Hybrid machine learning model based predictions for properties of poly(2-hydroxyethyl methacrylate)-poly(vinyl alcohol) composite cryogels embedded with bacterial cellulose.

Supermacroporous composite cryogels with enhanced adjustable functionality have received extensive interest in bioseparation, tissue engineering, and drug delivery. However, the variations in their components significantly impactfinal properties. This study presents a two-step hybrid machine learning approach for predicting the properties of innovative poly(2-hydroxyethyl methacrylate)-poly(vinyl alcohol) composite cryogels embedded with bacterial cellulose (pHEMA-PVA-BC) based on their compositions. By considering the ratios of HEMA (1.0-22.0 wt%), PVA (0.2-4.0 wt%), poly(ethylene glycol) diacrylate (1.0-4.5 wt%), BC (0.1-1.5 wt%), and water (68.0-96.0 wt%) as investigational variables, overlay sampling uniform design (OSUD) was employed to construct a high-quality dataset for model development. The random forest (RF) model was used to classify the preparation conditions. Then four models of artificial neural network, RF, gradient boosted regression trees (GBRT), and XGBoost were developed to predict the basic properties of the composite cryogels. The results showed that the RF model achieved an accurate three-class classification of preparation conditions. Among the four models, the GBRT model exhibited the best predictive performance of the basic properties, with the mean absolute percentage error of 16.04 %, 0.85 %, and 2.44 % for permeability, effective porosity, and height of theoretical plate (1.0 cm/min), respectively. Characterization results of the representative pHEMA-PVA-BC composite cryogel showed an effective porosity of 81.01 %, a permeability of 1.20 × 10-12 m2, and a range of height of theoretical plate between 0.40-0.49 cm at flow velocities of 0.5-3.0 cm/min. These indicate that the pHEMA-PVA-BC cryogel was an excellent material with supermacropores, low flow resistance and high mass transfer efficiency. Furthermore, the model output demonstrates that the alteration of the proportions of PVA (0.2-3.5 wt%) and BC (0.1-1.5 wt%) components in composite cryogels resulted in significant changes in the material basic properties. This work represents an attempt to efficiently design and prepare target composite cryogels using machine learning and providing valuable insights for the efficient development of polymers.

Microchannel liquid-flow focusing and cryo-polymerization preparation of supermacroporous cryogel beads for bioseparation.

Polymeric cryogels are sponge-like materials with supermacroporous structure, allowing them to be of interest as new chromatographic supports, cell scaffolds and drug carriers in biological and biomedical areas. The matrices of cryogels are always prepared in the form of monoliths by cryo-polymerization under frozen conditions. However, there are limited investigations on the production of cryogels in the form of adsorbent beads suitable for bioseparation. In this work, we provide a new approach by combining the microchannel liquid-flow focusing with cryo-polymerization for the preparation of polyacrylamide-based supermacroporous cryogel beads with a narrow particle size distribution. The present method was achieved by introducing the aqueous phase solution containing monomer, cross-linker and redox initiators, and the water-immiscible organic oil phase containing surfactant simultaneously into a microchannel with a cross-shaped junction, where the aqueous drops with uniform sizes were generated by the liquid shearing and the segmentation due to the steady flow focusing of the immiscible phase streams. These liquid drops were in situ suspended into the freezing bulk oil phase for cryo-polymerization and the cryogel matrix beads were obtained by thawing after the achievement of polymerization. By grafting the polymer chains containing sulfo binding groups onto these matrix beads, the cation-exchange cryogel beads for protein separation were produced. The results showed that at the aqueous phase velocities from 0.5 to 2.0 cm/s and the total velocities of the water-immiscible phase from 2.0 to 6.0 cm/s, the obtained cryogel beads by the present method have narrow size distributions with most of the bead diameters in the range from 800 to 1500 µm with supermacropores in sizes of about 3-50 µm. These beads also have high porosities with the averaged maximum porosity of 96.9% and the mean effective porosity of 86.2%, which are close to those of the polyacrylamide-based cryogel monoliths. The packed bed using the cryogel beads with mean diameter of 1248 µm, as an example, has reasonable and acceptable liquid dispersion, but high water permeability (4.29 × 10⁻¹° m²) and high bed voidage (90.2%) owing to the supermacropores within the beads, enhanced the rapid binding and separation of protein from the feedstock even at high flow velocities. The purity of the obtained lysozyme from chicken egg white by one-step chromatography using the packed bed was in the range of about 78-92% at the flow velocities of 0.5-15 cm/min, indicating that the present cryogel beads could be an effective chromatographic adsorbent for primary bioseparation.