Improving screening efficiency by combining propensity-based sampling with interaction score prediction via matrix completion. Philip Gerlee Linnéa Schmidt Naser Monsefi Teresia Kling Rebecka Jörnsten Sven Nelander 10.1371/journal.pone.0068598.g003 https://plos.figshare.com/articles/figure/_Improving_screening_efficiency_by_combining_propensity_based_sampling_with_interaction_score_prediction_via_matrix_completion_/754855 <p>A: We extend the simpler protocol (propensity-based sampling only, <a href="http://www.plosone.org/article/info:doi/10.1371/journal.pone.0068598#pone-0068598-g001" target="_blank">Figure 1C</a>), 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.</p> 2013-07-25 01:52:25 Computational biology genomics Genome analysis tools Genetic screens Functional genomics systems biology genetics Applied mathematics algorithms Drugs and devices Drug interactions oncology Cancer treatment Chemotherapy and drug treatment combining propensity-based sampling matrix