Project description:Background: Primary knee osteoarthritis (KOA) is a heterogeneous disease with clinical and molecular contributors. Biofluids contain microRNAs and metabolites that can be measured by omic technologies. Deep learning captures complex non-linear associations within multimodal data but, to date, has not been used for multi-omic-based endotyping of KOA patients. We developed a novel multimodal deep learning framework for clustering of multi-omic data from three subject-matched biofluids to identify distinct KOA endotypes and classify one-year post-total knee arthroplasty (TKA) pain/function responses. Materials and Methods: In 414 KOA patients, subject-matched plasma, synovial fluid and urine were analyzed by microRNA sequencing or metabolomics. Integrating 4 high-dimensional datasets comprising metabolites from plasma (n=151 features), along with microRNAs from plasma (n=421), synovial fluid (n=930), or urine (n=1225), a multimodal deep learning variational autoencoder architecture with K-means clustering was employed. Features influencing cluster assignment were identified and pathway analyses conducted. An integrative machine learning framework combining 4 molecular domains and a clinical domain was then used to classify WOMAC pain/function responses post-TKA within each cluster. Findings: Multimodal deep learning-based clustering of subjects across 4 domains yielded 3 distinct patient clusters. Feature signatures comprising microRNAs and metabolites across biofluids included 30, 16, and 24 features associated with Clusters 1-3, respectively. Pathway analyses revealed distinct pathways associated with each cluster. Integration of 4 multi-omic domains along with clinical data improved response classification performance, with Cluster 3 achieving AUC=0·879 for subject pain response classification and Cluster 2 reaching AUC=0·808 for subject function response, surpassing individual domain classifications by 12% and 15% respectively. Interpretation: We have developed a deep learning-based multimodal clustering model capable of integrating complex multi-fluid, multi-omic data to assist in KOA patient endotyping and test outcome response to TKA surgery.
Project description:This study aims to understand the systemic component of psoriasis pathogenesis since psoriasis patients have higher risk of developing diesases beyond skin inflammation. In this study, we collected sigmoidal gut biopsies to profile host transcriptomic changes associated with psoriasis patients and healthy subjects. This exepriment provided transcriptomic dataset of host response and is integrated with fecal metagenomic data and flow cytometry dataset as part of the multi-omic study.
Project description:This study utilizes multi-omic biological data to perform deep immunophenotyping on the major immune cell classes in COVID-19 patients. 10X Genomics Chromium Single Cell Kits were used with Biolegend TotalSeq-C human antibodies to gather single-cell transcriptomic, surface protein, and TCR/BCR sequence information from 254 COVID-19 blood draws (a draw near diagnosis (-BL) and a draw a few days later (-AC)) and 16 healthy donors.
Project description:Integrative multi-omic approaches have been increasingly applied to discovery and functional studies of complex human diseases. Short-term preoperative antibiotics have been adopted to reduce site infections in colorectal cancer (CRC) resections. We hypothesize that the antibiotics will impact analysis of multi-omic datasets generated from resection samples to investigate biological CRC risk factors. To assess the impact of preoperative antibiotics on integrated microbiome and human transcriptomic data generated from archived frozen CRC resection samples. Genomic DNA (gDNA) and RNA were extracted from 51 pairs of frozen sporadic CRC tumor and adjacent non-tumor mucosal samples from 50 CRC patients archived at a single medical center. 16S rRNA gene sequencing (V3V4 region, paired end (PE), 300 bp) and confirmatory quantitative polymerase chain reaction (qPCR) assays were conducted on gDNA. RNA sequencing IPE, 125bp) was performed on parallel tumor and non-tumor RNA samples with RNA Integrity Numbers (RIN) scores ≥ 6.
