Hang Chang

Lawrence Berkeley National Laboratory | LBL · Biological Systems & Engineering

It is imperative to identify patients with prostate cancer (PCa) who will benefit from androgen receptor signaling inhibitors that can impact quality of life upon prolonged use. Using our extensively-validated artificial-intelligence technique: cellular morphometric biomarker via machine learning (CMB-ML), we identified 13 CMBs from whole slide ima...

PURPOSE Tissue-agnostic biomarkers that capture the commonality in cancer biology, may provide a new avenue for treatment development and optimization across cancer types. Here, we aimed to evaluate and validate the clinical value of a tissue-agnostic cellular morphometrics biomarker (CMB) signature, which was discovered by artificial intelligence...

Ovarian cancer is one of the most lethal gynecological malignancies worldwide, posing immense challenges in early detection, displaying grim prognoses, and having high rates of recurrence and mortality. This malignancy exhibits a range of ethnic diversity-mortality rates, each with distinct sub-categories characterized by variations in both molecul...

Ionizing radiation induces complex changes in cells and tissues. The conventional approach to biological dosimetry has been to integrate physical and clinical measurements to optimize dose assessment. Molecular biodosimetry is an effective strategy to monitor radiation exposure and hematologic, cytogenetic, protein and transcript-based approaches h...

Metastasis to the lungs is a leading cause of death for patients with breast cancer. Therefore, effective therapies are urgently needed to prevent and treat lung metastasis. In this study, we uncovered a mechanism by which NAD(P)H:quinone oxidoreductase 1 (NQO1) orchestrates lung metastasis. NQO1 stabilized and upregulated peptidyl-prolyl cis-trans...

Background Deeper insights into ERBB2-driven cancers are essential to develop new treatment approaches for ERBB2+ breast cancers (BCs). We employed the Collaborative Cross (CC) mouse model to unearth genetic factors underpinning Erbb2-driven mammary tumour development and metastasis. Methods 732 F1 hybrid female mice between FVB/N MMTV-Erbb2 and 3...

Cellular nuclei recognition serves as a fundamental and essential step in the workflow of digital pathology. However, with disparate source organs and staining procedures among histology image clusters, the scanned tiles inherently conform to a non-uniform data distribution, which induces deteriorated promises for general cross-cohort usages. Despi...

The insights into interactions between host genetics and gut microbiome (GM) in colorectal tumor susceptibility (CTS) remains lacking. We used Collaborative Cross mouse population model to identify genetic and microbial determinants of Azoxymethane-induced CTS. We identified 4417 CTS-associated single nucleotide polymorphisms (SNPs) containing 334...

Non-invasive methods of detecting radiation exposure show promise to improve upon current approaches to biological dosimetry in ease, speed, and accuracy. Here we developed a pipeline that employs Fourier transform infrared (FTIR) spectroscopy in the mid-infrared spectrum to identify a signature of low dose ionizing radiation exposure in mouse ear...

Annotation scarcity and cross-modality/stain data distribution shifts are two major obstacles hindering the application of deep learning models for nuclei analysis, which holds a broad spectrum of potential applications in digital pathology. Recently, unsupervised domain adaptation (UDA) methods have been proposed to mitigate the distributional gap...

Background Luminal A tumours generally have a favourable prognosis but possess the highest 10‐year recurrence risk among breast cancers. Additionally, a quarter of the recurrence cases occur within 5 years post‐diagnosis. Identifying such patients is crucial as long‐term relapsers could benefit from extended hormone therapy, while early relapsers m...

Post-pregnancy breast cancer often carries a poor prognosis, posing a major clinical challenge. The increasing trend of later-life pregnancies exacerbates this risk, highlighting the need for effective chemoprevention strategies. Current options, limited to selective estrogen receptor modulators, aromatase inhibitors, or surgical procedures, offer...

Background: Deeper insights into ERBB2-driven cancers are essential to develop novel treatment avenues for ERBB2+ breast cancers (BCs). We employed Collaborative Cross (CC) mouse model, along with human translational evaluation, to unearth genetic factors underpinning Erbb2-driven mammary tumor development and metastasis. Methods: 732 F1 hybrid fem...

Background The insights into interactions between host genetics and gut microbiome (GM) in colorectal tumor susceptibility (CTS) remains lacking. We used Collaborative Cross mouse population model to identify genetic and microbial determinants of Azoxymethane-induced CTS. Results We identified 4417 CTS-associated SNPs containing 936 known human ge...

Hematologic toxicity is a common side effect of multimodal cancer therapy. Nearly all animal studies investigating the causes of radiotherapy-induced hematologic toxicity use inbred strains with limited genetic diversity and do not reflect the diverse responses observed in humans. We used the population-based Collaborative Cross (CC) mouse resource...

Introduction: Risk stratification of cutaneous squamous cell carcinoma (CSCC) is essential for managing patients. Artificial intelligence and machine learning might help stratify patients with CSCC by risk using more than solely clinical and histopathological factors. Methods: A retrospective cohort of 104 CSCCs excised with clear margins was re...

Background Despite their generally favorable prognosis, luminal A tumors paradoxically pose the highest ten-year recurrence risk among breast cancers, with a quarter recurring within five years. Identifying such patients is crucial as long-term relapsers could benefit from extended hormone therapy, while early relapsers may require aggressive treat...

Despite their generally favorable prognosis, luminal A tumors paradoxically pose the highest ten-year recurrence risk among breast cancers. From those that relapse, a quarter of them do it within five years after diagnosis. Identifying such patients is crucial, as long-term relapsers could benefit from extended hormone therapy, whereas early relaps...

The success of automated medical image analysis depends on large-scale and expert-annotated training sets. Unsupervised domain adaptation (UDA) has been raised as a promising approach to alleviate the burden of labeled data collection. However, they generally operate under the closed-set adaptation setting assuming an identical label set between th...

Cardiotoxicity due to anthracyclines (CDA) affects cancer patients, but we cannot predict who may suffer from this complication. CDA is a complex trait with a polygenic component that is mainly unidentified. We propose that levels of intermediate molecular phenotypes (IMPs) in the myocardium associated with histopathological damage could explain CD...

Aim We aimed to identify the ability of serum bile acids (BAs) and unsaturated fatty acids (UFAs) profiles to predict the development of diabetic retinopathy (DR) in type 2 diabetes mellitus (T2DM) patients. Methods We first used univariate and multivariate analysis to compare 15 serum BA and 11 UFA levels in healthy control (HC) group (n = 82), T...

Increased mitotic activity is associated with the genesis and aggressiveness of many cancers. To assess the clinical value of mitotic activity as prognostic biomarker, we performed a pan-cancer study on the mitotic network activity index (MNAI) constructed based on 54-gene mitotic apparatus network. Our pan-cancer assessment on TCGA (33 tumor types...

Introduction: Gut microbiome (GM) deregulation has been implicated in major conditions such as obesity and type 2 diabetes (T2DM). Our previous prospective study indicated that fecal microbiota transplantation (FMT) successfully improved patients with T2DM. We hypothesized that FMT may be a potential therapeutic method for T2DM, but its precise me...

CBX7 is a member of the chromobox gene family, which plays an important role in epigenetic transcriptional regulation. In this study, we found that compared to normal mammary tissues, mRNA levels of CBX7 are consistently significantly downregulated in breast cancers (BCs) across different datasets. Integrative multiomics analysis revealed the genet...

Increasing evidence has shown that thirdhand smoke (THS) exposure is likely to induce adverse health effects. An important knowledge gap remains in our understanding of THS exposure related to cancer risk in the human population. Population-based animal models are useful and powerful in investigating the interplay between host genetics and THS expo...

Increased mitotic activity is associated with the genesis and aggressiveness of many cancers. To assess the clinical value of mitotic activity as prognostic biomarker, we performed a pan-cancer study on the mitotic network activity index (MNAI) constructed based on 54-gene mitotic apparatus network. Our pan-cancer assessment on TCGA (33 tumor types...

Evidence showing a relationship between the mouse gut microbiome and properties such as phenotype and reaction to therapeutic agents and other treatments has increased significantly over the past 20 to 30 y. Recent concerns regarding the reproducibility of animal experiments have underscored the importance of understanding this relationship and how...

Background The effect of chemical exposure on obesity has raised great concerns. Real-world chemical exposure always imposes mixture impacts, however their exposure patterns and the corresponding associations with obesity have not been fully evaluated. Objectives To discover obesity-related mixed chemical exposure patterns in the general U.S. popu...

Coronavirus Disease 2019 (COVID-19) is currently a global pandemic, and early screening is one of the key factors for COVID-19 control and treatment. Here, we developed and validated chest CT-based imaging biomarkers for COVID-19 patient screening from two independent hospitals with 419 patients. We identified the vasculature-like signals from CT i...

BACKGROUND The development of precision medicine is essential for personalized treatment and improved clinical outcome, whereas biomarkers are critical for the success of precision therapies. AIM To investigate whether iCEMIGE (integration of CEll-morphometrics, MIcrobiome, and GEne biomarker signatures) improves risk stratification of breast canc...

BACKGROUND Lower grade gliomas (LGG) are heterogenous diseases by clinical, histological, and molecular criteria. We aimed to personalize the diagnosis and therapy of LGG patients by developing and validating robust cellular morphometric subtypes (CMS) and to uncover the molecular signatures underlying these subtypes. METHODS Cellular morphometric...

Background Increasing evidence shows that alterations in gut microbiome (GM) contribute to the development of type 2 diabetes mellitus (T2DM), and fecal microbiota transplantation (FMT) successfully treats various human diseases. However, the benefits of FMT therapy to T2DM patients remain unknown. Methods We enrolled 17 patients with T2DM for non...

Mouse models of cancer provide a powerful tool for investigating all aspects of cancer biology. In this study, we used our recently developed machine learning approach to identify the cellular morphometric biomarkers (CMB) from digital images of hematoxylin and eosin (H&E) micrographs of orthotopic Trp53 -null mammary tumors (n = 154) and to discov...

Understanding the spatial interactions between the elements of the tumor microenvironment -i.e. tumor cells. fibroblasts, immune cells- and how these interactions relate to the diagnosis or prognosis of a tumor is one of the goals of Computational Pathology. We present NaroNet, a Deep Learning framework that models the multi-scale tumor microenviro...

Radiotherapy is the current standard of care for more than 50% of all cancer patients. Improvements in radiotherapy (RT) technology have increased tumor targeting and normal tissue sparing. Radiations at ultra‑high dose rates required for FLASH‑RT effects have sparked interest in potentially providing additional differential therapeutic benefits. W...

Background Prognosis of breast cancer (BC) patients differs considerably and identifying reliable prognostic biomarker(s) is imperative. With evidence that the microbiome plays a critical role in the response to cancer therapies, we aimed to identify a cancer microbiome signature for predicting the prognosis of BC patients. Methods The TCGA BC micr...

Secreted angiopoietin/angiopoietin-like (ANGPT/ANGPTL) proteins are involved in many biological processes. However, the role of these proteins in human breast cancers (BCs) remains largely unclear. Here, we conducted integrated omics analyses to evaluate the clinical impact of ANGPT/ANGPTL proteins and to elucidate their biological functions. In BC...

Background A healthy gut microbiome is critical for glucose metabolism during pregnancy. In vivo studies indicate that trace element affects the composition and function of the gut microbiome and potentially leads to metabolic disorders but their relationships are largely unknown. We aimed to investigate whether the gut microbiome plays a role in t...

Lower grade gliomas (LGGs) are heterogenous diseases by clinical, histological and molecular criteria. Here, we developed a machine learning pipeline to extract cellular morphometric biomarkers from whole slide images of tissue histology; and identified and externally validated robust cellular morphometric subtypes of LGGs in multi-center cohorts....

Lower grade gliomas (LGGs) are heterogenous diseases by clinical, histological and molecular criteria. Here, we developed a machine learning pipeline to extract cellular morphometric biomarkers from whole slide images of tissue histology; and identified and externally validated robust cellular morphometric subtypes of LGGs in multi-center cohorts....

Growing evidence indicates that thirdhand smoke (THS) exposure induces many adverse health effects. However, it is unclear how THS exposure affects behavior and how host genetic background modulates phenotypic changes. Here we used the Collaborative Cross (CC) mouse population-based model to assess behavioral alterations immediately after THS expos...

The characterization and classification of white blood cells (WBC) are critical for the diagnosis of anemia, leukemia, and many other hematologic diseases. We developed WBC-Profiler, an unsupervised feature learning system for quantitative analysis of leukocytes. We demonstrate, through independent validation, that WBC-Profiler enables automatic ex...

The gut microbiome composition is influenced by many factors including environmental exposures. Here, we investigated the effect of thirdhand cigarette smoke (THS) and exposure age on gut microbiome diversity. C57BL/6 mice were exposed to THS at human exposure relevant levels for three weeks during three different life stages: postnatal (0–3 weeks...

We present NaroNet, a Machine Learning framework that integrates the multiscale spatial, in situ analysis of the tumor microenvironment (TME) with patient-level predictions into a seamless end-to-end learning pipeline. Trained only with patient-level labels, NaroNet quantifies the phenotypes, neighborhoods, and neighborhood interactions that have t...

Azoxymethane (AOM) is a widely used carcinogen to study chemical-induced colorectal carcinogenesis and is an agent for studying fulminant hepatic failure. The inter-strain susceptibility to acute toxicity by AOM has been reported, but its association with host genetics or gut microbiota remains largely unexplored. Here a cohort of genetically diver...

Growing evidence suggests that the gut microbiome (GM) plays a critical role in health and disease. However, the contribution of GM to psychiatric disorders, especially anxiety, remains unclear. We used the Collaborative Cross (CC) mouse population-based model to identify anxiety associated host genetic and GM factors. Anxiety-like behavior of 445...

In visual object tracking fields, the Siamese network tracker, based on the region proposal network (SiamRPN), has achieved promising tracking effects, both in speed and accuracy. However, it did not consider the relationship and differences between the long-range context information of various objects. In this paper, we add a global context block...

Medical image segmentation is a fundamental task in medical image analysis. Dynamic receptive field is very helpful for accurate medical image segmentation, which needs to be further studied and utilized. In this paper, we propose Match Feature U-Net, a novel, symmetric encoder–decoder architecture with dynamic receptive field for medical image seg...

The phrase “you are what you eat” is becoming increasingly true. Tiny residents of our GI tracts – gut microbes – affect more than just our digestion. Gut microbiota have recently been linked to host health and behavior through a connection called the “gut-brain axis,” but exactly how our gut microbes affect our brain function remains unclear. A re...

An amendment to this paper has been published and can be accessed via the original article.

Coronavirus Disease 2019 (COVID-19) is currently a global pandemic, and the early screening of COVID-19 is one of the key factors for COVID-19 control and treatment. Here, we developed and validated chest CT-based imaging biomarkers for COVID-19 patient screening. We identified the vasculature-like signals from CT images and found that, compared to...

Background: Recent evidence has linked the gut microbiome to host behavior via the gut-brain axis [1-3]; however, the underlying mechanisms remain unexplored. Here, we determined the links between host genetics, the gut microbiome and memory using the genetically defined Collaborative Cross (CC) mouse cohort, complemented with microbiome and metab...

Thirdhand smoke (THS), the residual tobacco smoke remaining in the environment after tobacco has been smoked, represents a hidden and underestimated public health hazard. Evidence supports its widespread presence in indoor environments. Exposure to secondhand smoke (SHS), a precursor of THS, has been well documented as a risk factor for human cance...

Hirschsprung disease (HSCR) is a birth defect with an approximate incidence of 1/5,000 live births, and up to one-third of HSCR patients develop Hirschsprung-associated enterocolitis (HAEC), the leading cause of HSCR-related death. Very little is known about the pathogenesis, prevention, and early diagnosis of HAEC. Here, we used a prospective stud...

The gastrointestinal microbiome and metabolome can provide a new angle to understand the development of health and disease. Stool samples are most frequently used for large-scale cohort studies. Standardized procedures for stool sample handling and storage can be a determining factor for performing microbiome or metabolome studies. In this study, w...

The characterization and classification of white blood cells (WBC) is critical for the diagnosis of anemia, leukemia and many other hematologic diseases. We developed WBC-Profiler, an unsupervised feature learning system for quantitative analysis of leukocytes. We demonstrate that WBC-Profiler enables automatic extraction of complex signatures from...

Document S1. Supplemental Experimental Procedures, Figures S1–S7, and Tables S1 and S2