Data-driven predictive modeling for cell line selection in biopharmaceutical production

1 . A method for facilitating selection of a cell line, from among a plurality of candidate cell lines that produce recombinant proteins, the method comprising:

measuring, using an opto-electronic cell line generation and analysis system comprising an analytical unit and a cell line generation and growth unit, a first plurality of attribute values for the plurality of candidate cell lines by performing a plurality of optical and assay measurements for the plurality of candidate cell lines, wherein performing the plurality of optical and assay measurements for the plurality of candidate cell lines includes measuring, using the analytical unit, at least cell counts and cell productivity scores at a plurality of physically isolated pens in the opto-electronic cell line generation and analysis system;

generating, using the opto-electronic cell line generation and analysis system, cells of the plurality of candidate cell lines, at least by moving individual cells into different pens of the plurality of physically isolated pens with one or more photoconductors activated by light patterns, wherein the individual cells are maintained within their respective pens throughout a cell line generation and analysis process;

acquiring, by one or more processors, a second plurality of attribute values for the plurality of candidate cell lines, wherein the second plurality of attribute values includes one or more attribute values measured at a cell pool screening stage of the plurality of candidate cell lines;

determining, by one or more processors, a ranking of the plurality of candidate cell lines according to a product quality attribute associated with hypothetical small-scale screening cultures for the plurality of candidate cell lines, wherein determining the ranking includes (i) predicting, for each of the plurality of candidate cell lines, a value of the product quality attribute by analyzing the first plurality of attribute values and the second plurality of attribute values using a machine learning based regression estimator, and (ii) comparing the predicted values; and

causing an indication of the ranking to be presented to a user via a user interface.

2 . The method of claim 1 , wherein measuring the first plurality of attribute values includes measuring:

a first attribute value corresponding to a first measurement of an attribute; and

a second attribute value corresponding to a second measurement of the attribute, the first measurement and the second measurement occurring on different days of the cell line generation and analysis process.

3 . The method of claim 1 , wherein acquiring the second plurality of attribute values includes receiving one or more of:

a measured cell pool titer;

a measured cell pool viable cell density (VCD); or

a measured cell pool viability.

4 . The method of claim 1 , wherein acquiring the second plurality of attribute values includes receiving attribute values measured on different days of the cell pool screening stage.

5 . The method of claim 1 , wherein the one or more product quality attributes include a cell growth metric.

6 . The method of claim 1 , wherein the one or more product quality attributes include one or more of (i) a titer or (ii) a specific productivity metric.

7 . The method of claim 1 , wherein:

determining the ranking includes determining the ranking according to titer, at least by (i) predicting, for each of the plurality of candidate cell lines, a titer by analyzing the first plurality of attribute values and the second plurality of attribute values using the machine learning based regression estimator, and (ii) comparing the predicted titers;

the first plurality of attribute values includes a value based on a cell productivity score; and

the second plurality of attribute values includes a value based on a cell pool titer.

8 . The method of claim 7 , wherein predicting the titer includes analyzing the first plurality of attribute values using a Ridge regression estimator.

9 . The method of claim 1 , wherein:

determining the ranking includes determining the ranking according to specific productivity, at least by (i) predicting, for each of the plurality of candidate cell lines, a specific productivity metric by analyzing the first plurality of attribute values and the second plurality of attribute values using the machine learning based regression estimator, and (ii) comparing the predicted specific productivity metrics;

the first plurality of attribute values includes a value based on a cell productivity score and a value based on cell count; and

the second plurality of attribute values includes a value based on cell pool titer.

10 . The method of claim 9 , wherein predicting the specific productivity metric includes using a Principal Component Analysis (PCA) regression estimator with two principal components.

11 . The method of claim 1 , wherein:

determining the ranking includes determining the ranking according to cell growth, at least by (i) predicting, for each of the plurality of candidate cell lines, a cell growth metric by analyzing the first plurality of attribute values and the second plurality of attribute values using the machine learning based regression estimator, and (ii) comparing the predicted cell growth metrics;

the first plurality of attribute values includes a value based on cell count; and

the second plurality of attribute values includes a value based on cell pool titer, a value based on cell pool time integral viable cell density (iVCD), a value based on cell pool viable cell densities (VCD) at different days, and a value based on cell pool viability at different days.

12 . The method of claim 11 , wherein predicting the cell growth metric includes using a Partial Least Squares (PLS) regression estimator with one principal component.

13 . The method of claim 1 , wherein the method further comprises evaluating performance of the machine learning based regression estimator at least by calculating a Spearman's rho or average Spearman's rho for the machine learning based regression estimator.

14 . The method of claim 1 , wherein the method further comprises:

based on the ranking, advancing one or more cell lines of the plurality of candidate cell lines to a next stage of cell line screening.

15 . The method of claim 14 , wherein the next stage of cell line screening is a fedbatch cell culture stage.

16 . A method for facilitating selection of a master cell line from among candidate cell lines that produce recombinant proteins, the method comprising:

receiving, by one or more processors of a computing system, a plurality of attribute values associated with a small-scale cell culture for a specific cell line, wherein at least some of the plurality of attribute values are measurements of the small-scale cell culture captured by performing a plurality of optical and assay measurements for the plurality of candidate cell lines, the plurality of optical and assay measurements for the plurality of candidate cell lines include at least measured cell counts and measured cell productivity scores at a plurality of physically isolated pens of an opto-electronic cell line generation and analysis system,

wherein performing the plurality of optical and assay measurements includes using the opto-electronic cell line generation and analysis system to (i) generate cells of the plurality of candidate cell lines, at least by moving individual cells into different pens of the plurality of physically isolated pens with one or more photoconductors activated by light patterns, and (ii) maintain the individual cells within their respective pens throughout a cell line generation and analysis process;

predicting, by the one or more processors, one or more attribute values associated with a hypothetical large-scale cell culture for the specific cell line, at least by analyzing the plurality of attribute values associated with the small-scale cell culture using a machine learning based regression estimator, wherein the predicted one or more attribute values include a titer and/or one or more product quality attribute values; and

causing, by the one or more processors, one or both of (i) the predicted one or more attribute values, and (ii) an indication of whether the predicted one or more attribute values satisfy one or more cell line selection criteria, to be presented to a user via a user interface to facilitate selection of the master cell line for use in drug product manufacturing.