High-throughput experimental techniques have produced a large amount of protein-protein interaction (PPI) data, but their coverage is still low and the PPI data also very noisy. Computational prediction PPIs can be used to discover new identify errors in data.We present novel deep learning framework, DPPI, model predict from sequence information alone. Our efficiently applies deep, Siamese-like convolutional neural network combined with random projection augmentation PPIs, leveraging...

Abstract Motivation: The interactions among proteins and the resulting networks of such have a central role in cell biology. Aligning these gives us important information, as conserved complexes evolutionary relationships. Although there been several publications on global alignment protein networks; however, none proposed methods are able to produce highly meaningful alignment. Moreover, time complexity current algorithms makes them impossible use for multiple large together. Results: We...

Abstract Motivation: High-throughput experimental techniques have produced a large amount of protein–protein interaction (PPI) data. The study PPI networks, such as comparative analysis, shall benefit the understanding life process and diseases at molecular level. One way analysis is to align networks identify conserved or species-specific subnetwork motifs. A few methods been developed for global network alignment, but it still remains challenging in terms both accuracy efficiency. Results:...

Reciprocal interactions between B and follicular T helper (Tfh) cells orchestrate the germinal center (GC) reaction, a hallmark of humoral immunity. Abnormal GC responses could lead to production pathogenic autoantibodies development autoimmunity. Here we show that miR-146a controls by targeting multiple CD40 signaling pathway components in cells; contrast, loss does not alter responses. However, specific deletion both its paralog, miR-146b, increases Tfh cell numbers enhanced reactions....

MicroRNAs (miRs) are tightly regulated in the immune system, and aberrant expression of miRs often results hematopoietic malignancies autoimmune diseases. Previously, it was suggested that elevated levels miR-27 T cells isolated from patients with multiple sclerosis facilitate disease progression by inhibiting Th2 immunity promoting pathogenic Th1 responses. Here we have demonstrated that, although mice cell-specific overexpression harbor dysregulated responses develop pathology, these...

As an increasing amount of protein-protein interaction (PPI) data becomes available, their computational interpretation has become important problem in bioinformatics. The alignment PPI networks from different species provides valuable information about conserved subnetworks, evolutionary pathways and functional orthologs. Although several methods have been proposed for global network alignment, there is a pressing need that produce more accurate alignments terms both topological...

Speech and language changes occur in Alzheimer's disease (AD), but few studies have characterized their longitudinal course. We analyzed open-ended speech samples from a prodromal-to-mild AD cohort to develop novel composite score characterize progressive changes. Participant the Clinical Dementia Rating (CDR) interview was compute metrics reflecting characteristics. determined aspects of that exhibited significant change over 18 months. Nine acoustic linguistic measures were combined create...

High-throughput experimental techniques have been producing more and protein–protein interaction (PPI) data. The PPI network alignment greatly benefits the understanding of evolutionary relationship among species, helps identify conserved subnetworks, provides extra information for functional annotations. Although a few methods developed multiple alignment, quality is still far from perfect, thus, new are needed. In this article, we present novel method, denoted as ConvexAlign, joint...

Abstract Background Novel automated tools for analyzing speech and language may provide new insights into Alzheimer’s disease (AD). Although changes occur in AD other neurodegenerative diseases, current clinical assessments to monitor these symptoms can be burdensome have limited sensitivity. Through analyses of open‐ended naturalistic collected from a standardized interview, we developed novel measure characterize progressive AD. Methods We analyzed Clinical Dementia Rating (CDR) recordings...

Basal airway epithelial cells (AEC) constitute stem/progenitor within the central airways and respond to mucosal injury in an ordered sequence of spreading, migration, proliferation, differentiation needed cell types. However, dynamic gene transcription early events after has not been studied AEC. We examined expression using microarrays following mechanical (MI) primary human AEC grown submersion culture generate basal air-liquid interface differentiated (dAEC) that include goblet ciliated...

Lynx (http://lynx.ci.uchicago.edu) is a web-based database and knowledge extraction engine. It supports annotation analysis of high-throughput experimental data generation weighted hypotheses regarding genes molecular mechanisms contributing to human phenotypes or conditions interest. Since the last release, base (LynxKB) has been periodically updated with latest versions existing databases supplemented additional information from public databases. These additions have enriched annotations...

Automated segmentation of anatomical sub-regions with high precision has become a necessity to enable the quantification and characterization cells/ tissues in histology images. Currently, machine learning model analyze sub-anatomical regions brain 2D histological images is not available. The scientists rely on manually segmenting which extremely time-consuming prone labeler-dependent bias. One major challenges accomplishing such task lack high-quality annotated that can be used train...

Parkinson's Disease (PD) is the second most common neurodegenerative disease in humans. PD characterized by gradual loss of dopaminergic neurons Substantia Nigra (SN). Counting number SN one important indexes evaluating drug efficacy animal models. Currently, analyzing and quantifying conducted manually experts through analysis digital pathology images which laborious, time-consuming, highly subjective. As such, a reliable unbiased automated system demanded for quantification images. Recent...

Automated segmentation of anatomical sub-regions with high precision has become a necessity to enable the quantification and characterization cells/ tissues in histology images. Currently, machine learning model analyze sub-anatomical regions brain 2D histological images is not available. The scientists rely on manually segmenting which extremely time-consuming prone labeler-dependent bias. One major challenges accomplishing such task lack high-quality annotated that can be used train...

The ability to predict the future trajectory of a patient is key step toward development therapeutics for complex diseases such as Alzheimer's disease (AD). However, most machine learning approaches developed prediction progression are either single-task or single-modality models, which can not be directly adopted our setting involving multi-task with high dimensional images. Moreover, those trained on single dataset (i.e. cohort), generalized other cohorts. We propose novel multimodal deep...

The implementation of Artificial Intelligence (AI) in the healthcare industry has garnered considerable attention, attributable to its prospective enhancement clinical outcomes, expansion access superior healthcare, cost reduction, and elevation patient satisfaction. Nevertheless, primary hurdle that persists is related quality accessible multi-modal data conjunction with evolution AI methodologies. This study delves into adoption large language models address specific challenges,...

Abstract Background Progressive language changes are established clinical characteristics of Alzheimer’s disease (AD). Advances in Natural Language Processing (NLP) enable more objective, nuanced measurement language, facilitating the development and validation speech biomarkers for tracking longitudinal decline function. We examined robustness generalizability our previously published biomarker score (Robin et al., 2023) an independent trial dataset. Method analyzed CDR interview recordings...

Biological networks provide insight into the complex organization of biological processes in a cell at system level. They are an effective tool for understanding comprehensive map functional interactions, finding modules and pathways. Reconstruction comparative analysis these useful information to identify modules, prioritization disease causing genes also identification drug targets. The talk will consist two parts. I discuss several methods protein-protein interaction network alignment...

High-throughput experimental techniques have produced an enormous number of gene expression profiles for various tissues the human body. Tissue-specificity is a key component in reflecting potentially different roles proteins diverse cell lineages. One way understanding tissue specificity by reconstructing tissue-specific co-expression networks (CENs) to analyze correlation between genes. A few methods been developed estimating CENs, but it still remains challenging terms both accuracy and...

Motivation: High-throughput experimental techniques have been producing more and protein-protein interaction (PPI) data. PPI network alignment greatly benefits the understanding of evolutionary relationship among species, helps identify conserved sub-networks provides extra information for functional annotations. Although a few methods developed multiple alignment, quality is still far away from perfect thus, new are needed. Result: In this paper, we present novel method, denoted as...

Abstract MicroRNAs (miRNAs) are tightly regulated in the immune system as aberrant expression of miRNAs often results hematopoietic malignancies and autoimmune diseases. Previously, elevated levels miR-27 T cells isolated from multiple sclerosis patients has been suggested to facilitate disease progression through inhibiting Th2 immunity promoting pathogenic Th1 responses. Here we show while mice with cell-specific overexpression harbor dysregulated responses develop pathology, these...