The set of descriptors is stored as a binary fingerprint of length F (the number of descriptors), where a value of 1 for the nth bit indicates that the nth descriptor is selected, and 0 indicates that it is not.
Additionally, the MorganFPs function also computes unhashed (keyed) fingerprints, where each substructure in the dataset is assigned a unique position in a binary fingerprint of length equal to the number of substructures existing in the dataset.
The construction of the DFP is based on the distribution of the probabilities of each position in a given binary fingerprint of fixed length.
As described in the Materials and methods Section, the substructure was fragmented and used to derive a binary occurrence fingerprint of length 57 for the extended similarity measure (1).
ChemAxon's Java API [54] was utilized to generate fixed-length ECFP_4 binary fingerprints with a length of 1,024 bits.
Extended Connectivity Fingerprints (ECFP) were calculated in RDKit using a Python based script to generate fixed-length ECFP4 binary fingerprints with a length of 1,024 bits counting each bit once [29].
One is 2D fingerprint based conventional similarity search (CSS) and the other is AVE profile based conventional similarity search (PBSS), which can be considered as replacing the binary fingerprint of the query compound by the AVE profile.
Small molecule relationships in the chemical space were determined by first converting each small molecule into a binary fingerprint of 881 elements using the PubChem 2-dimensional substructure fingerprints [ 64].
Results are reported for fingerprints of length N = 1024.
