Back

Machine learning approaches to quantitatively predict selectivity of compounds against hDAC1 and hDAC6 isoforms

Dogan, B.

2022-07-11 bioinformatics
10.1101/2022.07.10.499476 bioRxiv
Show abstract

The design of compounds selectively binding to specific isoforms of histone deacetylases (hDAC) is an ongoing research to prevent adverse side effects. Two of the most studied isoforms are hDAC1 and hDAC6 that are important targets to inhibit in various disease conditions. Here, various machine learning approaches were tested with the aim of developing models to predict the bioactivity and selectivity towards specific isoforms. Selectivity models were developed by directly training on the bioactivity differences of tested compounds against hDAC1 and hDAC6. Both classification and regression models were developed and compared to each other by using traditional evaluation metrics.

Matching journals

The top 8 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.