An affinity fingerprint is the vector consisting of compound's affinity or potency against the reference panel of protein targets. Here, we present the QAFFP fingerprint, 440 elements long in silico QSAR-based affinity fingerprint, components of which are predicted by Random Forest regression models trained on bioactivity data from the ChEMBL database. Both real-valued (rv-QAFFP) and binary (b-QAFFP) versions of the QAFFP fingerprint were implemented and their performance in similarity searching, biological activity classification and scaffold hopping was assessed and compared to that of the 1024 bits long Morgan2 fingerprint (the RDKit implementation of the ECFP4 fingerprint). In both similarity searching and biological activity classification, the QAFFP fingerprint yields retrieval rates, measured by AUC (similar to 0.65 and similar to 0.70 for similarity searching depending on data sets, and similar to 0.85 for classification) and EF5 (similar to 4.67 and similar to 5.82 for similarity searching depending on data sets, and similar to 2.10 for classification), comparable to that of the Morgan2 fingerprint (similarity searching AUC of similar to 0.57 and similar to 0.66, and EF5 of similar to 4.09 and similar to 6.41, depending on data sets, classification AUC of similar to 0.87, and EF5 of similar to 2.16). However, the QAFFP fingerprint outperforms the Morgan2 fingerprint in scaffold hopping as it is able to retrieve 1146 out of existing 1749 scaffolds, while the Morgan2 fingerprint reveals only 864 scaffolds.