Cheminformatic analysis of protein surfaces provides binding site insights and informs identification strategies

This work offers interpretable composition-interaction relationships and practical tool for binding site characterization. To facilitate application, we provide a free, open-source, fast, bindingsite identification tool (AABS), available at https://gitlab.com/Jukic/aabs. We anticipate that these findings and tool will advance binding site prediction and accelerate computationally intensive drug discovery within medicinal chemistry.