Rapid total sialic acid monitoring during cell culture process using a machine learning model based soft sensor.

Total sialic acid content (TSA) in biotherapeutic proteins is often a critical quality attribute as it impacts the drug efficacy. Traditional wet chemical assays to quantify TSA in biotherapeutic proteins during cell culture typically takes several hours or longer due to the complexity of the assay which involves isolation of sialic acid from the protein of interest, followed by sample preparation and chromatographic based separation for analysis. Here, we developed a machine learning model-based technology to rapidly predict TSA during cell culture by using typically measured process parameters. The technology features a user interface, where the users only have to upload cell culture process parameters as input variables and TSA values are instantly displayed on a dashboard platform based on the model predictions. In this study, multiple machine learning algorithms were assessed on our dataset, with the Random Forest model being identified as the most promising model. Feature importance analysis from the Random Forest model revealed that attributes like viable cell density (VCD), glutamate, ammonium, phosphate, and basal medium type are critical for predictions. Notably, while the model demonstrated strong predictability by Day 14 of observation, challenges remain in forecasting TSA values at the edges of the calibration range. This research not only emphasizes the transformative power of machine learning and soft sensors in bioprocessing but also introduces a rapid and efficient tool for sialic acid prediction, signaling significant advancements in bioprocessing. Future endeavors may focus on data augmentation to further enhance model precision and exploration of process control capabilities.

Optimizing pharmacogenomic decision-making by data science.

Healthcare systems have made rapid progress towards combining data science with precision medicine, particularly in pharmacogenomics. With the lack of predictability in medication effectiveness from patient to patient, acquiring the specifics of their genotype would be highly advantageous for patient treatment. Genotype-guided dosing adjustment improves clinical decision-making and helps optimize doses to deliver medications with greater efficacy and within safe margins. Current databases demand extensive effort to locate relevant genetic dosing information. To address this problem, Patient Optimization Pharmacogenomics (POPGx) was constructed. The objective of this paper is to describe the development of POPGx, a tool to simplify the approach for healthcare providers to determine pharmacogenomic dosing recommendations for patients taking multiple medications. Additionally, this tool educates patients on how their allele variations may impact gene function in case they need further healthcare consultations. POPGx was created on Konstanz Information Miner (KNIME). KNIME is a modular environment that allows users to conduct code-free data analysis. The POPGx workflow can access Clinical Pharmacogenomics Implementation Consortium (CPIC) guidelines and subsequently be able to present relevant dosing and counseling information. A KNIME representational state transfer (REST) application program interface (API) node was established to retrieve information from CPIC and drugs that are exclusively metabolized through CYP450, and these drugs were processed simultaneously to demonstrate competency of the workflow. The POPGx program provides a time-efficient method for users to retrieve relevant, patient-specific medication selection and dosing recommendations. Users input metabolizer gene, genetic allele data, and medication list to retrieve clear dosing information. The program is automated to display current guideline recommendations from CPIC. The integration of this program into healthcare systems has the potential to revolutionize patient care by giving healthcare practitioners an easy way to prescribe medications with greater efficacy and safety by utilizing the latest advancements in the field of pharmacogenomics.