Rejuve AI Technical Design

Rejuve has developed its own AI platform, applying a combination of logical, evolutionary and neural net algorithms, integrated within the SingularityNET platform in a manner tailored specifically to the needs of longevity science. Using this AI platform, Rejuve scientists are working to construct a multi-resolutional, mechanistic, and dynamic model of the human body, with which to infer candidate longevity treatments. This model can already be used to predict the outcome of treatments in general populations and for specific individuals, and as ongoing work makes it more and more complete, it will become more and more broad in scope and more and more accurate in its predictions.

The Rejuve AI platform comprises two distinct components, interlinked using customized AI methods.  The first ingredient is the OpenCog AGI engine, incorporating probabilistic evolutionary learning (MOSES), probabilistic logical inference (PLN), stochastic pattern mining and other AI methods, acting together on the “Bio-Atomspace”, a hypergraph knowledge store integrating biological knowledge from a variety of databases, ontologies and datasets.

The second major component of the Rejuve AI platform is a deep neural embedding framework, which combines multiple neural architectures to create embedding vectors representing aspects of each Rejuve  member’s body and health. This is connected to OpenCog via a biomedical-AI customized deployment of the DeepWalk graph embedding algorithm, which maps nodes in the Bio-Atomspace into embedding vectors that can be processed by deep neural networks.

Data to feed the AI platform will come from Rejuve members along with other available biological and medical databases. Different  members will contribute different types and amounts of data. For example, one person may contribute data from a wearable and from nutrition interviews, while another may contribute nutritional interviews, monthly blood test results, and information on their longevity supplements. Data from past studies and major member data contributors helps Rejuve’s AI interpret the smaller amounts of data contributed by lighter users, both to make recommendations to those users and to better leverage their data for further studies.

Rejuve’s AI platform addresses many of the common issues prevalent in healthcare data, including how to deal with partially overlapping, sparse, and multi-modal observational data. Health studies struggle in dealing with confounding issues present in observational data, which often mask causal connections. Rejuve’s AI system is often able to make sense out of this ambiguity, and from randomized controlled trials tries to reconstruct the whole out of observed individual causal relations.

Synergistic Data

One of the most powerful aspects of Rejuve’s AI approach is its ability to effectively integrate patterns found in multiple types of relevant data.

The volume of data and  computational power needed to solve complex health problems like aging has only recently been made available to research scientists. Progress in AI is improving at a rapid rate, however much of AI’s impressive recent gains still exists mostly in silos. AI has been applied to siloed data sources like healthcare claims, as well as biomarker, genomic, and imaging studies with significant success. Despite this progress, these successful siloed applications only weakly relate to the general issue of aging and when analyzing a complex system, like the human body, siloed artificial intelligence is not enough.

Rejuve seeks to improve this situation by combining these siloed views of the human body to more clearly understand the underlying complex system.  Rejuve’s analysis tools fuse multiple data channels that will facilitate the interpretation of sparsely overlapping observational data. So for example, when a dataset contains patients with measurable variables A and B, as well as patients with measurable variables B and C, Rejuve’s AI can interpret variables ‘A’ and ‘C’ by using the overlapping variable ‘B’. Rejuve desires to take specific information and insights, and then combine them to develop a greater high-level understanding of the human body. To be able to combine these silos, Rejuve has to offer a platform that allows for deeply synergistic data integration.


Today’s most popular data modeling methods, deep neural networks, can learn a system in amazing detail, but at the same time they are poor at making recommendations. Neural networks struggle with suggesting the best treatment to pursue in the models they have made of the world, mainly because these models are correlational rather than causal. Correlation is fine for general prediction, but when trying to predict how a treatment will work, principles of causation matter. Rejuve’s AI platform prioritizes understanding causation, leveraging appropriately tailored neural techniques combined with probabilistic causal logical inference methods. 


Modelling and understanding the human body is too broad and difficult a task for any one entity or organization to perform on its own. Rejuve believes that these constraints can be circumvented through a philosophy of crowdsourcing. Leveraging the SingularityNET platform, Rejuve is developing methods by which a society of researchers can come to consensus on models of increasing complexity, while exploring multiple combinations of models and datasets that make sense to combine together. Metrics of consonance, formally measuring the amount of sense that models and data make together, facilitate automated complexification in a decentralized manner. The models submitted by diverse researchers can be combined in an automated way, or via participation of researchers.

Ongoing Research Projects

The following are some of the research projects currently under development by Rejuve’s science team – some already well underway and some at earlier stages of progress.

AI-Driven Systems Biology Human Aging Model

Dr. Ben Goertzel, Michael Duncan, Denis Odinokov & Lin Zheng

AI-Driven Systems Biology Model of COVID-19

Dr. Ben Goertzel, Michael Duncan

P53 and Other Cancer Preventives and Therapies: A Researchers Retrospective and Call to Action ​

Dr. Dominic Man-Kit Lam et al.​

Novel Targeted Immuno-Stimulant Modulations for Prevention of Infectious Diseases, Cancer and Other Diseases​ ​

Dr. Dominic Man-Kit Lam et al.​

Application of Evolutionary and Probabilistic AI to Learn Stem Cell Differentiation and Somatic Trans-differentiation Protocols​ ​

Dr. Ben Goertzel & Michael Duncan​

Vision Research and Product Development​ ​

Dr. Dominic Man-Kit Lam et al.​

Immunotherapy and Gene Therapy​ ​

Dr. Dominic Man-Kit Lam et al.​