularai.github.io
Atom & Bond Featurizer
072
Lukas Sigmund @lukasmsigmund.bsky.social · 18/09/2025
Now published in @angewandtechemie.bsky.social: Our hybrid QM/ML model for the prediction of the outcome of the aromatic thianthrenation reaction – with @peonor.bsky.social , @valencekjell.com, and many great colleagues from @astra-zeneca.bsky.social. onlinelibrary.wiley.com/doi/10.1002/...
onlinelibrary.wiley.com
Predicting Reaction Feasibility and Selectivity of Aromatic C─H Thianthrenation with a QM–ML Hybrid Approach
This paper presents the open-source machine learning model PATTCH, which predicts the reaction feasibility and site-selectivity of aromatic C─H thianthrenation reactions. The model was built using bo....
193
Lukas Sigmund @lukasmsigmund.bsky.social · 19/05/2025
The thianthrenation reaction of aromatic C-H bonds now has its predictive ML model for assessing both reaction feasibility and selectivity. Many thanks to the amazing team, @peonor.bsky.social, @valencekjell.com, and my colleagues at @astra-zeneca.bsky.social. chemrxiv.org/engage/chemr...
chemrxiv.org
Predicting Reaction Feasibility and Selectivity of Aromatic C–H Thianthrenation with a QM-ML Hybrid Approach
The direct thianthrenation of aromatic C–H bonds is a valuable late-stage functionalization strategy that can assist, for example, the development of new drugs. We herein present a predictive computat...
041
Lukas Sigmund @lukasmsigmund.bsky.social · 10/03/2025
Now out in @chemicalscience.rsc.org: our review on regio- and site-selectivity prediction of organic reactions. Great collaboration with my colleagues at AstraZeneca and my academic mentor @valencekjell.com. doi.org/10.1039/D5SC00541H
doi.org
Computational tools for the prediction of site- and regioselectivity of organic reactions
The regio- and site-selectivity of organic reactions is one of the most important aspects when it comes to synthesis planning. Due to that, massive research efforts were invested into computational mo...
1102