DIET: Conditional independence testing with marginal dependence measures of residual information.

Conditional randomization tests (CRTs) assess whether a variable x is predictive of another variable y, having observed covariates z. CRTs require fitting a large number of predictive models, which is often computationally intractable. Existing solutions to reduce the cost of CRTs typically split the dataset into a train and test portion, or rely on heuristics for interactions, both of which lead to a loss in power. We propose the decoupled independence test (DIET), an algorithm that avoids both of these issues by leveraging marginal independence statistics to test conditional independence relationships. DIET tests the marginal independence of two random variables: Fx∣z(x∣z) and Fy∣z(y∣z) where F⋅∣z(⋅∣z) is a conditional cumulative distribution function (CDF) for the distribution p(⋅∣z). These variables are termed "information residuals." We give sufficient conditions for DIET to achieve finite sample type-1 error control and power greater than the type-1 error rate. We then prove that when using the mutual information between the information residuals as a test statistic, DIET yields the most powerful conditionally valid test. Finally, we show DIET achieves higher power than other tractable CRTs on several synthetic and real benchmarks.

Immunometabolic coevolution defines unique microenvironmental niches in ccRCC.

Tumor cell phenotypes and anti-tumor immune responses are shaped by local metabolite availability, but intratumoral metabolite heterogeneity (IMH) and its phenotypic consequences remain poorly understood. To study IMH, we profiled tumor/normal regions from clear cell renal cell carcinoma (ccRCC) patients. A common pattern of IMH transcended all patients, characterized by correlated fluctuations in the abundance of metabolites and processes associated with ferroptosis. Analysis of intratumoral metabolite-RNA covariation revealed that the immune composition of the microenvironment, especially the abundance of myeloid cells, drove intratumoral metabolite variation. Motivated by the strength of RNA-metabolite covariation and the clinical significance of RNA biomarkers in ccRCC, we inferred metabolomic profiles from the RNA sequencing data of ccRCC patients enrolled in 7 clinical trials, and we ultimately identifyied metabolite biomarkers associated with response to anti-angiogenic agents. Local metabolic phenotypes, therefore, emerge in tandem with the immune microenvironment, influence ongoing tumor evolution, and are associated with therapeutic sensitivity.

BayesTME: An end-to-end method for multiscale spatial transcriptional profiling of the tissue microenvironment.

Spatial variation in cellular phenotypes underlies heterogeneity in immune recognition and response to therapy in cancer and many other diseases. Spatial transcriptomics holds the potential to quantify such variation, but existing analysis methods are limited by their focus on individual tasks such as spot deconvolution. We present BayesTME, an end-to-end Bayesian method for analyzing spatial transcriptomics data. BayesTME unifies several previously distinct analysis goals under a single, holistic generative model. This unified approach enables BayesTME to deconvolve spots into cell phenotypes without any need for paired single-cell RNA-seq. BayesTME then goes beyond spot deconvolution to uncover spatial expression patterns among coordinated subsets of genes within phenotypes, which we term spatial transcriptional programs. BayesTME achieves state-of-the-art performance across myriad benchmarks. On human and zebrafish melanoma tissues, BayesTME identifies spatial transcriptional programs that capture fundamental biological phenomena such as bilateral symmetry and tumor-associated fibroblast and macrophage reprogramming. BayesTME is open source.

MIRTH: Metabolite Imputation via Rank-Transformation and Harmonization.

Out of the thousands of metabolites in a given specimen, most metabolomics experiments measure only hundreds, with poor overlap across experimental platforms. Here, we describe Metabolite Imputation via Rank-Transformation and Harmonization (MIRTH), a method to impute unmeasured metabolite abundances by jointly modeling metabolite covariation across datasets which have heterogeneous coverage of metabolite features. MIRTH successfully recovers masked metabolite abundances both within single datasets and across multiple, independently-profiled datasets. MIRTH demonstrates that latent information about otherwise unmeasured metabolites is embedded within existing metabolomics data, and can be used to generate novel hypotheses and simplify existing metabolomic workflows.

Dose-response modeling in high-throughput cancer drug screenings: an end-to-end approach.

Personalized cancer treatments based on the molecular profile of a patient's tumor are an emerging and exciting class of treatments in oncology. As genomic tumor profiling is becoming more common, targeted treatments for specific molecular alterations are gaining traction. To discover new potential therapeutics that may apply to broad classes of tumors matching some molecular pattern, experimentalists and pharmacologists rely on high-throughput, in vitro screens of many compounds against many different cell lines. We propose a hierarchical Bayesian model of how cancer cell lines respond to drugs in these experiments and develop a method for fitting the model to real-world high-throughput screening data. Through a case study, the model is shown to capture nontrivial associations between molecular features and drug response, such as requiring both wild type TP53 and overexpression of MDM2 to be sensitive to Nutlin-3(a). In quantitative benchmarks, the model outperforms a standard approach in biology, with $\approx20\%$ lower predictive error on held out data. When combined with a conditional randomization testing procedure, the model discovers markers of therapeutic response that recapitulate known biology and suggest new avenues for investigation. All code for the article is publicly available at https://github.com/tansey/deep-dose-response.

Deep direct likelihood knockoffs.

Predictive modeling often uses black box machine learning methods, such as deep neural networks, to achieve state-of-the-art performance. In scientific domains, the scientist often wishes to discover which features are actually important for making the predictions. These discoveries may lead to costly follow-up experiments and as such it is important that the error rate on discoveries is not too high. Model-X knockoffs [2] enable important features to be discovered with control of the false discovery rate (fdr). However, knockoffs require rich generative models capable of accurately modeling the knockoff features while ensuring they obey the so-called "swap" property. We develop Deep Direct Likelihood Knockoffs (ddlk), which directly minimizes the KL divergence implied by the knockoff swap property. ddlk consists of two stages: it first maximizes the explicit likelihood of the features, then minimizes the KL divergence between the joint distribution of features and knockoffs and any swap between them. To ensure that the generated knockoffs are valid under any possible swap, ddlk uses the Gumbel-Softmax trick to optimize the knockoff generator under the worst-case swap. We find ddlk has higher power than baselines while controlling the false discovery rate on a variety of synthetic and real benchmarks including a task involving a large dataset from one of the epicenters of COVID-19.

Double Empirical Bayes Testing.

Analyzing data from large-scale, multi-experiment studies requires scientists to both analyze each experiment and to assess the results as a whole. In this article, we develop double empirical Bayes testing (DEBT), an empirical Bayes method for analyzing multi-experiment studies when many covariates are gathered per experiment. DEBT is a two-stage method: in the first stage, it reports which experiments yielded significant outcomes; in the second stage, it hypothesizes which covariates drive the experimental significance. In both of its stages, DEBT builds on Efron (2008), which lays out an elegant empirical Bayes approach to testing. DEBT enhances this framework by learning a series of black box predictive models to boost power and control the false discovery rate (FDR). In Stage 1, it uses a deep neural network prior to report which experiments yielded significant outcomes. In Stage 2, it uses an empirical Bayes version of the knockoff filter (Candes et al., 2018) to select covariates that have significant predictive power of Stage-1 significance. In both simulated and real data, DEBT increases the proportion of discovered significant outcomes and selects more features when signals are weak. In a real study of cancer cell lines, DEBT selects a robust set of biologically-plausible genomic drivers of drug sensitivity and resistance in cancer.