HTP genomic engineering platform
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. A computer-implemented high-throughput method of genomic engineering to identify target genes that have a beneficial effect on a phenotypic parameter of interest, comprising:
a) engineering the genome of a plurality of host cells to create a promoter swap host cell library, said library comprising a plurality of host cells with one or more promoters from a promoter ladder operably linked to a plurality of target genes present in the host cell to thereby create a plurality of promoter:gene target combinations,
wherein said promoter ladder comprises a plurality of promoters exhibiting different expression profiles in the host cell;
b) screening members of the plurality of host cells of the promoter swap host cell library by measuring a phenotypic performance metric;
e) creating a data set, comprising: input variables representing particular promoter:gene target combinations, and output variables representing phenotypic performance metric measurements associated with the promoter:gene target combinations; and
d) utilizing a machine learning model to analyze the data set and identify a target gene that has a beneficial effect on a phenotypic parameter of interest.
2. The method of claim 1 , wherein engineering the genome of the plurality of host cells to create a promoter swap host cell library of step a) is conducted with a gene editing technology selected from the group consisting of: ZFNs, TALENS, and CRISPR.
3. The method of claim 1 , wherein engineering the genome of the plurality of host cells to create a promoter swap host cell library of step a) is conducted with a CRISPR gene editing technology.
4. The method of claim 1 , comprising: manufacturing a host cell that comprises the target gene identified in step d).
5. The method of claim 1 , comprising: manufacturing a host cell that comprises a genetic alteration within coding sequence of a target gene identified in step d), said genetic alteration selected from the group consisting of a single nucleotide polymorphism, nucleotide sequence insertion, nucleotide sequence deletion, and nucleotide sequence replacement.
6. The method of claim 1 , comprising: manufacturing a host cell that comprises the target gene identified in step d), said target gene operably linked to one or more heterologous promoters.
7. The method of claim 1 , wherein the target gene identified in step d) is uncharacterized for improving phenotypic performance at the time the analysis is conducted.
8. The method of claim 1 , wherein a combination of at least two target genes are identified in step d), said combination of target genes being uncharacterized for improving phenotypic performance at the time the analysis is conducted.
9. The method of claim 1 , comprising: utilizing a machine learning model to predict expected phenotypic performance of a host cell that comprises a genetic alteration to at least two identified target genes from step d).
10. The method 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.
11. The method of claim 1 , wherein the machine learning model incorporates epistatic effects.
12. The method of claim 1 , wherein the machine learning model is supervised, semi-supervised, or unsupervised.
13. The method of claim 1 , wherein the phenotypic parameter of interest is selected from the group consisting of: volumetric productivity of a product of interest, specific productivity of a product of interest, yield of a product of interest, and titer of a product of interest.
14. The method of claim 1 , wherein the phenotypic parameter of interest is production of a product of interest.
15. The method of claim 1 , wherein the phenotypic parameter of interest 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, and intracellular component molecule.