Potential rapid intraoperative cancer diagnosis using dynamic full-field optical coherence tomography and deep learning: A prospective cohort study in breast cancer patients.

An intraoperative diagnosis is critical for precise cancer surgery. However, traditional intraoperative assessments based on hematoxylin and eosin (H&E) histology, such as frozen section, are time-, resource-, and labor-intensive, and involve specimen-consuming concerns. Here, we report a near-real-time automated cancer diagnosis workflow for breast cancer that combines dynamic full-field optical coherence tomography (D-FFOCT), a label-free optical imaging method, and deep learning for bedside tumor diagnosis during surgery. To classify the benign and malignant breast tissues, we conducted a prospective cohort trial. In the modeling group (n = 182), D-FFOCT images were captured from April 26 to June 20, 2018, encompassing 48 benign lesions, 114 invasive ductal carcinoma (IDC), 10 invasive lobular carcinoma, 4 ductal carcinoma in situ (DCIS), and 6 rare tumors. Deep learning model was built up and fine-tuned in 10,357 D-FFOCT patches. Subsequently, from June 22 to August 17, 2018, independent tests (n = 42) were conducted on 10 benign lesions, 29 IDC, 1 DCIS, and 2 rare tumors. The model yielded excellent performance, with an accuracy of 97.62%, sensitivity of 96.88% and specificity of 100%; only one IDC was misclassified. Meanwhile, the acquisition of the D-FFOCT images was non-destructive and did not require any tissue preparation or staining procedures. In the simulated intraoperative margin evaluation procedure, the time required for our novel workflow (approximately 3 min) was significantly shorter than that required for traditional procedures (approximately 30 min). These findings indicate that the combination of D-FFOCT and deep learning algorithms can streamline intraoperative cancer diagnosis independently of traditional pathology laboratory procedures.

Accurate prediction of myopic progression and high myopia by machine learning.

Background: Myopia is a leading cause of visual impairment in Asia and worldwide. However, accurately predicting the progression of myopia and the high risk of myopia remains a challenge. This study aims to develop a predictive model for the development of myopia. Methods: We first retrospectively gathered 612 530 medical records from five independent cohorts, encompassing 227 543 patients ranging from infants to young adults. Subsequently, we developed a multivariate linear regression algorithm model to predict the progression of myopia and the risk of high myopia. Result: The model to predict the progression of myopia achieved an R2 value of 0.964 vs a mean absolute error (MAE) of 0.119D [95% confidence interval (CI): 0.119, 1.146] in the internal validation set. It demonstrated strong generalizability, maintaining consistent performance across external validation sets: R2 = 0.950 vs MAE = 0.119D (95% CI: 0.119, 1.136) in validation study 1, R2 = 0.950 vs MAE = 0.121D (95% CI: 0.121, 1.144) in validation study 2, and R2 = 0.806 vs MAE = -0.066D (95% CI: -0.066, 0.569) in the Shanghai Children Myopia Study. In the Beijing Children Eye Study, the model achieved an R2 of 0.749 vs a MAE of 0.178D (95% CI: 0.178, 1.557). The model to predict the risk of high myopia achieved an area under the curve (AUC) of 0.99 in the internal validation set and consistently high area under the curve values of 0.99, 0.99, 0.96 and 0.99 in the respective external validation sets. Conclusion: Our study demonstrates accurate prediction of myopia progression and risk of high myopia providing valuable insights for tailoring strategies to personalize and optimize the clinical management of myopia in children.

Accurate estimation of biological age and its application in disease prediction using a multimodal image Transformer system.

Aging in an individual refers to the temporal change, mostly decline, in the body's ability to meet physiological demands. Biological age (BA) is a biomarker of chronological aging and can be used to stratify populations to predict certain age-related chronic diseases. BA can be predicted from biomedical features such as brain MRI, retinal, or facial images, but the inherent heterogeneity in the aging process limits the usefulness of BA predicted from individual body systems. In this paper, we developed a multimodal Transformer-based architecture with cross-attention which was able to combine facial, tongue, and retinal images to estimate BA. We trained our model using facial, tongue, and retinal images from 11,223 healthy subjects and demonstrated that using a fusion of the three image modalities achieved the most accurate BA predictions. We validated our approach on a test population of 2,840 individuals with six chronic diseases and obtained significant difference between chronological age and BA (AgeDiff) than that of healthy subjects. We showed that AgeDiff has the potential to be utilized as a standalone biomarker or conjunctively alongside other known factors for risk stratification and progression prediction of chronic diseases. Our results therefore highlight the feasibility of using multimodal images to estimate and interrogate the aging process.

Optimized glycemic control of type 2 diabetes with reinforcement learning: a proof-of-concept trial.

The personalized titration and optimization of insulin regimens for treatment of type 2 diabetes (T2D) are resource-demanding healthcare tasks. Here we propose a model-based reinforcement learning (RL) framework (called RL-DITR), which learns the optimal insulin regimen by analyzing glycemic state rewards through patient model interactions. When evaluated during the development phase for managing hospitalized patients with T2D, RL-DITR achieved superior insulin titration optimization (mean absolute error (MAE) of 1.10 ± 0.03 U) compared to other deep learning models and standard clinical methods. We performed a stepwise clinical validation of the artificial intelligence system from simulation to deployment, demonstrating better performance in glycemic control in inpatients compared to junior and intermediate-level physicians through quantitative (MAE of 1.18 ± 0.09 U) and qualitative metrics from a blinded review. Additionally, we conducted a single-arm, patient-blinded, proof-of-concept feasibility trial in 16 patients with T2D. The primary outcome was difference in mean daily capillary blood glucose during the trial, which decreased from 11.1 (±3.6) to 8.6 (±2.4) mmol L-1 (P < 0.01), meeting the pre-specified endpoint. No episodes of severe hypoglycemia or hyperglycemia with ketosis occurred. These preliminary results warrant further investigation in larger, more diverse clinical studies. ClinicalTrials.gov registration: NCT05409391 .

Loss of the Novel Myelin Protein CMTM5 in Multiple Sclerosis Lesions and Its Involvement in Oligodendroglial Stress Responses.

This study comprehensively addresses the involvement of the protein CKLF-like Marvel transmembrane domain-containing family member 5 (CMTM5) in the context of demyelination and cytodegenerative autoimmune diseases, particularly multiple Sclerosis (MS). An observed reduction in CMTM5 expression in post-mortem MS lesions prompted further investigations in both in vitro and in vivo animal models. In the cuprizone animal model, we detected a decrease in CMTM5 expression in oligodendrocytes that is absent in other members of the CMTM protein family. Our findings also confirm these results in the experimental autoimmune encephalomyelitis (EAE) model with decreased CMTM5 expression in both cerebellum and spinal cord white matter. We also examined the effects of a Cmtm5 knockdown in vitro in the oligodendroglial Oli-neu mouse cell line using the CRISPR interference technique. Interestingly, we found no effects on cell response to thapsigargin-induced endoplasmic reticulum (ER) stress as determined by Atf4 activity, an indicator of cellular stress responses. Overall, these results substantiate previous findings suggesting that CMTM5, rather than contributing to myelin biogenesis, is involved in maintaining axonal integrity. Our study further demonstrates that the knockdown of Cmtm5 in vitro does not modulate oligodendroglial responses to ER stress. These results warrant further investigation into the functional role of CMTM5 during axonal degeneration in the context of demyelinating conditions.

Bioengineered human tissue regeneration and repair using endogenous stem cells.

We describe a general approach to produce bone and cartilaginous structures utilizing the self-regenerative capacity of the intercostal rib space to treat a deformed metacarpophalangeal joint and microtia. Anatomically precise 3D molds were positioned on the perichondro-periosteal or perichondral flap of the intercostal rib without any other exogenous elements. We find anatomically precise metacarpal head and auricle constructs within the implanted molds after 6 months. The regenerated metacarpal head was used successfully to surgically repair the deformed metacarpophalangeal joint. Auricle reconstructive surgery in five unilateral microtia patients yielded good aesthetic and functional results. Long-term follow-up revealed the auricle constructs were safe and stable. Single-cell RNA sequencing analysis reveal early infiltration of a cell population consistent with mesenchymal stem cells, followed by IL-8-stimulated differentiation into chondrocytes. Our results demonstrate the repair and regeneration of tissues using only endogenous factors and a viable treatment strategy for bone and tissue structural defects.

Deep-learning-enabled protein-protein interaction analysis for prediction of SARS-CoV-2 infectivity and variant evolution.

Host-pathogen interactions and pathogen evolution are underpinned by protein-protein interactions between viral and host proteins. An understanding of how viral variants affect protein-protein binding is important for predicting viral-host interactions, such as the emergence of new pathogenic SARS-CoV-2 variants. Here we propose an artificial intelligence-based framework called UniBind, in which proteins are represented as a graph at the residue and atom levels. UniBind integrates protein three-dimensional structure and binding affinity and is capable of multi-task learning for heterogeneous biological data integration. In systematic tests on benchmark datasets and further experimental validation, UniBind effectively and scalably predicted the effects of SARS-CoV-2 spike protein variants on their binding affinities to the human ACE2 receptor, as well as to SARS-CoV-2 neutralizing monoclonal antibodies. Furthermore, in a cross-species analysis, UniBind could be applied to predict host susceptibility to SARS-CoV-2 variants and to predict future viral variant evolutionary trends. This in silico approach has the potential to serve as an early warning system for problematic emerging SARS-CoV-2 variants, as well as to facilitate research on protein-protein interactions in general.

A transformer-based representation-learning model with unified processing of multimodal input for clinical diagnostics.

During the diagnostic process, clinicians leverage multimodal information, such as the chief complaint, medical images and laboratory test results. Deep-learning models for aiding diagnosis have yet to meet this requirement of leveraging multimodal information. Here we report a transformer-based representation-learning model as a clinical diagnostic aid that processes multimodal input in a unified manner. Rather than learning modality-specific features, the model leverages embedding layers to convert images and unstructured and structured text into visual tokens and text tokens, and uses bidirectional blocks with intramodal and intermodal attention to learn holistic representations of radiographs, the unstructured chief complaint and clinical history, and structured clinical information such as laboratory test results and patient demographic information. The unified model outperformed an image-only model and non-unified multimodal diagnosis models in the identification of pulmonary disease (by 12% and 9%, respectively) and in the prediction of adverse clinical outcomes in patients with COVID-19 (by 29% and 7%, respectively). Unified multimodal transformer-based models may help streamline the triaging of patients and facilitate the clinical decision-making process.

MedKPL: A heterogeneous knowledge enhanced prompt learning framework for transferable diagnosis.

Artificial Intelligence (AI) based diagnosis systems have emerged as powerful tools to reform traditional medical care. Each clinician now wants to have his own intelligent diagnostic partner to expand the range of services he can provide. However, the implementation of intelligent decision support systems based on clinical note has been hindered by the lack of extensibility of end-to-end AI diagnosis algorithms. When reading a clinical note, expert clinicians make inferences with relevant medical knowledge, which serve as prompts for making accurate diagnoses. Therefore, external medical knowledge is commonly employed as an augmentation for medical text classification tasks. Existing methods, however, cannot integrate knowledge from various knowledge sources as prompts nor can fully utilize explicit and implicit knowledge. To address these issues, we propose a Medical Knowledge-enhanced Prompt Learning (MedKPL) diagnostic framework for transferable clinical note classification. Firstly, to overcome the heterogeneity of knowledge sources, such as knowledge graphs or medical QA databases, MedKPL uniform the knowledge relevant to the disease into text sequences of fixed format. Then, MedKPL integrates medical knowledge into the prompt designed for context representation. Therefore, MedKPL can integrate knowledge into the models to enhance diagnostic performance and effectively transfer to new diseases by using relevant disease knowledge. The results of our experiments on two medical datasets demonstrate that our method yields superior medical text classification results and performs better in cross-departmental transfer tasks under few-shot or even zero-shot settings. These findings demonstrate that our MedKPL framework has the potential to improve the interpretability and transferability of current diagnostic systems.

MicroRNA-Disease Network Analysis Repurposes Methotrexate for the Treatment of Abdominal Aortic Aneurysm in Mice.

Abdominal aortic aneurysm (AAA) is a permanent dilatation of the abdominal aorta and is highly lethal. The main purpose of the current study is to search for noninvasive medical therapies for AAA, for which there is currently no effective drug therapy. Network medicine represents a cutting-edge technology, as analysis and modeling of disease networks can provide critical clues regarding the etiology of specific diseases and which therapeutics may be effective. Here, we proposed a novel algorithm to quantify disease relations based on a large accumulated microRNA-disease association dataset and then built a disease network covering 15 disease classes and 304 diseases. Analysis revealed some patterns for these diseases. For instance, diseases tended to be clustered and coherent in the network. Surprisingly, we found that AAA showed the strongest similarity with rheumatoid arthritis and systemic lupus erythematosus, both of which are autoimmune diseases, suggesting that AAA could be one type of autoimmune disease in etiology. Based on this observation, we further hypothesized that drugs for autoimmune disease could be repurposed for the prevention and therapy of AAA. Finally, animal experiments confirmed that methotrexate, a drug for autoimmune disease, was able to alleviated the formation and development of AAA.

A deep-learning system predicts glaucoma incidence and progression using retinal photographs.

BackgroundDeep learning has been widely used for glaucoma diagnosis. However, there is no clinically validated algorithm for glaucoma incidence and progression prediction. This study aims to develop a clinically feasible deep-learning system for predicting and stratifying the risk of glaucoma onset and progression based on color fundus photographs (CFPs), with clinical validation of performance in external population cohorts.MethodsWe established data sets of CFPs and visual fields collected from longitudinal cohorts. The mean follow-up duration was 3 to 5 years across the data sets. Artificial intelligence (AI) models were developed to predict future glaucoma incidence and progression based on the CFPs of 17,497 eyes in 9346 patients. The area under the receiver operating characteristic (AUROC) curve, sensitivity, and specificity of the AI models were calculated with reference to the labels provided by experienced ophthalmologists. Incidence and progression of glaucoma were determined based on longitudinal CFP images or visual fields, respectively.ResultsThe AI model to predict glaucoma incidence achieved an AUROC of 0.90 (0.81-0.99) in the validation set and demonstrated good generalizability, with AUROCs of 0.89 (0.83-0.95) and 0.88 (0.79-0.97) in external test sets 1 and 2, respectively. The AI model to predict glaucoma progression achieved an AUROC of 0.91 (0.88-0.94) in the validation set, and also demonstrated outstanding predictive performance with AUROCs of 0.87 (0.81-0.92) and 0.88 (0.83-0.94) in external test sets 1 and 2, respectively.ConclusionOur study demonstrates the feasibility of deep-learning algorithms in the early detection and prediction of glaucoma progression.FUNDINGNational Natural Science Foundation of China (NSFC); the High-level Hospital Construction Project, Zhongshan Ophthalmic Center, Sun Yat-sen University; the Science and Technology Program of Guangzhou, China (2021), the Science and Technology Development Fund (FDCT) of Macau, and FDCT-NSFC.

Lipid metabolism dysfunction induced by age-dependent DNA methylation accelerates aging.

Epigenetic alterations and metabolic dysfunction are two hallmarks of aging. However, the mechanism of how their interaction regulates aging, particularly in mammals, remains largely unknown. Here we show ELOVL fatty acid elongase 2 (Elovl2), a gene whose epigenetic alterations are most highly correlated with age prediction, contributes to aging by regulating lipid metabolism. We applied artificial intelligence to predict the protein structure of ELOVL2 and the interaction with its substrate. Impaired Elovl2 function disturbs lipid synthesis with increased endoplasmic reticulum stress and mitochondrial dysfunction, leading to key aging phenotypes at both cellular and physiological level. Furthermore, restoration of mitochondrial activity can rescue age-related macular degeneration (AMD) phenotypes induced by Elovl2 deficiency in human retinal pigmental epithelial (RPE) cells; this indicates a conservative mechanism in both human and mouse. Taken together, we revealed an epigenetic-metabolism axis contributing to aging and illustrate the power of an AI-based approach in structure-function studies.

Putative Prevention of XML Injection Against Myocardial Ischemia Is Mediated by PKC and PLA2 Proteins.

Background: Xinmailong (XML) injection is a CFDA-approved traditional Chinese medicine with clinical value for heart failure treatment. The present investigation was aimed to evaluate the potential protective roles of this injection on myocardial ischemia and the underlying molecular mechanism. Methods: In our study, we selected two models of myocardial ischemia rats. Rats were randomly divided into six groups, with saline or XML administrated 4 days before ischemia model establishment. ECG of different time intervals and biochemical parameters of end point were measured. The potential mechanisms of the protective role of XML were explored using system pharmacology and molecular biology approaches. Results: Myocardial ischemia rats demonstrated abnormal ECG and serum levels of cTnT. Pretreatment with XML significantly attenuated these damages, especially the medium doses. GO and KEGG analysis revealed that the 90 putative target genes were associated with pathways of fatty acid absorption/metabolism, inflammation, RAAS, and vascular smooth muscle. Further network pharmacology method identified five main chemical ingredients and potential targets of XML injection for myocardial ischemia. Mechanically, the beneficial effect of XML injection was mediated by the reactive oxygen species (ROS) inhibition and inflammation attenuation via regulating the expression levels of targets of PKC and PLA2. Conclusion: These findings indicate that XML exerts protective effects against myocardial injury, with attenuated ROS production, apoptosis, and inflammation. Therefore, we speculate that XML may be an alternative supplementary therapeutic agent for myocardial ischemia prevention.

Deep-learning models for the detection and incidence prediction of chronic kidney disease and type 2 diabetes from retinal fundus images.

Regular screening for the early detection of common chronic diseases might benefit from the use of deep-learning approaches, particularly in resource-poor or remote settings. Here we show that deep-learning models can be used to identify chronic kidney disease and type 2 diabetes solely from fundus images or in combination with clinical metadata (age, sex, height, weight, body-mass index and blood pressure) with areas under the receiver operating characteristic curve of 0.85-0.93. The models were trained and validated with a total of 115,344 retinal fundus photographs from 57,672 patients and can also be used to predict estimated glomerulal filtration rates and blood-glucose levels, with mean absolute errors of 11.1-13.4 ml min-1 per 1.73 m2 and 0.65-1.1 mmol l-1, and to stratify patients according to disease-progression risk. We evaluated the generalizability of the models for the identification of chronic kidney disease and type 2 diabetes with population-based external validation cohorts and via a prospective study with fundus images captured with smartphones, and assessed the feasibility of predicting disease progression in a longitudinal cohort.

Steering the Methane Dry Reforming Reactivity of Ni/La2O3 Catalysts by Controlled In Situ Decomposition of Doped La2NiO4 Precursor Structures.

The influence of A- and/or B-site doping of Ruddlesden-Popper perovskite materials on the crystal structure, stability, and dry reforming of methane (DRM) reactivity of specific A2BO4 phases (A = La, Ba; B = Cu, Ni) has been evaluated by a combination of catalytic experiments, in situ X-ray diffraction, X-ray absorption spectroscopy (XAS), X-ray photoelectron spectroscopy (XPS), and aberration-corrected electron microscopy. At room temperature, B-site doping of La2NiO4 with Cu stabilizes the orthorhombic structure (Fmmm) of the perovskite, while A-site doping with Ba yields a tetragonal space group (I4/mmm). We observed the orthorhombic-to-tetragonal transformation above 170 °C for La2Ni0.9Cu0.1O4 and La2Ni0.8Cu0.2O4, slightly higher than for undoped La2NiO4. Loss of oxygen in interstitial sites of the tetragonal structure causes further structure transformations for all samples before decomposition in the temperature range of 400 °C-600 °C. Controlled in situ decomposition of the parent or A/B-site doped perovskite structures in a DRM mixture (CH4:CO2 = 1:1) in all cases yields an active phase consisting of exsolved nanocrystalline metallic Ni particles in contact with hexagonal La2O3 and a mixture of (oxy)carbonate phases (hexagonal and monoclinic La2O2CO3, BaCO3). Differences in the catalytic activity evolve because of (i) the in situ formation of Ni-Cu alloy phases (in a composition of >7:1 = Ni:Cu) for La2Ni0.9Cu0.1O4, La2Ni0.8Cu0.2O4, and La1.8Ba0.2Ni0.9Cu0.1O4, (ii) the resulting Ni particle size and amount of exsolved Ni, and (iii) the inherently different reactivity of the present (oxy)carbonate species. Based on the onset temperature of catalytic DRM activity, the latter decreases in the order of La2Ni0.9Cu0.1O4 ∼ La2Ni0.8Cu0.2O4 ≥ La1.8Ba0.2Ni0.9Cu0.1O4 > La2NiO4 > La1.8Ba0.2NiO4. Simple A-site doped La1.8Ba0.2NiO4 is essentially DRM inactive. The Ni particle size can be efficiently influenced by introducing Ba into the A site of the respective Ruddlesden-Popper structures, allowing us to control the Ni particle size between 10 nm and 30 nm both for simple B-site and A-site doped structures. Hence, it is possible to steer both the extent of the metal-oxide-(oxy)carbonate interface and its chemical composition and reactivity. Counteracting the limitation of the larger Ni particle size, the activity can, however, be improved by additional Cu-doping on the B-site, enhancing the carbon reactivity. Exemplified for the La2NiO4 based systems, we show how the delicate antagonistic balance of doping with Cu (rendering the La2NiO4 structure less stable and suppressing coking by efficiently removing surface carbon) and Ba (rendering the La2NiO4 structure more stable and forming unreactive surface or interfacial carbonates) can be used to tailor prospective DRM-active catalysts.

EyeHealer: A large-scale anterior eye segment dataset with eye structure and lesion annotations.

Anterior segment eye diseases account for a significant proportion of presentations to eye clinics worldwide, including diseases associated with corneal pathologies, anterior chamber abnormalities (e.g. blood or inflammation), and lens diseases. The construction of an automatic tool for segmentation of anterior segment eye lesions would greatly improve the efficiency of clinical care. With research on artificial intelligence progressing in recent years, deep learning models have shown their superiority in image classification and segmentation. The training and evaluation of deep learning models should be based on a large amount of data annotated with expertise; however, such data are relatively scarce in the domain of medicine. Herein, the authors developed a new medical image annotation system, called EyeHealer. It is a large-scale anterior eye segment dataset with both eye structures and lesions annotated at the pixel level. Comprehensive experiments were conducted to verify its performance in disease classification and eye lesion segmentation. The results showed that semantic segmentation models outperformed medical segmentation models. This paper describes the establishment of the system for automated classification and segmentation tasks. The dataset will be made publicly available to encourage future research in this area.

Cold-Inducible Klf9 Regulates Thermogenesis of Brown and Beige Fat.

Promoting development and function of brown and beige fat may represent an attractive treatment of obesity. In the current study, we show that fat Klf9 expression is markedly induced by cold exposure and a ß-adrenergic agonist. Moreover, Klf9 expression levels in human white adipose tissue (WAT) are inversely correlated with adiposity, and Klf9 overexpression in primary fat cells stimulates cellular thermogenesis, which is Ucp1 dependent. Fat-specific Klf9 transgenic mice gain less weight and have smaller fat pads due to increased thermogenesis of brown and beige fat. Moreover, Klf9 transgenic mice displayed lower fasting blood glucose levels and improved glucose tolerance and insulin sensitivity under the high-fat diet condition. Conversely, Klf9 mutation in brown adipocytes reduces the expression of thermogenic genes, causing a reduction in cellular respiration. Klf9-mutant mice exhibited obesity and cold sensitivity due to impairments in the thermogenic function of fat. Finally, fat Klf9 deletion inhibits the ß3 agonist-mediated induction of WAT browning and brown adipose tissue thermogenesis. Mechanistically, cold-inducible Klf9 stimulates expression of Pgc1α, a master regulator of fat thermogenesis, by a direct binding to its gene promoter region, subsequently promoting energy expenditure. The current study reveals a critical role for KLF9 in mediating thermogenesis of brown and beige fat.

Annotation and curation of the causality information in LncRNADisease.

Disease causative non-coding RNAs (ncRNAs) are of great importance in understanding a disease, for they directly contribute to the development or progress of a disease. Identifying the causative ncRNAs can provide vital implications for biomedical researches. In this work, we updated the long non-coding RNA disease database (LncRNADisease) with long non-coding RNA (lncRNA) causality information with manual annotations of the causal associations between lncRNAs/circular RNAs (circRNAs) and diseases by reviewing related publications. Of the total 11 568 experimental associations, 2297 out of 10 564 lncRNA-disease associations and 198 out of 1004 circRNA-disease associations were identified to be causal, whereas 635 lncRNAs and 126 circRNAs were identified to be causative for the development or progress of at least one disease. The updated information and functions of the database can offer great help to future researches involving lncRNA/circRNA-disease relationship. The latest LncRNADisease database is available at http://www.rnanut.net/lncrnadisease.

Profiling and bioinformatic analysis reveal differential microRNA expression in the left and right kidneys in normal mice.

Physiological and pathophysiological differences exist between the left and right kidneys; however, the molecular bases for these differences remain unknown. Since miRNAs are involved in kidney function and the development of kidney diseases, we examined their differential expression through miRNA profiling of the left and right kidneys of normal mice. We find that 36 miRNAs exhibit higher expression, whereas 22 miRNAs show lower expression in the left than the right kidneys in mice under physiological condition. Ten miRNAs were further examined by quantitative PCR assays, and four of them with high expression level were confirmed by Northern blot. Through bioinformatic analysis, we dissected the function and network of the differentially expressed miRNAs, providing insights into the physiological and pathophysiological differences between the left and the right kidneys.

Benchmark of computational methods for predicting microRNA-disease associations.

BACKGROUND: A series of miRNA-disease association prediction methods have been proposed to prioritize potential disease-associated miRNAs. Independent benchmarking of these methods is warranted to assess their effectiveness and robustness. RESULTS: Based on more than 8000 novel miRNA-disease associations from the latest HMDD v3.1 database, we perform systematic comparison among 36 readily available prediction methods. Their overall performances are evaluated with rigorous precision-recall curve analysis, where 13 methods show acceptable accuracy (AUPRC > 0.200) while the top two methods achieve a promising AUPRC over 0.300, and most of these methods are also highly ranked when considering only the causal miRNA-disease associations as the positive samples. The potential of performance improvement is demonstrated by combining different predictors or adopting a more updated miRNA similarity matrix, which would result in up to 16% and 46% of AUPRC augmentations compared to the best single predictor and the predictors using the previous similarity matrix, respectively. Our analysis suggests a common issue of the available methods, which is that the prediction results are severely biased toward well-annotated diseases with many associated miRNAs known and cannot further stratify the positive samples by discriminating the causal miRNA-disease associations from the general miRNA-disease associations. CONCLUSION: Our benchmarking results not only provide a reference for biomedical researchers to choose appropriate miRNA-disease association predictors for their purpose, but also suggest the future directions for the development of more robust miRNA-disease association predictors.