Automated system for HTP genomic engineering
The present disclosure provides a HTP microbial genomic engineering platform that is computationally driven and integrates molecular biology, automation, and advanced machine learning protocols. This integrative platform utilizes a suite of HTP molecular tool sets to create HTP genetic design libraries, which are derived from, inter alia, scientific insight and iterative pattern recognition. The HTP genomic engineering platform described herein is microbial strain host agnostic and therefore can be implemented across taxa. Furthermore, the disclosed platform can be implemented to modulate or improve any microbial host parameter of interest.
1. An automated system for engineering a host cell with a combination of genetic alterations, comprising:
i) a memory;
ii) a processor in communication with the memory, the processor configured to:
a) populate a machine learning model with a training data set, containing: input variables representing a plurality of genetic alterations that have been introduced into a host cell, and output variables representing phenotypic measurements associated with the genetic alterations;
b) generate, in silico, a pool of design candidate host cells incorporating at least two genetic alterations from the plurality of genetic alterations;
c) utilize the machine learning model to predict an expected phenotypic metric of a member of the pool of design candidate host cells that comprises a combination of genetic alterations selected from step (a), said combination being uncharacterized for its effect on the phenotypic metric at the time of carrying out step (c); and
iii) automated robotics in communication with the processor.
2. The automated system of claim 1 , wherein the automated robotics comprise: a DNA synthesis module, cloning module, transformation module, culturing module, screening module, sequencing module, or combination thereof.
3. The automated system of claim 1 , wherein the automated robotics are configured to manufacture a member of the pool of design candidate host cells.
4. The automated system of claim 1 , wherein the automated robotics comprise: liquid or particle handlers that enable manipulation of liquid or particles added to or removed from cultures comprising the host cells.
5. The automated system of claim 1 , wherein the automated robotics comprise: one or more robotic arms.
6. The automated system of claim 1 , wherein the automated robotics comprise: integrated thermal cyclers.
7. The automated system of claim 1 , where the automated robotics comprise: an electroporation system.
8. The automated system of claim 1 , wherein the automated robotics comprise: plate handlers, plate sealers, plate piercers, lid handlers, disposable tip assemblies, washable tip assemblies, 96 well loading blocks, cooled reagent racks, microtiter plate pipette positions, cooled microtiter plate pipette positions, stacking towers for plates and tips, magnetic bead processing stations, filtrations systems, plate shakers, barcode readers and applicators, computer systems, or combinations thereof.
9. The automated system of claim 1 , wherein the automated robotics comprise liquid or particle handlers and the processor is configured to send a signal to the liquid or particle handler robotics to cause the liquid or particle handler robotics to conduct: liquid or particle manipulation, aspiration, dispensing, mixing, diluting, washing, volumetric transfers, retrieving of pipette tips, discarding of pipette tips, and/or repetitive pipetting.
10. The automated system of claim 1 , wherein the automated robotics are compatible with multi-well plates, deep-well plates, square well plates, reagent troughs, test tubes, mini tubes, microfuge tubes, cryovials, filters, microarray chips, optic fibers, beads, agarose gel, acrylamide gel, solid-phase matrices, or combinations thereof.
11. The automated system of claim 1 , wherein the machine learning model incorporates at least one of the following: linear regression, kernel ridge regression, logistic regression, neural networks, support vector machines (SVMs), decision trees, hidden Markov models, Bayesian networks, a Gram-Schmidt process, reinforcement-based learning, cluster-based learning, hierarchical clustering, genetic algorithms, or combinations thereof.
12. The automated system of claim 1 , wherein the machine learning model incorporates epistatic effects.
13. The automated system of claim 1 , wherein the machine learning model is supervised, semi-supervised, or unsupervised.
14. The automated system of claim 1 , wherein the plurality of genetic alterations are selected from the group consisting of: a single nucleotide polymorphism, nucleotide sequence insertion, nucleotide sequence deletion, and nucleotide sequence replacement.
15. The automated system of claim 1 , wherein the plurality of genetic alterations comprise one or more promoters.
16. The automated system of claim 1 , wherein the plurality of genetic alterations comprise one or more heterologous promoters from a promoter ladder operably linked to an endogenous target gene.
17. The automated system of claim 1 , wherein the plurality of genetic alterations comprise genetic alterations from a library selected from the group consisting of: a promoter swap library, a SNP swap library, a start/stop codon library, an optimized sequence library, a terminator swap library, and combinations thereof.
18. The automated system of claim 1 , wherein the expected phenotypic metric is production of a product of interest, said product of interest selected from the group consisting of: a small molecule, enzyme, protein, peptide, amino acid, organic acid, synthetic compound, fuel, alcohol, primary extracellular metabolite, secondary extracellular metabolite, intracellular component molecule, and combinations thereof.
19. A computerized system for designing a host cell to have a beneficial combination of genetic alterations, comprising:
i) a memory;
ii) a processor in communication with the memory, the processor configured to:
a) populate a machine learning model with a training data set, containing: a plurality of genetic alteration input variables representing a plurality of genetic alterations that have been introduced into a host cell, and a plurality of experimentally validated phenotypic performance output variables representing phenotypic performance measurements associated with the plurality of introduced genetic alterations;
b) generate, in silico, a pool of genetic alteration designs that can be incorporated into candidate host cells, at least one genetic alteration design of the pool comprising a combination of genetic alterations that is uncharacterized for improving phenotypic performance at the time of generating the pool of genetic alteration designs; and
c) utilize the machine learning model to predict an expected phenotypic performance metric of a candidate host cell that comprises a genetic alteration design from said pool.
20. The computerized system of claim 19 , wherein the machine learning model incorporates at least one of the following: linear regression, kernel ridge regression, logistic regression, neural networks, support vector machines (SVMs), decision trees, hidden Markov models, Bayesian networks, a Gram-Schmidt process, reinforcement-based learning, cluster-based learning, hierarchical clustering, genetic algorithms, or combinations thereof.
21. The computerized system of claim 19 , wherein the machine learning model incorporates epistatic effects.
22. The computerized system of claim 19 , wherein the machine learning model is supervised, semi-supervised, or unsupervised.
23. The computerized system of claim 19 , wherein the plurality of genetic alterations are selected from the group consisting of: a single nucleotide polymorphism, nucleotide sequence insertion, nucleotide sequence deletion, and nucleotide sequence replacement.
24. The computerized system of claim 19 , wherein the plurality of genetic alterations comprise one or more promoters.
25. The computerized system of claim 19 , wherein the plurality of genetic alterations comprise one or more heterologous promoters from a promoter ladder operably linked to an endogenous target gene.
26. The computerized system of claim 19 , wherein the plurality of genetic alterations comprise genetic alterations from a library selected from the group consisting of: a promoter swap library, a SNP swap library, a start/stop codon library, an optimized sequence library, a terminator swap library, and combinations thereof.
27. The computerized system of claim 19 , wherein the expected phenotypic performance metric is production of a product of interest, said product of interest selected from the group consisting of: a small molecule, enzyme, protein, peptide, amino acid, organic acid, synthetic compound, fuel, alcohol, primary extracellular metabolite, secondary extracellular metabolite, intracellular component molecule, and combinations thereof.