Dietary biomarker metabolite detection is frequently studied but lacks insight into underlying biomechanism and suffers empirically from small cohorts of feeding trials. Our earlier work engineered 3 novel features to integrate prior knowledge from a genome-scale metabolic model with metabolomes to suggest diet-relevant underlying metabolic reactions and subsystems and improve predictive modeling. This study extends our earlier work by inspecting the impact of using reaction and subsystem features together, the effect of prior knowledge volume on diet assessment, and the robustness of proposed features for multi-diet assessment. We also propose a new feature in this work. We notice several experimental settings perform better with reaction and subsystem features together. We see that diet assessment can improve with higher volumes of prior, but the volume often becomes irrelevant as long as some amount of prior is used. We show our features generalize well for multi-diet assessment.

Longitudinal metabolomics frequently benefits biomarker discovery and other applications. Existing studies ignore prior knowledge of holistic metabolic systems, which can yield interpretable features and causal insights. We integrate longitudinal metabolome with prior knowledge from a genome-scale metabolic model and propose a graph recurrent neural network-based novel representation learning framework to infer interpretable heuristic features for metabolic reactions and metabolic subsystems. In downstream clustering and classification, our proposed features often outperform and sometimes match metabolome-based performances. Our novel features can also reveal new hypotheses on causal mechanisms, such as potential reactions and subsystems involved in underlying biomechanism. Novel causal understanding and improved downstream performances affirm the impact of domain knowledge in time-series metabolome analyses.

Statistical analysis is increasingly confronted with complex data from metric spaces. Petersen and Müller (2019) established a general paradigm of Fréchet regression with complex metric space valued responses and Euclidean predictors. However, the local approach therein involves nonparametric kernel smoothing and suffers from the curse of dimensionality. To address this issue, we in this paper propose a novel random forest weighted local Fréchet regression paradigm. The main mechanism of our approach relies on a locally adaptive kernel generated by random forests. Our first method uses these weights as the local average to solve the conditional Fréchet mean, while the second method performs local linear Fréchet regression, both significantly improving existing Fréchet regression methods. Based on the theory of infinite order U-processes and infinite order $M_{m_n}$-estimator, we establish the consistency, rate of convergence, and asymptotic normality for our local constant estimator, which covers the current large sample theory of random forests with Euclidean responses as a special case. Numerical studies show the superiority of our methods with several commonly encountered types of responses such as distribution functions, symmetric positive-definite matrices, and sphere data. The practical merits of our proposals are also demonstrated through the application to New York taxi data and human mortality data.

Recent advances in dynamic treatment regimes (DTRs) facilitate the search for optimal treatments, which are tailored to individuals' specific needs and able to maximize their expected clinical benefits. However, existing algorithms relying on consistent trajectories, such as inverse probability weighting estimators (IPWEs), could suffer from insufficient sample size under optimal treatments and a growing number of decision-making stages, particularly in the context of chronic diseases. To address these challenges, we propose a novel individualized learning method which estimates the DTR with a focus on prioritizing alignment between the observed treatment trajectory and the one obtained by the optimal regime across decision stages. By relaxing the restriction that the observed trajectory must be fully aligned with the optimal treatments, our approach substantially improves the sample efficiency and stability of IPWE-based methods. In particular, the proposed learning scheme builds a more general framework which includes the popular outcome weighted learning framework as a special case of ours. Moreover, we introduce the notion of stage importance scores along with an attention mechanism to explicitly account for heterogeneity among decision stages. We establish the theoretical properties of the proposed approach, including Fisher consistency and the finite-sample performance bound. Empirically, we evaluate the proposed method in extensive simulated environments and a real case study for the COVID-19 pandemic.

MOTIVATION: A gradient boosting decision tree (GBDT) is a powerful ensemble machine-learning method that has the potential to accelerate biomarker discovery from high-dimensional molecular data. Recent algorithmic advances, such as extreme gradient boosting (XGB) and light gradient boosting (LGB), have rendered the GBDT training more efficient, scalable and accurate. However, these modern techniques have not yet been widely adopted in discovering biomarkers for censored survival outcomes, which are key clinical outcomes or endpoints in cancer studies. RESULTS: In this paper, we present a new R package 'Xsurv' as an integrated solution that applies two modern GBDT training frameworks namely, XGB and LGB, for the modeling of right-censored survival outcomes. Based on our simulations, we benchmark the new approaches against traditional methods including the stepwise Cox regression model and the original gradient boosting function implemented in the package 'gbm'. We also demonstrate the application of Xsurv in analyzing a melanoma methylation dataset. Together, these results suggest that Xsurv is a useful and computationally viable tool for screening a large number of prognostic candidate biomarkers, which may facilitate future translational and clinical research. AVAILABILITY AND IMPLEMENTATION: 'Xsurv' is freely available as an R package at: https://github.com/topycyao/Xsurv. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.