Search

Cellular metabolism is a highly interconnected network with thousands of reactions that convert nutrients into the molecular building blocks of life. Metabolic connectivity varies greatly with cellular context and environmental conditions, and it remains a challenge to compare genome-scale metabolism across cell types because of the high dimensionality of the reaction flux space. Here, we employ self-supervised learning and genome-scale metabolic models to compress the flux space into low-dimensional representations that preserve structure across cell types. We trained variational autoencoders (VAEs) on large fluxomic data (N = 800, 000) sampled from patient-derived models for various cancer cell types. The VAE embeddings have an improved ability to distinguish cell types than the uncompressed fluxomic data, and sufficient predictive power to classify cell types with high accuracy. We tested the ability of these classifiers to assign cell type identities to unlabelled patient-derived metabolic models not employed during VAE training. We further employed the pre-trained VAE to embed another 38 cell types and trained multilabel classifiers that display promising generalization performance. Our approach distils the metabolic space into a semantically rich vector that can be used as a foundation for predictive modelling, clustering or comparing metabolic capabilities across organisms.

Abstract: High-performance catalysts and photovoltaics form key components for various technological applications. Because catalytic and photovoltaic reactions occur at the interfaces between reactants and surfaces, the chemical, physical, and structural properties of interfaces have been the focus of many studies. One route towards the improvement and optimization of such interfaces is the preparation of microporous materials from amphiphilic copolymers, which can also be surface coated with inorganic nanoparticles to obtain different properties. In this work, we have prepared microporous hybrid films with fluorescent properties from amphiphilic block copolymers surface coated with ZnS (NPs) based on the breath figure (BF) mechanism, keeping constant the concentration of ZnS NPs, solvent, humidity and substrates. The morphological and optical properties were investigated by microscopic and optical characterization techniques. As a result, the fabrication method facilitates the preparation of fluorescent porous films with varying morphological properties (shapes and diameter pore). The hybrid porous films containing polystyrene-b-polyacrylic acid, polystyrene-b-polyitaconic acid and polystyrene-b-polydialylmalonic acid were obtained with an average pore size of 0.57 ± 0.04 μm, 0.78 ± 0.03 μm and 1.50 ± 0.04 μm, respectively. An increase in the water contact angle (WCA) was observed in the block copolymer porous films after functional process with ZnS (NPs). Graphic abstract: