Multipath Adaptive Gated Bottleneck Latent ODE with Raman Data Fusion for Cell Culture Process Forecasting

2026-06-24

AI Summary

Accurate multi-day prediction of key parameters in mammalian cell culture remains challenging due to sparse measurements, heterogeneous operating conditions, and trajectory divergence in later phases. This work proposes an adaptive framework that integrates a Gated Bottleneck Latent Ordinary Differential Equation (GB-Latent ODE) with Multi-Path Just-In-Time Fine-Tuning (MP-JIT-FT), and for the first time effectively incorporates Raman spectroscopy-based soft sensor pseudo-observations. The approach enhances sparse data modeling through variable-level learnable gating and mask-aware bottleneck mechanisms, and generates confidence-weighted multi-path probabilistic forecasts via local trajectory clustering, thereby overcoming the limitations of single-point average predictions. Evaluated on 38 fed-batch bioreactor runs (5 L scale), the method outperforms the global Latent ODE baseline on 8 out of 9 target variables, achieving the best average performance; multi-path prediction yields substantial gains in scenarios with early similarity and late divergence, while Raman integration is most effective when early dynamics are representative.

Abstract

Mammalian cell-culture processes underpin the manufacture of many biopharmaceuticals, yet keeping a run on track is hard: critical process parameters drift over days, and an off-specification trend is often confirmed too late to intervene. Early-stage, multi-day forecasts could enable timely adjustment of feeding, sampling, and control, but bioprocess forecasting is challenging because measurements are sparse and irregularly sampled, operating conditions are heterogeneous across cell lines and media, and runs with near-identical early behaviour can diverge into different futures. We propose an adaptive framework combining a Gated Bottleneck Latent Ordinary Differential Equation (GB-Latent ODE) with Multi-Path Just-In-Time Fine Tuning (MP-JIT-FT). The GB-Latent ODE augments the stan dard Latent ODE with learnable variable-wise gating and a mask-aware bottleneck that compress high-dimensional sparse inputs, improving learning under limited data. Given a partially observed run, MP-JIT-FT retrieves similar historical trajectories, clusters the local neighbourhood into candidate regimes, and fine-tunes a separate model per regime to produce multiple plausible paths, each with a reconstruction-based confidence score, not a single averaged forecast. We further fuse Raman spectroscopy data: a machine-learning soft sensor turns dense Raman spectra into pseudo-observations that enrich the sparse offline measurements for more robust training. On 38 fed-batch 5L bioreactor runs spanning 14 conditions, MP-JIT-FT with Raman fusion achieves the best average rank and outperforms a global Latent ODE baseline on 8 of 9 target variables. Using local-divergence metrics, we show the multi-path gains are largest when locally similar prefixes diverge, whereas Raman fusion helps most when early dynamics are representative of later behaviour.

Problem

• bioprocess forecasting
• sparse measurements
• heterogeneous conditions
• trajectory divergence
• early intervention

Innovation

• Latent ODE
• Multi-Path Forecasting
• Raman Data Fusion
• Gated Bottleneck
• Just-In-Time Fine Tuning