CHO clone demo

Choose better clones for the next run

Start with clone measurements over time. Compare growth, product, waste, model fit, and how the selection score changes as the model learns.

Synthetic demo. No confidential data used. All data is generated for the demo. The page calculates screen metrics in the browser and loads a precomputed CHO model review.

Page 1 of 8

Data gathered

Start from the longitudinal measurements collected in a first-pass clone screen.

Page 1 data gathered

Every clone starts as raw measurements over time

The synthetic screen contains 50 clones, 2 replicates, and 7 measured days. VCD means viable cell density: the concentration of living cells in the culture, shown as 10^6 viable cells/mL.

VCDLiving-cell concentration over time. It drives IVCD and productivity calculations.
FeedsGlucose and glutamine additions between samples. They are needed for fed-batch mass balance.
Long tableOne row per clone, replicate, and day, so the demo keeps the raw observations auditable.

Metric direction explorer

Clone calculation workbench

Clone

Interval calculations

Calculations use consecutive measured timepoints

Metric directions

Compare clones before any ranking decision

Raw measurements over time

All 50 clones are visible; the selected clone is highlighted

Final decision

Final clone ranking after CHO model review

Selection comparison

Screen-only, CHO model, and final top 5

Learning feature matrix

Each clone gets the same derived parameters before the model updates the score

Heuristic starting score

Score v1 is editable because it starts as an assumption

Interactive prediction

Manual weights are tested against a real measured target

Hypothesis search

Metastate searches for functions that predict the target better

Score update

Accepted hypotheses become subscores for Score v2

Internal optimization cycles

The digital twin keeps updates that improve concordance

Updated ranking

Score v2 changes the next-cycle shortlist

FBA-ready constraints

Screen-derived rates become model bounds for each clone

CHO model

CHO model review across all clones

Final recommendation

Run the normal 5-clone follow-up, but monitor clone-specific failure modes

Export evidence

Download the data behind the story

Formula drawer and units
IVCDsum((VCD_start + VCD_end) / 2 * days_between_samples)Area under the living-cell curve. This tells us how many viable cells were available to make product.
qPproduct made / IVCDProduct made per living cell per day. This separates true productivity from simply having more cells.
Feed-corrected glucosestart glucose + feed added - end glucoseIn fed-batch data, feed additions must be counted before calling a concentration drop consumption.
Metabolite rateconcentration change / interval IVCDUptake and secretion rates are calculated between measured days, then summarized for the production window.
FBA unit conversionpmol/cell/day -> mmol/gDW/hUses the explicit dry-cell-weight assumption so process rates can be displayed as model bounds.
Uncertainty boundsmeasured rate +/- 20%Bounds use ranges because exact constraints would overstate measurement precision.
Assumptions and limitations

Assumptions: dry cell weight 330 pg/cell, mAb molecular weight 150 kDa, uncertainty bounds +/-20%, feed represented as mM-equivalent added since previous sample.

Limitations: this v1 does not run a full CHO genome-scale model in the browser. It does not claim exact intracellular flux prediction from endpoint data. The score improves with amino-acid panels, oxygen and CO2 signals, replicate metadata, and real process context.

Current FBA layer: the demo uses CHO.net 1.2 with native CHO exchange reactions and a native mAb product reaction to review measured clone behavior. For a production scientific package, replace or extend the compact model with the approved CHO model for the specific cell line and process.

Raw long table

All clone observations with units