Mild cognitive impairment (MCI) and Alzheimer’s Disease (AD) are complex diseases with their molecular architecture not elucidated. APOE, Amyloid Beta Precursor Protein (APP), and Presenilin-1 (PSEN1) are well-known genes associated with both MCI and AD. Recently, epigenetic alterations and dysregulated regulatory elements, such as microRNAs (miRNAs), have been reported associated with neurodegeneration. In this study, differential expression analysis (DEA) was performed for genes and miRNAs based on microarray and RNA-Seq data. Global gene profile of healthy individuals, early and late mild cognitive impairment (EMCI and LMCI, respectively), and AD was obtained from ADNI Cohort. miRNA global profile of healthy individuals and AD patients was extracted from public RNA-Seq data. DEA performed with limma package on ADNI Cohort data highlighted eight differential expressed (DE) genes (AGER, LINC00483, MMP19, CATSPER1, ARFGAP1, GPER1, PHLPP2, TRPM2) (false discovery rate (FDR) p-value < 0.05) between EMCI and LMCI patients. Previous molecular studies showed associations between these genes with dementia and neurological-related pathways. Five dysregulated miRNAs were identified by DEA performed with RNA-Seq data and edgeR (FDR p-value < 0.002). All reported miRNAs in AD interact with the aforementioned genes. Our integrative transcriptomic analysis was able to identify a set of miRNA–gene interactions that may be involved in cognitive and neurodegeneration processes.

Nuclear DNA has been the main source of genome-wide loci association in neurodegenerative diseases, only partially accounting for the heritability of Alzheimer’s Disease (AD). In this context, mitochondrial DNA (mtDNA) is gaining more attention. Here, we investigated mitochondrial genes and genetic variants that may influence mild cognitive impairment and AD, through an integrative analysis including differential gene expression and mitochondrial genome-wide epistasis. We assessed the expression of mitochondrial genes in different brain tissues from two public RNA-Seq databases (GEO and GTEx). Then, we analyzed mtDNA from the ADNI Cohort and investigated epistasis regarding mitochondrial variants and levels of A${\beta }_{1-42}$, TAU, and Phosphorylated TAU (PTAU) from cognitively healthy controls, and both mild cognitive impairment (MCI) and AD cases. We identified multiple differentially expressed mitochondrial genes in the comparisons between cognitively healthy individuals and AD patients. We also found increased protein levels in MCI and AD patients when compared to healthy controls, as well as novel candidate networks of mtDNA epistasis, which included variants in all mitochondrially-encoded oxidative phosphorylation complexes, 12S rRNA and MT-DLOOP. Our results highlight layers of potential interactions involving mitochondrial genetics and suggest specific molecular alterations as potential biomarkers for AD.

Emerging deep learning-based applications in precision medicine include computational histopathological analysis. However, there is a lack of the required training image datasets to generate classification and detection models. This phenomenon occurs mainly due to human factors that make it difficult to obtain well-annotated data. The present study provides a curated public collection of histopathological images (DeepHP) and a convolutional neural network model for diagnosing gastritis. Images from gastric biopsy histopathological exams were used to investigate the performance of the proposed model in detecting gastric mucosa with Helicobacter pylori infection. The DeepHP database comprises 394,926 histopathological images, of which 111 K were labeled as Helicobacter pylori positive and 283 K were Helicobacter pylori negative. We investigated the classification performance of three Convolutional Neural Network architectures. The models were tested and validated with two distinct image sets of 15% (59K patches) chosen randomly. The VGG16 architecture showed the best results with an Area Under the Curve of 0.998%. The results showed that CNN could be used to classify histopathological images from gastric mucosa with marked precision. Our model evidenced high potential and application in the computational pathology field.

ClinVar is a web platform that stores ∼789,000 genetic associations with complex diseases. A partial set of these cataloged genetic associations has challenged clinicians and geneticists, often leading to conflicting interpretations or uncertain clinical impact significance. In this study, we addressed the (re)classification of genetic variants by AmazonForest, which is a random-forest-based pathogenicity metaprediction model that works by combining functional impact data from eight prediction tools. We evaluated the performance of representation learning algorithms such as autoencoders to propose a better strategy. All metaprediction models were trained with ClinVar data, and genetic variants were annotated with eight functional impact predictors cataloged with SnpEff/SnpSift. AmazonForest implements the best random forest model with a one hot data-encoding strategy, which shows an Area Under ROC Curve of ≥0.93. AmazonForest was employed for pathogenicity prediction of a set of ∼101,000 genetic variants of uncertain significance or conflict of interpretation. Our findings revealed ∼24,000 variants with high pathogenic probability ($R{F}_{prob}\ge 0.9$). In addition, we show results for Alzheimer’s Disease as a demonstration of its application in clinical interpretation of genetic variants in complex diseases. Lastly, AmazonForest is available as a web tool and R object that can be loaded to perform pathogenicity predictions.

ClinVar is a web platform that stores around 774k curated entries, which allows exploring genetic variants and their associations with complex phenotypes. A partial set of ClinVar’s genetic associations were reported with conflict of interpretation or uncertain clinical impact significance, which currently challenges clinicians and geneticists. Here, we evaluate the performance of data pre-processing methods combined with classical prediction methods, such as Naive Bayes, Random Forest, and Support Vector Machine to build a meta-prediction model aiming to improve genetic pathogenicity interpretation. Models were trained with ClinVar data (September 2020), and genetic variants were annotated with eight functional impact predictors catalogued with SnpEff/SnpSift (v4.3). A 10-fold cross-validation strategy was performed for evaluation by accuracy, F1-Score, Receiver Operating Characteristic, Area Under Curve. The best meta-prediction model raises by combining one-hot encoding with tree-based classifiers as Random Forest, which shows Area Under Curve ≥ 0,93. We predict pathogenicity for 109k genetic variants, which were found labeled as uncertain significance or conflict of interpretation. Additionally, we implemented AmazonForest (https://www.lghm.ufpa.br/amazonforest), a web tool to query data for a set of 5k variants that were predicted with high pathogenic probability (RFprob >= 0.9).