Our results are also consistent with a previous review reporting more evidence on the effects of map study in improving recall than transfer performance [ 83].
Both ISS and ISC significantly improve the recall performance but only the ISC search approach improves the precision.
One of the objectives in 2D similarity searches is to improve the recall performance.
Furthermore, it is also interesting to observe that the ISS search approach of an iterative search with active references only improves the recall performance but not the precision performance.
On the other hand, introducing AVE profile into iterative ISS and ISC only slightly improves their recall performance (Fig. 6) but not their precision performance (Fig. 7), and as a result, the general search performance of PBISS and PISC does not further improve when compared to the fingerprint based ISS and ISC (Fig. 3; Table 1).
The reason that profiles show limited ability to improve the recall performance in iterative searches is because fingerprints of references in the same cluster are usually of high self-identity, and therefore the newly formed profile of the cluster is still highly similar to the original fingerprint.
The present study demonstrates that when performance is off ceiling, and the study is sufficiently powered, sleep improves recall, even in the absence of interference.
A point of calibration may improve recall.
Usually, intersection will improve precision but degrade recall while union will improve recall but degrade precision.
In the text mining component, the PubMed abstract retrieval for each protein was shown to improve Information Retrieval (IR) recall performance without sacrificing precision The quality of disease drug identifications was shown to outperform comparable systems with balanced sensitivity, specificity, and positive predictive values (for details, refer to Li et al. [ 16]).
