MLLGJun 8, 2018

Black Box FDR

arXiv:1806.03143v119 citations
Originality Incremental advance
AI Analysis

This addresses the need for more powerful statistical analysis in large-scale scientific studies, such as cancer research, though it appears incremental as an extension of existing FDR methods with black box models.

The authors tackled the problem of analyzing multi-experiment studies with many covariates by developing BB-FDR, an empirical-Bayes method that uses black box models to boost power and control false discovery rates, resulting in outperforming state-of-the-art methods in benchmarks and increasing significant outcomes in cancer drug efficacy studies.

Analyzing large-scale, multi-experiment studies requires scientists to test each experimental outcome for statistical significance and then assess the results as a whole. We present Black Box FDR (BB-FDR), an empirical-Bayes method for analyzing multi-experiment studies when many covariates are gathered per experiment. BB-FDR learns a series of black box predictive models to boost power and control the false discovery rate (FDR) at two stages of study analysis. In Stage 1, it uses a deep neural network prior to report which experiments yielded significant outcomes. In Stage 2, a separate black box model of each covariate is used to select features that have significant predictive power across all experiments. In benchmarks, BB-FDR outperforms competing state-of-the-art methods in both stages of analysis. We apply BB-FDR to two real studies on cancer drug efficacy. For both studies, BB-FDR increases the proportion of significant outcomes discovered and selects variables that reveal key genomic drivers of drug sensitivity and resistance in cancer.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes