Resources
1. Dynamic driver network (DDN) based model integrated to the Maine Health Information Exchange workflow to characterize the critical transition state prior to the type 2 diabetes mellitus (T2DM) disease. (A) Based on clinical records of 1.3 million people from Maine State, USA, we carried out a population study and extracted a sub-cohort with 7,334 patients with the first T2DM confirmative diagnosis during the study period. (B) The progression of T2DM can be divided into three stages, i.e., the normal state with relatively low entropy, the transition state right before the critical transition with relatively high entropy, the disease state with relatively low entropy. The sharp increase of entropy is expected to characterize the transition state before getting into the disease state. (C) With a transition-based network entropy, the features can be classified into three layers, and the DDN can be obtained. Based on the dynamical characteristics (such as comprehensive clinic history, or time-course information) the cluster analysis suffices to separate the network into a few functional modules. Further analysis via network entropy aggregates these modules and identifies the DDN. (D) Employing the transition-based network entropy method, we succeed in presenting the existence of a transition state (orange) between a normal state (green) and a disease state (red). The network structure of features can be divided into two parts, the DDN, and other downstream features. The DDN provides the indicative warning signals to the sudden deterioration of diabetes.
2 Deep learning of the pathological whole slide image (WSI). Our team has over 20 years of experience in image deep learning. Our expertise will be crucial in spearheading the development of an AI-based pipeline for automatic, accurate, comprehensive, interpretable, and reproducible feature extraction from whole slide images (WSI). Our lab routinely utilizes a deep neural network called "DeepLabV3" to perform H&E tissue segmentation. Pathologists labeled neuroblastoma (NB) H&E images to identify four regions of interest: stromal region (Stroma), tumoral region (Tumor), lymphocytes aggregated region (Lymph), and an excluded region. All included regions, namely Stroma, Tumor, and Lymph, will encompass all H&E regions (All). We will extract various image-based pathological registration and segmentation statistics features for tumor tissue grading analytics.
3 Formalinâfixed, paraffinâembedded (FFPE), Targeted Proteomics with Laser Microdissection and Quantitative LC-MS/MS
FFPE long-term-banked pathological tissue blocks offer an invaluable resource for clinical and biomarker research. Our laboratory developed a unique technology to extract tumor or tumor microenvironment proteomes. Step 1: Prepare the FFPE tissue from a tumor biopsy on a customized Director slide; Step 2: Under the guidance of a pathologist, laser capture microdissect only the tumor region; Step 3: Liquefy the tissue and then digest it in preparation for targeted multiplex proteomic analysis; Step 4: Perform targeted multiplex proteomic analysis; Step 5: Quantify the protein biomarkers at the attomole level in every tissue; Steps 6/7: Analyze the data and report the results. In collaboration with industrial partners, including a CAP/CLIA laboratory and AstraZeneca, our lab has access to 10,000 clinical FFPE tumor biopsy samples that have been processed and reported. Our targeted multiplex proteomics will provide research and clinical utility for precision medicine, particularly in the field of oncology.