Acute Crit Care. 2024 Apr 1. doi: 10.4266/acc.2023.01424.e1. Online ahead of print.

NO ABSTRACT

PMID:38556908 | DOI:10.4266/acc.2023.01424.e1

Tissue Eng Part A. 2024 Mar 31. doi: 10.1089/ten.TEA.2024.0014. Online ahead of print.

ABSTRACT

In recent years, there has been a significant expansion in the realm of processing microscopy images, thanks to the advent of machine learning techniques. These techniques offer diverse applications for image processing. Currently, numerous methods are employed for processing microscopy images in the field of biology, ranging from conventional machine learning algorithms to sophisticated deep learning artificial neural networks with millions of parameters. However, a comprehensive grasp of the intricacies of these methods usually necessitates proficiency in programming and advanced mathematics. In our comprehensive review, we explore various widely used deep learning approaches tailored for the processing of microscopy images. Our emphasis is on algorithms that have gained popularity in the field of biology and have been adapted to cater to users lacking programming expertise. In essence, our target audience comprises biologists interested in exploring the potential of deep learning algorithms, even without programming skills. Throughout the review, we elucidate each algorithm's fundamental concepts and capabilities without delving into mathematical and programming complexities. Crucially, all the highlighted algorithms are accessible on open platforms without requiring code, and we provide detailed descriptions and links within our review. It's essential to recognize that addressing each specific problem demands an individualized approach. Consequently, our focus is not on comparing algorithms but on delineating the problems they are adept at solving. In practical scenarios, researchers typically select multiple algorithms suited to their tasks and experimentally determine the most effective one. It is worth noting that microscopy extends beyond the realm of biology; its applications span diverse fields such as geology and material science. While our review predominantly centers on biomedical applications, the algorithms and principles outlined here are equally applicable to other scientific domains. Furthermore, a number of the proposed solutions can be modified for use in entirely distinct computer vision cases.

PMID:38556835 | DOI:10.1089/ten.TEA.2024.0014

Exp Mol Med. 2024 Apr 1. doi: 10.1038/s12276-024-01189-z. Online ahead of print.

ABSTRACT

Sarcopenia, the progressive decline in skeletal muscle mass and function, is observed in various conditions, including cancer and aging. The complex molecular biology of sarcopenia has posed challenges for the development of FDA-approved medications, which have mainly focused on dietary supplementation. Targeting a single gene may not be sufficient to address the broad range of processes involved in muscle loss. This study analyzed the gene expression signatures associated with cancer formation and 5-FU chemotherapy-induced muscle wasting. Our findings suggest that dimenhydrinate, a combination of 8-chlorotheophylline and diphenhydramine, is a potential therapeutic for sarcopenia. In vitro experiments demonstrated that dimenhydrinate promotes muscle progenitor cell proliferation through the phosphorylation of Nrf2 by 8-chlorotheophylline and promotes myotube formation through diphenhydramine-induced autophagy. Furthermore, in various in vivo sarcopenia models, dimenhydrinate induced rapid muscle tissue regeneration. It improved muscle regeneration in animals with Duchenne muscular dystrophy (DMD) and facilitated muscle and fat recovery in animals with chemotherapy-induced sarcopenia. As an FDA-approved drug, dimenhydrinate could be applied for sarcopenia treatment after a relatively short development period, providing hope for individuals suffering from this debilitating condition.

PMID:38556548 | DOI:10.1038/s12276-024-01189-z

J Dent. 2024 Mar 29:104970. doi: 10.1016/j.jdent.2024.104970. Online ahead of print.

ABSTRACT

OBJECTIVES: Deep networks have been preliminarily studied in caries diagnosis based on clinical X-ray images nowadays. However, the performance of different deep networks on caries detection is still unclear. This study aims to comprehensively compare the caries detection performances of recent multifarious deep networks with clinical dentist level as a bridge.

METHODS: Based on the self-collected periapical radiograph dataset in clinic, four most popular deep networks in two types, namely YOLOv5 and DETR object detection networks, and UNet and Trans-UNet segmentation networks, were included in the comparison study. Five dentists carried out the caries detection on the same testing dataset for reference. Key tooth-level metrics, including precision, sensitivity, specificity, F1-score and Youden index, were obtained, based on which statistical analysis was conducted.

RESULTS: The F1-score order of deep networks is YOLOv5 (0.87), Trans-UNet (0.86), DETR (0.82) and UNet (0.80) in caries detection. A same ranking order is found using the Youden index combining sensitivity and specificity, which are 0.76, 0.73, 0.69 and 0.64 respectively. A moderate level of concordance was observed between all networks and the gold standard. No significant difference (p>0.05) was found between deep networks and between the well-trained network and dentists in caries detection.

CONCLUSIONS: Among investigated deep networks, YOLOv5 is recommended to be priority for caries detection in terms of its high metrics. The well-trained deep network could be used as a good assistance for dentists to detect and diagnose caries.

CLINICAL SIGNIFICANCE: The well-trained deep network shows a promising potential clinical application prospect. It can provide valuable support to healthcare professionals in facilitating detection and diagnosis of dental caries.

PMID:38556194 | DOI:10.1016/j.jdent.2024.104970

J Cardiovasc Magn Reson. 2024 Mar 29:101042. doi: 10.1016/j.jocmr.2024.101042. Online ahead of print.

ABSTRACT

BACKGROUND: Diastolic left ventricular dysfunction is a powerful contributor to the symptoms and prognosis of patients with heart failure. In patients with depressed left ventricular systolic function the EA ratio is the first step to defining the grade of diastolic dysfunction. Doppler echocardiography is the preferred imaging technique for diastolic function assessment, while CMR is less established as a method. Previous 4D Flow-based studies have looked at the EA ratio proximally to the mitral valve, requiring manual interaction. In this study we compare an automated, deep learning-based, and two semiautomated approaches for 4D Flow CMR-based EA ratio assessment to conventional, gold standard echo-based methods.

METHODS: Ninety-seven subjects with chronic ischemic heart disease underwent a cardiac echo followed by an MRI investigation. 4D Flow-based EA ratio values were computed using three different approaches; two semi-automated, assessing the EA ratio by measuring the inflow velocity (MVvel) and the inflow volume (MVflow) at the mitral valve plane, and one fully automated, creating a full LV segmentation using a deep learning-based method within which the EA ratio could be assessed without constraint to the mitral plane (LVvel).

RESULTS: MVvel, MVflow, and LVvel EA ratios were strongly associated with Echo EA ratio (R2= 0.60, 0.58, 0.72). LVvel peak E and A showed moderate association to Echo peak E and A, while MVvel values were weakly associated. MVvel and MVflow EA ratios were very strongly associated with LVvel (R2= 0.84, 0.86). MVvel peak E was moderately associated with LVvel, while peak A showed strong association (R2= 0.26, 0.57).

DISCUSSION AND CONCLUSION: Peak E, peak A and EA ratio are integral to the assessment of diastolic dysfunction and may expand the utility of CMR studies in patients with cardiovascular disease. While underestimation of absolute peak E and A velocities was noted, the EA ratio measured with all three 4D Flow methods was strongly associated with the gold standard Doppler echocardiography. The automatic, deep learning-based method performed best, with the most favorable runtime of ~40seconds. As both semiautomatic methods associated very strongly to LVvel, they could be employed as an alternative for estimation of EA ratio.

PMID:38556134 | DOI:10.1016/j.jocmr.2024.101042

J Am Soc Echocardiogr. 2024 Mar 29:S0894-7317(24)00163-9. doi: 10.1016/j.echo.2024.03.017. Online ahead of print.

ABSTRACT

BACKGROUND: Although regional wall motion abnormality (RWMA) detection is foundational to transthoracic echocardiography (TTE), current methods are prone to inter-observer variability. We aimed to develop a deep learning (DL) model for RWMA assessment and compare it to expert and novice readers.

METHODS: We used 15,746 TTE studies-including 25,529 apical videos-which were split into training, validation, and test datasets. A convolutional neural network was trained and validated using apical 2-, 3-, and 4-chamber videos to predict the presence of RWMA in 7 regions defined by coronary perfusion territories, using the ground truth derived from clinical TTE reports. Within the test cohort, DL model accuracy was compared to 6 expert and 3 novice readers using F1 score evaluation, with the ground truth of RWMA defined by expert readers. Significance between the DL model and novices was assessed using the permutation test.

RESULTS: Within the test cohort, the DL model accurately identified any RWMA with AUC 0.96 (0.92-0.98). The mean F1 scores of the experts and the DL model were numerically similar for 6/7 regions: anterior (86 vs 84), anterolateral (80 vs 74), inferolateral (83 vs 87), inferoseptal (86 vs 86), apical (88 vs 87), inferior (79 vs 81), and any RWMA (90 vs 94 respectively), while in the anteroseptal region F1 score of the DL model was lower than the experts (75 vs 89). Using F1 scores, the DL model outperformed both novices 1 (p=0.002) and 2 (p=0.02) for the detection of any RWMA.

CONCLUSIONS: DL provides accurate detection of RWMA which was comparable to experts and outperformed a majority of novices. DL may improve the efficiency of RWMA assessment and serve as a teaching tool for novices.

PMID:38556038 | DOI:10.1016/j.echo.2024.03.017

Med Phys. 2024 Mar 31. doi: 10.1002/mp.17029. Online ahead of print.

ABSTRACT

BACKGROUND: Deep-learning-based image reconstruction and noise reduction methods (DLIR) have been increasingly deployed in clinical CT. Accurate image quality assessment of these methods is challenging as the performance measured using physical phantoms may not represent the true performance of DLIR in patients since DLIR is trained mostly on patient images.

PURPOSE: In this work, we aim to develop a patient-data-based virtual imaging trial framework and, as a first application, use it to measure the spatial resolution properties of a DLIR method.

METHODS: The patient-data-based virtual imaging trial framework consists of five steps: (1) insertion of lesions into projection domain data using the acquisition geometry of the patient exam to simulate different lesion characteristics; (2) insertion of noise into projection domain data using a realistic photon statistical model of the CT system to simulate different dose levels; (3) creation of DLIR-processed images from projection or image data; (4) creation of ensembles of DLIR-processed patient images from a large number of noise and lesion realizations; and (5) evaluation of image quality using ensemble DLIR images. This framework was applied to measure the spatial resolution of a ResNet based deep convolutional neural network (DCNN) trained on patient images. Lesions in a cylindrical shape and different contrast levels (-500, -100, -50, -20, -10 HU) were inserted to the lower right lobe of the liver in a patient case. Multiple dose levels were simulated (50%, 25%, 12.5%). Each lesion and dose condition had 600 noise realizations. Multiple reconstruction and denoising methods were used on all the noise realizations, including the original filtered-backprojection (FBP), iterative reconstruction (IR), and the DCNN method with three different strength setting (DCNN-weak, DCNN-medium, and DCNN-strong). Mean lesion signal was calculated by performing ensemble averaging of all the noise realizations for each lesion and dose condition and then subtracting the lesion-present images from the lesion absent images. Modulation transfer functions (MTFs) both in-plane and along the z-axis were calculated based on the mean lesion signals. The standard deviations of MTFs at each condition were estimated with bootstrapping: randomly sampling (with replacement) all the DLIR/FBP/IR images from the ensemble data (600 samples) at each condition. The impact of varying lesion contrast, dose levels, and denoising strengths were evaluated. Statistical analysis with paired t-test was used to compare the z-axis and in-plane spatial resolution of five algorithms for five different contrasts and three dose levels.

RESULTS: The in-plane and z-axis spatial resolution degradation of DCNN becomes more severe as the contrast or radiation dose decreased, or DCNN denoising strength increased. In comparison with FBP, a 59.5% and 4.1% reduction of in-plane and z-axis MTF (in terms of spatial frequencies at 50% MTF), respectively, was observed at low contrast (-10 HU) for DCNN with the highest denoising strength at 25% routine dose level. When the dose level reduces from 50% to 12.5% of routine dose, the in-plane and z-axis MTFs reduces from 92.1% to 76.3%, and from 98.9% to 95.5%, respectively, at contrast of -100 HU, using FBP as the reference. For most conditions of contrasts and dose levels, significant differences were found among the five algorithms, with the following relationship in both in-plane and cross-plane spatial resolution: FBP > DCNN-Weak > IR > DCNN-Medium > DCNN-Strong. The spatial resolution difference among algorithms decreases at higher contrast or dose levels.

CONCLUSIONS: A patient-data-based virtual imaging trial framework was developed and applied to measuring the spatial resolution properties of a DCNN noise reduction method at different contrast and dose levels using real patient data. As with other non-linear image reconstruction and post-processing techniques, the evaluated DCNN method degraded the in-plane and z-axis spatial resolution at lower contrast levels, lower radiation dose, and higher denoising strength.

PMID:38555876 | DOI:10.1002/mp.17029

J Environ Manage. 2024 Mar 30;357:120773. doi: 10.1016/j.jenvman.2024.120773. Online ahead of print.

ABSTRACT

Extraction of coastline from optical remote sensing images is of paramount importance for coastal zone management, erosion monitoring, and intelligent ocean construction. However, nearshore marine environment complexity presents a challenge when capturing small-scale and detailed information regarding coastlines. Furthermore, the presence of numerous tidal flats, suspended sediments, and coastal biological communities exacerbates the reduction in segmentation accuracy, which is particularly noticeable in medium-high-resolution remote sensing image segmentation tasks. Most previous related studies, based primarily on convolutional neural networks (CNNs) or traditional feature extraction methods, faced challenges in detailed pixel-level refinement and lacked comprehensive understanding of the studied images. Therefore, we proposed a new U-shaped deep learning model (STIRUnet) that combines the excellent global modeling ability of SwinTransformer with an improved CNN using an inverted residual module. The proposed method has the capability of global supervised feature learning and layer-by-layer feature extraction, and we conducted sea-land segmentation experiments using GF-HNCD and BSD remote sensing image datasets to validate the performance of the proposed model. The results indicate the following: 1) suspended sediments and coastal biological communities are major contributors to coastline blurring, and 2) the recovery of minute features (e.g., narrow watercourses and microscale artificial structures) effectively enhances edge details and leads to more realistic segmentation outcomes. The findings of this study are highly important in relation of accurate extraction of sea-land information in complex marine environments, and they offer novel insights regarding mixed-pixel identification.

PMID:38555845 | DOI:10.1016/j.jenvman.2024.120773

Comput Biol Chem. 2024 Mar 20;110:108055. doi: 10.1016/j.compbiolchem.2024.108055. Online ahead of print.

ABSTRACT

Accurate classification of membrane proteins like ion channels and transporters is critical for elucidating cellular processes and drug development. We present DeepPLM_mCNN, a novel framework combining Pretrained Language Models (PLMs) and multi-window convolutional neural networks (mCNNs) for effective classification of membrane proteins into ion channels and ion transporters. Our approach extracts informative features from protein sequences by utilizing various PLMs, including TAPE, ProtT5_XL_U50, ESM-1b, ESM-2_480, and ESM-2_1280. These PLM-derived features are then input into a mCNN architecture to learn conserved motifs important for classification. When evaluated on ion transporters, our best performing model utilizing ProtT5 achieved 90% sensitivity, 95.8% specificity, and 95.4% overall accuracy. For ion channels, we obtained 88.3% sensitivity, 95.7% specificity, and 95.2% overall accuracy using ESM-1b features. Our proposed DeepPLM_mCNN framework demonstrates significant improvements over previous methods on unseen test data. This study illustrates the potential of combining PLMs and deep learning for accurate computational identification of membrane proteins from sequence data alone. Our findings have important implications for membrane protein research and drug development targeting ion channels and transporters. The data and source codes in this study are publicly available at the following link: https://github.com/s1129108/DeepPLM_mCNN.

PMID:38555810 | DOI:10.1016/j.compbiolchem.2024.108055

Brief Funct Genomics. 2024 Mar 30:elae009. doi: 10.1093/bfgp/elae009. Online ahead of print.

ABSTRACT

Genomic data analysis has witnessed a surge in complexity and volume, primarily driven by the advent of high-throughput technologies. In particular, studying chromatin loops and structures has become pivotal in understanding gene regulation and genome organization. This systematic investigation explores the realm of specialized bioinformatics pipelines designed specifically for the analysis of chromatin loops and structures. Our investigation incorporates two protein (CTCF and Cohesin) factor-specific loop interaction datasets from six distinct pipelines, amassing a comprehensive collection of 36 diverse datasets. Through a meticulous review of existing literature, we offer a holistic perspective on the methodologies, tools and algorithms underpinning the analysis of this multifaceted genomic feature. We illuminate the vast array of approaches deployed, encompassing pivotal aspects such as data preparation pipeline, preprocessing, statistical features and modelling techniques. Beyond this, we rigorously assess the strengths and limitations inherent in these bioinformatics pipelines, shedding light on the interplay between data quality and the performance of deep learning models, ultimately advancing our comprehension of genomic intricacies.

PMID:38555493 | DOI:10.1093/bfgp/elae009

Med Sci Monit. 2024 Mar 31;30:e943168. doi: 10.12659/MSM.943168.

ABSTRACT

Native vertebral osteomyelitis, also termed spondylodiscitis, is an antibiotic-resistant disease that requires long-term treatment. Without proper treatment, NVO can lead to severe nerve damage or even death. Therefore, it is important to accurately diagnose the cause of NVO, especially in spontaneous cases. Infectious NVO is characterized by the involvement of 2 adjacent vertebrae and intervertebral discs, and common infectious agents include Staphylococcus aureus, Mycobacterium tuberculosis, Brucella abortus, and fungi. Clinical symptoms are generally nonspecific, and early diagnosis and appropriate treatment can prevent irreversible sequelae. Advances in pathologic histologic imaging have led physicians to look more forward to being able to differentiate between tuberculous and septic spinal discitis. Therefore, research in identifying and differentiating the imaging features of these 4 common NVOs is essential. Due to the diagnostic difficulties, clinical and radiologic diagnosis is the mainstay of provisional diagnosis. With the advent of the big data era and the emergence of convolutional neural network algorithms for deep learning, the application of artificial intelligence (AI) technology in orthopedic imaging diagnosis has gradually increased. AI can assist physicians in imaging review, effectively reduce the workload of physicians, and improve diagnostic accuracy. Therefore, it is necessary to present the latest clinical research on NVO and the outlook for future AI applications.

PMID:38555491 | DOI:10.12659/MSM.943168

Ageing Res Rev. 2024 Mar 28:102285. doi: 10.1016/j.arr.2024.102285. Online ahead of print.

ABSTRACT

Parkinson's Disease (PD) is a progressive neurodegenerative illness triggered by decreased dopamine secretion. Deep Learning (DL) has gained substantial attention in PD diagnosis research, with an increase in the number of published papers in this discipline. PD detection using DL has presented more promising outcomes as compared with common machine learning approaches. This article aims to conduct a bibliometric analysis and a literature review focusing on the prominent developments taking place in this area. To achieve the target of the study, we retrieved and analyzed the available research papers in the Scopus database. Following that, we conducted a bibliometric analysis to inspect the structure of keywords, authors, and countries in the surveyed studies by providing visual representations of the bibliometric data using VOSviewer software. The study also provides an in-depth review of the literature focusing on different indicators of PD, deployed approaches, and performance metrics. The outcomes indicate the firm development of PD diagnosis using DL approaches over time and a large diversity of studies worldwide. Additionally, the literature review presented a research gap in DL approaches related to incremental learning, particularly in relation to big data analysis.

PMID:38554785 | DOI:10.1016/j.arr.2024.102285

Comput Biol Med. 2024 Mar 13;173:108306. doi: 10.1016/j.compbiomed.2024.108306. Online ahead of print.

ABSTRACT

The incidence of colorectal cancer (CRC), one of the deadliest cancers around the world, is increasing. Tissue microenvironment (TME) features such as tumor-infiltrating lymphocytes (TILs) can have a crucial impact on diagnosis or decision-making for treating patients with CRC. While clinical studies showed that TILs improve the host immune response, leading to a better prognosis, inter-observer agreement for quantifying TILs is not perfect. Incorporating machine learning (ML) based applications in clinical routine may promote diagnosis reliability. Recently, ML has shown potential for making progress in routine clinical procedures. We aim to systematically review the TILs analysis based on ML in CRC histological images. Deep learning (DL) and non-DL techniques can aid pathologists in identifying TILs, and automated TILs are associated with patient outcomes. However, a large multi-institutional CRC dataset with a diverse and multi-ethnic population is necessary to generalize ML methods.

PMID:38554659 | DOI:10.1016/j.compbiomed.2024.108306

Brief Bioinform. 2024 Mar 27;25(3):bbae127. doi: 10.1093/bib/bbae127.

ABSTRACT

MOTIVATION: Accurately predicting molecular metabolic stability is of great significance to drug research and development, ensuring drug safety and effectiveness. Existing deep learning methods, especially graph neural networks, can reveal the molecular structure of drugs and thus efficiently predict the metabolic stability of molecules. However, most of these methods focus on the message passing between adjacent atoms in the molecular graph, ignoring the relationship between bonds. This makes it difficult for these methods to estimate accurate molecular representations, thereby being limited in molecular metabolic stability prediction tasks.

RESULTS: We propose the MS-BACL model based on bond graph augmentation technology and contrastive learning strategy, which can efficiently and reliably predict the metabolic stability of molecules. To our knowledge, this is the first time that bond-to-bond relationships in molecular graph structures have been considered in the task of metabolic stability prediction. We build a bond graph based on 'atom-bond-atom', and the model can simultaneously capture the information of atoms and bonds during the message propagation process. This enhances the model's ability to reveal the internal structure of the molecule, thereby improving the structural representation of the molecule. Furthermore, we perform contrastive learning training based on the molecular graph and its bond graph to learn the final molecular representation. Multiple sets of experimental results on public datasets show that the proposed MS-BACL model outperforms the state-of-the-art model.

AVAILABILITY AND IMPLEMENTATION: The code and data are publicly available at https://github.com/taowang11/MS.

PMID:38555479 | DOI:10.1093/bib/bbae127

Brief Bioinform. 2024 Mar 27;25(3):bbae123. doi: 10.1093/bib/bbae123.

ABSTRACT

Antigen presentation on MHC class II (pMHCII presentation) plays an essential role in the adaptive immune response to extracellular pathogens and cancerous cells. But it can also reduce the efficacy of large-molecule drugs by triggering an anti-drug response. Significant progress has been made in pMHCII presentation modeling due to the collection of large-scale pMHC mass spectrometry datasets (ligandomes) and advances in machine learning. Here, we develop graph-pMHC, a graph neural network approach to predict pMHCII presentation. We derive adjacency matrices for pMHCII using Alphafold2-multimer and address the peptide-MHC binding groove alignment problem with a simple graph enumeration strategy. We demonstrate that graph-pMHC dramatically outperforms methods with suboptimal inductive biases, such as the multilayer-perceptron-based NetMHCIIpan-4.0 (+20.17% absolute average precision). Finally, we create an antibody drug immunogenicity dataset from clinical trial data and develop a method for measuring anti-antibody immunogenicity risk using pMHCII presentation models. Our model increases receiver operating characteristic curve (ROC)-area under the ROC curve (AUC) by 2.57% compared to just filtering peptides by hits in OASis alone for predicting antibody drug immunogenicity.

PMID:38555476 | DOI:10.1093/bib/bbae123

Brief Bioinform. 2024 Mar 27;25(3):bbae121. doi: 10.1093/bib/bbae121.

ABSTRACT

As key oncogenic drivers in non-small-cell lung cancer (NSCLC), various mutations in the epidermal growth factor receptor (EGFR) with variable drug sensitivities have been a major obstacle for precision medicine. To achieve clinical-level drug recommendations, a platform for clinical patient case retrieval and reliable drug sensitivity prediction is highly expected. Therefore, we built a database, D3EGFRdb, with the clinicopathologic characteristics and drug responses of 1339 patients with EGFR mutations via literature mining. On the basis of D3EGFRdb, we developed a deep learning-based prediction model, D3EGFRAI, for drug sensitivity prediction of new EGFR mutation-driven NSCLC. Model validations of D3EGFRAI showed a prediction accuracy of 0.81 and 0.85 for patients from D3EGFRdb and our hospitals, respectively. Furthermore, mutation scanning of the crucial residues inside drug-binding pockets, which may occur in the future, was performed to explore their drug sensitivity changes. D3EGFR is the first platform to achieve clinical-level drug response prediction of all approved small molecule drugs for EGFR mutation-driven lung cancer and is freely accessible at https://www.d3pharma.com/D3EGFR/index.php.

PMID:38555474 | DOI:10.1093/bib/bbae121

Brief Bioinform. 2024 Mar 27;25(3):bbae119. doi: 10.1093/bib/bbae119.

ABSTRACT

Predicting interactions between microbes and hosts plays critical roles in microbiome population genetics and microbial ecology and evolution. How to systematically characterize the sophisticated mechanisms and signal interplay between microbes and hosts is a significant challenge for global health risks. Identifying microbe-host interactions (MHIs) can not only provide helpful insights into their fundamental regulatory mechanisms, but also facilitate the development of targeted therapies for microbial infections. In recent years, computational methods have become an appealing alternative due to the high risk and cost of wet-lab experiments. Therefore, in this study, we utilized rich microbial metagenomic information to construct a novel heterogeneous microbial network (HMN)-based model named KGVHI to predict candidate microbes for target hosts. Specifically, KGVHI first built a HMN by integrating human proteins, viruses and pathogenic bacteria with their biological attributes. Then KGVHI adopted a knowledge graph embedding strategy to capture the global topological structure information of the whole network. A natural language processing algorithm is used to extract the local biological attribute information from the nodes in HMN. Finally, we combined the local and global information and fed it into a blended deep neural network (DNN) for training and prediction. Compared to state-of-the-art methods, the comprehensive experimental results show that our model can obtain excellent results on the corresponding three MHI datasets. Furthermore, we also conducted two pathogenic bacteria case studies to further indicate that KGVHI has excellent predictive capabilities for potential MHI pairs.

PMID:38555472 | DOI:10.1093/bib/bbae119

Brief Bioinform. 2024 Mar 27;25(3):bbae112. doi: 10.1093/bib/bbae112.

ABSTRACT

Single-cell RNA sequencing has achieved massive success in biological research fields. Discovering novel cell types from single-cell transcriptomics has been demonstrated to be essential in the field of biomedicine, yet is time-consuming and needs prior knowledge. With the unprecedented boom in cell atlases, auto-annotation tools have become more prevalent due to their speed, accuracy and user-friendly features. However, existing tools have mostly focused on general cell-type annotation and have not adequately addressed the challenge of discovering novel rare cell types. In this work, we introduce scNovel, a powerful deep learning-based neural network that specifically focuses on novel rare cell discovery. By testing our model on diverse datasets with different scales, protocols and degrees of imbalance, we demonstrate that scNovel significantly outperforms previous state-of-the-art novel cell detection models, reaching the most AUROC performance(the only one method whose averaged AUROC results are above 94%, up to 16.26% more comparing to the second-best method). We validate scNovel's performance on a million-scale dataset to illustrate the scalability of scNovel further. Applying scNovel on a clinical COVID-19 dataset, three potential novel subtypes of Macrophages are identified, where the COVID-related differential genes are also detected to have consistent expression patterns through deeper analysis. We believe that our proposed pipeline will be an important tool for high-throughput clinical data in a wide range of applications.

PMID:38555470 | DOI:10.1093/bib/bbae112

J Transl Med. 2024 Mar 30;22(1):321. doi: 10.1186/s12967-024-05127-5.

ABSTRACT

BACKGROUND: Colorectal cancer (CRC) is the third most prevalent cancer globally, and liver metastasis (CRLM) is the primary cause of death. Hence, it is essential to discover novel prognostic biomarkers and therapeutic drugs for CRLM.

METHODS: This study developed two liver metastasis-associated prognostic signatures based on differentially expressed genes (DEGs) in CRLM. Additionally, we employed an interpretable deep learning model utilizing drug sensitivity databases to identify potential therapeutic drugs for high-risk CRLM patients. Subsequently, in vitro and in vivo experiments were performed to verify the efficacy of these compounds.

RESULTS: These two prognostic models exhibited superior performance compared to previously reported ones. Obatoclax, a BCL-2 inhibitor, showed significant differential responses between high and low risk groups classified by prognostic models, and demonstrated remarkable effectiveness in both Transwell assay and CT26 colorectal liver metastasis mouse model.

CONCLUSIONS: This study highlights the significance of developing specialized prognostication approaches and investigating effective therapeutic drugs for patients with CRLM. The application of a deep learning drug response model provides a new drug discovery strategy for translational medicine in precision oncology.

PMID:38555418 | DOI:10.1186/s12967-024-05127-5

Sci Rep. 2024 Mar 30;14(1):7551. doi: 10.1038/s41598-024-58163-y.

ABSTRACT

Transfer learning plays a pivotal role in addressing the paucity of data, expediting training processes, and enhancing model performance. Nonetheless, the prevailing practice of transfer learning predominantly relies on pre-trained models designed for the natural image domain, which may not be well-suited for the medical image domain in grayscale. Recognizing the significance of leveraging transfer learning in medical research, we undertook the construction of class-balanced pediatric radiograph datasets collectively referred to as PedXnets, grounded in radiographic views using the pediatric radiographs collected over 24 years at Asan Medical Center. For PedXnets pre-training, approximately 70,000 X-ray images were utilized. Three different pre-training weights of PedXnet were constructed using Inception V3 for various radiation perspective classifications: Model-PedXnet-7C, Model-PedXnet-30C, and Model-PedXnet-68C. We validated the transferability and positive effects of transfer learning of PedXnets through pediatric downstream tasks including fracture classification and bone age assessment (BAA). The evaluation of transfer learning effects through classification and regression metrics showed superior performance of Model-PedXnets in quantitative assessments. Additionally, visual analyses confirmed that the Model-PedXnets were more focused on meaningful regions of interest.

PMID:38555414 | DOI:10.1038/s41598-024-58163-y