In longitudinal studies variables are measured repeatedly over time, leading to clustered and correlated observations. If the goal of the study is to develop prediction models, machine learning approaches such as the powerful random forest (RF) are often promising alternatives to standard statistical methods, especially in the context of high-dimensional data. In this paper, we review extensions of the standard RF method for the purpose of longitudinal data analysis. Extension methods are categorized according to the data structures for which they are designed. We consider both univariate and multivariate response longitudinal data and further categorize the repeated measurements according to whether the time effect is relevant. Even though most extensions are proposed for low-dimensional data, some can be applied to high-dimensional data. Information of available software implementations of the reviewed extensions is also given. We conclude with discussions on the limitations of our review and some future research directions.

Machine learning methods and in particular random forests are promising approaches for prediction based on high dimensional omics data sets. They provide variable importance measures to rank predictors according to their predictive power. If building a prediction model is the main goal of a study, often a minimal set of variables with good prediction performance is selected. However, if the objective is the identification of involved variables to find active networks and pathways, approaches that aim to select all relevant variables should be preferred. We evaluated several variable selection procedures based on simulated data as well as publicly available experimental methylation and gene expression data. Our comparison included the Boruta algorithm, the Vita method, recurrent relative variable importance, a permutation approach and its parametric variant (Altmann) as well as recursive feature elimination (RFE). In our simulation studies, Boruta was the most powerful approach, followed closely by the Vita method. Both approaches demonstrated similar stability in variable selection, while Vita was the most robust approach under a pure null model without any predictor variables related to the outcome. In the analysis of the different experimental data sets, Vita demonstrated slightly better stability in variable selection and was less computationally intensive than Boruta. In conclusion, we recommend the Boruta and Vita approaches for the analysis of high-dimensional data sets. Vita is considerably faster than Boruta and thus more suitable for large data sets, but only Boruta can also be applied in low-dimensional settings.

Increased levels of the urinary albumin-to-creatinine ratio (UACR) are associated with higher risk of kidney disease progression and cardiovascular events, but underlying mechanisms are incompletely understood. Here, we conduct trans-ethnic (n = 564,257) and European-ancestry specific meta-analyses of genome-wide association studies of UACR, including ancestry- and diabetes-specific analyses, and identify 68 UACR-associated loci. Genetic correlation analyses and risk score associations in an independent electronic medical records database (n = 192,868) reveal connections with proteinuria, hyperlipidemia, gout, and hypertension. Fine-mapping and trans-Omics analyses with gene expression in 47 tissues and plasma protein levels implicate genes potentially operating through differential expression in kidney (including TGFB1, MUC1, PRKCI, and OAF), and allow coupling of UACR associations to altered plasma OAF concentrations. Knockdown of OAF and PRKCI orthologs in Drosophila nephrocytes reduces albumin endocytosis. Silencing fly PRKCI further impairs slit diaphragm formation. These results generate a priority list of genes and pathways for translational research to reduce albuminuria.

Yield losses caused by fungal pathogens represent a major threat to global food production. One of the most devastating fungal wheat pathogens isZymoseptoria tritici. Despite the importance of this fungus, the underlying mechanisms of plant–pathogen interactions are poorly understood. Here we present a conceptual framework based on coinfection assays, comparative metabolomics, and microbiome profiling to study the interaction ofZ. triticiin susceptible and resistant wheat. We demonstrate thatZ. triticisuppresses the production of immune-related metabolites in a susceptible cultivar. Remarkably, this fungus-induced immune suppression spreads within the leaf and even to other leaves, a phenomenon that we term “systemic induced susceptibility”. Using a comparative metabolomics approach, we identify defense-related biosynthetic pathways that are suppressed and induced in susceptible and resistant cultivars, respectively. We show that these fungus-induced changes correlate with changes in the wheat leaf microbiome. Our findings suggest that immune suppression by this hemibiotrophic pathogen impacts specialized plant metabolism, alters its associated microbial communities, and renders wheat vulnerable to further infections.

Chronic inflammatory diseases (CIDs) are systems disorders that affect diverse organs including the intestine, joints and skin. The essential amino acid tryptophan (Trp) can be broken down to various bioactive derivatives important for immune regulation. Increased Trp catabolism has been observed in some CIDs, so we aimed to characterise the specificity and extent of Trp degradation as a systems phenomenon across CIDs. We used high performance liquid chromatography and targeted mass spectrometry to assess the serum and stool levels of Trp and Trp derivatives. Our retrospective study incorporates both cross-sectional and longitudinal components, as we have included a healthy population as a reference and there are also multiple observations per patient over time. We found reduced serum Trp levels across the majority of CIDs, and a prevailing negative relationship between Trp and systemic inflammatory marker C-reactive protein (CRP). Notably, serum Trp was low in several CIDs even in the absence of measurable systemic inflammation. Increases in the kynurenine-to-Trp ratio (Kyn:Trp) suggest that these changes result from increased degradation along the kynurenine pathway. Increases in Kyn:Trp indicate the kynurenine pathway as a major route for CID-related Trp metabolism disruption and the specificity of the network changes indicates excessive Trp degradation relative to other proteogenic amino acids. Our results suggest that increased Trp catabolism is a common metabolic occurrence in CIDs that may directly affect systemic immunity. This work was supported by the DFG Cluster of Excellence 2167 "Precision medicine in chronic inflammation" (KA, SSchr, PR, BH, SWa), the BMBF (e:Med Juniorverbund "Try-IBD" 01ZX1915A and 01ZX2215, the e:Med Network iTREAT 01ZX2202A, and GUIDE-IBD 031L0188A), EKFS (2020_EKCS.11, KA), DFG RU5042 (PR, KA), and Innovative Medicines Initiative 2 Joint Undertakings ("Taxonomy, Treatments, Targets and Remission", 831434, "ImmUniverse", 853995, "BIOMAP", 821511).

Machine learning methods and in particular random forests (RFs) are a promising alternative to standard single SNP analyses in genome-wide association studies (GWAS). RFs provide variable importance measures (VIMs) to rank SNPs according to their predictive power. However, in contrast to the established genome-wide significance threshold, no clear criteria exist to determine how many SNPs should be selected for downstream analyses. We propose a new variable selection approach, recurrent relative variable importance measure (r2VIM). Importance values are calculated relative to an observed minimal importance score for several runs of RF and only SNPs with large relative VIMs in all of the runs are selected as important. Evaluations on simulated GWAS data show that the new method controls the number of false-positives under the null hypothesis. Under a simple alternative hypothesis with several independent main effects it is only slightly less powerful than logistic regression. In an experimental GWAS data set, the same strong signal is identified while the approach selects none of the SNPs in an underpowered GWAS. The novel variable selection method r2VIM is a promising extension to standard RF for objectively selecting relevant SNPs in GWAS while controlling the number of false-positive results.