@article {Kuwahara853762, author = {Hiroyuki Kuwahara and Xin Gao}, title = {Analysis of the effects of related fingerprints on molecular similarity using an eigenvalue entropy approach}, elocation-id = {853762}, year = {2019}, doi = {10.1101/853762}, publisher = {Cold Spring Harbor Laboratory}, abstract = {Two-dimensional (2D) chemical fingerprints are widely used as numerical features for the quantification of structural similarity of chemical compounds, which is an important step in similarity-based virtual screening (VS). Here, using an eigenvalue-based entropy approach, we sought to identify 2D fingerprints with little to no contribution to shaping the eigenvalue distribution of the feature matrix as related fingerprints and examined the degree to which these related 2D fingerprints influence molecular similarity scores via Tanimoto coefficient. We found that there are many related fingerprints in publicly available fingerprint schemes and that their presence in the feature set tends to decrease the similarity scores. Our results have implication in the optimal selection of 2D fingerprints and the identification of potential hits for compounds with target biological activity in VS.}, URL = {https://www.biorxiv.org/content/early/2019/11/25/853762}, eprint = {https://www.biorxiv.org/content/early/2019/11/25/853762.full.pdf}, journal = {bioRxiv} }