Hybrid Graph Convolutional Network With Online Masked Autoencoder for Robust Multimodal Cancer Survival Prediction.

Cancer survival prediction requires exploiting related multimodal information (e.g., pathological, clinical and genomic features, etc.) and it is even more challenging in clinical practices due to the incompleteness of patient's multimodal data. Furthermore, existing methods lack sufficient intra- and inter-modal interactions, and suffer from significant performance degradation caused by missing modalities. This manuscript proposes a novel hybrid graph convolutional network, entitled HGCN, which is equipped with an online masked autoencoder paradigm for robust multimodal cancer survival prediction. Particularly, we pioneer modeling the patient's multimodal data into flexible and interpretable multimodal graphs with modality-specific preprocessing. HGCN integrates the advantages of graph convolutional networks (GCNs) and a hypergraph convolutional network (HCN) through node message passing and a hyperedge mixing mechanism to facilitate intra-modal and inter-modal interactions between multimodal graphs. With HGCN, the potential for multimodal data to create more reliable predictions of patient's survival risk is dramatically increased compared to prior methods. Most importantly, to compensate for missing patient modalities in clinical scenarios, we incorporated an online masked autoencoder paradigm into HGCN, which can effectively capture intrinsic dependence between modalities and seamlessly generate missing hyperedges for model inference. Extensive experiments and analysis on six cancer cohorts from TCGA show that our method significantly outperforms the state-of-the-arts in both complete and missing modal settings. Our codes are made available at https://github.com/lin-lcx/HGCN.

Expanding the Applicability of an Innovative Laccase TTI in Intelligent Packaging by Adding an Enzyme Inhibitor to Change Its Coloration Kinetics.

Enzymatic time-temperature indicators (TTIs) usually suffer from instability and inefficiency in practical use as food quality indicator during storage. The aim of this study was to address the aforementioned problem by immobilizing laccase on electrospun chitosan fibers to increase the stability and minimize the usage of laccase. The addition of NaN3, as and enzyme inhibitor, was intended to extend this laccase TTI coloration rate and activation energy (Ea) range, so as to expand the application range of TTIs for evaluating changes in the quality of foods during storage. A two-component time-temperature indicator was prepared by immobilizing laccase on electrospun chitosan fibers as a TTI film, and by using guaiacol solution as a coloration substrate. The color difference of the innovative laccase TTI was discovered to be <3, and visually indistinguishable when OD500 reached 3.2; the response reaction time was regarded as the TTI's coloration endpoint. Enzyme immobilization and the addition of NaN3 increased coloration Km and reduced coloration Vmax. The coloration Vmax decreased to 64% when 0.1 mM NaN3 was added to the TTI, which exhibited noncompetitive inhibition and a slower coloration rate. Coloration hysteresis appeared in the TTI with NaN3, particularly at low temperatures. For TTI coloration, the Ea increased to 29.92-66.39 kJ/mol when 15-25 µg/cm2 of laccase was immobilized, and the endpoint increased to 11.0-199.5 h when 0-0.10 mM NaN3 was added. These modifications expanded the applicability of laccase TTIs in intelligent food packaging.