Additional file 4: of PubChem atom environments

PubChem atom environments. This file contains all atom environments generated in this study for PubChem Substance and PubChem Compound in SMARTS format. Each SMARTS string is followed by a semicolon-separated incidence vector that specifies in how many records in which repository and with what radius the respective fragment was generated. As each, PubChem Substance and Compound, were fragmented with three radii in total (r = 1,2,3), the vector contains six values. Association between position in the vector, PubChem Substance/Compound, and atom environment radius is as follows: position 1) Substance r = 1; position 2) Substance r = 2; position 3) Substance r = 3; position 4) Compound r = 1; position 5) Compound r = 2; position 6) Compound r = 3. File is sorted by lexicographical order of SMARTS strings.