Integration of just-in-time learning with variational autoencoder for cell culture process monitoring based on Raman spectroscopy.

Protein production in the biopharmaceutical industry necessitates the utilization of multiple analytical techniques and control methodologies to ensure both safety and consistency. To facilitate real-time monitoring and control of cell culture processes, Raman spectroscopy has emerged as a versatile analytical technology. This technique, categorized as a Process Analytical Technology, employs chemometric models to establish correlations between Raman signals and key variables of interest. One notable approach for achieving real-time monitoring is through the application of just-in-time learning (JITL), an industrial soft sensor modeling technique that utilizes Raman signals to estimate process variables promptly. The conventional Raman-based JITL method relies on the K-nearest neighbor (KNN) algorithm with Euclidean distance as the similarity measure. However, it falls short of addressing the impact of data uncertainties. To rectify this limitation, this study endeavors to integrate JITL with a variational autoencoder (VAE). This integration aims to extract dominant Raman features in a nonlinear fashion, which are expressed as multivariate Gaussian distributions. Three experimental runs using different cell lines were chosen to compare the performance of the proposed algorithm with commonly utilized methods in the literature. The findings indicate that the VAE-JITL approach consistently outperforms partial least squares, convolutional neural network, and JITL with KNN similarity measure in accurately predicting key process variables.

Cell culture product quality attribute prediction using convolutional neural networks and Raman spectroscopy.

Advanced process control in the biopharmaceutical industry often lacks real-time measurements due to resource constraints. Raman spectroscopy and Partial Least Squares (PLS) models are often used to monitor bioprocess cultures in real-time. In spite of the ease of training, the accuracy of the PLS model is impacted if it is not used to predict quality attributes for the cell lines it is trained on. To address this issue, a deep convolutional neural network (CNN) is proposed for offline modeling of metabolites using Raman spectroscopy. By utilizing asymmetric least squares smoothing to adjust Raman spectra baselines, a generic training data set is created by amalgamating spectra from various cell lines and operating conditions. This data set, combined with their derivatives, forms a two-dimensional model input. The CNN model is developed and validated for predicting different quality variables against measurements from various continuous and fed-batch experimental runs. Validation results confirm that the deep CNN model is an accurate generic model of the process to predict real-time quality attributes, even in experimental runs not included in the training data. This model is robust and versatile, requiring no recalibration when deployed at different sites to monitor various cell lines and experimental runs.

Machine learning-based model predictive controller design for cell culture processes.

The biopharmaceutical industry continuously seeks to optimize the critical quality attributes to maintain the reliability and cost-effectiveness of its products. Such optimization demands a scalable and optimal control strategy to meet the process constraints and objectives. This work uses a model predictive controller (MPC) to compute an optimal feeding strategy leading to maximized cell growth and metabolite production in fed-batch cell culture processes. The lack of high-fidelity physics-based models and the high complexity of cell culture processes motivated us to use machine learning algorithms in the forecast model to aid our development. We took advantage of linear regression, the Gaussian process and neural network models in the MPC design to maximize the daily protein production for each batch. The control scheme of the cell culture process solves an optimization problem while maintaining all metabolites and cell culture process variables within the specification. The linear and nonlinear models are developed based on real cell culture process data, and the performance of the designed controllers is evaluated by running several real-time experiments.

Background noise disrupts host-parasitoid interactions.

The soundscape serves as a backdrop for acoustic signals dispatched within and among species, spanning mate attraction to parasite host detection. Elevated background sound levels from human-made and natural sources may interfere with the reception of acoustic signals and alter species interactions and whole ecological communities. We investigated whether background noise influences the ability of the obligate parasitoid Ormia ochracea to locate its host, the variable field cricket (Gryllus lineaticeps). As O. ochracea use auditory cues to locate their hosts, we hypothesized that higher background noise levels would mask or distract flies from cricket calls and result in a decreased ability to detect and navigate to hosts. We used a field manipulation where fly traps baited with playback of male cricket advertisement calls were exposed to a gradient of experimental traffic and ocean surf noise. We found that increases in noise amplitude caused a significant decline in O. ochracea caught, suggesting that background noise can influence parasitoid-host interactions and potentially benefit hosts. As human-caused sensory pollution increases globally, soundscapes may influence the evolution of tightly co-evolved host-parasitoid relationships. Future work should investigate whether female cricket phonotaxis towards males is similarly affected by noise levels.

Advances in industrial biopharmaceutical batch process monitoring: Machine-learning methods for small data problems.

Biopharmaceutical manufacturing comprises of multiple distinct processing steps that require effective and efficient monitoring of many variables simultaneously in real-time. The state-of-the-art real-time multivariate statistical batch process monitoring (BPM) platforms have been in use in recent years to ensure comprehensive monitoring is in place as a complementary tool for continued process verification to detect weak signals. This article addresses a longstanding, industry-wide problem in BPM, referred to as the "Low-N" problem, wherein a product has a limited production history. The current best industrial practice to address the Low-N problem is to switch from a multivariate to a univariate BPM, until sufficient product history is available to build and deploy a multivariate BPM platform. Every batch run without a robust multivariate BPM platform poses risk of not detecting potential weak signals developing in the process that might have an impact on process and product performance. In this article, we propose an approach to solve the Low-N problem by generating an arbitrarily large number of in silico batches through a combination of hardware exploitation and machine-learning methods. To the best of authors' knowledge, this is the first article to provide a solution to the Low-N problem in biopharmaceutical manufacturing using machine-learning methods. Several industrial case studies from bulk drug substance manufacturing are presented to demonstrate the efficacy of the proposed approach for BPM under various Low-N scenarios.

Retinal Structure in Cobalamin C Disease: Mechanistic and Therapeutic Implications.

PURPOSE: To describe the retinal structure in a patient with cobalamin C (cblC) disease. METHODS: A 13-year-old male patient diagnosed with cblC disease during a perinatal metabolic screening prompted by jaundice and hypotony underwent ophthalmic examinations, electroretinography (ERG) and spectral domain optical coherence tomography (SD-OCT). RESULTS: The patient carried a homozygous (c.271dupA) mutation in the methylmalonic aciduria and homocystinuria type C (MMACHC) gene. At age 3 months he had a normal eye exam. A pigmentary maculopathy progressed to chorioretinal atrophy from 5-10 months. ERG at 7 months was normal. A nystagmus remained stable since the age of 2 years. At age 13, visual acuity was 20/250 (right eye) and 20/400 (left eye), with a +5.00 D correction, a level of vision maintained since first measurable at age 5 years. SD-OCT showed bilateral macular coloboma-like lesions; there was also a thickened surface layer with ganglion cell layer thinning. Photoreceptor outer segment loss and thinning of the outer nuclear layer (ONL) transitioned to regions with no discernible ONL with a delaminated, thickened, inner retina. CONCLUSIONS: A thick surface layer near the optic nerve resembling an immature retina and an initially normal macula that rapidly developed coloboma-like lesions suggest there may be an interference with retinal/foveal development in cblC, a mechanism of maculopathy that may be shared by other early onset retinal degenerations. Photoreceptor loss and inner retinal remodeling confirm associated photoreceptor degeneration.