Methods to incorporate machine learning analytics for optimizing protein purity, potency and quality in an on-demand production system for point-of-care delivery

1. A portable and compact cell-free bioprocessing system for the production of on-demand synthesized protein for point-of-care delivery, the system comprising:

a protein expression module for producing the on-demand synthesized protein, wherein the protein expression module is associated with on-board analytics;

a protein purification module for purification of the on-demand synthesized protein, wherein the protein purification module is associated with on-board analytics, and wherein the purification module comprises two UV sensors, a multiplicity of programmable syringe pumps, and pressure sensors that generate in-line real-time testing data during a two-step purification process; and

an artificial intelligence (AI) machine learning module,

wherein the on-board analytics comprise multiple sensors for collecting data during the production of the on-demand synthesized protein, to be analyzed by the AI machine learning module, and wherein the AI machine learning module collects and stores in-line real-time testing data of purified protein from the protein purification module and provides information on product quality and potency for each batch of the on-demand synthesized protein relative to previously produced proteins.

2. The portable and compact cell-free bioprocessing system according to claim 1 , wherein the protein expression module comprises at least one dialysis cassette or reactor for inclusion of cell lysate, a reaction mixture, and DNA or mRNA for production of the on-demand synthesized protein.

3. The portable and compact cell-free bioprocessing system according to claim 2 , wherein the cell lysate is from CHO cells or E. coli cells.

4. The portable and compact cell-free bioprocessing system according to claim 2 , wherein the cell lysate is combined with a buffer for entry into the protein expression module to provide a homogeneous mixture for entering therein.

5. The portable and compact cell-free bioprocessing system according to claim 2 , wherein the reaction mixture comprises at least one of amino acids, nucleotides, co-factors, enzymes, ribosomes, tRNA, polymerases, and transcriptional factors.

6. The portable and compact cell-free bioprocessing system according to claim 5 , wherein the reaction mixture further comprises at least one species selected from the group consisting of salts, polymeric compounds, cyclic AMP, inhibitors for protein or nucleic acid degrading enzymes, inhibitors or regulators of protein synthesis, oxidation/reduction adjusters, non-denaturing surfactants, and buffer components.

7. The portable and compact cell-free bioprocessing system according to claim 1 , wherein the protein purification module comprises a metal ion affinity chromatography column for initial purification and an ion-exchange chromatography column for a polishing step.

8. The portable and compact cell-free bioprocessing system according to claim 1 , wherein each purification process comprises an inline UV sensor comprising an in-line flow cell and light sources and detectors for measuring UV absorbance at about 280 nm to monitor the two-step purification process.

9. The portable and compact cell-free bioprocessing system according to claim 1 , wherein the on-board analytics comprise multiple sensors for collecting data during the production process to be analyzed by a cloud based machine learning system.

10. The portable and compact cell-free bioprocessing system according to claim 9 , wherein the multiple sensors measure for dissolved oxygen, pH, absorbance, pressure and temperature.

11. The portable and compact cell-free bioprocessing system according to claim 1 , wherein the machine learning system uses a blind source separation (BSS) algorithm.

12. The portable and compact cell-free bioprocessing system according to claim 11 , wherein the (BSS) algorithm uses independent-component analysis (ICA) that extracts independent source signals when the source signals are active simultaneously and is a BSS algorithm depending on using Artificial Neural Networks.

13. The portable and compact cell-free bioprocessing system according to claim 1 , wherein each purification process comprises at least one real-time test selected from the group consisting of absorbance, circular dichroism, fluorescence measurements, and lifetime measurements.

14. The portable and compact cell-free bioprocessing system according to claim 1 , wherein the machine learning system is a cloud-based server or a physical server connected to the bioprocessing system.

15. The portable and compact cell-free bioprocessing system according to claim 13 , wherein the numerical or analysis data is captured by a smart phone app and transferred through a smartphone to a server for analysis.

16. The portable and compact cell-free bioprocessing system according to claim 13 , wherein the numerical or analysis data is evaluated and an output is is provided to the bioprocessing system, wherein the output comprises visual data selected from bar graphs, frequency graphs, and/or audio signals.

17. The portable and compact cell-free bioprocessing system according to claim 1 , further comprising a microfluidic mixer positioned between the protein expression module and the protein purification module to mix expressed protein with buffer.

18. The portable and compact cell-free bioprocessing system according to claim 1 , wherein UV and pressure sensor profiles are used to estimate purity and concentration of the on-demand synthesized protein, detect production deviations, and reject a batch of the on-demand synthesized protein.

19. A method of analyzing the purity and quality of an on-demand synthesized protein produced in the bioprocessing system of claim 1 , the method comprising:

obtaining at least pressure and UV sensor data from the purification module for the on-demand synthesized protein;

transmitting the data to a computer aided classification system;

extracting features from the data with the computer aided classification system to classify the on-demand synthesized protein and process conditions, wherein extracted features characterize the on-demand synthesized protein and such sample characterization is compared to previously characterized extracted features to provide classified features of the on-demand synthesized protein; and

applying an unsupervised clustering process to the classified features to provide a plurality of output clusters to provide enhanced identification of the on-demand synthesized protein during the process.