It has become evident from the COVID-19 global pandemic that current systems and related technologies are not capable of preventing or successfully controlling the spreads of zoonotic infectious agents. One of the features of these infectious organisms is their ability to infect both people and animals while some carriers remain asymptomatic for a period of time or for the entire duration of the infection. We believe it is imperative that during pandemic outbreaks the entire population must be tested for the presence of infection agents. In addition, we believe that AI models should be developed to analyze data and forecast zoonotic diseases outbreak and ultimately prevent epidemics and pandemics from occurring in the future. GeneThera’s goal is to develop the infrastructure of a nationwide zoonotic infectious diseases “alert shield” (ZIDAS) which would operate to predict, detect and manage the spread of pandemics and ultimately prevent pandemics from developing, similar to a “nuclear shield,” which is designed to detect incoming nuclear warheads and destroy them before they can be deployed. We believe that a global network of AI controlled laboratory robotic systems may be able to perform such a task.

Our model is based on a Ultra High Throughput Molecular Robotic/AI Platform (MORAP) which combines the use of advance robotic integrated systems with AI software systems. The MORAP will encompass a global network of interactive molecular laboratories operated using advanced integrated robotic and machine learning cloud-based software systems, which would be able to share data and interact with each other. MORAP will be capable of processing millions of samples and collecting, storing and analyzing data. MORAP nationwide communication network is accomplished through advanced cloud-based software systems, machine learning and Internet-of-Things (IoT) networks. The MORAP is readily replicated and scaled utilizing identical instrumentation and software.

We have designed the MORAP’s second generation molecular robotic/AI laboratory system prototype. MORAP system would be capable, in a full-scale commercial platform, to perform over 100,000 samples/daily with minimal human intervention.

We envision the MORAP’s cloud-based AI-integrated software system with a dual purpose: 1) data obtained from each individual robotic laboratory system would be sent to the cloud to be stored where data could be analyzed and risk factors could be evaluated; and 2) each individual robotic laboratory system as part of the MORAP network could be configured in the cloud. The individual robotic laboratory systems, identical in each location, would be controlled and operated through MORAP’s cloud-based software.

The MORAP’s cloud software architecture would:

  • Collect and analyze data from each run performed by each robotic clone;
  • Compare data between runs from individual robotic clones and determined risk factors;
  • Send commands to operate each robotic clone; and
  • Run diagnostics for each clone and alert and possibly fix any software or hardware problem the system may experience.

Each individual robotic unit is composed of different equipment controlled by the integrated software. The MORAP cloud-base system would be function as the ‘brain’ of the entire network.

Our integrated platform is being designed to targeted zoonotic diseases in general; however, we intend to focus our robotic/AI and therapeutic technologies on SARS-Cov-2 and other zoonotic infectious diseases.

We have previously developed a molecular system for the detection of a zoonotic bacterium called Mycobacterium Avian Paratuberculosis {MAP), This bacterium has been linked to Crohn’s diseases in humans and is found in the milk of infected dairy cows. Samples from milk obtained from supermarket shelves were either ‘spiked’ with different concentrations of Mycobacterium Avian Para tuberculosis or ‘naturally processed.’ The bacterial DNA was isolated using both, manual and robotic-based DNA extraction procedures and analyzed using the real time PCR technology. Using this methodology, we can detect between two (2) and twenty (20) bacterial particles from 10 ml of milk. We believe that our test will be very useful for early detection of Mycobacterium Avian Para tuberculosis, both in milk samples and in infected cows.

Overview of the Artificial Intelligence Infrastructure including IoT and Data Collection

PHASE 1(a)

Completion Criteria & Features:

  • Demonstration and proof-of-concept
  • Limited interactivity, but high visual impact
  • Designed to demonstrate what the full platform would look like.
  • UI / UX improvements
  • Refine the concept further

Further capture the requirements for proprietary model creation

PHASE 1(b) – Full Platform Development (6 months):

In parallel with test lab creation and development efforts, we will begin work on the research and development of  AI technologies and data collection, which will serve as the basis for the  Cloud Platform.

Phase 1a/b Summary: The objective of Phase 1a/b, is to build a proof-of-concept and the underlying infrastructure.

PHASE 2 – Ramp up

The objective of Phase 2 is to create a functioning commercial application of the technology.

Completion Goals & Features

  • A fully working version of the cloud platform
  • Multiple nodes (labs) providing testing data to the network.

Pending business goals of scaling up to multi-location nodes/labs.

  • Ensure that data redundancy, disaster recovery and failover systems are in place
  • Facilitate the administration of multiple node/lab locations
  • Complete development of Platform Beta Version

PHASE 3 – Ongoing AI Development

Once the AI platform is operational GeneThera will begin to accumulate vast amounts of complex data, which we will continue to analyze in new and novel ways on an ongoing basis.

In Phase 3 ongoing AI support will consist of:

  • The development of new proprietary AI research to discover actionable insights.
  • The identification and development of new diagnostic assays utilizing Artificial Intelligence.
  • Refining and improving data collection methods, increasing bandwidth as required, and scaling cloud resources dynamically, as dependent on demand loads.