Deep learning is emerging in many industrial sectors in hand with big data analytics to streamline production. In the biomanufacturing sector, big data infrastructure is lagging comparatively to other industries. A promising approach is to combine Deep Neural Networks (DNN) with prior knowledge in Hybrid Neural Network (HNN) workflows that are less dependent on the quality and quantity of data. This paper reviews published articles over the past 30 years on the topic of HNN applications to bioprocesses. It revealed that HNNs were applied to various bioprocesses, including microbial cultures, animal cells cultures, mixed microbial cultures, and enzyme biocatalysis. HNNs were mainly applied for process analysis, process monitoring, development of software sensors, open- and closed-loop control, batch-to-batch control, model predictive control, intensified design of experiments, quality-by-design, and recently for the development of digital twins. Most previous HNN studies combined shallow Feedforward Neural Networks (FFNNs) with physical laws, such as macroscopic material balance equations, following the semiparametric design principle. Only recently, deep HNNs based on deep FFNNs, Convolution Neural Networks (CNN), Long Short-Term Memory (LSTM) networks and Physics Informed Neural Networks (PINNs) have been reported. The biopharma sector is currently a major driver but applications to biologics quality attributes, new modalities, and downstream processing are significant research gaps.

This study conducted an extensive analysis of campylobacteriosis surveillance in Portugal from 2009 to 2021, aiming to investigate demographic shifts, seasonal variations, and antimicrobial resistance (AMR) within Campylobacter isolates. Surveillance network and sentinel laboratory-based system data revealed a substantial under-notification of campylobacteriosis cases, suggesting an underestimated disease burden. A paradigm shift was observed in notification rates, with a notable prevalence among the pediatric population, particularly in children aged 1-4 years, diverging from European reports. However, the study also highlighted an emerging trend of Campylobacter infections in younger adults (15-44 years). The study unveiled a unique seasonal distribution of cases, defying typical summer peaks seen elsewhere. AMR analysis revealed extremely to very high-level resistance to ciprofloxacin and tetracycline, both in C. jejuni (93.7% and 79.2%, respectively) and in C. coli (96.5% and 93.2%, respectively), stable throughout the studied period (2013-2021). C. coli also exhibited significantly higher resistance to erythromycin, gentamicin, ampicillin, amoxicillin-clavulanic acid (decreased resistance), and ertapenem compared to C. jejuni (P<0.001). In conclusion, the study highlights the need for enhanced surveillance efforts and emphasizes worrying AMR levels. The implementation of WGS-based surveillance is recommended to attain a more profound comprehension of disease patterns and the evolving landscape of AMR.