AI identifies potent inducers of breast cancer stem cell differentiation based on adversarial learning from gene expression data.

Cancer stem cells (CSCs) are a subpopulation of cancer cells within tumors that exhibit stem-like properties and represent a potentially effective therapeutic target toward long-term remission by means of differentiation induction. By leveraging an artificial intelligence approach solely based on transcriptomics data, this study scored a large library of small molecules based on their predicted ability to induce differentiation in stem-like cells. In particular, a deep neural network model was trained using publicly available single-cell RNA-Seq data obtained from untreated human-induced pluripotent stem cells at various differentiation stages and subsequently utilized to screen drug-induced gene expression profiles from the Library of Integrated Network-based Cellular Signatures (LINCS) database. The challenge of adapting such different data domains was tackled by devising an adversarial learning approach that was able to effectively identify and remove domain-specific bias during the training phase. Experimental validation in MDA-MB-231 and MCF7 cells demonstrated the efficacy of five out of six tested molecules among those scored highest by the model. In particular, the efficacy of triptolide, OTS-167, quinacrine, granisetron and A-443654 offer a potential avenue for targeted therapies against breast CSCs.

Molecular Dynamics Simulation Study on the Occurrence of Shale Oil in Hybrid Nanopores.

The molecular dynamics simulation was used to simulate the influence of the composite wall stacking effect on shale oil occurrence. The kerogen-illite heterogeneous wall pore model was established to study the effects of temperature, pore size, and wall component ratio on the adsorption ratio and diffusion capacity of shale oil. The calculation results show that the fluid density distribution in the hybrid nanopore is not uniform. When the pore size increases, the proportion of the first adsorption layer to the total adsorption amount decreases rapidly, and the phenomenon of the "solid-like layer" of shale oil in small pores is more obvious. In addition, increases in temperature have little effect on the density peak of the first adsorption layer. With increases in organic matter content in the shale pore model, the diffusion coefficient of fluid decreases gradually, along with adsorption capacity. The influence of the irregular arrangement of kerogen molecules on the adsorption of shale oil is greater than the influence of surface roughness caused by illite on the adsorption.

PPML-Omics: A privacy-preserving federated machine learning method protects patients' privacy in omic data.

Modern machine learning models toward various tasks with omic data analysis give rise to threats of privacy leakage of patients involved in those datasets. Here, we proposed a secure and privacy-preserving machine learning method (PPML-Omics) by designing a decentralized differential private federated learning algorithm. We applied PPML-Omics to analyze data from three sequencing technologies and addressed the privacy concern in three major tasks of omic data under three representative deep learning models. We examined privacy breaches in depth through privacy attack experiments and demonstrated that PPML-Omics could protect patients' privacy. In each of these applications, PPML-Omics was able to outperform methods of comparison under the same level of privacy guarantee, demonstrating the versatility of the method in simultaneously balancing the privacy-preserving capability and utility in omic data analysis. Furthermore, we gave the theoretical proof of the privacy-preserving capability of PPML-Omics, suggesting the first mathematically guaranteed method with robust and generalizable empirical performance in protecting patients' privacy in omic data.

A unified method to revoke the private data of patients in intelligent healthcare with audit to forget.

Revoking personal private data is one of the basic human rights. However, such right is often overlooked or infringed upon due to the increasing collection and use of patient data for model training. In order to secure patients' right to be forgotten, we proposed a solution by using auditing to guide the forgetting process, where auditing means determining whether a dataset has been used to train the model and forgetting requires the information of a query dataset to be forgotten from the target model. We unified these two tasks by introducing an approach called knowledge purification. To implement our solution, we developed an audit to forget software (AFS), which is able to evaluate and revoke patients' private data from pre-trained deep learning models. Here, we show the usability of AFS and its application potential in real-world intelligent healthcare to enhance privacy protection and data revocation rights.

Predicting the antigenic evolution of SARS-COV-2 with deep learning.

The relentless evolution of SARS-CoV-2 poses a significant threat to public health, as it adapts to immune pressure from vaccines and natural infections. Gaining insights into potential antigenic changes is critical but challenging due to the vast sequence space. Here, we introduce the Machine Learning-guided Antigenic Evolution Prediction (MLAEP), which combines structure modeling, multi-task learning, and genetic algorithms to predict the viral fitness landscape and explore antigenic evolution via in silico directed evolution. By analyzing existing SARS-CoV-2 variants, MLAEP accurately infers variant order along antigenic evolutionary trajectories, correlating with corresponding sampling time. Our approach identified novel mutations in immunocompromised COVID-19 patients and emerging variants like XBB1.5. Additionally, MLAEP predictions were validated through in vitro neutralizing antibody binding assays, demonstrating that the predicted variants exhibited enhanced immune evasion. By profiling existing variants and predicting potential antigenic changes, MLAEP aids in vaccine development and enhances preparedness against future SARS-CoV-2 variants.

Accurate transcriptome-wide identification and quantification of alternative polyadenylation from RNA-seq data with APAIQ.

Alternative polyadenylation (APA) enables a gene to generate multiple transcripts with different 3' ends, which is dynamic across different cell types or conditions. Many computational methods have been developed to characterize sample-specific APA using the corresponding RNA-seq data, but suffered from high error rate on both polyadenylation site (PAS) identification and quantification of PAS usage (PAU), and bias toward 3' untranslated regions. Here we developed a tool for APA identification and quantification (APAIQ) from RNA-seq data, which can accurately identify PAS and quantify PAU in a transcriptome-wide manner. Using 3' end-seq data as the benchmark, we showed that APAIQ outperforms current methods on PAS identification and PAU quantification, including DaPars2, Aptardi, mountainClimber, SANPolyA, and QAPA. Finally, applying APAIQ on 421 RNA-seq samples from liver cancer patients, we identified >540 tumor-associated APA events and experimentally validated two intronic polyadenylation candidates, demonstrating its capacity to unveil cancer-related APA with a large-scale RNA-seq data set.

A comprehensive benchmarking with practical guidelines for cellular deconvolution of spatial transcriptomics.

Spatial transcriptomics technologies are used to profile transcriptomes while preserving spatial information, which enables high-resolution characterization of transcriptional patterns and reconstruction of tissue architecture. Due to the existence of low-resolution spots in recent spatial transcriptomics technologies, uncovering cellular heterogeneity is crucial for disentangling the spatial patterns of cell types, and many related methods have been proposed. Here, we benchmark 18 existing methods resolving a cellular deconvolution task with 50 real-world and simulated datasets by evaluating the accuracy, robustness, and usability of the methods. We compare these methods comprehensively using different metrics, resolutions, spatial transcriptomics technologies, spot numbers, and gene numbers. In terms of performance, CARD, Cell2location, and Tangram are the best methods for conducting the cellular deconvolution task. To refine our comparative results, we provide decision-tree-style guidelines and recommendations for method selection and their additional features, which will help users easily choose the best method for fulfilling their concerns.

Artificial Leaf for Solar-Driven Ammonia Conversion at Milligram-Scale Using Triple Junction III-V Photoelectrode.

Developing a green and energy-saving alternative to the traditional Haber-Bosch process for converting nitrogen into ammonia is urgently needed. Imitating from biological nitrogen fixation and photosynthesis processes, this work develops a monolithic artificial leaf based on triple junction (3J) InGaP/GaAs/Ge cell for solar-driven ammonia conversion under ambient conditions. A gold layer serves as the catalytic site for nitrogen fixation with photogenerated electrons. The Au/Ti/3J InGaP/GaAs/Ge photoelectrochemical (PEC) device achieves high ammonia production rates and Faradaic efficiencies in a two-electrode system without applying external potential. For example, at 0.2 sunlight intensity, the solar-to-ammonia (STA) conversion efficiency reaches 1.11% and the corresponding Faradaic efficiency is up to 28.9%. By integrating a Ni foil on the anode side for the oxygen evolution reaction (OER), the monolithic artificial leaf exhibits an ammonia production rate of 8.5 µg cm-2 h at 1.5 sunlight intensity. Additionally, a 3 × 3 cm unassisted wireless PEC device is fabricated that produces 1.0039 mg of ammonia in the 36-h durability test. Thus, the new artificial leaf can successfully and directly convert solar energy into chemical energy and generate useful products in an environmentally friendly approach.

Applications of deep learning in understanding gene regulation.

Gene regulation is a central topic in cell biology. Advances in omics technologies and the accumulation of omics data have provided better opportunities for gene regulation studies than ever before. For this reason deep learning, as a data-driven predictive modeling approach, has been successfully applied to this field during the past decade. In this article, we aim to give a brief yet comprehensive overview of representative deep-learning methods for gene regulation. Specifically, we discuss and compare the design principles and datasets used by each method, creating a reference for researchers who wish to replicate or improve existing methods. We also discuss the common problems of existing approaches and prospectively introduce the emerging deep-learning paradigms that will potentially alleviate them. We hope that this article will provide a rich and up-to-date resource and shed light on future research directions in this area.

Vision transformer-based weakly supervised histopathological image analysis of primary brain tumors.

Diagnosis of primary brain tumors relies heavily on histopathology. Although various computational pathology methods have been developed for automated diagnosis of primary brain tumors, they usually require neuropathologists' annotation of region of interests or selection of image patches on whole-slide images (WSI). We developed an end-to-end Vision Transformer (ViT) - based deep learning architecture for brain tumor WSI analysis, yielding a highly interpretable deep-learning model, ViT-WSI. Based on the principle of weakly supervised machine learning, ViT-WSI accomplishes the task of major primary brain tumor type and subtype classification. Using a systematic gradient-based attribution analysis procedure, ViT-WSI can discover diagnostic histopathological features for primary brain tumors. Furthermore, we demonstrated that ViT-WSI has high predictive power of inferring the status of three diagnostic glioma molecular markers, IDH1 mutation, p53 mutation, and MGMT methylation, directly from H&E-stained histopathological images, with patient level AUC scores of 0.960, 0.874, and 0.845, respectively.

Optimization of binding affinities in chemical space with generative pre-trained transformer and deep reinforcement learning.

Background: The key challenge in drug discovery is to discover novel compounds with desirable properties. Among the properties, binding affinity to a target is one of the prerequisites and usually evaluated by molecular docking or quantitative structure activity relationship (QSAR) models. Methods: In this study, we developed SGPT-RL, which uses a generative pre-trained transformer (GPT) as the policy network of the reinforcement learning (RL) agent to optimize the binding affinity to a target. SGPT-RL was evaluated on the Moses distribution learning benchmark and two goal-directed generation tasks, with Dopamine Receptor D2 (DRD2) and Angiotensin-Converting Enzyme 2 (ACE2) as the targets. Both QSAR model and molecular docking were implemented as the optimization goals in the tasks. The popular Reinvent method was used as the baseline for comparison. Results: The results on the Moses benchmark showed that SGPT-RL learned good property distributions and generated molecules with high validity and novelty. On the two goal-directed generation tasks, both SGPT-RL and Reinvent were able to generate valid molecules with improved target scores. The SGPT-RL method achieved better results than Reinvent on the ACE2 task, where molecular docking was used as the optimization goal. Further analysis shows that SGPT-RL learned conserved scaffold patterns during exploration. Conclusions: The superior performance of SGPT-RL in the ACE2 task indicates that it can be applied to the virtual screening process where molecular docking is widely used as the criteria. Besides, the scaffold patterns learned by SGPT-RL during the exploration process can assist chemists to better design and discover novel lead candidates.

Annotating TSSs in Multiple Cell Types Based on DNA Sequence and RNA-seq Data via DeeReCT-TSS.

The accurate annotation of transcription start sites (TSSs) and their usage are critical for the mechanistic understanding of gene regulation in different biological contexts. To fulfill this, specific high-throughput experimental technologies have been developed to capture TSSs in a genome-wide manner, and various computational tools have also been developed for in silico prediction of TSSs solely based on genomic sequences. Most of these computational tools cast the problem as a binary classification task on a balanced dataset, thus resulting in drastic false positive predictions when applied on the genome scale. Here, we present DeeReCT-TSS, a deep learning-based method that is capable of identifying TSSs across the whole genome based on both DNA sequence and conventional RNA sequencing data. We show that by effectively incorporating these two sources of information, DeeReCT-TSS significantly outperforms other solely sequence-based methods on the precise annotation of TSSs used in different cell types. Furthermore, we develop a meta-learning-based extension for simultaneous TSS annotations on 10 cell types, which enables the identification of cell type-specific TSSs. Finally, we demonstrate the high precision of DeeReCT-TSS on two independent datasets by correlating our predicted TSSs with experimentally defined TSS chromatin states. The source code for DeeReCT-TSS is available at https://github.com/JoshuaChou2018/DeeReCT-TSS_release and https://ngdc.cncb.ac.cn/biocode/tools/BT007316.

DeeReCT-APA: Prediction of Alternative Polyadenylation Site Usage Through Deep Learning.

Alternative polyadenylation (APA) is a crucial step in post-transcriptional regulation. Previous bioinformatic studies have mainly focused on the recognition of polyadenylation sites (PASs) in a given genomic sequence, which is a binary classification problem. Recently, computational methods for predicting the usage level of alternative PASs in the same gene have been proposed. However, all of them cast the problem as a non-quantitative pairwise comparison task and do not take the competition among multiple PASs into account. To address this, here we propose a deep learning architecture, Deep Regulatory Code and Tools for Alternative Polyadenylation (DeeReCT-APA), to quantitatively predict the usage of all alternative PASs of a given gene. To accommodate different genes with potentially different numbers of PASs, DeeReCT-APA treats the problem as a regression task with a variable-length target. Based on a convolutional neural network-long short-term memory (CNN-LSTM) architecture, DeeReCT-APA extracts sequence features with CNN layers, uses bidirectional LSTM to explicitly model the interactions among competing PASs, and outputs percentage scores representing the usage levels of all PASs of a gene. In addition to the fact that only our method can quantitatively predict the usage of all the PASs within a gene, we show that our method consistently outperforms other existing methods on three different tasks for which they are trained: pairwise comparison task, highest usage prediction task, and ranking task. Finally, we demonstrate that our method can be used to predict the effect of genetic variations on APA patterns and sheds light on future mechanistic understanding in APA regulation. Our code and data are available at https://github.com/lzx325/DeeReCT-APA-repo.

Computer-aided drug repurposing for cancer therapy: Approaches and opportunities to challenge anticancer targets.

Despite huge efforts made in academic and pharmaceutical worldwide research, current anticancer therapies achieve effective treatment in a limited number of neoplasia cases only. Oncology terms such as big killers - to identify tumours with yet a high mortality rate - or undruggable cancer targets, and chemoresistance, represent the current therapeutic debacle of cancer treatments. In addition, metastases, tumour microenvironments, tumour heterogeneity, metabolic adaptations, and immunotherapy resistance are essential features controlling tumour response to therapies, but still, lack effective therapeutics or modulators. In this scenario, where the pharmaceutical productivity and drug efficacy in oncology seem to have reached a plateau, the so-called drug repurposing - i.e. the use of old drugs, already in clinical use, for a different therapeutic indication - is an appealing strategy to improve cancer therapy. Opportunities for drug repurposing are often based on occasional observations or on time-consuming pre-clinical drug screenings that are often not hypothesis-driven. In contrast, in-silico drug repurposing is an emerging, hypothesis-driven approach that takes advantage of the use of big-data. Indeed, the extensive use of -omics technologies, improved data storage, data meaning, machine learning algorithms, and computational modeling all offer unprecedented knowledge of the biological mechanisms of cancers and drugs' modes of action, providing extensive availability for both disease-related data and drugs-related data. This offers the opportunity to generate, with time and cost-effective approaches, computational drug networks to predict, in-silico, the efficacy of approved drugs against relevant cancer targets, as well as to select better responder patients or disease' biomarkers. Here, we will review selected disease-related data together with computational tools to be exploited for the in-silico repurposing of drugs against validated targets in cancer therapies, focusing on the oncogenic signaling pathways activation in cancer. We will discuss how in-silico drug repurposing has the promise to shortly improve our arsenal of anticancer drugs and, likely, overcome certain limitations of modern cancer therapies against old and new therapeutic targets in oncology.

Frailty index and all-cause and cause-specific mortality in Chinese adults: a prospective cohort study.

BACKGROUND: The fraily index is a useful proxy measure of accelerated biological ageing and in estimating all-cause and cause-specific mortality in older individuals in European and US populations. However, the predictive value of the frailty index in other populations outside of Europe and the USA and in adults younger than 50 years is unknown. We aimed to examine the association between the frailty index and mortality in a population of Chinese adults. METHODS: In this prospective cohort study, we used data from the China Kadoorie Biobank. We included adults aged 30-79 years from ten areas (five urban areas and five rural areas) of China who had no missing values for the items that made up the frailty index. We did not exclude participants on the basis of baseline morbidity status. We calculated the follow-up person-years from the baseline date to either the date of death, loss to follow-up, or Dec 31, 2017, whichever came first, through linkage with the registries of China's Disease Surveillance Points system and local residential records. Active follow-up visits to local communities were done annually for participants who were not linked to any established registries. Causes of death from official death certificates were supplemented, if necessary, by reviewing medical records or doing standard verbal autopsy procedures. The frailty index was calculated using 28 baseline variables, all of which were health status deficits measured by use of questionnaires and physical examination. We defined three categories of frailty status: robust (frailty index ≤0·10), prefrail (frailty index >0·10 to <0·25), and frail (frailty index ≥0·25). The primary outcomes were all-cause mortality and cause-specific mortality in Chinese adults aged 30-79 years. We used a Cox proportional hazards model to estimate the associations between the frailty index and all-cause and cause-specific mortality, adjusting for chronological age, education, and lifestyle factors. FINDINGS: 512 723 participants, recruited between June 25, 2004, and July 15, 2008, were followed up for a median of 10·8 years (IQR 10·2-13·1; total follow-up 5 551 974 person-years). 291 954 (56·9%) people were categorised as robust, 205 075 (40·0%) people were categorised as prefrail, and 15 694 (3·1%) people were categorised as frail. Women aged between 45 years and 79 years had a higher mean frailty index and a higher prevalence of frailty than did men. During follow-up, 49 371 deaths were recorded. After adjustment for established and potential risk factors for death, each 0·1 increment in the frailty index was associated with a higher risk of all-cause mortality (hazard ratio [HR] 1·68, 95% CI 1·66-1·71). Such associations were stronger among younger adults than among older adults (pinteraction<0·0001), with HRs per 0·1 increment of the frailty index of 1·95 (95% CI 1·87-2·03) for those younger than 50 years, 1·80 (1·76-1·83) for those aged 50-64 years, and 1·56 (1·53-1·59) for those 65 years and older. After adjustments, there was no difference between the sexes in the association between the frailty index and all-cause mortality (pinteraction=0·75). For each 0·1 increment of the frailty index, the corresponding HRs for risk of death were 1·89 (95% CI 1·83-1·94) from ischaemic heart disease, 1·84 (1·79-1·89) from cerebrovascular disease, 1·19 (1·16-1·22) from cancer, 2·54 (2·45-2·63) from respiratory disease, 1·78 (1·59-2·00) from infection, and 1·78 (1·73-1·83) from all other causes. INTERPRETATION: The frailty index is associated with all-cause and cause-specific mortality independent of chronological age in younger and older Chinese adults. The identification of younger adults with accelerated ageing by use of surrogate measures could be useful for the prevention of premature death and the extension of healthy active life expectancy. FUNDING: The National Natural Science Foundation of China, the National Key R&D Program of China, the Chinese Ministry of Science and Technology, the Kadoorie Charitable Foundation, and the Wellcome Trust.

A combination of two ELISA tests for nasopharyngeal carcinoma screening in endemic areas based on a case-control study.

For populations with a high risk of nasopharyngeal carcinoma (NPC) in Guangdong province in southern China, mass screening is the first choice to prevent death from NPC. To improve the performance of NPC screening, we used a combination based on the IgA antibody against the Epstein-Barr virus (EBV) capsid antigen (VCA-IgA) and the IgA antibody against Epstein-Barr virus nuclear antigen 1 (EBNA1-IgA) to NPC screening by enzyme-linked immunosorbent assay (ELISA). A multiplication model was applied to measure the level of the combination. We evaluated the NPC screening effect of the markers.A case-control study was performed to assess the NPC screening effect of the markers. A total of 10,894 serum specimens were collected, including 554 samples from NPC patients and 10,340 samples from healthy controls. In the training stage, 640 subjects were randomly selected, including 320 NPC cases and 320 healthy controls. In the verification stage, 10,254 subjects were used to verify the NPC screening effect of the combination. Receiver operating characteristic (ROC) analysis was performed. In the verification stage, the combination achieved an sensitivity of 91.45%, a specificity of 93.45%, and an area under the ROC curve (AUC) of 0.978 (95% CI [0.968-0.987]). Compared with VCA-IgA and EBNA1-IgA individually, the combination had an improved screening performance. A probability (PROB) calculated by logistic regression model based on VCA-IgA and EBNA1-IgA was applied to NPC screening by ELISA in China. The AUC of the combination was a little bit larger than the PROB. There was a slight increase (3.13%) in the sensitivity of the combination compared to the sensitivity of the PROB, while the specificity was lower for the combination (92.50%) than for the PROB (95.94%). We successfully applied a combination of two ELISA tests based on VCA-IgA and EBNA1-IgA for NPC screening by using a multiplication model. The results suggested that the combination was effective and can be an option for NPC screening.

Metabolically healthy obesity, transition to unhealthy metabolic status, and vascular disease in Chinese adults: A cohort study.

BACKGROUND: Metabolically healthy obesity (MHO) and its transition to unhealthy metabolic status have been associated with risk of cardiovascular disease (CVD) in Western populations. However, it is unclear to what extent metabolic health changes over time and whether such transition affects risks of subtypes of CVD in Chinese adults. We aimed to examine the association of metabolic health status and its transition with risks of subtypes of vascular disease across body mass index (BMI) categories. METHODS AND FINDINGS: The China Kadoorie Biobank was conducted during 25 June 2004 to 15 July 2008 in 5 urban (Harbin, Qingdao, Suzhou, Liuzhou, and Haikou) and 5 rural (Henan, Gansu, Sichuan, Zhejiang, and Hunan) regions across China. BMI and metabolic health information were collected. We classified participants into BMI categories: normal weight (BMI 18.5-23.9 kg/m²), overweight (BMI 24.0-27.9 kg/m²), and obese (BMI ≥ 28 kg/m²). Metabolic health was defined as meeting less than 2 of the following 4 criteria (elevated waist circumference, hypertension, elevated plasma glucose level, and dyslipidemia). The changes in obesity and metabolic health status were defined from baseline to the second resurvey with combination of overweight and obesity. Among the 458,246 participants with complete information and no history of CVD and cancer, the mean age at baseline was 50.9 (SD 10.4) years, and 40.8% were men, and 29.0% were current smokers. During a median 10.0 years of follow-up, 52,251 major vascular events (MVEs), including 7,326 major coronary events (MCEs), 37,992 ischemic heart disease (IHD), and 42,951 strokes were recorded. Compared with metabolically healthy normal weight (MHN), baseline MHO was associated with higher hazard ratios (HRs) for all types of CVD; however, almost 40% of those participants transitioned to metabolically unhealthy status. Stable metabolically unhealthy overweight or obesity (MUOO) (HR 2.22, 95% confidence interval [CI] 2.00-2.47, p < 0.001) and transition from metabolically healthy to unhealthy status (HR 1.53, 1.34-1.75, p < 0.001) were associated with higher risk for MVE, compared with stable healthy normal weight. Similar patterns were observed for MCE, IHD, and stroke. Limitations of the analysis included lack of measurement of lipid components, fasting plasma glucose, and visceral fat, and there might be possible misclassification. CONCLUSIONS: Among Chinese adults, MHO individuals have increased risks of MVE. Obesity remains a risk factor for CVD independent of major metabolic factors. Our data further suggest that metabolic health is a transient state for a large proportion of Chinese adults, with the highest vascular risk among those remained MUOO.

A Rapid, Accurate and Machine-Agnostic Segmentation and Quantification Method for CT-Based COVID-19 Diagnosis.

COVID-19 has caused a global pandemic and become the most urgent threat to the entire world. Tremendous efforts and resources have been invested in developing diagnosis, prognosis and treatment strategies to combat the disease. Although nucleic acid detection has been mainly used as the gold standard to confirm this RNA virus-based disease, it has been shown that such a strategy has a high false negative rate, especially for patients in the early stage, and thus CT imaging has been applied as a major diagnostic modality in confirming positive COVID-19. Despite the various, urgent advances in developing artificial intelligence (AI)-based computer-aided systems for CT-based COVID-19 diagnosis, most of the existing methods can only perform classification, whereas the state-of-the-art segmentation method requires a high level of human intervention. In this paper, we propose a fully-automatic, rapid, accurate, and machine-agnostic method that can segment and quantify the infection regions on CT scans from different sources. Our method is founded upon two innovations: 1) the first CT scan simulator for COVID-19, by fitting the dynamic change of real patients' data measured at different time points, which greatly alleviates the data scarcity issue; and 2) a novel deep learning algorithm to solve the large-scene-small-object problem, which decomposes the 3D segmentation problem into three 2D ones, and thus reduces the model complexity by an order of magnitude and, at the same time, significantly improves the segmentation accuracy. Comprehensive experimental results over multi-country, multi-hospital, and multi-machine datasets demonstrate the superior performance of our method over the existing ones and suggest its important application value in combating the disease.

Deep learning in bioinformatics: Introduction, application, and perspective in the big data era.

Deep learning, which is especially formidable in handling big data, has achieved great success in various fields, including bioinformatics. With the advances of the big data era in biology, it is foreseeable that deep learning will become increasingly important in the field and will be incorporated in vast majorities of analysis pipelines. In this review, we provide both the exoteric introduction of deep learning, and concrete examples and implementations of its representative applications in bioinformatics. We start from the recent achievements of deep learning in the bioinformatics field, pointing out the problems which are suitable to use deep learning. After that, we introduce deep learning in an easy-to-understand fashion, from shallow neural networks to legendary convolutional neural networks, legendary recurrent neural networks, graph neural networks, generative adversarial networks, variational autoencoder, and the most recent state-of-the-art architectures. After that, we provide eight examples, covering five bioinformatics research directions and all the four kinds of data type, with the implementation written in Tensorflow and Keras. Finally, we discuss the common issues, such as overfitting and interpretability, that users will encounter when adopting deep learning methods and provide corresponding suggestions. The implementations are freely available at https://github.com/lykaust15/Deep_learning_examples.

A Highly Ionic Conductive, Healable, and Adhesive Polysiloxane-Supported Ionogel.

A new kind of polysiloxane-supported ionogel is successfully designed via locking ionic liquids (ILs), 1-ethyl-3-methylimidazolium bis(trifluoromethylsulfonyl)imide ([EMIM][Tf2 N]), into poly(aminopropyl-methylsiloxane) (PAPMS) grafted with [2-(methacryloyloxy)ethyl] trimethylammonium chloride (METAC) in the presence of tannic acid (TA). The novel ionogel exhibits good mechanical and recovery properties, as well as high ionic conductivity (1.19 mS cm-1 ) at 25 °C. In addition, the totally physical dual-crosslinked network based on ionic aggregates among METAC and the hydrogen bonds between PAPMS and TA provides excellent self-healing ability, which allows the damaged ionogel to almost completely heal (≈83%) in 12 h at room temperature. Interestingly, the obtained ionogel also shows satisfactory adhesive behavior to various solid materials. Moreover, this novel ionogel can maintain its high ionic conductivity and recovery property even at subzero temperatures. Therefore, this polysiloxane-supported ionogel is anticipated to be advantageous in flexible electronic devices such as sensors and supercapacitors, even at low temperatures.