Biomedical Big Data Technologies, Applications, and Challenges for Precision Medicine: A Review.

The explosive growth of biomedical Big Data presents both significant opportunities and challenges in the realm of knowledge discovery and translational applications within precision medicine. Efficient management, analysis, and interpretation of big data can pave the way for groundbreaking advancements in precision medicine. However, the unprecedented strides in the automated collection of large-scale molecular and clinical data have also introduced formidable challenges in terms of data analysis and interpretation, necessitating the development of novel computational approaches. Some potential challenges include the curse of dimensionality, data heterogeneity, missing data, class imbalance, and scalability issues. This overview article focuses on the recent progress and breakthroughs in the application of big data within precision medicine. Key aspects are summarized, including content, data sources, technologies, tools, challenges, and existing gaps. Nine fields-Datawarehouse and data management, electronic medical record, biomedical imaging informatics, Artificial intelligence-aided surgical design and surgery optimization, omics data, health monitoring data, knowledge graph, public health informatics, and security and privacy-are discussed.

COV2Var, a function annotation database of SARS-CoV-2 genetic variation.

The COVID-19 pandemic, caused by the coronavirus SARS-CoV-2, has resulted in the loss of millions of lives and severe global economic consequences. Every time SARS-CoV-2 replicates, the viruses acquire new mutations in their genomes. Mutations in SARS-CoV-2 genomes led to increased transmissibility, severe disease outcomes, evasion of the immune response, changes in clinical manifestations and reducing the efficacy of vaccines or treatments. To date, the multiple resources provide lists of detected mutations without key functional annotations. There is a lack of research examining the relationship between mutations and various factors such as disease severity, pathogenicity, patient age, patient gender, cross-species transmission, viral immune escape, immune response level, viral transmission capability, viral evolution, host adaptability, viral protein structure, viral protein function, viral protein stability and concurrent mutations. Deep understanding the relationship between mutation sites and these factors is crucial for advancing our knowledge of SARS-CoV-2 and for developing effective responses. To fill this gap, we built COV2Var, a function annotation database of SARS-CoV-2 genetic variation, available at http://biomedbdc.wchscu.cn/COV2Var/. COV2Var aims to identify common mutations in SARS-CoV-2 variants and assess their effects, providing a valuable resource for intensive functional annotations of common mutations among SARS-CoV-2 variants.

Revealing chronic disease progression patterns using Gaussian process for stage inference.

OBJECTIVE: The early stages of chronic disease typically progress slowly, so symptoms are usually only noticed until the disease is advanced. Slow progression and heterogeneous manifestations make it challenging to model the transition from normal to disease status. As patient conditions are only observed at discrete timestamps with varying intervals, an incomplete understanding of disease progression and heterogeneity affects clinical practice and drug development. MATERIALS AND METHODS: We developed the Gaussian Process for Stage Inference (GPSI) approach to uncover chronic disease progression patterns and assess the dynamic contribution of clinical features. We tested the ability of the GPSI to reliably stratify synthetic and real-world data for osteoarthritis (OA) in the Osteoarthritis Initiative (OAI), bipolar disorder (BP) in the Adolescent Brain Cognitive Development Study (ABCD), and hepatocellular carcinoma (HCC) in the UTHealth and The Cancer Genome Atlas (TCGA). RESULTS: First, GPSI identified two subgroups of OA based on image features, where these subgroups corresponded to different genotypes, indicating the bone-remodeling and overweight-related pathways. Second, GPSI differentiated BP into two distinct developmental patterns and defined the contribution of specific brain region atrophy from early to advanced disease stages, demonstrating the ability of the GPSI to identify diagnostic subgroups. Third, HCC progression patterns were well reproduced in the two independent UTHealth and TCGA datasets. CONCLUSION: Our study demonstrated that an unsupervised approach can disentangle temporal and phenotypic heterogeneity and identify population subgroups with common patterns of disease progression. Based on the differences in these features across stages, physicians can better tailor treatment plans and medications to individual patients.

StemDriver: a knowledgebase of gene functions for hematopoietic stem cell fate determination.

StemDriver is a comprehensive knowledgebase dedicated to the functional annotation of genes participating in the determination of hematopoietic stem cell fate, available at http://biomedbdc.wchscu.cn/StemDriver/. By utilizing single-cell RNA sequencing data, StemDriver has successfully assembled a comprehensive lineage map of hematopoiesis, capturing the entire continuum from the initial formation of hematopoietic stem cells to the fully developed mature cells. Extensive exploration and characterization were conducted on gene expression features corresponding to each lineage commitment. At the current version, StemDriver integrates data from 42 studies, encompassing a diverse range of 14 tissue types spanning from the embryonic phase to adulthood. In order to ensure uniformity and reliability, all data undergo a standardized pipeline, which includes quality data pre-processing, cell type annotation, differential gene expression analysis, identification of gene categories correlated with differentiation, analysis of highly variable genes along pseudo-time, and exploration of gene expression regulatory networks. In total, StemDriver assessed the function of 23 839 genes for human samples and 29 533 genes for mouse samples. Simultaneously, StemDriver also provided users with reference datasets and models for cell annotation. We believe that StemDriver will offer valuable assistance to research focused on cellular development and hematopoiesis.

Development of 18F-Labeled hydrophilic trans-cyclooctene as a bioorthogonal tool for PET probe construction.

We report the development of a hydrophilic 18F-labeled a-TCO derivative [18F]3 (log P = 0.28) through a readily available precursor and a single-step radiofluorination reaction (RCY up to 52%). We demonstrated that [18F]3 can be used to construct not only multiple small molecule/peptide-based PET agents, but protein/diabody-based imaging probes in parallel.

Exploring Acute Pancreatitis Clinical Pathways Using a Novel Process Mining Method.

Mining process models of medical behavior from electronic medical records is an effective way to optimize clinical pathways. However, clinical medical behavior is an extremely complex field with high nonlinearity and variability, and thus we need to adopt a more effective method. In this study, we developed a fuzzy process mining method for complex clinical pathways. Firstly, we designed a multi-level expert classification system with fuzzy values to preserve finer details. Secondly, we categorized medical events into long-term and temporary events for more specific data processing. Subsequently, we utilized electronic medical record (EMR) data of acute pancreatitis spanning 9 years, collected from a large general hospital in China, to evaluate the effectiveness of our method. The results demonstrated that our modeling process was simple and understandable, allowing for a more comprehensive representation of medical intricacies. Moreover, our method exhibited high patient coverage (>0.94) and discrimination (>0.838). These findings were corroborated by clinicians, affirming the accuracy and effectiveness of our approach.

Cell-type-specific alternative polyadenylation promotes oncogenic gene expression in non-small cell lung cancer progression.

Disrupted alternative polyadenylation (APA) is frequently involved in tumorigenesis and cancer progression by regulating the gene expression of oncogenes and tumor suppressors. However, limited knowledge of tumor-type- and cell-type-specific APA events may lead to novel APA events and their functions being overlooked. Here, we compared APA events across different cell types in non-small cell lung cancer (NSCLC) and normal tissues and identified functionally related APA events in NSCLC. We found several cell-specific 3'-UTR alterations that regulate gene expression changes showed prognostic value in NSCLC. We further investigated the function of APA-mediated 3'-UTR shortening through loss of microRNA (miRNA)-binding sites, and we identified and experimentally validated several oncogene-miRNA-tumor suppressor axes. According to our analyses, we found SPARC as an APA-regulated oncogene in cancer-associated fibroblasts in NSCLC. Knockdown of SPARC attenuates lung cancer cell invasion and metastasis. Moreover, we found high SPARC expression associated with resistance to several drugs except cisplatin. NSCLC patients with high SPARC expression could benefit more compared to low-SPARC-expression patients with cisplatin treatment. Overall, our comprehensive analysis of cell-specific APA events shed light on the regulatory mechanism of cell-specific oncogenes and provided opportunities for combination of APA-regulated therapeutic target and cell-specific therapy development.

LVPT: Lazy Velocity Pseudotime Inference Method.

The emergence of RNA velocity has enriched our understanding of the dynamic transcriptional landscape within individual cells. In light of this breakthrough, we embarked on integrating RNA velocity with cellular pseudotime inference, aiming to improve the prediction of cell orders along biological trajectories beyond existing methods. Here, we developed LVPT, a novel method for pseudotime and trajectory inference. LVPT introduces a lazy probability to indicate the probability that the cell stays in the original state and calculates the transition matrix based on RNA velocity to provide the probability and direction of cell differentiation. LVPT shows better and comparable performance of pseudotime inference compared with other existing methods on both simulated datasets with different structures and real datasets. The validation results were consistent with prior knowledge, indicating that LVPT is an accurate and efficient method for pseudotime inference.

Preliminary Evaluation of 18F-Labeled Benzylguanidine Analogs as NET Tracers for Myocardial Infarction Diagnosis.

PURPOSE: Heart failure (HF) remains a major cause of late morbidity and mortality after myocardial infarction (MI). To date, no clinically established 18F-labeled sympathetic nerve PET tracers for monitoring myocardial infarction are available. Therefore, in this study, we synthesized a series of 18F-labeled benzyl guanidine analogs and evaluated their efficacy as cardiac neuronal norepinephrine transporter (NET) tracers for myocardial imaging. We also investigated the preliminary diagnostic capabilities of these tracers in myocardial infarction animal models, as well as the structure-activity relationship of these tracers. PROCEDURES: Three benzyl guanidine-NET tracers, including [18F]1, [18F]2, and [18F]3, were synthesized and evaluated in vivo as PET tracers in a myocardial infarction mouse model. [18F]LMI1195 was used as a positive control for the tracers. H&E staining of the isolated myocardial infarction heart tissue sections was performed to verify the efficacy of the selected PET tracer. RESULTS: Our data show that [18F]3 had a moderate decay corrected labeling yield (~10%) and high radiochemical purity (>95%) compared to other tracers. The uptake of [18F]3 in normal mouse hearts was 1.7±0.1%ID/cc at 1 h post-injection (p. i.), while it was 2.4±0.1, 2.6±0.9, and 2.1±0.4%ID/cc in the MI mouse hearts at 1, 2, and 3 days after surgery, respectively. Compared with [18F]LMI1195, [18F]3 had a better myocardial imaging effect in terms of the contrast between normal and MI hearts. The area of myocardial infarction shown by PET imaging corresponded well with the infarcted tissue demonstrated by H&E staining. CONCLUSIONS: With an obvious cardiac uptake contrast between normal mice and the myocardial infarction mouse model, [18F]3 appears to be a potential tool in the diagnosis of myocardial infarction. Therefore, it is necessary to conduct further structural modification studies on the chemical structure of [18F]3 to improve its in vivo stability and diagnostic detection ability to achieve reliable and practical imaging effects.

COVIDanno, COVID-19 annotation in human.

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the etiologic agent of coronavirus disease 19 (COVID-19), has caused a global health crisis. Despite ongoing efforts to treat patients, there is no universal prevention or cure available. One of the feasible approaches will be identifying the key genes from SARS-CoV-2-infected cells. SARS-CoV-2-infected in vitro model, allows easy control of the experimental conditions, obtaining reproducible results, and monitoring of infection progression. Currently, accumulating RNA-seq data from SARS-CoV-2 in vitro models urgently needs systematic translation and interpretation. To fill this gap, we built COVIDanno, COVID-19 annotation in humans, available at http://biomedbdc.wchscu.cn/COVIDanno/. The aim of this resource is to provide a reference resource of intensive functional annotations of differentially expressed genes (DEGs) among different time points of COVID-19 infection in human in vitro models. To do this, we performed differential expression analysis for 136 individual datasets across 13 tissue types. In total, we identified 4,935 DEGs. We performed multiple bioinformatics/computational biology studies for these DEGs. Furthermore, we developed a novel tool to help users predict the status of SARS-CoV-2 infection for a given sample. COVIDanno will be a valuable resource for identifying SARS-CoV-2-related genes and understanding their potential functional roles in different time points and multiple tissue types.

Automated CT Pancreas Segmentation for Acute Pancreatitis Patients by combining a Novel Object Detection Approach and U-Net.

Acute pancreatitis is an inflammatory disorder of the pancreas. Medical imaging, such as computed tomography (CT), has been widely used to detect volume changes in the pancreas for acute pancreatitis diagnosis. Many pancreas segmentation methods have been proposed but no methods for pancreas segmentation from acute pancreatitis patients. The segmentation of an inflamed pancreas is more challenging than the normal pancreas due to the following two reasons. 1) The inflamed pancreas invades surrounding organs and causes blurry boundaries. 2) The inflamed pancreas has higher shape, size, and location variability than the normal pancreas. To overcome these challenges, we propose an automated CT pancreas segmentation approach for acute pancreatitis patients by combining a novel object detection approach and U-Net. Our approach includes a detector and a segmenter. Specifically, we develop an FCN-guided region proposal network (RPN) detector to localize the pancreatitis regions. The detector first uses a fully convolutional network (FCN) to reduce the background interference of medical images and generates a fixed feature map containing the acute pancreatitis regions. Then the RPN is employed on the feature map to precisely localize the acute pancreatitis regions. After obtaining the location of pancreatitis, the U-Net segmenter is used on the cropped image according to the bounding box. The proposed approach is validated using a collected clinical dataset with 89 abdominal contrast-enhanced 3D CT scans from acute pancreatitis patients. Compared with other start-of-the-art approaches for normal pancreas segmentation, our method achieves better performance on both localization and segmentation in acute pancreatitis patients.

CVAM: CNA Profile Inference of the Spatial Transcriptome Based on the VGAE and HMM.

Tumors are often polyclonal due to copy number alteration (CNA) events. Through the CNA profile, we can understand the tumor heterogeneity and consistency. CNA information is usually obtained through DNA sequencing. However, many existing studies have shown a positive correlation between the gene expression and gene copy number identified from DNA sequencing. With the development of spatial transcriptome technologies, it is urgent to develop new tools to identify genomic variation from the spatial transcriptome. Therefore, in this study, we developed CVAM, a tool to infer the CNA profile from spatial transcriptome data. Compared with existing tools, CVAM integrates the spatial information with the spot's gene expression information together and the spatial information is indirectly introduced into the CNA inference. By applying CVAM to simulated and real spatial transcriptome data, we found that CVAM performed better in identifying CNA events. In addition, we analyzed the potential co-occurrence and mutual exclusion between CNA events in tumor clusters, which is helpful to analyze the potential interaction between genes in mutation. Last but not least, Ripley's K-function is also applied to CNA multi-distance spatial pattern analysis so that we can figure out the differences of different gene CNA events in spatial distribution, which is helpful for tumor analysis and implementing more effective treatment measures based on spatial characteristics of genes.

Inferring evolutionary trajectories from cross-sectional transcriptomic data to mirror lung adenocarcinoma progression.

Lung adenocarcinoma (LUAD) is a deadly tumor with dynamic evolutionary process. Although much endeavors have been made in identifying the temporal patterns of cancer progression, it remains challenging to infer and interpret the molecular alterations associated with cancer development and progression. To this end, we developed a computational approach to infer the progression trajectory based on cross-sectional transcriptomic data. Analysis of the LUAD data using our approach revealed a linear trajectory with three different branches for malignant progression, and the results showed consistency in three independent cohorts. We used the progression model to elucidate the potential molecular events in LUAD progression. Further analysis showed that overexpression of BUB1B, BUB1 and BUB3 promoted tumor cell proliferation and metastases by disturbing the spindle assembly checkpoint (SAC) in the mitosis. Aberrant mitotic spindle checkpoint signaling appeared to be one of the key factors promoting LUAD progression. We found the inferred cancer trajectory allows to identify LUAD susceptibility genetic variations using genome-wide association analysis. This result shows the opportunity for combining analysis of candidate genetic factors with disease progression. Furthermore, the trajectory showed clear evident mutation accumulation and clonal expansion along with the LUAD progression. Understanding how tumors evolve and identifying mutated genes will help guide cancer management. We investigated the clonal architectures and identified distinct clones and subclones in different LUAD branches. Validation of the model in multiple independent data sets and correlation analysis with clinical results demonstrate that our method is effective and unbiased.

Increased tryptophan, but not increased glucose metabolism, predict resistance of pembrolizumab in stage III/IV melanoma.

Clinical trials of combined IDO/PD1 blockade in metastatic melanoma (MM) failed to show additional clinical benefit compared to PD1-alone inhibition. We reasoned that a tryptophan-metabolizing pathway other than the kynurenine one is essential. We immunohistochemically stained tissues along the nevus-to-MM progression pathway for tryptophan-metabolizing enzymes (TMEs; TPH1, TPH2, TDO2, IDO1) and the tryptophan transporter, LAT1. We assessed tryptophan and glucose metabolism by performing baseline C11-labeled α-methyl tryptophan (C11-AMT) and fluorodeoxyglucose (FDG) PET imaging of tumor lesions in a prospective clinical trial of pembrolizumab in MM (clinicaltrials.gov, NCT03089606). We found higher protein expression of all TMEs and LAT1 in melanoma cells than tumor-infiltrating lymphocytes (TILs) within MM tumors (n = 68). Melanoma cell-specific TPH1 and LAT1 expressions were significantly anti-correlated with TIL presence in MM. High melanoma cell-specific LAT1 and low IDO1 expression were associated with worse overall survival (OS) in MM. Exploratory optimal cutpoint survival analysis of pretreatment 'high' vs. 'low' C11-AMT SUVmax of the hottest tumor lesion per patient revealed that the 'low' C11-AMT SUVmax was associated with longer progression-free survival in our clinical trial (n = 26). We saw no such trends with pretreatment FDG PET SUVmax. Treatment of melanoma cell lines with telotristat, a TPH1 inhibitor, increased IDO expression and kynurenine production in addition to suppression of serotonin production. High melanoma tryptophan metabolism is a poor predictor of pembrolizumab response and an adverse prognostic factor. Serotoninergic but not kynurenine pathway activation may be significant. Melanoma cells outcompete adjacent TILs, eventually depriving the latter of an essential amino acid.

Genetic impact on the association of sleep patterns and chronic kidney disease: A prospective cohort study of 157,175 UK Biobank participants.

OBJECTIVES: The association between sleep pattern and chronic kidney disease (CKD) incidence, and whether the association is dependent on the genetic backgrounds has not been addressed. We sought to investigate the association of multidimensional sleep pattern with CKD in consideration of genetic polymorphisms. METHODS: In this prospective cohort study of 157,175 participants from the UK Biobank, sleep patterns were derived by multiple correspondence analysis (MCA) and k-means clustering of individual sleep traits (sleep duration, insomnia, chronotype, daytime sleepiness, snoring, and night shift status). Cox proportional hazard regression was used to estimate the association between sleep patterns and CKD incidence. Gene-environment-wide interaction study (GEWIS) was performed to detect whether gene polymorphisms were modifiers on this association. RESULTS: Compared with "healthy sleep" pattern, increased CKD incidence was observed in the clusters with "long sleep duration" (hazard ratios (HR) 1.42, 95% confidence intervals (CI), 1.18-1.72) and "night shift" (HR 1.23, 95% CI, 1.05-1.45) patterns, but not with the "short sleep duration" pattern. By GEWIS, we identified 167 SNPs as suggestive effect modifiers that interacted with unhealthy sleep patterns and affected the risk of CKD. CONCLUSIONS: Unhealthy sleep patterns, with features of long sleep duration and night shift, may increase the risk of CKD. The study highlights the interaction of sleep and individual genetic risk to affect health outcomes.

A novel integrated approach to predicting cancer immunotherapy efficacy.

Immunotherapies have revolutionized cancer treatment modalities; however, predicting clinical response accurately and reliably remains challenging. Neoantigen load is considered as a fundamental genetic determinant of therapeutic response. However, only a few predicted neoantigens are highly immunogenic, with little focus on intratumor heterogeneity (ITH) in the neoantigen landscape and its link with different features in the tumor microenvironment. To address this issue, we comprehensively characterized neoantigens arising from nonsynonymous mutations and gene fusions in lung cancer and melanoma. We developed a composite NEO2IS to characterize interplays between cancer and CD8+ T-cell populations. NEO2IS improved prediction accuracy of patient responses to immune-checkpoint blockades (ICBs). We found that TCR repertoire diversity was consistent with the neoantigen heterogeneity under evolutionary selections. Our defined neoantigen ITH score (NEOITHS) reflected infiltration degree of CD8+ T lymphocytes with different differentiation states and manifested the impact of negative selection pressure on CD8+ T-cell lineage heterogeneity or tumor ecosystem plasticity. We classified tumors into distinct immune subtypes and examined how neoantigen-T cells interactions affected disease progression and treatment response. Overall, our integrated framework helps profile neoantigen patterns that elicit T-cell immunoreactivity, enhance the understanding of evolving tumor-immune interplays and improve prediction of ICBs efficacy.

The transcription factor CSL homolog in Penaeus vannamei positively regulates the transcription of the hemocyanin small subunit gene.

Hemocyanin, a copper-containing respiratory protein, is abundantly present in hemolymph of arthropods and mollusks and performs a variety of immunological functions. However, the regulatory mechanisms of hemocyanin gene transcription remain largely unclear. Our previous work showed that knockdown of the transcription factor CSL, a component of the Notch signaling pathway, downregulated the expression of Penaeus vannamei hemocyanin small subunit gene (PvHMCs), indicating the involvement of CSL in regulating the PvHMCs transcription. In this study, we identified a CSL binding motif ("GAATCCCAGA", +1675/+1684 bp) in the core promoter of PvHMCs (designated as HsP3). Dual luciferase reporter assay and electrophoretic mobility shift assay (EMSA) demonstrated that the CSL homolog in P. vannamei (PvCSL) could directly bind and activate the HsP3 promoter. Moreover, in vivo silencing of PvCSL significantly attenuated the mRNA and protein expression of PvHMCs. Finally, in response to Vibrio parahaemolyticus, Streptococcus iniae and white spot syndrome virus (WSSV) challenge, the transcript of PvCSL and PvHMCs showed a positive correlation, suggesting that PvCSL could also modulate the expression of PvHMCs upon pathogen stimulation. Taken together, our present finding is the first to demonstrate that PvCSL is a crucial factor in transcriptional control of PvHMCs.

Real-time prediction of organ failures in patients with acute pancreatitis using longitudinal irregular data.

It is extremely important to identify patients with acute pancreatitis who are at high risk for developing persistent organ failures early in the course of the disease. Due to the irregularity of longitudinal data and the poor interpretability of complex models, many models used to identify acute pancreatitis patients with a high risk of organ failure tended to rely on simple statistical models and limited their application to the early stages of patient admission. With the success of recurrent neural networks in modeling longitudinal medical data and the development of interpretable algorithms, these problems can be well addressed. In this study, we developed a novel model named Multi-task and Time-aware Gated Recurrent Unit RNN (MT-GRU) to directly predict organ failure in patients with acute pancreatitis based on irregular medical EMR data. Our proposed end-to-end multi-task model achieved significantly better performance compared to two-stage models. In addition, our model not only provided an accurate early warning of organ failure for patients throughout their hospital stay, but also demonstrated individual and population-level important variables, allowing physicians to understand the scientific basis of the model for decision-making. By providing early warning of the risk of organ failure, our proposed model is expected to assist physicians in improving outcomes for patients with acute pancreatitis.

Development of [18F]F-5-OMe-Tryptophans through Photoredox Radiofluorination: A New Method to Access Tryptophan-Based PET Agents.

Although various radiolabeled tryptophan analogs have been developed to monitor tryptophan metabolism using positron emission tomography (PET) for various human diseases including melanoma and other cancers, their application can be limited due to the complicated synthesis process. In this study, we demonstrated that photoredox radiofluorination represents a simple method to access novel tryptophan-based PET agents. In brief, 4-F-5-OMe-tryptophans (l/d-T13) and 6-F-5-OMe-tryptophans (l/d-T18) were easily synthesized. The 18F-labeled analogs were produced by photoredox radiofluorination with radiochemical yields ranging from 2.6 ± 0.5% to 32.4 ± 4.1% (3 ≤ n ≤ 5, enantiomeric excess ≥ 99.0%) and over 98.0% radiochemical purity. Small animal imaging showed that l-[18F]T13 achieved 9.58 ± 0.26%ID/g tumor uptake and good contrast in B16F10 tumor-bearing mice (n = 3). Clearly, l-[18F]T13 exhibited prominent tumor uptake, warranting future evaluations of its potential usage in precise immunotherapy monitoring.

Centralized contrastive loss with weakly supervised progressive feature extraction for fine-grained common thorax disease retrieval in chest x-ray.

BACKGROUND: Medical images have already become an essential tool for the diagnosis of many diseases. Thus a large number of medical images are being generated due to the daily routine inspection. An efficient image-based disease retrieval system will not only make full use of existing data, but also help physicians to prognosis the diseases. Medical image retrieval is represented by the classification and localization of common thorax diseases in x-ray images. Although extensive efforts have been put into this field, there are still many challenges. PURPOSE: Most of the existing fine-grained image research methods just apply existing deep learning frameworks in extracting the image features. However, these high-level features mainly focus on the global representations of the object, rather than simultaneously considering the local ones. It requires fine-grained details to classify the images with similar lesion areas. Thus, it is necessary to combine the global features and local ones to make the features more discriminative. On the other hand, training CNN models based on current existing strategies have a high time complexity, and is hard to get the discriminative features mentioned above. In addition, the visual retrieval method of fine-grained medical images still has the problem of insufficient sample data with accurate annotation information. METHODS: To address above challenges, we introduced a novel fine-grained medical images retrieval method. First, a centralized contrastive loss (CCLoss) is proposed as our metric learning loss function. Parameters are updated by using the center point, which not only improves the distinguishing performance of features, but also effectively reduces the time complexity of the algorithm. In addition, a weakly supervised progressive feature extraction method is proposed to gradually extract the combined features. And the attention mechanism module is applied to screen the target information after the initial positioning for fine refinement, so as to separate the features with a high degree of discrimination. The retrieval of 14 different chest diseases is evaluated on the chest x-ray datasets. RESULTS: Compared with the existing research methods, the proposed method shows a better retrieval result for Recall@8 by 2.26 % ∼ 4.6 % $\%{\sim }4.6\%$ and achieves a very efficient training speed which is 100 times faster than the pair-wise loss-based training strategy. We also assessed the effects of Recall@k (k = 2, 4, 6, 8) for progressive features extracted from different steps to obtain a model with the best retrieval performance. CONCLUSIONS: The proposed model is capable of learning discriminative representations from chest x-ray datasets, and it achieves better performance compared with other state-of-the-art methods. Therefore, the developed model would be useful in the diagnosis of common thorax disease or unknown chest disease.