Personalized nutrition and lifestyle recommendations is a fast growing field and includes assessing an individual’s health and fitness status by combining genetic information with more traditional means including diet preferences, age, lifestyle, and health history. In addition, recent advances in wearables technology allows to track and analyze individual’s sleep, day activity patterns along with resting heart rate and other metrics. In order to analyze correlations between biomarkers and sleep and day activity patterns to produce actionable biological insights, we used data collected from healthy individuals using an automated, web-based personalized nutrition and lifestyle platform. With a machine learning approach, we found associations between sleep, activity and exercise patterns, resting heart rate, and blood biomarkers. Some of those associations are of a particular interest, for example, insights on how physical activity can affect sleeping patterns depending on the intensity and timing of the exercise. Quantifying correlations between lifestyle patterns and measured biomarkers allows us to be more precise in recommending specific interventions (such as lifestyle and diet changes) and increases the chances of bringing individual’s biomarkers into optimal zone.