The exponential cost of linear search on a parameter grid of a given precision rules it out in all but the simplest problems and random algorithms such as uniform design or the covariance matrix adaptation-evolution strategy (CMA-ES) are usually applied.
In this work, we also introduce a new high-precision rule-based PPI extraction algorithm.
As we can see from the results, our high-precision rule-based system is quite effective in many aspects especially for use cases involving large corpora.
For example, we can use an existing high-performance extraction algorithm in the first phase and then pipeline the results to our high-precision rule-based algorithm for the second screening.
We also proposed a high-precision rule-based PPI extraction method and showed our method achieves substantially higher precision than two state-of-the-art PPI extraction baselines in both per-relation and per-instance evaluation.
This two-tier system has many possible materializations; for example, in the first tier, we run our high-precision rule-based extraction method and pipeline all the negatively labeled instances to an SVM classifier in the second tier for an additional screening.
The DEEP2 results don't have the precision to rule out the quasar study that seems to show a changing fine-structure constant.
Other associations, although large in magnitude and in the hypothesized directions, were not estimated with sufficient precision to rule out other net effects.
The uncertainties from competing interpretations of the fossil record, through the choice of rate models and sequence partition strategies, to competing phylogenetic hypotheses all contribute to an evolutionary timescale that lacks sufficient precision to rule out many hypotheses.
While rule-based approaches can achieve high precision, their rules can reduce recall.
