Back

Development of a QSAR model to predict molecular inhibition of human STAT3

Patterson, J. M.; Winstead, C.; Milligan, K.

2021-11-01 bioinformatics
10.1101/2021.10.29.466511 bioRxiv
Show abstract

Herein is described a method to develop a QSAR model to predict the molecular inhibition of human STAT3. The model was built using machine learning using Python 3.3. A random forest machine learning algorithm was deployed. The model produced a R2 value of 0.86, indicating that our QSAR model is effective at predicting inhibitory compounds of STAT3.

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.