Symmetric spatiotemporal learning network with sparse meter graph for short-term energy-consumption prediction in manufacturing systems.

Short-term energy-consumption prediction is the basis of anomaly detection, real-time scheduling, and energy-saving control in manufacturing systems. Most existing methods focus on single-node energy-consumption prediction and suffer from difficult parameter collection and modelling. Although several methods have been presented for multinode energy-consumption prediction, their prediction performance needs to be improved owing to a lack of appropriate knowledge guidance and learning networks for complex spatiotemporal relationships. This study presents a symmetric spatiotemporal learning network (SSTLN) with a sparse meter graph (SMG) (SSTLN-SMG) that aims to predict multiple nodes based on energy-consumption time series and general process knowledge. The SMG expresses process knowledge by abstracting production nodes, material flows, and energy usage, and provides initial guidance for the SSTLN to extract spatial features. SSTLN, a symmetrical stack of graph convolutional networks (GCN) and gated linear units (GLU), is devised to achieve a trade-off not only between spatial and temporal feature extraction but also between detail capture and noise suppression. Extensive experiments were performed using datasets from an aluminium profile plant. The experimental results demonstrate that the proposed method allows multinode energy-consumption prediction with less prediction error than state-of-the-art methods, methods with deformed meter graphs, and methods with deformed learning networks.

Digital ray: enhancing cataractous fundus images using style transfer generative adversarial networks to improve retinopathy detection.

BACKGROUND/AIMS: The aim of this study was to develop and evaluate digital ray, based on preoperative and postoperative image pairs using style transfer generative adversarial networks (GANs), to enhance cataractous fundus images for improved retinopathy detection. METHODS: For eligible cataract patients, preoperative and postoperative colour fundus photographs (CFP) and ultra-wide field (UWF) images were captured. Then, both the original CycleGAN and a modified CycleGAN (C2ycleGAN) framework were adopted for image generation and quantitatively compared using Frechet Inception Distance (FID) and Kernel Inception Distance (KID). Additionally, CFP and UWF images from another cataract cohort were used to test model performances. Different panels of ophthalmologists evaluated the quality, authenticity and diagnostic efficacy of the generated images. RESULTS: A total of 959 CFP and 1009 UWF image pairs were included in model development. FID and KID indicated that images generated by C2ycleGAN presented significantly improved quality. Based on ophthalmologists' average ratings, the percentages of inadequate-quality images decreased from 32% to 18.8% for CFP, and from 18.7% to 14.7% for UWF. Only 24.8% and 13.8% of generated CFP and UWF images could be recognised as synthetic. The accuracy of retinopathy detection significantly increased from 78% to 91% for CFP and from 91% to 93% for UWF. For retinopathy subtype diagnosis, the accuracies also increased from 87%-94% to 91%-100% for CFP and from 87%-95% to 93%-97% for UWF. CONCLUSION: Digital ray could generate realistic postoperative CFP and UWF images with enhanced quality and accuracy for overall detection and subtype diagnosis of retinopathies, especially for CFP.\ TRIAL REGISTRATION NUMBER: This study was registered with ClinicalTrials.gov (NCT05491798).

Deep Augmented Metric Learning Network for Prostate Cancer Classification in Ultrasound Images.

Prostate cancer screening often relies on cost-intensive MRIs and invasive needle biopsies. Transrectal ultrasound imaging, as a more affordable and non-invasive alternative, faces the challenge of high inter-class similarity and intra-class variability between benign and malignant prostate cancers. This complexity requires more stringent differentiation of subtle features for accurate auxiliary diagnosis. In response, we introduce the novel Deep Augmented Metric Learning (DAML) network, specifically tailored for ultrasound-based prostate cancer classification. The DAML network represents a significant innovation in the metric learning space, introducing the Semantic Differences Mining Strategy (SDMS) to effectively discern and represent subtle differences in prostate ultrasound images, thereby enhancing tumor classification accuracy. Additionally, the DAML network strategically addresses class variability and limited sample sizes by combining the Linear Interpolation Augmentation Strategy (LIAS) and Permutation-Aided Reconstruction Loss (PARL). This approach enriches feature representation and introduces variability with straightforward structures, mirroring the efficacy of advanced sample generation techniques. We carried out comprehensive empirical assessments of the DAML model by testing its key components against a range of models, ensuring its effectiveness. Our results demonstrate the enhanced performance of the DAML model, achieving classification accuracies of 0.857 and 0.888 for benign and malignant cancers, respectively, underscoring its effectiveness in prostate cancer classification via medical imaging.

Molecular and immune characterization of Chinese early-stage non-squamous non-small cell lung cancer: a multi-omics cohort study.

Background: Albeit considered with superior survival, around 30% of the early-stage non-squamous non-small cell lung cancer (Ns-NSCLC) patients relapse within 5 years, suggesting unique biology. However, the biological characteristics of early-stage Ns-NSCLC, especially in the Chinese population, are still unclear. Methods: Multi-omics interrogation of early-stage Ns-NSCLC (stage I-III), paired blood samples and normal lung tissues (n=76) by whole-exome sequencing (WES), RNA sequencing, and T-cell receptor (TCR) sequencing were conducted. Results: An average of 128 exonic mutations were identified, and the most frequently mutant gene was EGFR (55%), followed by TP53 (37%) and TTN (26%). Mutations in MUC17, ABCA2, PDE4DIP, and MYO18B predicted significantly unfavorable disease-free survival (DFS). Moreover, cytobands amplifications in 8q24.3, 14q13.1, 14q11.2, and deletion in 3p21.1 were highlighted in recurrent cases. Higher incidence of human leukocyte antigen loss of heterozygosity (HLA-LOH), higher tumor mutational burden (TMB) and tumor neoantigen burden (TNB) were identified in ever-smokers than never-smokers. HLA-LOH also correlated with higher TMB, TNB, intratumoral heterogeneity (ITH), and whole chromosomal instability (wCIN) scores. Interestingly, higher ITH was an independent predictor of better DFS in early-stage Ns-NSCLC. Up-regulation of immune-related genes, including CRABP2, ULBP2, IL31RA, and IL1A, independently portended a dismal prognosis. Enhanced TCR diversity of peripheral blood mononuclear cells (PBMCs) predicted better prognosis, indicative of a noninvasive method for relapse surveillance. Eventually, seven machine-learning (ML) algorithms were employed to evaluate the predictive accuracy of clinical, genomic, transcriptomic, and TCR repertoire data on DFS, showing that clinical and RNA features combination in the random forest (RF) algorithm, with area under the curve (AUC) of 97.5% and 83.3% in the training and testing cohort, respectively, significantly outperformed other methods. Conclusions: This study comprehensively profiled the genomic, transcriptomic, and TCR repertoire spectrums of Chinese early-stage Ns-NSCLC, shedding light on biological underpinnings and candidate biomarkers for prognosis development.

MetagenomicKG: a knowledge graph for metagenomic applications.

Motivation: The sheer volume and variety of genomic content within microbial communities makes metagenomics a field rich in biomedical knowledge. To traverse these complex communities and their vast unknowns, metagenomic studies often depend on distinct reference databases, such as the Genome Taxonomy Database (GTDB), the Kyoto Encyclopedia of Genes and Genomes (KEGG), and the Bacterial and Viral Bioinformatics Resource Center (BV-BRC), for various analytical purposes. These databases are crucial for genetic and functional annotation of microbial communities. Nevertheless, the inconsistent nomenclature or identifiers of these databases present challenges for effective integration, representation, and utilization. Knowledge graphs (KGs) offer an appropriate solution by organizing biological entities and their interrelations into a cohesive network. The graph structure not only facilitates the unveiling of hidden patterns but also enriches our biological understanding with deeper insights. Despite KGs having shown potential in various biomedical fields, their application in metagenomics remains underexplored. Results: We present MetagenomicKG, a novel knowledge graph specifically tailored for metagenomic analysis. MetagenomicKG integrates taxonomic, functional, and pathogenesis-related information from widely used databases, and further links these with established biomedical knowledge graphs to expand biological connections. Through several use cases, we demonstrate its utility in enabling hypothesis generation regarding the relationships between microbes and diseases, generating sample-specific graph embeddings, and providing robust pathogen prediction. Availability and Implementation: The source code and technical details for constructing the MetagenomicKG and reproducing all analyses are available at Github: https://github.com/KoslickiLab/MetagenomicKG. We also host a Neo4j instance: http://mkg.cse.psu.edu:7474 for accessing and querying this graph.

Regulation of rheumatoid arthritis microenvironment via a self-healing injectable hydrogel for improved inflammation elimination and bone repair.

The rheumatoid arthritis (RA) microenvironment is often followed by a vicious circle of high inflammation, endogenous gas levels imbalance, and poor treatment. To break the circle, we develop a dual-gas-mediated injectable hydrogel for modulating the immune microenvironment of RA and simultaneously releasing therapeutic drugs. The hydrogel (DNRS gel) could be broken down on-demand by consuming excessive nitric oxide (NO) and releasing therapeutic hydrogen sulfide (H2S), resulting in endogenous gas restoration, inflammation alleviation, and macrophage polarization to M2 type. Additionally, the hydrogel could suppress osteoclastogenesis and enhance osteogenesis. Furthermore, the intra-articularly injected hydrogel with methotrexate (MTX/DNRS gel) significantly alleviated inflammation and clinical symptoms and promoted the repair of bone erosion in the collagen-induced arthritis rat model. As a result, in vivo results demonstrated that MTX/DNRS gel restored the microenvironment and improved the therapeutic effect of MTX. This study provides a novel understanding of developing versatile smart delivery platforms for RA treatment.

Tunable molecular editing of indoles with fluoroalkyl carbenes.

Building molecular complexity from simple feedstocks through precise peripheral and skeletal modifications is central to modern organic synthesis. Nevertheless, a controllable strategy through which both the core skeleton and the periphery of an aromatic heterocycle can be modified with a common substrate remains elusive, despite its potential to maximize structural diversity and applications. Here we report a carbene-initiated chemodivergent molecular editing of indoles that allows both skeletal and peripheral editing by trapping an electrophilic fluoroalkyl carbene generated in situ from fluoroalkyl N-triftosylhydrazones. A variety of fluorine-containing N-heterocyclic scaffolds have been efficiently achieved through tunable chemoselective editing reactions at the skeleton or periphery of indoles, including one-carbon insertion, C3 gem-difluoroolefination, tandem cyclopropanation and N1 gem-difluoroolefination, and cyclopropanation. The power of this chemodivergent molecular editing strategy has been highlighted through the modification of the skeleton or periphery of natural products in a controllable and chemoselective manner. The reaction mechanism and origins of the chemo- and regioselectivity have been probed by both experimental and theoretical methods.

Titanium-based substrate modified with nanoenzyme for accelerating the repair of bone defect.

Titanium (Ti) and titanium alloy are the most common metal materials in clinical orthopedic surgery. However, in the initial stage of surgery and implantation, the production of excessive reactive oxygen species (ROS) can induce oxidative stress (OS) microenvironment. OS will further inhibit the growth of new bone, resulting in surgical failure. In this study, based on the fact that nanoscale manganese dioxide (MnO2) can show H2O2-like enzyme activity, a MnO2 nanocoating was prepared on mciro-nano structured surface of Ti substrate via a two-step method of alkaline thermal and hydrothermal treatment. The results of scanning electron microscopy (SEM), X-ray diffractometer (XRD) and X-ray photoelectron spectroscopy (XPS) showed that the nano-MnO2 coating was successfully fabricated on the surface of Ti substrate. The results of measurement of H2O2, dissolved O2 and intracellular ROS in vitro showed that the treated Ti substrate could efficiently eliminate H2O2 and reduce ROS. Furthermore, the modified Ti substrate could promote the early adhesion, proliferation and osteogenic differentiation of MSCs, which was demonstrated by experimental results of cell morphology, cell viability, alkaline phosphatase, collagen, and mineralization deposition. The results of quantitative real-time polymerase chain reaction (qRT-PCR) of MSCs adhered the modified Ti substrate showed that the expression of genes related to osteogenic differentiation significantly increased. More importantly, the modified Ti implant could eliminate ROS at the injury site, reduce OS and promote the regeneration of bone tissue, which was demonstrated via hematoxylin/eosin, Masson's trichrome and immunohistochemical staining. In conclusion, the modified Ti implant presented here had the effect of reducing OS and promoting osseointegration. Relevant research ideas and results provide new methods for the research and development of functional implants, which have potential application value in the field of orthopedics.

Superspreading-Based Fabrication of Thermostable Nanoporous Polyimide Membranes for High Safety Separators of Lithium-Ion Batteries.

The development of thermally stable separators is a promising approach to address the safety issues of lithium-ion batteries (LIBs) owing to the serious shrinkage of commercial polyolefin separators at elevated temperatures. However, achieving controlled nanopores with a uniform size distribution in thermostable polymeric separators and high electrochemical performance is still a great challenge. In this study, nanoporous polyimide (PI) membranes with excellent thermal stability as high-safety separators is developed for LIBs using a superspreading strategy. The superspreading of polyamic acid solutions enables the generation of thin and uniform liquid layers, facilitating the formation of thin PI membranes with controllable and uniform nanopores with narrow size distribution ranging from 121 ± 5 nm to 86 ± 6 nm. Such nanoporous PI membranes display excellent structural stability at elevated temperatures up to 300 °C for at least 1 h. LIBs assembled with nanoporous PI membranes as separators show high specific capacity and Coulombic efficiency and can work normally after transient treatment at a high temperature (150 °C for 20 min) and high ambient temperature, indicating their promising application as high-safety separators for rechargeable batteries.

Synergistic D-Amino Acids Based Antimicrobial Cocktails Formulated via High-Throughput Screening and Machine Learning.

Antimicrobial resistance (AMR) from pathogenic bacterial biofilms has become a global health issue while developing novel antimicrobials is inefficient and costly. Combining existing multiple drugs with enhanced efficacy and/or reduced toxicity may be a promising approach to treat AMR. D-amino acids mixtures coupled with antibiotics can provide new therapies for drug-resistance infection with reduced toxicity by lower drug dosage requirements. However, iterative trial-and-error experiments are not tenable to prioritize credible drug formulations, owing to the extremely large number of possible combinations. Herein, a new avenue is provide to accelerate the exploration of desirable antimicrobial formulations via high-throughput screening and machine learning optimization. Such an intelligent method can navigate the large search space and rapidly identify the D-amino acid mixtures with the highest anti-biofilm efficiency and also the synergisms between D-amino acid mixtures and antibiotics. The optimized drug cocktails exhibit high antimicrobial efficacy while remaining non-toxic, which is demonstrated not only from in vitro assessments but also the first in vivo study using a lung infection mouse model.

MOPDDI: Predicting Drug-Drug Interaction Events Based on Multimodal Mutual Orthogonal Projection and Intermodal Consistency Loss.

Predicting accurately the mechanisms of drug-drug interaction (DDI) events is crucial in drug research and development. Existing methods used to predict these events are primarily based on deep learning and have achieved satisfactory results. However, they rarely consider the presence of redundant co-information between the multimodal data of a drug and the need for consistency in the predicted features of each drug modality. Herein, we propose a new method for drug interaction event prediction based on multimodal mutual orthogonal projection and intermodal consistency loss. Our method obtains the features of each modality through a multimodal mutual orthogonal projection module, which eliminates redundant common information with other modalities. In addition, we use the consistency loss between modalities and make the predicted features of each modality more similar. In comparative experiments, our proposed method achieves a prediction accuracy of 0.9500, and an area under the precision-recall (AUPR) curve is 0.9833 for known DDIs. This method outperforms existing methods. The results show that the proposed method is capable of accurately predicting DDIs. The source code is available at https://github.com/xiaqixiaqi/MOPDDI.