NON-ANIMAL HUMAN RELEVANT WORKSTATION SYSTEM AND METHOD FOR TESTING NEUROVIRULENCE AND NEUROTOXICITY IN VACCINES

Abstract

A system and method for test predicting human neurovirulence and neurotoxicity risks is disclosed. The system comprises a real-time platform or TRANS-MSC (Configured Human induced Pluripotent Stem Cells) unit and a trained digital platform. The TRANS-MSC incubates the vaccine/biologic, drug/API, cosmetic/ingredient, anti-venom aliquots collected from the produced batches in the manufacturing system. The digital platform is embedded with artificial intelligence (AI) and machine learning (ML) modules, augmented with a robotic process automation framework. The AI modules predict human neurovirulence, human neurotoxicity patterns along with any adventitious microbial contaminants in the process. The AI and ML modules are trained with a plurality of TRANS-MSC acquired phenotype micrographs and a plurality of neurotoxic genes involved in viral, bacterial, fungal infections. Further, the test is customized to a genetically distinct population, user’s library of research-grade, ingredients, intermittents, final products, etc. that are at the risk of causing neurovirulence or neurotoxicity in the clinics.

Description

Claims

1. A computer-implemented system for testing human neurovirulence in a vaccine comprising: a real-time platform or TRANS-MSC (Human Mesenchymal Stem Cells) unit configured to incubate the vaccine/biologic aliquots collected from the produced batches of vaccine, anda digital platform with embedded artificial intelligence (AI) and machine learning (ML) modules, augmented with robotic process automation framework, wherein the artificial intelligence modules are configured to predict neurovirulence, and by corollary, the degree of neuroattenuation of a vaccine along with any adventitious microbial contaminants in the test system,wherein the digital platform is trained with various human virus and bacteria-induced neurovirulent and neurotoxic cellular morphology patterns configured to develop a bandwidth for detecting the anomalies in real-time assaying.

2. A computer-implemented system for test predicting induced human neurotoxicity in a drug comprising: a real-time platform or TRANS-MSC unit configured to incubate the drug/API aliquots collected from the produced batches anda digital platform with embedded artificial intelligence (AI) and machine learning (ML) modules, augmented with robotic process automation framework, wherein the artificial intelligence modules are configured to predict neurotoxicity of a drug/API along with any adventitious microbial contaminants in the test system,wherein the digital platform is trained with various human virus, mycoplasma like fungiand bacteria-induced neurovirulent and neurotoxic cellular morphology patterns configured to develop a bandwidth for detecting the anomalies in real-time assaying.

3. A computer-implemented system for test predicting induced human neurotoxicity in a cosmetic product comprising: a real-time platform or TRANS-MSC unit configured to incubate the cosmetic chemical/ingredient aliquots collected from the produced batches anda digital platform with embedded artificial intelligence (AI) and machine learning (ML) modules, augmented with robotic process automation framework, wherein the artificial intelligence modules are configured to predict neurotoxicity of a drug/API along with any adventitious microbial contaminants in the test system,wherein the digital platform is trained with various human virus, mycoplasma like fungiand bacteria-induced neurovirulent and neurotoxic cellular morphology patterns configured to develop a bandwidth for detecting the anomalies in real-time assaying.

4. A computer-implemented system for test predicting induced human neurotoxicity in a natural product comprising: a real-time platform or TRANS-MSC unit configured to incubate the natural product/it’s API aliquots collected from the produced batches anda digital platform with embedded artificial intelligence (AI) and machine learning (ML) modules, augmented with robotic process automation framework, wherein the artificial intelligence modules are configured to predict neurotoxicity of a drug/API along with any adventitious microbial contaminants in the test system,wherein the digital platform is trained with various human virus, mycoplasma like fungiand bacteria-induced neurovirulent and neurotoxic cellular morphology patterns configured to develop a bandwidth for detecting the anomalies in real-time assaying.

5. A computer-implemented system for test predicting induced human neurotoxicity in a cell based druggable candidate comprising: a real-time platform or TRANS-MSC unit configured to incubate the cell based drug culture supernatant collected from the produced batches anda digital platform with embedded artificial intelligence (AI) and machine learning (ML) modules, augmented with robotic process automation framework, wherein the artificial intelligence modules are configured to predict neurotoxicity of a drug/API along with any adventitious microbial contaminants in the test system,wherein the digital platform is trained with various human virus, mycoplasma like fungiand bacteria-induced neurovirulent and neurotoxic cellular morphology patterns configured to develop a bandwidth for detecting the anomalies in real-time assaying.

6. The system of claim 1-5, wherein the TRANS-MSC is a phenotypically responsive, genotypically reactive, functionally readable configured, characterized hiPSC based system, amenable to batch-wise large-scale production.

7. The system of claims 1-5, wherein the artificial intelligence and machine learning modules are trained with a plurality of TRANS-MSC acquired phenotype micrographs and a plurality of neurotoxic genes involved in viral, bacterial, fungal infections.

8. The system of claims 1-5, wherein the aliquots collected from the batches are added to the TRANS-MSC unit seeded in a 6-well plate.

9. The system of claims 1-5, wherein the aliquots collected from the batches are added to the TRANS-MSC unit seeded in a 96-well plate.

10. The system of claims 8-9, wherein the plate is incubated for a specified period in an incubator and the effects of the test material on the cells are recorded as phase-contrast microscopic images at the end of the incubation period.

11. The system of claims 1-5, wherein the digital platform is loaded with a number of specified images to train the system to discern between cells with different morphology as a result of treating them with the test material.

12. A system for testing neurovirulence or neurotoxicity or neurovirulence and neurotoxicity of claims 1-5, comprising: a computing device having at least one processor and a memory in communication with the processor, wherein the memory stores a set of instructions executable by the processor;one or more databases in communication with the computing device via a network configured to store a plurality of reference data, anda user device associated with a user in communication with the computing device via the network configured to fed or upload an image data for analysis, wherein the computing device is configured to, extract phenotype images acquired on TRANS-MSC platform or data source treated with vaccine aliquot of the batch, wherein the phenotype data points acquired from images supported by respective genotype profiles run by the reference data;map the extracted data with the functional annotation (AI/ML/NLP (Neural) with the reference data or training data sets;aggregate business rules for the extracted data, andvisualize and analyze the extracted data by feeding into the software powered by machine learning algorithms that generate a scorecard and evaluate neurovirulence test and cellular infiltration.

13. The system of claim 12, wherein the batch needs to be discarded or recalled when the test material of the batch is found to be positive for the assay performed.

14. The system of claim 12, wherein the score predicts human neurovirulent phenotype, human neurotoxic cellular phenotype, cellular infiltrations, adverse events, and microbiological contamination.

15. The system of claim 12, wherein the digital platform is application software or mobile application or web-based application or desktop application.

16. The system of claim 12, detects microbial contamination in the intermittent/finished batches and generates sterility report.

17. The system of claim 12, is adopted to detect neurovirulence signals in pharmacovigilance.

18. A method for test predicting human neurovirulence, human neurotoxic risks in a vaccine, drug, cosmetic, anti-venom products using a computer-implemented system having a real-time in vitro cell based platform or TRANS-MSC unit configured to incubate the test material’s aliquots collected from the produced batches, and a digital platform with embedded artificial intelligence (AI) and machine learning (ML) modules, augmented with robotic process automation framework, wherein the artificial intelligence modules are configured to predict neurovirulence, neurotoxicity patterns along with any adventitious microbial contaminants in the test system, wherein the method comprising the steps of: adding the test material collected from the produced batches into the TRANS-MSC unit seeded in a 6-well plate or 96-well plate;incubating the plate for a specified period in a CO2 incubator and the effects of the test material on the cells are recorded as phase-contrast microscopic images at the end of the incubation;feeding a specified number of images into the digital platform;grading the cells into different categories, andquantifying the damage caused and generating a score that is predictive of the test material’s′ s propensity for causing human neurovirulence, neurotoxicity to humansto quantify the deleterious potential for safety testing and prediction of risk.

19. The method of claim 18, wherein the affected cells are categorized into cells-in-shock, infiltrated, apoptotic, necrotic, and dead.

20. The method of claim 18, wherein the quantitative nature of the assay and the automation of the test process reduces the technical variability between measurements and allows comparison with neurovirulence measurements from other test formats without the need of either positive control or negative control in the method.

21. The method of claim 20, wherein the test is customized to a genetically distinct population, or to the user’s library of research-grade, clinical-grade raw materials, intermediates, APIs, final products that are at the risk of causing neurovirulence or neurotoxicity in the clinics.