High-sensitivity pattern discovery in large, paired multiomic datasets.

MOTIVATION: Modern biological screens yield enormous numbers of measurements, and identifying and interpreting statistically significant associations among features are essential. In experiments featuring multiple high-dimensional datasets collected from the same set of samples, it is useful to identify groups of associated features between the datasets in a way that provides high statistical power and false discovery rate (FDR) control. RESULTS: Here, we present a novel hierarchical framework, HAllA (Hierarchical All-against-All association testing), for structured association discovery between paired high-dimensional datasets. HAllA efficiently integrates hierarchical hypothesis testing with FDR correction to reveal significant linear and non-linear block-wise relationships among continuous and/or categorical data. We optimized and evaluated HAllA using heterogeneous synthetic datasets of known association structure, where HAllA outperformed all-against-all and other block-testing approaches across a range of common similarity measures. We then applied HAllA to a series of real-world multiomics datasets, revealing new associations between gene expression and host immune activity, the microbiome and host transcriptome, metabolomic profiling and human health phenotypes. AVAILABILITY AND IMPLEMENTATION: An open-source implementation of HAllA is freely available at http://huttenhower.sph.harvard.edu/halla along with documentation, demo datasets and a user group. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

A statistical model for describing and simulating microbial community profiles.

Many methods have been developed for statistical analysis of microbial community profiles, but due to the complex nature of typical microbiome measurements (e.g. sparsity, zero-inflation, non-independence, and compositionality) and of the associated underlying biology, it is difficult to compare or evaluate such methods within a single systematic framework. To address this challenge, we developed SparseDOSSA (Sparse Data Observations for the Simulation of Synthetic Abundances): a statistical model of microbial ecological population structure, which can be used to parameterize real-world microbial community profiles and to simulate new, realistic profiles of known structure for methods evaluation. Specifically, SparseDOSSA's model captures marginal microbial feature abundances as a zero-inflated log-normal distribution, with additional model components for absolute cell counts and the sequence read generation process, microbe-microbe, and microbe-environment interactions. Together, these allow fully known covariance structure between synthetic features (i.e. "taxa") or between features and "phenotypes" to be simulated for method benchmarking. Here, we demonstrate SparseDOSSA's performance for 1) accurately modeling human-associated microbial population profiles; 2) generating synthetic communities with controlled population and ecological structures; 3) spiking-in true positive synthetic associations to benchmark analysis methods; and 4) recapitulating an end-to-end mouse microbiome feeding experiment. Together, these represent the most common analysis types in assessment of real microbial community environmental and epidemiological statistics, thus demonstrating SparseDOSSA's utility as a general-purpose aid for modeling communities and evaluating quantitative methods. An open-source implementation is available at http://huttenhower.sph.harvard.edu/sparsedossa2.

Multivariable association discovery in population-scale meta-omics studies.

It is challenging to associate features such as human health outcomes, diet, environmental conditions, or other metadata to microbial community measurements, due in part to their quantitative properties. Microbiome multi-omics are typically noisy, sparse (zero-inflated), high-dimensional, extremely non-normal, and often in the form of count or compositional measurements. Here we introduce an optimized combination of novel and established methodology to assess multivariable association of microbial community features with complex metadata in population-scale observational studies. Our approach, MaAsLin 2 (Microbiome Multivariable Associations with Linear Models), uses generalized linear and mixed models to accommodate a wide variety of modern epidemiological studies, including cross-sectional and longitudinal designs, as well as a variety of data types (e.g., counts and relative abundances) with or without covariates and repeated measurements. To construct this method, we conducted a large-scale evaluation of a broad range of scenarios under which straightforward identification of meta-omics associations can be challenging. These simulation studies reveal that MaAsLin 2's linear model preserves statistical power in the presence of repeated measures and multiple covariates, while accounting for the nuances of meta-omics features and controlling false discovery. We also applied MaAsLin 2 to a microbial multi-omics dataset from the Integrative Human Microbiome (HMP2) project which, in addition to reproducing established results, revealed a unique, integrated landscape of inflammatory bowel diseases (IBD) across multiple time points and omics profiles.

Estimation of Baseline Serum Creatinine with Machine Learning.

INTRODUCTION: Comparing current to baseline serum creatinine is important in detecting acute kidney injury. In this study, we report a regression-based machine learning model to predict baseline serum creatinine. METHODS: We developed and internally validated a gradient boosting model on patients admitted in Mayo Clinic intensive care units from 2005 to 2017 to predict baseline creatinine. The model was externally validated on the Medical Information Mart for Intensive Care III (MIMIC III) cohort in all ICU admissions from 2001 to 2012. The predicted baseline creatinine from the model was compared with measured serum creatinine levels. We compared the performance of our model with that of the backcalculated estimated serum creatinine from the Modification of Diet in Renal Disease (MDRD) equation. RESULTS: Following ascertainment of eligibility criteria, 44,370 patients from the Mayo Clinic and 6,112 individuals from the MIMIC III cohort were enrolled. Our model used 6 features from the Mayo Clinic and MIMIC III datasets, including the presence of chronic kidney disease, weight, height, and age. Our model had significantly lower error than the MDRD backcalculation (mean absolute error [MAE] of 0.248 vs. 0.374 in the Mayo Clinic test data; MAE of 0.387 vs. 0.465 in the MIMIC III cohort) and higher correlation (intraclass correlation coefficient [ICC] of 0.559 vs. 0.050 in the Mayo Clinic test data; ICC of 0.357 vs. 0.030 in the MIMIC III cohort). DISCUSSION/CONCLUSION: Using machine learning models, baseline serum creatinine could be estimated with higher accuracy than the backcalculated estimated serum creatinine level.

A Bayesian method for detecting pairwise associations in compositional data.

Compositional data consist of vectors of proportions normalized to a constant sum from a basis of unobserved counts. The sum constraint makes inference on correlations between unconstrained features challenging due to the information loss from normalization. However, such correlations are of long-standing interest in fields including ecology. We propose a novel Bayesian framework (BAnOCC: Bayesian Analysis of Compositional Covariance) to estimate a sparse precision matrix through a LASSO prior. The resulting posterior, generated by MCMC sampling, allows uncertainty quantification of any function of the precision matrix, including the correlation matrix. We also use a first-order Taylor expansion to approximate the transformation from the unobserved counts to the composition in order to investigate what characteristics of the unobserved counts can make the correlations more or less difficult to infer. On simulated datasets, we show that BAnOCC infers the true network as well as previous methods while offering the advantage of posterior inference. Larger and more realistic simulated datasets further showed that BAnOCC performs well as measured by type I and type II error rates. Finally, we apply BAnOCC to a microbial ecology dataset from the Human Microbiome Project, which in addition to reproducing established ecological results revealed unique, competition-based roles for Proteobacteria in multiple distinct habitats.

Accurate and interpretable prediction of ICU-acquired AKI.

PURPOSE: We developed and validated two parsimonious algorithms to predict the time of diagnosis of any stage of acute kidney injury (any-AKI) or moderate-to-severe AKI in clinically actionable prediction windows. MATERIALS AND METHODS: In this retrospective single-center cohort of adult ICU admissions, we trained two gradient-boosting models: 1) any-AKI model, predicting the risk of any-AKI at least 6 h before diagnosis (50,342 admissions), and 2) moderate-to-severe AKI model, predicting the risk of moderate-to-severe AKI at least 12 h before diagnosis (39,087 admissions). Performance was assessed before disease diagnosis and validated prospectively. RESULTS: The models achieved an area under the receiver operating characteristic curve (AUROC) of 0.756 at six hours (any-AKI) and 0.721 at 12 h (moderate-to-severe AKI) prior. Prospectively, both models had high positive predictive values (0.796 and 0.546 for any-AKI and moderate-to-severe AKI models, respectively) and triggered more in patients who developed AKI vs. those who did not (median of 1.82 [IQR 0-4.71] vs. 0 [IQR 0-0.73] and 2.35 [IQR 0.14-4.96] vs. 0 [IQR 0-0.8] triggers per 8 h for any-AKI and moderate-to-severe AKI models, respectively). CONCLUSIONS: The two AKI prediction models have good discriminative performance using common features, which can aid in accurately and informatively monitoring AKI risk in ICU patients.

Association of systolic, diastolic, mean, and pulse pressure with morbidity and mortality in septic ICU patients: a nationwide observational study.

BACKGROUND: Intensivists target different blood pressure component values to manage intensive care unit (ICU) patients with sepsis. We aimed to evaluate the relationship between individual blood pressure components and organ dysfunction in critically ill septic patients. METHODS: In this retrospective observational study, we evaluated 77,328 septic patients in 364 ICUs in the eICU Research Institute database. Primary exposure was the lowest cumulative value of each component; mean, systolic, diastolic, and pulse pressure, sustained for at least 120 min during ICU stay. Primary outcome was ICU mortality and secondary outcomes were composite outcomes of acute kidney injury or death and myocardial injury or death during ICU stay. Multivariable logistic regression spline and threshold regression adjusting for potential confounders were conducted to evaluate associations between exposures and outcomes. Sensitivity analysis was conducted in 4211 patients with septic shock. RESULTS: Lower values of all blood pressures components were associated with a higher risk of ICU mortality. Estimated change-points for the risk of ICU mortality were 69 mmHg for mean, 100 mmHg for systolic, 60 mmHg for diastolic, and 57 mmHg for pulse pressure. The strength of association between blood pressure components and ICU mortality as determined by slopes of threshold regression were mean (- 0.13), systolic (- 0.11), diastolic (- 0.09), and pulse pressure (- 0.05). Equivalent non-linear associations between blood pressure components and ICU mortality were confirmed in septic shock patients. We observed a similar relationship between blood pressure components and secondary outcomes. CONCLUSION: Blood pressure component association with ICU mortality is the strongest for mean followed by systolic, diastolic, and weakest for pulse pressure. Critical care teams should continue to follow MAP-based resuscitation, though exploratory analysis focusing on blood pressure components in different sepsis phenotypes in critically ill ICU patients is needed.

Machine learning prediction of the total duration of invasive and non-invasive ventilation During ICU Stay.

Predicting the duration of ventilation in the ICU helps in assessing the risk of ventilator-induced lung injury, ensuring sufficient oxygenation, and optimizing resource allocation. Prior models provided a prediction of total duration without distinguishing between invasive and non-invasive ventilation. This work proposes two independent gradient boosting regression models for predicting the duration of invasive and non-invasive ventilation based on commonly available ICU features. These models are trained on 2.6 million patient stays across 350 US hospitals between 2010 to 2019. The mean absolute error (MAE) for the prediction of duration was 2.08 days for invasive ventilation and 0.36 days for non-invasive ventilation. The total ventilation duration predicted by our model had MAE of 2.38 days, which outperformed the gold standard (APACHE) with MAE of 3.02 days. The feature importance analysis of the trained models showed that, for invasive ventilation, high average heart rate, diagnosis of respiratory infection and admissions from locations other than the operating room were associated with longer ventilation durations. For non-invasive ventilation, higher respiratory rates and having any GCS measurement were associated with longer durations.

Predicting acute kidney injury in critically ill patients using comorbid conditions utilizing machine learning.

BACKGROUND: Acute kidney injury (AKI) carries a poor prognosis. Its incidence is increasing in the intensive care unit (ICU). Our purpose in this study is to develop and externally validate a model for predicting AKI in the ICU using patient data present prior to ICU admission. METHODS: We used data of 98 472 adult ICU admissions at Mayo Clinic between 1 January 2005 and 31 December 2017 and 51 801 encounters from Medical Information Mart for Intensive Care III (MIMIC-III) cohort. A gradient-boosting model was trained on 80% of the Mayo Clinic cohort using a set of features to predict AKI acquired in the ICU. RESULTS: AKI was identified in 39 307 (39.9%) encounters in the Mayo Clinic cohort. Patients who developed AKI in the ICU were older and had higher ICU and in-hospital mortality compared to patients without AKI. A 30-feature model yielded an area under the receiver operating curve of 0.690 [95% confidence interval (CI) 0.682-0.697] in the Mayo Clinic cohort set and 0.656 (95% CI 0.648-0.664) in the MIMIC-III cohort. CONCLUSIONS: Using machine learning, AKI among ICU patients can be predicted using information available prior to admission. This model is independent of ICU information, making it valuable for stratifying patients at admission.

Including urinary output to define AKI enhances the performance of machine learning models to predict AKI at admission.

PURPOSE: Acute kidney injury (AKI) is a prevalent and detrimental condition in intensive care unit patients. Most AKI predictive models only predict creatinine-triggered AKI (AKICr) and might underperform when predicting urine-output-triggered AKI (AKIUO). We aimed to describe how admission AKICr prediction models perform in all AKI patients. MATERIALS AND METHODS: Three types of models were trained: 1) pAKIany, predicting AKI based on creatinine or urine output, 2) pAKIUO, predicting AKI based only on urine output, and 3) pAKICr, predicting AKI based only on creatinine. We compared model performance and predictive features. RESULTS: The pAKIany models had the best overall performance (AUROC 0.673-0.716) and the most consistent performance across three patient cohorts grouped by type of AKI trigger (min AUROC of 0.636). The pAKICr models had fair performance in predicting AKICr (AUROCs 0.702-0.748) but poor performance predicting AKIUO (AUROCs 0.581-0.695). The predictive features for the pAKICr models and pAKIUO models were distinct, while top features for the pAKIany models were consistently a combination of those for the pAKICr and pAKIUO models. CONCLUSION: Ignoring urine output in the outcome during model training resulted in models that are unlikely to predict AKIUO adequately and may miss a substantial proportion of patients in practice.

Assessment of variation in microbial community amplicon sequencing by the Microbiome Quality Control (MBQC) project consortium.

In order for human microbiome studies to translate into actionable outcomes for health, meta-analysis of reproducible data from population-scale cohorts is needed. Achieving sufficient reproducibility in microbiome research has proven challenging. We report a baseline investigation of variability in taxonomic profiling for the Microbiome Quality Control (MBQC) project baseline study (MBQC-base). Blinded specimen sets from human stool, chemostats, and artificial microbial communities were sequenced by 15 laboratories and analyzed using nine bioinformatics protocols. Variability depended most on biospecimen type and origin, followed by DNA extraction, sample handling environment, and bioinformatics. Analysis of artificial community specimens revealed differences in extraction efficiency and bioinformatic classification. These results may guide researchers in experimental design choices for gut microbiome studies.

Fluoride Depletes Acidogenic Taxa in Oral but Not Gut Microbial Communities in Mice.

Fluoridation of drinking water and dental products prevents dental caries primarily by inhibiting energy harvest in oral cariogenic bacteria (such as Streptococcus mutans and Streptococcus sanguinis), thus leading to their depletion. However, the extent to which oral and gut microbial communities are affected by host fluoride exposure has been underexplored. In this study, we modeled human fluoride exposures to municipal water and dental products by treating mice with low or high levels of fluoride over a 12-week period. We then used 16S rRNA gene amplicon and shotgun metagenomic sequencing to assess fluoride's effects on oral and gut microbiome composition and function. In both the low- and high-fluoride groups, several operational taxonomic units (OTUs) belonging to acidogenic bacterial genera (such as Parabacteroides, Bacteroides, and Bilophila) were depleted in the oral community. In addition, fluoride-associated changes in oral community composition resulted in depletion of gene families involved in central carbon metabolism and energy harvest (2-oxoglutarate ferredoxin oxidoreductase, succinate dehydrogenase, and the glyoxylate cycle). In contrast, fluoride treatment did not induce a significant shift in gut microbial community composition or function in our mouse model, possibly due to absorption in the upper gastrointestinal tract. Fluoride-associated perturbations thus appeared to have a selective effect on the composition of the oral but not gut microbial community in mice. Future studies will be necessary to understand possible implications of fluoride exposure for the human microbiome. IMPORTANCE Fluoride has been added to drinking water and dental products since the 1950s. The beneficial effects of fluoride on oral health are due to its ability to inhibit the growth of bacteria that cause dental caries. Despite widespread human consumption of fluoride, there have been only two studies of humans that considered the effect of fluoride on human-associated microbial communities, which are increasingly understood to play important roles in health and disease. Notably, neither of these studies included a true cross-sectional control lacking fluoride exposure, as study subjects continued baseline fluoride treatment in their daily dental hygiene routines. To our knowledge, this work (in mice) is the first controlled study to assess the independent effects of fluoride exposure on the oral and gut microbial communities. Investigating how fluoride interacts with host-associated microbial communities in this controlled setting represents an effort toward understanding how common environmental exposures may potentially influence health.

Reprograming of gut microbiome energy metabolism by the FUT2 Crohn's disease risk polymorphism.

Fucosyltransferase 2 (FUT2) is an enzyme that is responsible for the synthesis of the H antigen in body fluids and on the intestinal mucosa. The H antigen is an oligosaccharide moiety that acts as both an attachment site and carbon source for intestinal bacteria. Non-secretors, who are homozygous for the loss-of-function alleles of FUT2 gene (sese), have increased susceptibility to Crohn's disease (CD). To characterize the effect of FUT2 polymorphism on the mucosal ecosystem, we profiled the microbiome, meta-proteome and meta-metabolome of 75 endoscopic lavage samples from the cecum and sigmoid of 39 healthy subjects (12 SeSe, 18 Sese and 9 sese). Imputed metagenomic analysis revealed perturbations of energy metabolism in the microbiome of non-secretor and heterozygote individuals, notably the enrichment of carbohydrate and lipid metabolism, cofactor and vitamin metabolism and glycan biosynthesis and metabolism-related pathways, and the depletion of amino-acid biosynthesis and metabolism. Similar changes were observed in mice bearing the FUT2(-/-) genotype. Metabolomic analysis of human specimens revealed concordant as well as novel changes in the levels of several metabolites. Human metaproteomic analysis indicated that these functional changes were accompanied by sub-clinical levels of inflammation in the local intestinal mucosa. Therefore, the colonic microbiota of non-secretors is altered at both the compositional and functional levels, affecting the host mucosal state and potentially explaining the association of FUT2 genotype and CD susceptibility.

The treatment-naive microbiome in new-onset Crohn's disease.

Inflammatory bowel diseases (IBDs), including Crohn's disease (CD), are genetically linked to host pathways that implicate an underlying role for aberrant immune responses to intestinal microbiota. However, patterns of gut microbiome dysbiosis in IBD patients are inconsistent among published studies. Using samples from multiple gastrointestinal locations collected prior to treatment in new-onset cases, we studied the microbiome in the largest pediatric CD cohort to date. An axis defined by an increased abundance in bacteria which include Enterobacteriaceae, Pasteurellacaea, Veillonellaceae, and Fusobacteriaceae, and decreased abundance in Erysipelotrichales, Bacteroidales, and Clostridiales, correlates strongly with disease status. Microbiome comparison between CD patients with and without antibiotic exposure indicates that antibiotic use amplifies the microbial dysbiosis associated with CD. Comparing the microbial signatures between the ileum, the rectum, and fecal samples indicates that at this early stage of disease, assessing the rectal mucosal-associated microbiome offers unique potential for convenient and early diagnosis of CD.

Integrative analysis of the microbiome and metabolome of the human intestinal mucosal surface reveals exquisite inter-relationships.

BACKGROUND: Consistent compositional shifts in the gut microbiota are observed in IBD and other chronic intestinal disorders and may contribute to pathogenesis. The identities of microbial biomolecular mechanisms and metabolic products responsible for disease phenotypes remain to be determined, as do the means by which such microbial functions may be therapeutically modified. RESULTS: The composition of the microbiota and metabolites in gut microbiome samples in 47 subjects were determined. Samples were obtained by endoscopic mucosal lavage from the cecum and sigmoid colon regions, and each sample was sequenced using the 16S rRNA gene V4 region (Illumina-HiSeq 2000 platform) and assessed by UPLC mass spectroscopy. Spearman correlations were used to identify widespread, statistically significant microbial-metabolite relationships. Metagenomes for identified microbial OTUs were imputed using PICRUSt, and KEGG metabolic pathway modules for imputed genes were assigned using HUMAnN. The resulting metabolic pathway abundances were mostly concordant with metabolite data. Analysis of the metabolome-driven distribution of OTU phylogeny and function revealed clusters of clades that were both metabolically and metagenomically similar. CONCLUSIONS: The results suggest that microbes are syntropic with mucosal metabolome composition and therefore may be the source of and/or dependent upon gut epithelial metabolites. The consistent relationship between inferred metagenomic function and assayed metabolites suggests that metagenomic composition is predictive to a reasonable degree of microbial community metabolite pools. The finding that certain metabolites strongly correlate with microbial community structure raises the possibility of targeting metabolites for monitoring and/or therapeutically manipulating microbial community function in IBD and other chronic diseases.