Microbiome studies have revealed gut microbiota\'s potential impact on complex diseases. However, many studies often focus on one disease per cohort. We developed a meta-analysis workflow for gut microbiome profiles and analyzed shotgun metagenomic data covering 11 diseases. Using interpretable machine learning and differential abundance analysis, our findings reinforce the generalization of binary classifiers for Crohn\'s disease (CD) and colorectal cancer (CRC) to hold-out cohorts and highlight the key microbes driving these classifications. We identified high microbial similarity in disease pairs like CD vs ulcerative colitis (UC), CD vs CRC, Parkinson\'s disease vs type 2 diabetes (T2D), and schizophrenia vs T2D. We also found strong inverse correlations in Alzheimer\'s disease vs CD and UC. These findings, detected by our pipeline, provide valuable insights into these diseases.
OBJECTIVE: Assessing disease similarity is an essential initial step preceding a disease-based approach for drug repositioning. Our study provides a modest first step in underscoring the potential of integrating microbiome insights into the disease similarity assessment. Recent microbiome research has predominantly focused on analyzing individual diseases to understand their unique characteristics, which by design excludes comorbidities in individuals. We analyzed shotgun metagenomic data from existing studies and identified previously unknown similarities between diseases. Our research represents a pioneering effort that utilizes both interpretable machine learning and differential abundance analysis to assess microbial similarity between diseases.

The categorization of human diseases is mainly based on the affected organ system and phenotypic characteristics. This is limiting the view to the pathological manifestations, while it neglects mechanistic relationships that are crucial to develop therapeutic strategies. This work aims to advance the understanding of diseases and their relatedness beyond traditional phenotypic views. Hence, the similarity among 502 diseases is mapped using six different data dimensions encompassing molecular, clinical, and pharmacological information retrieved from public sources. Multiple distance measures and multi-view clustering are used to assess the patterns of disease relatedness. The integration of all six dimensions into a consensus map of disease relationships reveals a divergent disease view from the International Classification of Diseases (ICD), emphasizing novel insights offered by a multi-view disease map. Disease features such as genes, pathways, and chemicals that are enriched in distinct disease groups are identified. Finally, an evaluation of the top similar diseases of three candidate diseases common in the Western population shows concordance with known epidemiological associations and reveals rare features shared between Type 2 diabetes (T2D) and Alzheimer\'s disease. A revision of disease relationships holds promise for facilitating the reconstruction of comorbidity patterns, repurposing drugs, and advancing drug discovery in the future.

Microbiome studies have revealed gut microbiota\'s potential impact on complex diseases. However, many studies often focus on one disease per cohort. We developed a meta-analysis workflow for gut microbiome profiles and analyzed shotgun metagenomic data covering 11 diseases. Using interpretable machine learning and differential abundance analysis, our findings reinforce the generalization of binary classifiers for Crohn\'s disease (CD) and colorectal cancer (CRC) to hold-out cohorts and highlight the key microbes driving these classifications. We identified high microbial similarity in disease pairs like CD vs ulcerative colitis (UC), CD vs CRC, Parkinson\'s disease vs type 2 diabetes (T2D), and schizophrenia vs T2D. We also found strong inverse correlations in Alzheimer\'s disease vs CD and UC. These findings detected by our pipeline provide valuable insights into these diseases.

There is strong evidence to support that mutations and dysregulation of miRNAs are associated with a variety of diseases, including cancer. However, the experimental methods used to identify disease-related miRNAs are expensive and time-consuming. Effective computational approaches to identify disease-related miRNAs are in high demand and would aid in the detection of lncRNA biomarkers for disease diagnosis, treatment, and prevention. In this study, we develop an ensemble learning framework to reveal the potential associations between miRNAs and diseases (ELMDA). The ELMDA framework does not rely on the known associations when calculating miRNA and disease similarities and uses multi-classifiers voting to predict disease-related miRNAs. As a result, the average AUC of the ELMDA framework was 0.9229 for the HMDD v2.0 database in a fivefold cross-validation. All potential associations in the HMDD V2.0 database were predicted, and 90% of the top 50 results were verified with the updated HMDD V3.2 database. The ELMDA framework was implemented to investigate gastric neoplasms, prostate neoplasms and colon neoplasms, and 100%, 94%, and 90%, respectively, of the top 50 potential miRNAs were validated by the HMDD V3.2 database. Moreover, the ELMDA framework can predict isolated disease-related miRNAs. In conclusion, ELMDA appears to be a reliable method to uncover disease-associated miRNAs.

COVID-19 vaccines greatly reduce the risk of infection with SARS-CoV-2. However, some people have adverse reactions after vaccination, and these can sometimes be severe. Gender, age, vaccines, and especially certain diseases histories are related to severe adverse reactions following COVID-19 vaccination. However, there are thousands of diseases and only some are known to be related to these severe adverse reactions. The risk of severe adverse reactions with other diseases remains unknown. Therefore, there is a need for predictive studies to provide improved medical care and minimize risk. Herein, we analyzed the statistical results of existing COVID-19 vaccine adverse reaction data and proposed a COVID-19 vaccine severe adverse reaction risk prediction method, named CVSARRP. The performance of the CVSARRP method was tested using the leave-one-out cross-validation approach. The correlation coefficient between the predicted and real risk is greater than 0.86. The CVSARRP method predicts the risk from adverse reactions to severe adverse reactions after COVID-19 vaccination for 10855 diseases. People with certain diseases, such as central nervous system diseases, heart diseases, urinary system disease, anemia, cancer, and respiratory tract disease, among others, may potentially have increased of severe adverse reactions following vaccination against COVID-19 and experiencing adverse events.

BACKGROUND: MicroRNAs (miRNAs) have been confirmed to be inextricably linked to the emergence of human complex diseases. The identification of the disease-related miRNAs has gradually become a routine way to unveil the genetic mechanisms of examined disorders.
METHODS: In this study, a method BLNIMDA based on a weighted bi-level network was proposed for predicting hidden associations between miRNAs and diseases. For this purpose, the known associations between miRNAs and diseases as well as integrated similarities between miRNAs and diseases are mapped into a bi-level network. Based on the developed bi-level network, the miRNA-disease associations (MDAs) are defined as strong associations, potential associations and no associations. Then, each miRNA-disease pair (MDP) is assigned two information properties according to the bidirectional information distribution strategy, i.e., associations of miRNA towards disease and vice-versa. Finally, two affinity weights for each MDP obtained from the information properties and the association type are then averaged as the final association score of the MDP. Highlights of the BLNIMDA lie in the definition of MDA types, and the introduction of affinity weights evaluation from the bidirectional information distribution strategy and defined association types, which ensure the comprehensiveness and accuracy of the final prediction score of MDAs.
RESULTS: Five-fold cross-validation and leave-one-out cross-validation are used to evaluate the performance of the BLNIMDA. The results of the Area Under Curve show that the BLNIMDA has many advantages over the other seven selected computational methods. Furthermore, the case studies based on four common diseases and miRNAs prove that the BLNIMDA has good predictive performance.
CONCLUSIONS: Therefore, the BLNIMDA is an effective method for predicting hidden MDAs.

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder with heterogeneous clinical presentation, variable severity, and multiple comorbidities. A complex underlying genetic architecture matches the clinical heterogeneity, and evidence indicates that several co-occurring brain disorders share a genetic component with ASD. In this study, we established a genetic similarity disease network approach to explore the shared genetics between ASD and frequent comorbid brain diseases (and subtypes), namely Intellectual Disability, Attention-Deficit/Hyperactivity Disorder, and Epilepsy, as well as other rarely co-occurring neuropsychiatric conditions in the Schizophrenia and Bipolar Disease spectrum. Using sets of disease-associated genes curated by the DisGeNET database, disease genetic similarity was estimated from the Jaccard coefficient between disease pairs, and the Leiden detection algorithm was used to identify network disease communities and define shared biological pathways. We identified a heterogeneous brain disease community that is genetically more similar to ASD, and that includes Epilepsy, Bipolar Disorder, Attention-Deficit/Hyperactivity Disorder combined type, and some disorders in the Schizophrenia Spectrum. To identify loss-of-function rare de novo variants within shared genes underlying the disease communities, we analyzed a large ASD whole-genome sequencing dataset, showing that ASD shares genes with multiple brain disorders from other, less genetically similar, communities. Some genes (e.g., SHANK3, ASH1L, SCN2A, CHD2, and MECP2) were previously implicated in ASD and these disorders. This approach enabled further clarification of genetic sharing between ASD and brain disorders, with a finer granularity in disease classification and multi-level evidence from DisGeNET. Understanding genetic sharing across disorders has important implications for disease nosology, pathophysiology, and personalized treatment.

Drug-Induced Liver Injury (DILI), despite its low occurrence rate, can cause severe side effects or even lead to death. Thus, it is one of the leading causes for terminating the development of new, and restricting the use of already-circulating, drugs. Moreover, its multifactorial nature, combined with a clinical presentation that often mimics other liver diseases, complicate the identification of DILI-related (or \"positive\") literature, which remains the main medium for sourcing results from the clinical practice and experimental studies. This work-contributing to the \"Literature AI for DILI Challenge\" of the Critical Assessment of Massive Data Analysis (CAMDA) 2021- presents an automated pipeline for distinguishing between DILI-positive and negative publications. We used Natural Language Processing (NLP) to filter out the uninformative parts of a text, and identify and extract mentions of chemicals and diseases. We combined that information with small-molecule and disease embeddings, which are capable of capturing chemical and disease similarities, to improve classification performance. The former were directly sourced from the Chemical Checker (CC). For the latter, we collected data that encode different aspects of disease similarity from the National Library of Medicine\'s (NLM) Medical Subject Headings (MeSH) thesaurus and the Comparative Toxicogenomics Database (CTD). Following a similar procedure as the one used in the CC, vector representations for diseases were learnt and evaluated. Two Neural Network (NN) classifiers were developed: a baseline model that accepts texts as input and an augmented, extended, model that also utilises chemical and disease embeddings. We trained, validated, and tested the classifiers through a Nested Cross-Validation (NCV) scheme with 10 outer and 5 inner folds. During this, the baseline and extended models performed virtually identically, with F1-scores of 95.04 ± 0.61% and 94.80 ± 0.41%, respectively. Upon validation on an external, withheld, dataset that is meant to assess classifier generalisability, the extended model achieved an F1-score of 91.14 ± 1.62%, outperforming its baseline counterpart which received a lower score of 88.30 ± 2.44%. We make further comparisons between the classifiers and discuss future improvements and directions, including utilising chemical and disease embeddings for visualisation and exploratory analysis of the DILI-positive literature.

BACKGROUND: Measuring similarity between complex diseases has significant implications for revealing the pathogenesis of diseases and development in the domain of biomedicine. It has been consentaneous that functional associations between disease-related genes and semantic associations can be applied to calculate disease similarity. Currently, more and more studies have demonstrated the profound involvement of non-coding RNA in the regulation of genome organization and gene expression. Thus, taking ncRNA into account can be useful in measuring disease similarities. However, existing methods ignore the regulation functions of ncRNA in biological process. In this study, we proposed a novel deep-learning method to deduce disease similarity.
RESULTS: In this article, we proposed a novel method, ImpAESim, a framework integrating multiple networks embedding to learn compact feature representations and disease similarity calculation. We first utilize three different disease-related information networks to build up a heterogeneous network, after a network diffusion process, RWR, a compact feature learning model composed of classic Auto Encoder (AE) and improved AE model is proposed to extract constraints and low-dimensional feature representations. We finally obtain an accurate and low-dimensional feature representation of diseases, then we employed the cosine distance as the measurement of disease similarity.
CONCLUSIONS: ImpAESim focuses on extracting a low-dimensional vector representation of features based on ncRNA regulation, and gene-gene interaction network. Our method can significantly reduce the calculation bias resulted from the sparse disease associations which are derived from semantic associations.

Long noncoding RNA (lncRNA), a type of more than 200 nucleotides non-coding RNA, is related to various complex diseases. To precisely identify the potential lncRNA-disease association is important to understand the disease pathogenesis, to develop new drugs, and to design individualized diagnosis and treatment methods for different human diseases. Compared with the complexity and high cost of biological experiments, computational methods can quickly and effectively predict potential lncRNA-disease associations. Thus, it is a promising avenue to develop computational methods for lncRNA-disease prediction. However, owing to the low prediction accuracy ofstate of the art methods, it is vastly challenging to accurately and effectively identify lncRNA-disease at present. This article proposed an integrated method called LPARP, which is based on label-propagation algorithm and random projection to address the issue. Specifically, the label-propagation algorithm is initially used to obtain the estimated scores of lncRNA-disease associations, and then random projections are used to accurately predict disease-related lncRNAs.The empirical experiments showed that LAPRP achieved good prediction on three golddatasets, which is superior to existing state-of-the-art prediction methods. It can also be used to predict isolated diseases and new lncRNAs. Case studies of bladder cancer, esophageal squamous-cell carcinoma, and colorectal cancer further prove the reliability of the method. The proposed LPARP algorithm can predict the potential lncRNA-disease interactions stably and effectively with fewer data. LPARP can be used as an effective and reliable tool for biomedical research.