Table 2 Results summary of the new parser from the Smith, ChEMBL, PubChem and ChemSpider WLN conversion and match testing
Data set | Set size | Exact matches | Greedy matches | New parser | Old parser |
|---|---|---|---|---|---|
Smith WLN | 421 | 421 | 421 | 421 (100%) | 217 (52%) |
ChEMBL | 2934 | 2931 | 2934 | 2931 (99.8%) | 2930 (99.7%) |
PubChem | 6589 | 5745 | 7810 | 4934 (75%) | 4364 (66%) |
ChemSpider | 15941 | 12949 | 20264 | 11962 (75%) | 11526(71%) |