MolCompass provides detailed analysis of the predictive confidence of machine learning models, particularly in binary classification tasks such as toxicity determination. MolCompass uses interactive graphical tools to map chemical compounds and visualize areas where models are prone to error, explains Sergei Sosnin, a senior researcher at the University of Vienna. The tool helps researchers identify blind spots in chemical space by highlighting compounds that are predicted with high confidence but actually produce incorrect results.
The tool was tested on an estrogen receptor binding model and showed that while it worked well with some compounds, such as steroids, it had trouble with others, such as small non-cyclic chemicals.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
