Project description:Despite the diversity of liquid biopsy transcriptomic repertoire, numerous studies often 30 exploit only a single RNA type signature for diagnostic biomarker potential. This frequently results 31 in insufficient sensitivity and specificity necessary to reach diagnostic utility. Combinatorial biomarker approaches may offer a more reliable diagnosis. Here we investigated the synergistic contributions of circRNA and mRNA signatures derived from blood platelets as biomarkers for lung cancer detection. We developed a comprehensive bioinformatics pipeline permitting analysis of platelet-circRNA and mRNA derived from non-cancer individuals and lung cancer patients. An optimal selected signature is then used to generate the predictive classification model using machine learning algorithm. Using an individual signature of 21 circRNA and 28 mRNA, the predictive models reached an Area Under the Curve (AUC) of 0.88 and 0.81, respectively. Importantly, combinatorial analysis including both types of RNAs resulted in an 8-target signature (6 mRNA and 2 40 circRNA) enhancing the differentiation of lung cancer from controls (AUC of 0.92). Additionally, we identified five biomarkers potentially specific for early-stage detection of lung cancer. Our proof-of-concept study presents the first multi-analyte-based approach for the analysis of platelets-derived biomarkers, providing a potential combinatorial diagnostic signature for lung cancer detection.
Project description:Acute myocardial infarction (AMI) is a leading cause of global morbidity and mortality, requiring deeper insights into its molecular mechanisms for improved diagnosis and treatment. This study combines proteomics, multi-omics, and machine learning (ML) to identify key proteins and pathways associated with AMI.
Project description:High-throughput screening and gene signature analyses frequently identify lead therapeutic compounds with unknown modes of action (MoAs), and the resulting uncertainties can lead to the failure of clinical trials. We developed a multi-omics approach for uncovering MoAs through an interpretable machine learning model of the effects of compounds on transcriptomic, epigenomic, metabolomic, and proteomic data. We applied this approach to examine compounds with beneficial effects in models of Huntington’s disease, finding common MoAs for previously unrelated compounds that were not predicted based on similarities in the compounds’ structures, connectivity scores, or binding targets. We experimentally validated two such disease-relevant MoAs, autophagy activation and bioenergetics manipulation. This interpretable machine learning approach can be used to find and evaluate MoAs in future drug development efforts.
Project description:Histologic diagnosis of sellar masses can be challenging, particularly in rare neoplasms and tumors without definitive biomarkers. DNA methylation has recently emerged as a useful diagnostic tool. To illustrate the clinical utility of machine-learning-based DNA methylation classifiers, we report a rare case of primary sellar esthesioneuroblastoma diagnosed by DNA methylation classificiation but histologically mimicking a nonfunctioning pituitary adenoma.
Project description:Precision medicine's potential to transform complex autoimmune-disease treatment is often challenged by limited data availability and inadequate sample size when compared to the number of molecular features found in high-throughput multi-omics datasets. Addressing this issue, the novel framework PRoBeNet (Predictive Response Biomarkers using Network medicine) was developed. ProBeNet operates under the hypothesis that the therapeutic effect of a drug propagates through a protein–protein interaction network to reverse disease states. ProBeNet prioritizes biomarkers by considering (1) therapy-targeted proteins, (2) disease-specific molecular signatures, and (3) an underlying network of interactions among cellular components (the human interactome). With ProBeNet, biomarkers were discovered predicting patient responses to both an established autoimmune therapy (infliximab) and an investigational compound (a MAPK3/1 inhibitor). Predictive power of ProBeNet biomarkers was validated with retrospective gene-expression data from ulcerative-colitis and rheumatoid-arthritis patients and prospective data from ulcerative-colitis and Crohn’s disease patient-derived tissues. Machine-learning models using ProBeNet biomarkers significantly outperformed models using either all genes or randomly selected genes, especially when data were limited (fewer than 20 samples). These results illustrate the value of ProBeNet for reducing features and for constructing robust machine-learning models when limited data are available. ProBeNet may be used to develop companion and complementary diagnostic assays for complex autoimmune-disease therapies, which may help stratify suitable patient subgroups in clinical trials, approve new drugs, and improve patient outcomes.
Project description:Multi-omics data-driven personalized health profiling can provide valuable insight into metabolic perturbations in people living with HIV (PWH) under successful antiretroviral therapy (ART). We integrated transcriptomics, proteomics, and metabolomics to identify and stratify the immunometabolically compromised treated PWH (n=158). Based on clinical and lifestyle data, 44% (70/158) of PWH were at risk of immunometabolic complications. We identified six plasma biomarkers to define the at-risk phenotype using advanced machine learning and a Bayesian classifier that drives a network of proteins reasoned for monocyte immunosenescence. We identified metabolic perturbations driven by central carbon metabolic flux led to chronic monocyte activation impairing its early functional properties. Further, we discovered that the host-induced spermidine-mediated microenvironment was responsible for chronic inflammation leading to synaptic dysregulation in vitro, potentiating the risk of neuropsychiatric clinical phenotypes in the at-risk PWH. Novel intervention targeting metabolically-perturbed chronic inflammatory conditions can lead to healthier aging in the at-risk PWH.
Project description:Relapse remains a determinant of treatment failure and contributes significantly to mortality in acute myeloid leukemia (AML) patients. Despite efforts to understand AML progression and relapse mechanisms, findings on acquired gene mutations in relapse vary, suggesting inherent genetic heterogeneity and emphasizing the role of epigenetic modifications. Herein, we characterized genetic and epigenetic changes in AML progression using multi-omics approaches to elucidate the underlying mechanisms of relapse. Differential interaction analysis showed significant 3D chromatin landscape reorganization between relapse and diagnosis samples. Comparing global open chromatin profiles revealed that relapse samples had significantly fewer accessible chromatin regions than diagnosis samples. In addition, we discovered that relapse-related upregulation was achieved either by forming new active enhancer contacts or by losing interactions with poised enhancers/potential silencers. Altogether, our study highlights the impact of genetic and epigenetic changes on AML progression, underlining the importance of multi-omics approaches in understanding disease relapse mechanisms and guiding potential therapeutic interventions.
Project description:The diagnosis of primary lung adenocarcinomas with intestinal or mucinous differentiation (PAIM) remains challenging due to the overlapping histomorphological, immunohistochemical and genetic characteristics with lung metastatic colorectal cancer (lmCRC). This study aimed to explore the protein biomarkers that could distinguish between PAIM and lmCRC. To uncover differences between the two diseases, we used tandem mass tagging (TMT)-based shotgun proteomics to characterize proteomes of formalin-fixed paraffin-embedded (FFPE) tumor samples of PAIM (n = 22) and lmCRC (n = 17). Then three machine learning algorithms, namely support vector machine (SVM), random forest and the Least Absolute Shrinkage and Selection Operator (LASSO), were utilized to select protein features with diagnostic significance. These candidate proteins were further validated in an independent cohort (PAIM, n = 11; lmCRC, n = 19) by immunochemistry (IHC) to confirm their diagnostic performance. In total, 105 proteins out of 7871 proteins were significantly dysregulated between PAIM and lmCRC samples and well-separated two groups by Uniform Manifold Approximation and Projection (UMAP). The upregulated proteins in PAIM were involved in actin cytoskeleton organization, platelet degranulation, and regulation of leukocyte chemotaxis, while downregulated ones were involved in mitochondrial transmembrane transport, vasculature development, and stem cell proliferation. A set of 10 candidate proteins (high-level expression in lmCRC: CDH17, ATP1B3, GLB1, OXNAD1, LYST, FABP1; high-level expression in PAIM: NARR, MLPH, S100A14, CK7) was ultimately selected to distinguish PAIM from lmCRC by machine learning algorithms. We further confirmed using IHC that the five protein biomarkers including CDH17, CK7, MLPH, FABP1 and NARR were effective biomarkers for distinguishing PAIM from lmCRC. Our study depicts PAIM-specific proteomic characteristics and demonstrates the potential utility of new protein biomarkers for the differential diagnosis of PAIM and lmCRC. These findings may contribute to improving the diagnostic accuracy and guide appropriate treatments for these patients.
Project description:Nonalcoholic steatohepatitis (NASH) is a major cause of liver fibrosis with increasing prevalence worldwide. Currently there are no approved drugs available. The development of new therapies is difficult as diagnosis and staging requires biopsies. Consequently, predictive plasma biomarkers would be useful for drug development. Here we present a multi-omics approach to characterize the molecular pathophysiology and to identify new plasma biomarkers in a choline-deficient L-amino acid-defined diet rat NASH model. We analyzed liver samples by RNA-Seq and proteomics, revealing disease relevant signatures and a high correlation between mRNA and protein changes. Comparison to human data showed an overlap of inflammatory, metabolic, and developmental pathways.