MOMA: a multi-task attention learning algorithm for multi-omics data interpretation and classification.

MOTIVATION: Accurate diagnostic classification and biological interpretation are important in biology and medicine, which are data-rich sciences. Thus, integration of different data types is necessary for the high predictive accuracy of clinical phenotypes, and more comprehensive analyses for predicting the prognosis of complex diseases are required. RESULTS: Here, we propose a novel multi-task attention learning algorithm for multi-omics data, termed MOMA, which captures important biological processes for high diagnostic performance and interpretability. MOMA vectorizes features and modules using a geometric approach and focuses on important modules in multi-omics data via an attention mechanism. Experiments using public data on Alzheimer's disease and cancer with various classification tasks demonstrated the superior performance of this approach. The utility of MOMA was also verified using a comparison experiment with an attention mechanism that was turned on or off and biological analysis. AVAILABILITY AND IMPLEMENTATION: The source codes are available at https://github.com/dmcb-gist/MOMA. SUPPLEMENTARY INFORMATION: Supplementary materials are available at Bioinformatics online.

Prediction of anti-vascular endothelial growth factor agent-specific treatment outcomes in neovascular age-related macular degeneration using a generative adversarial network.

To develop an artificial intelligence (AI) model that predicts anti-vascular endothelial growth factor (VEGF) agent-specific anatomical treatment outcomes in neovascular age-related macular degeneration (AMD), thereby assisting clinicians in selecting the most suitable anti-VEGF agent for each patient. This retrospective study included patients diagnosed with neovascular AMD who received three loading injections of either ranibizumab or aflibercept. Training was performed using optical coherence tomography (OCT) images with an attention generative adversarial network (GAN) model. To test the performance of the AI model, the sensitivity and specificity to predict the presence of retinal fluid after treatment were calculated for the AI model, an experienced (Examiner 1), and a less experienced (Examiner 2) human examiners. A total of 1684 OCT images from 842 patients (419 treated with ranibizumab and 423 treated with aflibercept) were used as the training set. Testing was performed using images from 98 patients. In patients treated with ranibizumab, the sensitivity and specificity, respectively, were 0.615 and 0.667 for the AI model, 0.385 and 0.861 for Examiner 1, and 0.231 and 0.806 for Examiner 2. In patients treated with aflibercept, the sensitivity and specificity, respectively, were 0.857 and 0.881 for the AI model, 0.429 and 0.976 for Examiner 1, and 0.429 and 0.857 for Examiner 2. In 18.5% of cases, the fluid status of synthetic posttreatment images differed between ranibizumab and aflibercept. The AI model using GAN might predict anti-VEGF agent-specific short-term treatment outcomes with relatively higher sensitivity than human examiners. Additionally, there was a difference in the efficacy in fluid resolution between the anti-VEGF agents. These results suggest the potential of AI in personalized medicine for patients with neovascular AMD.

SDGCCA: Supervised Deep Generalized Canonical Correlation Analysis for Multi-Omics Integration.

Integration of multi-omics data provides opportunities for revealing biological mechanisms related to certain phenotypes. We propose a novel method of multi-omics integration called supervised deep generalized canonical correlation analysis (SDGCCA) for modeling correlation structures between nonlinear multi-omics manifolds that aims at improving the classification of phenotypes and revealing the biomarkers related to phenotypes. SDGCCA addresses the limitations of other canonical correlation analysis (CCA)-based models (such as deep CCA, deep generalized CCA) by considering complex/nonlinear cross-data correlations between multiple (≥2) modalities. Although there are a few methods to learn nonlinear CCA projections for classifying phenotypes, they only consider two views. Methods extended to multiple views either do not perform classification or do not provide feature ranking. In contrast, SDGCCA is a nonlinear multi-view CCA projection method that performs classification and ranks features. When we applied SDGCCA in predicting patients with Alzheimer's disease (AD) and discrimination of early- and late-stage cancers, it outperformed other CCA-based and other supervised methods. In addition, we demonstrate that SDGCCA can be applied for feature selection to identify important multi-omics biomarkers. On applying AD data, SDGCCA identified clusters of genes in multi-omics data, well known to be associated with AD.

JDSNMF: Joint Deep Semi-Non-Negative Matrix Factorization for Learning Integrative Representation of Molecular Signals in Alzheimer's Disease.

High dimensional multi-omics data integration can enhance our understanding of the complex biological interactions in human diseases. However, most studies involving unsupervised integration of multi-omics data focus on linear integration methods. In this study, we propose a joint deep semi-non-negative matrix factorization (JDSNMF) model, which uses a hierarchical non-linear feature extraction approach that can capture shared latent features from the complex multi-omics data. The extracted latent features obtained from JDSNMF enabled a variety of downstream tasks, including prediction of disease and module analysis. The proposed model is applicable not only to sample-matched multiple data (e.g., multi-omics data from one cohort) but also to feature-matched multiple data (e.g., omics data from multiple cohorts), and therefore it can be flexibly applied to various cases. We demonstrate the capabilities of JDSNMF using sample-matched simulated data and feature-matched multi-omics data from Alzheimer's disease cohorts, evaluating the feature extraction performance in the context of classification. In a test application, we identify AD- and age-related modules from the latent matrices using an explainable artificial intelligence and regression model. These results show that the JDSNMF model is effective in identifying latent features having a complex interplay of potential biological signatures.

A Biodegradable Secondary Battery and its Biodegradation Mechanism for Eco-Friendly Energy-Storage Systems.

The production of rechargeable batteries is rapidly expanding, and there are going to be new challenges in the near future about how the potential environmental impact caused by the disposal of the large volume of the used batteries can be minimized. Herein, a novel strategy is proposed to address these concerns by applying biodegradable device technology. An eco-friendly and biodegradable sodium-ion secondary battery (SIB) is developed through extensive material screening followed by the synthesis of biodegradable electrodes and their seamless assembly with an unconventional biodegradable separator, electrolyte, and package. Each battery component decomposes in nature into non-toxic compounds or elements via hydrolysis and/or fungal degradation, with all of the biodegradation products naturally abundant and eco-friendly. Detailed biodegradation mechanisms and toxicity influence of each component on living organisms are determined. In addition, this new SIB delivers performance comparable to that of conventional non-degradable SIBs. The strategy and findings suggest a novel eco-friendly biodegradable paradigm for large-scale rechargeable battery systems.

High-efficiency and high-power rechargeable lithium-sulfur dioxide batteries exploiting conventional carbonate-based electrolytes.

Shedding new light on conventional batteries sometimes inspires a chemistry adoptable for rechargeable batteries. Recently, the primary lithium-sulfur dioxide battery, which offers a high energy density and long shelf-life, is successfully renewed as a promising rechargeable system exhibiting small polarization and good reversibility. Here, we demonstrate for the first time that reversible operation of the lithium-sulfur dioxide battery is also possible by exploiting conventional carbonate-based electrolytes. Theoretical and experimental studies reveal that the sulfur dioxide electrochemistry is highly stable in carbonate-based electrolytes, enabling the reversible formation of lithium dithionite. The use of the carbonate-based electrolyte leads to a remarkable enhancement of power and reversibility; furthermore, the optimized lithium-sulfur dioxide battery with catalysts achieves outstanding cycle stability for over 450 cycles with 0.2 V polarization. This study highlights the potential promise of lithium-sulfur dioxide chemistry along with the viability of conventional carbonate-based electrolytes in metal-gas rechargeable systems.