Abstract
<jats:p>Many modern computational tools to describe or predict the behaviour of organic chemicals rely on molecular fingerprints. Fingerprints are used as descriptors for structure activity relationship modelling and structure-based clustering of chemicals across the fields of environmental chemistry, technology and (eco)toxicology. Here we highlight, how Extended Connectivity fingerprint (ECFP), RDKit fingerprint, Atom Pair fingerprint, and Torsion fingerprint, among others, are susceptible to “bit collisions”, which results in the same fingerprint for different molecular structures in a given dataset. Bit collisions can be introduced during hashing, where two distinct fragments result in the same hash, or more commonly, where the folding operation assigns two different structures to the same bit index. Using two curated datasets (pesticide degradation and global chemical inventory data) we show that bit collision is inversely related to the bit size of fingerprints and is more pronounced in Atom Pair and RDKit fingerprints compared to ECFP and Torsion fingerprints. In additions, molecular size and atom count is positively related to bit collisions. At the widely used bit length of 1024 bits, bit collisions occurred for more than 50% of the molecules across all fingerprint types and in both tested datasets. Finally, we showcase how bit collisions can be detrimental for predictive modelling of targets with high certainty, such as hydrophobicity, while their effect is less visible for more uncertain and “noisy” targets such as persistence. Overall, this study provides guidance on fingerprint and bit size selection for predictive modelling in environmental chemistry, ecotoxicology and environmental technology.</jats:p>