%0 Figure %A Gerlee, Philip %A Schmidt, Linnéa %A Monsefi, Naser %A Kling, Teresia %A Jörnsten, Rebecka %A Nelander, Sven %D 2013 %T Improving screening efficiency by combining propensity-based sampling with interaction score prediction via matrix completion. %U https://plos.figshare.com/articles/figure/_Improving_screening_efficiency_by_combining_propensity_based_sampling_with_interaction_score_prediction_via_matrix_completion_/754855 %R 10.1371/journal.pone.0068598.g003 %2 https://plos.figshare.com/ndownloader/files/1130686 %K Computational biology %K genomics %K Genome analysis tools %K Genetic screens %K Functional genomics %K systems biology %K genetics %K Applied mathematics %K algorithms %K Drugs and devices %K Drug interactions %K oncology %K Cancer treatment %K Chemotherapy and drug treatment %K combining %K propensity-based %K sampling %K matrix %X

A: We extend the simpler protocol (propensity-based sampling only, Figure 1C), adding a projection-based predictor to choose likely synergistic pairs (steps 3 and 4). If the prediction-driven screening discovery rate is higher than the preceding propensity-based screening, a new prediction-driven screening cycle is started (step 5). We switch between propensity-based sampling and prediction to increase the fractional discovery rate. B: Fractional discovery rate across 9 data sets show marked improvement over brute-force screening. C: Estimates of the screening efficiency demonstrate that the full protocol (steps 1–5) gives better performance than propensity-based sampling only (steps 1–2). Yellow block: additional contribution by projecting onto in the largest yeast SGA screen.

%I PLOS ONE