Accurate measurement of the biological markers of the aging process could provide an "aging clock" measuring predicted longevity and enable the quantification of the effects of specific lifestyle choices on healthy aging. Using machine learning techniques, we demonstrate that chronological age can be predicted accurately from (1) the expression level of human genes in capillary blood and (2) the expression level of microbial genes in stool samples. The latter uses a very large metatranscriptomic dataset, stool samples from 90,303 individuals, which arguably results in a higher quality microbiome-aging model than prior work. Our analysis suggests associations between biological age and lifestyle/health factors, e.g., people on a paleo diet or with IBS tend to have higher model-predicted ages and people on a vegetarian diet tend to have lower model-predicted ages. We delineate the key pathways of systems-level biological decline based on the age-specific features of our model.

Limiting post-meal glycemic response is an important factor in reducing the risk of chronic metabolic diseases, and contributes to significant health benefits in people with elevated levels of blood sugar. In this study, we collected gut microbiome activity (i.e., metatranscriptomic) data and measured the glycemic responses of 550 adults who consumed more than 30,000 meals from omnivore or vegetarian/gluten-free diets. We demonstrate that gut microbiome activity makes a statistically significant contribution to individual variation in glycemic response, in addition to anthropometric factors and the nutritional composition of foods. We describe predictive models (multilevel mixed-effects regression and gradient boosting machine) of variation in glycemic response among individuals ingesting the same foods. We introduce functional features aggregated from microbial activity data as candidates for association with mechanisms of glycemic control. In summary, we demonstrate for the first time that metatranscriptomic activity of the gut microbiome is correlated with glycemic response among adults.

Despite advances in cancer treatment, the 5-year mortality rate for oral cancers (OC) is 40%, mainly due to the lack of early diagnostics. To advance early diagnostics for high-risk and average-risk populations, we developed and evaluated machine-learning (ML) classifiers using metatranscriptomic data from saliva samples ( n = 433) collected from oral premalignant disorders (OPMD), OC patients ( n = 71) and normal controls ( n = 171). Our diagnostic classifiers yielded a receiver operating characteristics (ROC) area under the curve (AUC) up to 0.9, sensitivity up to 83% (92.3% for stage 1 cancer) and specificity up to 97.9%. Our metatranscriptomic signature incorporates both taxonomic and functional microbiome features, and reveals a number of taxa and functional pathways associated with OC. We demonstrate the potential clinical utility of an AI/ML model for diagnosing OC early, opening a new era of non-invasive diagnostics, enabling early intervention and improved patient outcomes.

Chronic diseases are the leading cause of morbidity and mortality globally. Yet, the majority of them have unknown etiologies, and genetic contribution is weak. In addition, many of the chronic diseases go through the cycles of relapse and remission, during which the genomic DNA does not change. This strongly suggests that human gene expression is the main driver of chronic disease onset and relapses. To identify the etiology of chronic diseases and develop more effective preventative measures, a comprehensive gene expression analysis of the human body is needed. Blood tissue is easy to access and contains a large number of expressed genes involved in many fundamental aspects of our physiology. We report here the development of a whole blood transcriptome clinical test that is high throughput, automated, inexpensive, and clinically validated. The test requires only 50 microliters of blood from a finger prick, enabling access by diverse populations that have been traditionally under-represented in clinical research. The transcripts in the samples are preserved at the time of collection and can be stored and/or transported at ambient temperatures for up to 28 days. The sample preservative protects integrity, while also inactivating all pathogens (bacteria, fungi, and viruses), enabling safe transportation globally. Given its unique set of usability features and clinical performance, this test should be integrated into longitudinal, population-scale, systems biology studies. ### Competing Interest Statement All authors are current employees of Viome, Inc. or were employees when contributing work was performed.

Accurate measurement of the biological markers of the aging process could provide an “aging clock” measuring predicted longevity and allow for the quantification of the effects of specific lifestyle choices on healthy aging. Using modern machine learning techniques, we demonstrate that chronological age can be predicted accurately from (a) the expression level of human genes in capillary blood, and (b) the expression level of microbial genes in stool samples. The latter uses the largest existing metatranscriptomic dataset, stool samples from 90,303 individuals, and is the highest-performing gut microbiome-based aging model reported to date. Our analysis suggests associations between biological age and lifestyle/health factors, e.g., people on a paleo diet or with IBS tend to be biologically older, and people on a vegetarian diet tend to be biologically younger. We delineate the key pathways of systems-level biological decline based on the age-specific features of our model; targeting these mechanisms can aid in development of new anti-aging therapeutic strategies. ### Competing Interest Statement All authors are employees of Viome Inc, a for-profit company

To prevent and treat chronic diseases, including cancer, a global application of systems biology is needed. We report here a whole blood transcriptome test that needs only 50 μl of capillary (fingerprick) blood. This test is suitable for global applications because the samples are preserved at ambient temperature for up to 4 weeks and the RNA preservative inactivates all pathogens, enabling safe transportation. Both the laboratory and bioinformatic steps are automated and performed in a clinical lab, which minimizes batch effects and creates unbiased datasets. Given its clinical testing performance and accessibility to traditionally underrepresented and diverse populations, this test offers a unique ability to reveal molecular mechanisms of disease and enable longitudinal, population-scale studies.