Mixing & hydrodynamics, mass transfer / kLa / OTR, shear & gradients, geometry and operating conditions change.
BioAna Twin
Predict & simulate. From bench to scale.
Modality-native predictive and simulation intelligence for biologics, cell therapy, gene therapy, fermentation and RNA/oligo processes — connecting physics, process data and AI/ML so teams can understand, predict, simulate and decide with confidence.
SCENARIO ENGINE2,000 L → 10,000 L
SCIENTIFIC CONSTRAINTSkLa ≥ 8.5 h⁻¹Tip speed ≤ 6.2 m/sDO ≥ 30%
PROCESS RESPONSE
SCALE-UP SCENARIO
Candidate Baseline Confidence
REVIEWABLE RECOMMENDATIONCandidate operating regionConfidence · high
✓Evidence attached · model v2.1 · scientist approval required
01 — THE OPPORTUNITY
“Bioprocess development is still constrained by physical experimentation. Complex biology makes every run valuable, but much of what is learned remains difficult to reuse.”
Today, teams rely on run → analyze → learn → adjust — another physical run to validate the next change. That means more experiments, slower learning and knowledge fragmented across data, models and SME memory. The opportunity: learn more from every run, and predict before the next one.
02 — SCALE CHANGES MORE THAN THE REACTOR
The engineering changes.
Biology responds.
Quality follows.
From bench and development scale, through pilot, to commercial scale — the scale-up challenge is finding the operating conditions that preserve biology and product quality as the engineering environment changes.
Growth & viability, metabolism, lactate & ammonia and cellular stress respond.
Titer & yield, CQAs, batch consistency and process robustness emerge.
SAME MODEL · SAME CONSTRAINTS · CARRIED EVIDENCE
2 LBENCH
High mixing homogeneity · short gradients · kLa headroom
200 LPILOT
Longer mixing times · emerging pCO₂ and DO gradients
2,000 LMANUFACTURING
Scale-limited OTR · shear and gradient trade-offs dominate
03 — SCIENTIFICALLY CONSTRAINED
Physics constrains. Data grounds.
AI learns. Science guides.
BioAna combines physics, process history, AI/ML and domain knowledge to predict what is likely to happen before the next run.
Physics
Mixing · mass transfer · shear · scale effects
Data
Historical runs · process conditions · biology · quality
AI / ML
Learn relationships · predict outcomes · explore scenarios
Domain knowledge
Biology · constraints · SME expertise
Performance titer / yieldQuality CQAsOperating window recommended conditionsConfidence uncertainty / risk
04 — HUB + TWIN, THE CLOSED LOOP
A digital twin is only as good
as the context behind it.
BioAna Hub continuously connects, contextualizes and aligns process data so BioAna Twin can predict, simulate and improve with every run — governed end to end by BioAna OS.
Connect
Bioreactors, historians, PAT, ELN/LIMS, MES and lab data.
Hub: contextualize
Run alignment, equipment context, process + quality data.
Twin: predict & simulate
Scale-up, what-if scenarios, operating windows.
Decide
Scientist/engineer compares scenarios and selects conditions.
Learn
New run, new evidence feeds back into the loop.
BioAna OS
Security, governance, auditability and model lifecycle throughout.
05 — MODALITY-SPECIFIC INTELLIGENCE
One platform.
Different science by modality.
BioAna Twin keeps the platform core consistent while adapting scientific context, models and decision logic to each modality it predicts for.
Biologics
Understands: Growth & viability · kLa/OTR/mass transfer · mixing & scale effects · CPP → CQA relationships
Predicts: Titer / yield · CQAs · scale-up behavior · operating window · confidence
Cell therapy
Understands: Growth & viability · phenotype evolution · transduction/editing efficiency · donor variability
Predicts: Expansion yield · phenotype/composition shifts · potency indicators · confidence
Gene therapy
Understands: Vector production kinetics · transfection efficiency · multiplicity/dose effects · batch variability
Predicts: Vector yield · quality attributes · potency indicators · scale-up behavior
Fermentation
Understands: Growth kinetics · substrate uptake · oxygen demand · overflow metabolism · scale effects
Predicts: Biomass / yield · product titer · OUR/OTR limits · feed trajectory · productivity
RNA & Oligo
Understands: Reaction efficiency · impurity formation · purification performance · batch variability
Predicts: Yield · purity · impurity profile · product quality attributes · confidence
Multi-program
Understands: Client, program and modality context preserved across a shared platform core
Predicts: Program-specific models and predictions within governed tenant boundaries
06 — PREDICTION WITH A REASON
Show the prediction.
Show what holds it up.
BioAna Twin keeps predictions connected to experimental evidence, process constraints, model version and uncertainty—so teams can challenge the answer before acting on it.
Evidence selected historical runsConstraints engineering + biologyReview required before action
Predicted outcomeObserved evidenceConfidence region
Normalized process responseCulture duration
Day 0Day 3Day 6Day 9Day 12Harvest
MODELED OPERATING REGIONConstrained by oxygen-transfer and shear limits
07 — SEE THE WHOLE SPACE
The answer isn't a number.
It's a region.
Single-point predictions hide the trade-offs. Twin maps predicted performance across the full operating space — showing where the process is robust, where it is fragile, and where the next experiment would teach the most.
- Predicted response surface across CPP combinations
- Historical runs overlaid on the same coordinates
- Recommended exploration region with uncertainty attached
08 — REAL PRODUCT
A decision workflow.
Not a model gallery.
What changes when process assumptions move?
Day-by-day prediction of titer, viability and glycoforms with a disclosed uncertainty band — before any material is committed.
app.bioana.ai/twinBIOANA TWIN
PROGRAMmAb IgG1 · CHO fed-batchDECISION2,000 L → 10,000 L transferOBJECTIVEQuality Objective BSCREEN01 · Process Simulation
Process Simulation
Day-by-day trajectory prediction with disclosed uncertainty
Scenario InputsCOMMERCIAL-LIKE
Scale10,000 L
Agitation57 RPM
Aeration0.206 vvm
DO setpoint45 %
Temperature37.0 → 34.5 °C
pH7.00 constant
Glucose strategyStandard fed-batch
Harvest dayDay 14
GUIDED SCENARIOSBaseline 2K transferCooler production phaseAggressive feedpH shift day 6
Predicted Trajectory±8.1% uncertainty · model v2.1
Titer (normalized)ViabilityConfidence band
Day 0Day 3Day 6Day 9Day 12Harvest
Titer2.451 g/L±0.19
Viability91.9 %
G0 / G1 / G239 / 34 / 21 %
Lactate1.8 g/L
Ammonia3.1 mM
Quality score87 / 100vs. Objective B
09 — TRY IT YOURSELF
Move the levers.
Watch the trade-offs move too.
This sandbox mirrors how BioAna Twin frames a scenario — inputs on the left, predicted response on the right, and a confidence signal attached to every result. No data leaves this page and nothing writes back to a control system.
SCENARIO 04 · SCIENTIST SANDBOXSimulation only
Explore the operating space. No control-system writeback occurs from this demo.
Bench
2,000 L
Predicted titer4.95 g/L
End viability91.1%
Model confidence90%
Operating-window signalPromising · review
SCIENTIST REVIEWCandidate operating region
Feed +4% · DO ≥ 32% · agitation constrained
Evidence attachedModel v2.1Review required
10 — HUMAN-GOVERNED
Intelligence proposes.
Science decides.
BioAna produces evidence-linked recommendations with uncertainty, review context and approval gates—not invisible automation.
Explore governance ↗11 — ONE PLATFORM, MANY DECISIONS
The same intelligence foundation.
Development through manufacturing.
BioAna applies the same connected data, modality context and predictive intelligence across the full process lifecycle — and into manufacturing support for deviations, root-cause analysis and continuous improvement.
Design better experiments
Predict larger-scale behavior
Tune operating conditions
Anticipate CQAs and performance
Carry process knowledge forward
12 — THE EXPERIMENTAL DIVIDEND
Run the sweep virtually.
Spend the reactor time where it counts.
A physical DoE across feed, DO and agitation can consume a quarter of experiments. Twin sweeps that space in silico against models, physics constraints and prior evidence — so the committed runs are chosen, not guessed.
120+
01Scenarios explored in silico
Feed, DO, agitation, temperature and scale combinations simulated against models and prior evidence
12
02Candidate conditions
Ranked by predicted outcome, uncertainty and engineering constraint headroom
3
03Physical runs committed
High-value experiments approved through governed scientist review
Illustrative workflow — the point is the shape: explore widely in silico, commit narrowly in the lab.
Start with one decision
Make process uncertainty visible.
Define the evidence, physics, model and validation path needed to support your next scale-up, transfer or PPQ decision.
Design a Twin pilot ↗