Abstract: Embodiments include prodrug compounds, that can be used, inter alia, for treating an ailment such as cancer. The prodrug compounds can include an active agent component such as a cyclic monoterpene. The compounds can also include a prodrug component such as cholecalciferol or retinoic acid. Benefits of the prodrug compounds include increased solubility, increased half-lives, increased stability, increased lipophilicity, improved targeting (e.g., to tumor cells) and/or increased permeability/transmission across the blood-brain barrier.

Abstract: Embodiments include therapeutic small molecules for use in treating addiction and neurological disorder by stimulating neuroplasticity. The therapeutic small molecule can increase neuroplasticity and improve neural function by affecting upstream regulators of FOS, JUN, BDNF, CDC42 and CCL2. The therapeutic small molecule can also aid in reduction of Amyloid plaques via binding with amyloid beta (a4).

Abstract: Applicants have identified biomarkers that can be expressed at elevated levels in subjects who are prone to developing diabetes. The biomarkers can include misfolded proinsulin, correctly folded proinsulin, follistatin, hemoglobin A1c, C-Reactive Protein, Interleukin 18 and Interleukin 1 Receptor Antagonist, glutamic decarboxylase autoantibodies, islet cell autoantibodies, insulin autoantibodies, zinc transporter protein autoantibodies, insulinoma associated-2 autoantibodies, C-reactive protein, protectin D1, a lipoxin and a maresin. Embodiments include methods of predicting or assessing a subject's risk of developing diabetes before onset of the disease. The methods can also determine the progression and/or prognosis of diabetes. A subject who is at risk of developing the disease can be any of Type 1, Type 1.5 or Type 2 diabetes.

Abstract: The disclosure generally describes computer-implemented methods, software, and systems for generating a health recommendation. A computer-implemented method includes receiving genetic data and user data of a user. The genetic data is processed to generate vector representations of a fixed size by using an unsupervised learning algorithm. Health risk features are extracted from the vector representations by using a multi-layer convolutional neural network. Dietary conditions associated with the health risk features are determined and used to generate the health recommendation. The health recommendation is displayed for the user.