PLoS One. 2024 Jun 25;19(6):e0306094. doi: 10.1371/journal.pone.0306094. eCollection 2024.

ABSTRACT

Deep learning, a pivotal branch of artificial intelligence, has increasingly influenced the financial domain with its advanced data processing capabilities. This paper introduces Factor-GAN, an innovative framework that utilizes Generative Adversarial Networks (GAN) technology for factor investing. Leveraging a comprehensive factor database comprising 70 firm characteristics, Factor-GAN integrates deep learning techniques with the multi-factor pricing model, thereby elevating the precision and stability of investment strategies. To explain the economic mechanisms underlying deep learning, we conduct a subsample analysis of the Chinese stock market. The findings reveal that the deep learning-based pricing model significantly enhances return prediction accuracy and factor investment performance in comparison to linear models. Particularly noteworthy is the superior performance of the long-short portfolio under Factor-GAN, demonstrating an annualized return of 23.52% with a Sharpe ratio of 1.29. During the transition from state-owned enterprises (SOEs) to non-SOEs, our study discerns shifts in factor importance, with liquidity and volatility gaining significance while fundamental indicators diminish. Additionally, A-share listed companies display a heightened emphasis on momentum and growth indicators relative to their dual-listed counterparts. This research holds profound implications for the expansion of explainable artificial intelligence research and the exploration of financial technology applications.

PMID:38917175 | DOI:10.1371/journal.pone.0306094

PLoS One. 2024 Jun 25;19(6):e0305947. doi: 10.1371/journal.pone.0305947. eCollection 2024.

ABSTRACT

Cephalometric analysis is critically important and common procedure prior to orthodontic treatment and orthognathic surgery. Recently, deep learning approaches have been proposed for automatic 3D cephalometric analysis based on landmarking from CBCT scans. However, these approaches have relied on uniform datasets from a single center or imaging device but without considering patient ethnicity. In addition, previous works have considered a limited number of clinically relevant cephalometric landmarks and the approaches were computationally infeasible, both impairing integration into clinical workflow. Here our aim is to analyze the clinical applicability of a light-weight deep learning neural network for fast localization of 46 clinically significant cephalometric landmarks with multi-center, multi-ethnic, and multi-device data consisting of 309 CBCT scans from Finnish and Thai patients. The localization performance of our approach resulted in the mean distance of 1.99 ± 1.55 mm for the Finnish cohort and 1.96 ± 1.25 mm for the Thai cohort. This performance turned out to be clinically significant i.e., ≤ 2 mm with 61.7% and 64.3% of the landmarks with Finnish and Thai cohorts, respectively. Furthermore, the estimated landmarks were used to measure cephalometric characteristics successfully i.e., with ≤ 2 mm or ≤ 2° error, on 85.9% of the Finnish and 74.4% of the Thai cases. Between the two patient cohorts, 33 of the landmarks and all cephalometric characteristics had no statistically significant difference (p < 0.05) measured by the Mann-Whitney U test with Benjamini-Hochberg correction. Moreover, our method is found to be computationally light, i.e., providing the predictions with the mean duration of 0.77 s and 2.27 s with single machine GPU and CPU computing, respectively. Our findings advocate for the inclusion of this method into clinical settings based on its technical feasibility and robustness across varied clinical datasets.

PMID:38917161 | DOI:10.1371/journal.pone.0305947

PLOS Digit Health. 2024 Jun 25;3(6):e0000539. doi: 10.1371/journal.pdig.0000539. eCollection 2024 Jun.

ABSTRACT

For a number of antiarrhythmics, drug loading requires a 3-day hospitalization with continuous monitoring for QT-prolongation. Automated QT monitoring with wearable ECG monitors would enable out-of-hospital care. We therefore develop a deep learning model that infers QT intervals from ECG Lead-I-the lead that is often available in ambulatory ECG monitors-and use this model to detect clinically meaningful QT-prolongation episodes during Dofetilide drug loading. QTNet-a deep neural network that infers QT intervals from Lead-I ECG-was trained using over 3 million ECGs from 653 thousand patients at the Massachusetts General Hospital and tested on an internal-test set consisting of 633 thousand ECGs from 135 thousand patients. QTNet is further evaluated on an external-validation set containing 3.1 million ECGs from 667 thousand patients at another healthcare institution. On both evaluations, the model achieves mean absolute errors of 12.63ms (internal-test) and 12.30ms (external-validation) for estimating absolute QT intervals. The associated Pearson correlation coefficients are 0.91 (internal-test) and 0.92 (external-validation). Finally, QTNet was used to detect Dofetilide-induced QT prolongation in a publicly available database (ECGRDVQ-dataset) containing ECGs from subjects enrolled in a clinical trial evaluating the effects of antiarrhythmic drugs. QTNet detects Dofetilide-induced QTc prolongation with 87% sensitivity and 77% specificity. The negative predictive value of the model is greater than 95% when the pre-test probability of drug-induced QTc prolongation is below 25%. These results show that drug-induced QT prolongation risk can be tracked from ECG Lead-I using deep learning.

PMID:38917157 | DOI:10.1371/journal.pdig.0000539

PLoS One. 2024 Jun 25;19(6):e0304999. doi: 10.1371/journal.pone.0304999. eCollection 2024.

ABSTRACT

In recent years, the classification and identification of surface materials on earth have emerged as fundamental yet challenging research topics in the fields of geoscience and remote sensing (RS). The classification of multi-modality RS data still poses certain challenges, despite the notable advancements achieved by deep learning technology in RS image classification. In this work, a deep learning architecture based on convolutional neural network (CNN) is proposed for the classification of multimodal RS image data. The network structure introduces a cross modality reconstruction (CMR) module in the multi-modality feature fusion stage, called CMR-Net. In other words, CMR-Net is based on CNN network structure. In the feature fusion stage, a plug-and-play module for cross-modal fusion reconstruction is designed to compactly integrate features extracted from multiple modalities of remote sensing data, enabling effective information exchange and feature integration. In addition, to validate the proposed scheme, extensive experiments were conducted on two multi-modality RS datasets, namely the Houston2013 dataset consisting of hyperspectral (HS) and light detection and ranging (LiDAR) data, as well as the Berlin dataset comprising HS and synthetic aperture radar (SAR) data. The results demonstrate the effectiveness and superiority of our proposed CMR-Net compared to several state-of-the-art methods for multi-modality RS data classification.

PMID:38917124 | DOI:10.1371/journal.pone.0304999

PLoS One. 2024 Jun 25;19(6):e0281568. doi: 10.1371/journal.pone.0281568. eCollection 2024.

ABSTRACT

Deep learning, a subset of machine learning that utilizes neural networks, has seen significant advancements in recent years. These advancements have led to breakthroughs in a wide range of fields, from natural language processing to computer vision, and have the potential to revolutionize many industries or organizations. They have also demonstrated exceptional performance in the identification and mapping of seagrass images. However, these deep learning models, particularly the popular Convolutional Neural Networks (CNNs) require architectural engineering and hyperparameter tuning. This paper proposes a Deep Neuroevolutionary (DNE) model that can automate the architectural engineering and hyperparameter tuning of CNNs models by developing and using a novel metaheuristic algorithm, named 'Boosted Atomic Orbital Search (BAOS)'. The proposed BAOS is an improved version of the recently proposed Atomic Orbital Search (AOS) algorithm which is based on the principle of atomic model and quantum mechanics. The proposed algorithm leverages the power of the Lévy flight technique to boost the performance of the AOS algorithm. The proposed DNE algorithm (BAOS-CNN) is trained, evaluated and compared with six popular optimisation algorithms on a patch-based multi-species seagrass dataset. This proposed BAOS-CNN model achieves the highest overall accuracy (97.48%) among the seven evolutionary-based CNN models. The proposed model also achieves the state-of-the-art overall accuracy of 92.30% and 93.5% on the publicly available four classes and five classes version of the 'DeepSeagrass' dataset, respectively. This multi-species seagrass dataset is available at: https://ro.ecu.edu.au/datasets/141/.

PMID:38917071 | DOI:10.1371/journal.pone.0281568

Aging Dis. 2024 May 17. doi: 10.14336/AD.2024.0169. Online ahead of print.

ABSTRACT

Non-small-cell lung carcinoma (NSCLC) often carries a dire prognosis. The advent of neoadjuvant chemoimmunotherapy (NCI) has become a promising approach in NSCLC treatment, making the identification of reliable biomarkers for major pathological response (MPR) crucial. This study aimed to devise a deep learning (DL) model to estimate the MPR to NCI in lung squamous cell carcinoma (LUSC) patients and uncover its biological mechanism. We enrolled a cohort of 309 LUSC patients from various medical institutions. A ResNet50 model, trained on contrast-enhanced computed tomography images, was developed, and validated to predict MPR. We examined somatic mutations, genomic data, tumor-infiltrating immune cells, and intra-tumor microorganisms. Post-treatment, 149 (48.22%) patients exhibited MPR. The DL model demonstrated excellent predictive accuracy, evidenced by an area under the receiver operating characteristic curve (AUC) of 0.95 (95% CI: 0.98-1.00) and 0.90 (95% CI: 0.81-0.98) in the first and second validation sets, respectively. Multivariate logistic regression analysis identified the DL model score (low vs. high) as an independent predictor of MPR. The prediction of MPR (P-MPR) correlated with mutations in four genes, as well as gene ontology and pathways tied to immune response and antigen processing and presentation. Analysis also highlighted diversity in immune cells within the tumor microenvironment and in peripheral blood. Moreover, the presence of four distinct bacteria varied among intra-tumor microorganisms. Our DL model proved highly effective in predicting MPR in LUSC patients undergoing NCI, significantly advancing our understanding of the biological mechanisms involved.

PMID:38916736 | DOI:10.14336/AD.2024.0169

MAGMA. 2024 Jun 25. doi: 10.1007/s10334-024-01172-9. Online ahead of print.

ABSTRACT

PURPOSE: To develop a new MR coronary angiography (MRCA) technique by employing a zigzag fan-shaped centric ky-kz k-space trajectory combined with high-resolution deep learning reconstruction (HR-DLR).

METHODS: All imaging data were acquired from 12 healthy subjects and 2 patients using two clinical 3-T MR imagers, with institutional review board approval. Ten healthy subjects underwent both standard 3D fast gradient echo (sFGE) and centric ky-kz k-space trajectory FGE (cFGE) acquisitions to compare the scan time and image quality. Quantitative measures were also performed for signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) as well as sharpness of the vessel. Furthermore, the feasibility of the proposed cFGE sequence was assessed in two patients. For assessing the feasibility of the centric ky-kz trajectory, the navigator-echo window of a 30-mm threshold was applied in cFGE, whereas sFGE was applied using a standard 5-mm threshold. Image quality of MRCA using cFGE with HR-DLR and sFGE without HR-DLR was scored in a 5-point scale (non-diagnostic = 1, fair = 2, moderate = 3, good = 4, and excellent = 5). Image evaluation of cFGE, applying HR-DLR, was compared with sFGE without HR-DLR. Friedman test, Wilcoxon signed-rank test, or paired t tests were performed for the comparison of related variables.

RESULTS: The actual MRCA scan time of cFGE with a 30-mm threshold was acquired in less than 5 min, achieving nearly 100% efficiency, showcasing its expeditious and robustness. In contrast, sFGE was acquired with a 5-mm threshold and had an average scan time of approximately 15 min. Overall image quality for MRCA was scored 3.3 for sFGE and 2.7 for cFGE without HR-DLR but increased to 3.6 for cFGE with HR-DLR and (p < 0.05). The clinical result of patients obtained within 5 min showed good quality images in both patients, even with a stent, without artifacts. Quantitative measures of SNR, CNR, and sharpness of vessel presented higher in cFGE with HR-DLR.

CONCLUSION: Our findings demonstrate a robust, time-efficient solution for high-quality MRCA, enhancing patient comfort and increasing clinical throughput.

PMID:38916681 | DOI:10.1007/s10334-024-01172-9

Syst Biol. 2024 Jun 25:syae029. doi: 10.1093/sysbio/syae029. Online ahead of print.

ABSTRACT

Models have always been central to inferring molecular evolution and to reconstructing phylogenetic trees. Their use typically involves the development of a mechanistic framework reflecting our understanding of the underlying biological processes, such as nucleotide substitu- tions, and the estimation of model parameters by maximum likelihood or Bayesian inference. However, deriving and optimizing the likelihood of the data is not always possible under complex evolutionary scenarios or even tractable for large datasets, often leading to unrealistic simplifying assumptions in the fitted models. To overcome this issue, we coupled stochastic simulations of genome evolution with a new supervised deep learning model to infer key parameters of molecular evolution. Our model is designed to directly analyze multiple sequence alignments and estimate per-site evolutionary rates and divergence, without requiring a known phylogenetic tree. The accuracy of our predictions matched that of likelihood-based phylogenetic inference, when rate heterogeneity followed a simple gamma distribution, but it strongly exceeded it under more complex patterns of rate variation, such as codon models. Our approach is highly scalable and can be efficiently applied to genomic data, as we showed on a dataset of 26 million nucleotides from the clownfish clade. Our simulations also showed that the integration of per-site rates obtained by deep learning within a Bayesian framework led to significantly more accu- rate phylogenetic inference, particularly with respect to the estimated branch lengths. We thus propose that future advancements in phylogenetic analysis will benefit from a semi-supervised learning approach that combines deep-learning estimation of substitution rates, which allows for more flexible models of rate variation, and probabilistic inference of the phylogenetic tree, which guarantees interpretability and a rigorous assessment of statistical support.

PMID:38916476 | DOI:10.1093/sysbio/syae029

Cyberpsychol Behav Soc Netw. 2024 Jun 25. doi: 10.1089/cyber.2023.0737. Online ahead of print.

ABSTRACT

This article provides an overview of the mental health challenges faced by pilots and air traffic controllers (ATCs), whose stressful professional lives may negatively impact global flight safety and security. The adverse effects of mental health disorders on their flight performance pose a particular safety risk, especially in sudden unexpected startle situations. Therefore, the early detection, prediction and prevention of mental health deterioration in pilots and ATCs, particularly among those at high risk, are crucial to minimize potential air crash incidents caused by human factors. Recent research in artificial intelligence (AI) demonstrates the potential of machine and deep learning, edge and cloud computing, virtual reality and wearable multimodal physiological sensors for monitoring and predicting mental health disorders. Longitudinal monitoring and analysis of pilots' and ATCs physiological, cognitive and behavioral states could help predict individuals at risk of undisclosed or emerging mental health disorders. Utilizing AI tools and methodologies to identify and select these individuals for preventive mental health training and interventions could be a promising and effective approach to preventing potential air crash accidents attributed to human factors and related mental health problems. Based on these insights, the article advocates for the design of a multidisciplinary mental healthcare ecosystem in modern aviation using AI tools and technologies, to foster more efficient and effective mental health management, thereby enhancing flight safety and security standards. This proposed ecosystem requires the collaboration of multidisciplinary experts, including psychologists, neuroscientists, physiologists, psychiatrists, etc. to address these challenges in modern aviation.

PMID:38916063 | DOI:10.1089/cyber.2023.0737

Proc IEEE Int Symp Biomed Imaging. 2020 Apr;2020:981-985. doi: 10.1109/isbi45749.2020.9098620. Epub 2020 May 22.

ABSTRACT

Deep neural networks yield promising results in a wide range of computer vision applications, including landmark detection. A major challenge for accurate anatomical landmark detection in volumetric images such as clinical CT scans is that large-scale data often constrain the capacity of the employed neural network architecture due to GPU memory limitations, which in turn can limit the precision of the output. We propose a multi-scale, end-to-end deep learning method that achieves fast and memory-efficient landmark detection in 3D images. Our architecture consists of blocks of shift-equivariant networks, each of which performs landmark detection at a different spatial scale. These blocks are connected from coarse to fine-scale, with differentiable resampling layers, so that all levels can be trained together. We also present a noise injection strategy that increases the robustness of the model and allows us to quantify uncertainty at test time. We evaluate our method for carotid artery bifurcations detection on 263 CT volumes and achieve a better than state-of-the-art accuracy with mean Euclidean distance error of 2.81mm.

PMID:38915907 | PMC:PMC11194796 | DOI:10.1109/isbi45749.2020.9098620

Front Neurol. 2024 Jun 10;15:1398876. doi: 10.3389/fneur.2024.1398876. eCollection 2024.

ABSTRACT

BACKGROUND: Arteriovenous malformations (AVMs) are rare vascular anomalies involving a disorganization of arteries and veins with no intervening capillaries. In the past 10 years, radiomics and machine learning (ML) models became increasingly popular for analyzing diagnostic medical images. The goal of this review was to provide a comprehensive summary of current radiomic models being employed for the diagnostic, therapeutic, prognostic, and predictive outcomes in AVM management.

METHODS: A systematic literature review was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines, in which the PubMed and Embase databases were searched using the following terms: (cerebral OR brain OR intracranial OR central nervous system OR spine OR spinal) AND (AVM OR arteriovenous malformation OR arteriovenous malformations) AND (radiomics OR radiogenomics OR machine learning OR artificial intelligence OR deep learning OR computer-aided detection OR computer-aided prediction OR computer-aided treatment decision). A radiomics quality score (RQS) was calculated for all included studies.

RESULTS: Thirteen studies were included, which were all retrospective in nature. Three studies (23%) dealt with AVM diagnosis and grading, 1 study (8%) gauged treatment response, 8 (62%) predicted outcomes, and the last one (8%) addressed prognosis. No radiomics model had undergone external validation. The mean RQS was 15.92 (range: 10-18).

CONCLUSION: We demonstrated that radiomics is currently being studied in different facets of AVM management. While not ready for clinical use, radiomics is a rapidly emerging field expected to play a significant future role in medical imaging. More prospective studies are warranted to determine the role of radiomics in the diagnosis, prediction of comorbidities, and treatment selection in AVM management.

PMID:38915798 | PMC:PMC11194423 | DOI:10.3389/fneur.2024.1398876

bioRxiv [Preprint]. 2024 Jun 14:2024.06.14.599076. doi: 10.1101/2024.06.14.599076.

ABSTRACT

An important and largely unsolved problem in synthetic biology is how to target gene expression to specific cell types. Here, we apply iterative deep learning to design synthetic enhancers with strong differential activity between two human cell lines. We initially train models on published datasets of enhancer activity and chromatin accessibility and use them to guide the design of synthetic enhancers that maximize predicted specificity. We experimentally validate these sequences, use the measurements to re-optimize the predictor, and design a second generation of enhancers with improved specificity. Our design methods embed relevant transcription factor binding site (TFBS) motifs with higher frequencies than comparable endogenous enhancers while using a more selective motif vocabulary, and we show that enhancer activity is correlated with transcription factor expression at the single cell level. Finally, we characterize causal features of top enhancers via perturbation experiments and show enhancers as short as 50bp can maintain specificity.

PMID:38915713 | PMC:PMC11195158 | DOI:10.1101/2024.06.14.599076

bioRxiv [Preprint]. 2024 Jun 12:2024.06.10.598319. doi: 10.1101/2024.06.10.598319.

ABSTRACT

MOTIVATION: In recent years deep learning has become one of the central approaches in a number of applications, including many tasks in genomics. However, as models grow in depth and complexity, they either require more data or a strategic initialization technique to improve performance.

RESULTS: In this project, we introduce cGen, a novel unsupervised, model-agnostic contrastive pre-training method for sequence-based models. cGen can be used before training to initialize weights, reducing the size of the dataset needed. It works through learning the intrinsic features of the reference genome and makes no assumptions on the underlying structure. We show that the embeddings produced by the unsupervised model are already informative for gene expression prediction and that the sequence features provide a meaningful clustering. We demonstrate that cGen improves model performance in various sequence-based deep learning applications, such as chromatin profiling prediction and gene expression. Our findings suggest that using cGen, particularly in areas constrained by data availability, could improve the performance of deep learning genomic models without the need to modify the model architecture.

PMID:38915667 | PMC:PMC11195128 | DOI:10.1101/2024.06.10.598319

bioRxiv [Preprint]. 2024 Jun 10:2024.06.07.597994. doi: 10.1101/2024.06.07.597994.

ABSTRACT

Autofluorescence microscopy uses intrinsic sources of molecular contrast to provide cellular-level information without extrinsic labels. However, traditional cell segmentation tools are often optimized for high signal-to-noise ratio (SNR) images, such as fluorescently labeled cells, and unsurprisingly perform poorly on low SNR autofluorescence images. Therefore, new cell segmentation tools are needed for autofluorescence microscopy. Cellpose is a deep learning network that is generalizable across diverse cell microscopy images and automatically segments single cells to improve throughput and reduce inter-human biases. This study aims to validate Cellpose for autofluorescence imaging, specifically from multiphoton intensity images of NAD(P)H. Manually segmented nuclear masks of NAD(P)H images were used to train new Cellpose models. These models were applied to PANC-1 cells treated with metabolic inhibitors and patient-derived cancer organoids (across 9 patients) treated with chemotherapies. These datasets include co-registered fluorescence lifetime imaging microscopy (FLIM) of NAD(P)H and FAD, so fluorescence decay parameters and the optical redox ratio (ORR) were compared between masks generated by the new Cellpose model and manual segmentation. The Dice score between repeated manually segmented masks was significantly lower than that of repeated Cellpose masks (p<0.0001) indicating greater reproducibility between Cellpose masks. There was also a high correlation (R 2 >0.9) between Cellpose and manually segmented masks for the ORR, mean NAD(P)H lifetime, and mean FAD lifetime across 2D and 3D cell culture treatment conditions. Masks generated from Cellpose and manual segmentation also maintain similar means, variances, and effect sizes between treatments for the ORR and FLIM parameters. Overall, Cellpose provides a fast, reliable, reproducible, and accurate method to segment single cells in autofluorescence microscopy images such that functional changes in cells are accurately captured in both 2D and 3D culture.

PMID:38915614 | PMC:PMC11195115 | DOI:10.1101/2024.06.07.597994

bioRxiv [Preprint]. 2024 Jun 10:2024.06.05.597673. doi: 10.1101/2024.06.05.597673.

ABSTRACT

The human cerebral cortex, pivotal for advanced cognitive functions, is composed of six distinct layers and dozens of functionally specialized areas 1,2 . The layers and areas are distinguished both molecularly, by diverse neuronal and glial cell subtypes, and structurally, through intricate spatial organization 3,4 . While single-cell transcriptomics studies have advanced molecular characterization of human cortical development, a critical gap exists due to the loss of spatial context during cell dissociation 5,6,7,8 . Here, we utilized multiplexed error-robust fluorescence in situ hybridization (MERFISH) 9 , augmented with deep-learning-based cell segmentation, to examine the molecular, cellular, and cytoarchitectural development of human fetal cortex with spatially resolved single-cell resolution. Our extensive spatial atlas, encompassing 16 million single cells, spans eight cortical areas across four time points in the second and third trimesters. We uncovered an early establishment of the six-layer structure, identifiable in the laminar distribution of excitatory neuronal subtypes by mid-gestation, long before the emergence of cytoarchitectural layers. Notably, while anterior-posterior gradients of neuronal subtypes were generally observed in most cortical areas, a striking exception was the sharp molecular border between primary (V1) and secondary visual cortices (V2) at gestational week 20. Here we discovered an abrupt binary shift in neuronal subtype specification at the earliest stages, challenging the notion that continuous morphogen gradients dictate mid-gestation cortical arealization 6,10 . Moreover, integrating single-nuclei RNA-sequencing and in situ whole transcriptomics revealed an early upregulation of synaptogenesis in V1-specific Layer 4 neurons, suggesting a role of synaptogenesis in this discrete border formation. Collectively, our findings underscore the crucial role of spatial relationships in determining the molecular specification of cortical layers and areas. This work not only provides a valuable resource for the field, but also establishes a spatially resolved single-cell analysis paradigm that paves the way for a comprehensive developmental atlas of the human brain.

PMID:38915567 | PMC:PMC11195106 | DOI:10.1101/2024.06.05.597673

bioRxiv [Preprint]. 2024 Jun 16:2024.06.16.599221. doi: 10.1101/2024.06.16.599221.

ABSTRACT

PSSR2 improves and expands on the previously established PSSR (Point-Scanning Super-Resolution) workflow for simultaneous super-resolution and denoising of undersampled microscopy data. PSSR2 is designed to put state-of-the-art technology into the hands of the general microscopy and biology research community, enabling user-friendly implementation of PSSR workflows with little to no programming experience required, especially through its integrated CLI and Napari plugin.

PMID:38915557 | PMC:PMC11195205 | DOI:10.1101/2024.06.16.599221

bioRxiv [Preprint]. 2024 Jun 14:2024.06.12.598686. doi: 10.1101/2024.06.12.598686.

ABSTRACT

The spatial arrangement of cells is vital in developmental processes and organogenesis in multicellular life forms. Deep learning models trained with spatial omics data uncover complex patterns and relationships among cells, genes, and proteins in a high-dimensional space, providing new insights into biological processes and diseases. State-of-the-art in silico spatial multi-cell gene expression methods using histological images of tissue stained with hematoxylin and eosin (H&E) to characterize cellular heterogeneity. These computational techniques offer the advantage of analyzing vast amounts of spatial data in a scalable and automated manner, thereby accelerating scientific discovery and enabling more precise medical diagnostics and treatments. In this work, we developed a vision transformer (ViT) framework to map histological signatures to spatial single-cell transcriptomic signatures, named SPiRiT ( S patial Omics P rediction and R eproducibility integrated T ransformer). Our framework was enhanced by integrating cross validation with model interpretation during hyper-parameter tuning. SPiRiT predicts single-cell spatial gene expression using the matched histopathological image tiles of human breast cancer and whole mouse pup, evaluated by Xenium (10x Genomics) datasets. Furthermore, ViT model interpretation reveals the high-resolution, high attention area (HAR) that the ViT model uses to predict the gene expression, including marker genes for invasive cancer cells ( FASN ), stromal cells ( POSTN ), and lymphocytes ( IL7R ). In an apple-to-apple comparison with the ST-Net Convolutional Neural Network algorithm, SPiRiT improved predictive accuracy by 40% using human breast cancer Visium (10x Genomics) dataset. Cancer biomarker gene prediction and expression level are highly consistent with the tumor region annotation. In summary, our work highlights the feasibility to infer spatial single-cell gene expression using tissue morphology in multiple-species, i.e., human and mouse, and multi-organs, i.e., mouse whole body morphology. Importantly, incorporating model interpretation and vision transformer is expected to serve as a general-purpose framework for spatial transcriptomics.

PMID:38915550 | PMC:PMC11195284 | DOI:10.1101/2024.06.12.598686

bioRxiv [Preprint]. 2024 Jun 14:2024.06.11.598572. doi: 10.1101/2024.06.11.598572.

ABSTRACT

Cells are among the most dynamic entities, constantly undergoing various processes such as growth, division, movement, and interaction with other cells as well as the environment. Time-lapse microscopy is central to capturing these dynamic behaviors, providing detailed temporal and spatial information that allows biologists to observe and analyze cellular activities in real-time. The analysis of time-lapse microscopy data relies on two fundamental tasks: cell segmentation and cell tracking. Integrating deep learning into bioimage analysis has revolutionized cell segmentation, producing models with high precision across a wide range of biological images. However, developing generalizable deep-learning models for tracking cells over time remains challenging due to the scarcity of large, diverse annotated datasets of time-lapse movies of cells. To address this bottleneck, we propose a GAN-based time-lapse microscopy generator, termed tGAN, designed to significantly enhance the quality and diversity of synthetic annotated time-lapse microscopy data. Our model features a dual-resolution architecture that adeptly synthesizes both low and high-resolution images, uniquely capturing the intricate dynamics of cellular processes essential for accurate tracking. We demonstrate the performance of tGAN in generating high-quality, realistic, annotated time-lapse videos. Our findings indicate that tGAN decreases dependency on extensive manual annotation to enhance the precision of cell tracking models for time-lapse microscopy.

PMID:38915545 | PMC:PMC11195160 | DOI:10.1101/2024.06.11.598572

Sci Rep. 2024 Jun 24;14(1):14510. doi: 10.1038/s41598-024-64072-x.

ABSTRACT

Grape cultivation is important globally, contributing to the agricultural economy and providing diverse grape-based products. However, the susceptibility of grapes to disease poses a significant threat to yield and quality. Traditional disease identification methods demand expert knowledge, which limits scalability and efficiency. To address these limitations our research aims to design an automated deep learning approach for grape leaf disease detection. This research introduces a novel dual-track network for classifying grape leaf diseases, employing a combination of the Swin Transformer and Group Shuffle Residual DeformNet (GSRDN) tracks. The Swin Transformer track exploits shifted window techniques to construct hierarchical feature maps, enhancing global feature extraction. Simultaneously, the GSRDN track combines Group Shuffle Depthwise Residual block and Deformable Convolution block to extract local features with reduced computational complexity. The features from both tracks are concatenated and processed through Triplet Attention for cross-dimensional interaction. The proposed model achieved an accuracy of 98.6%, the precision, recall, and F1-score are recorded as 98.7%, 98.59%, and 98.64%, respectively as validated on a dataset containing grape leaf disease information from the PlantVillage dataset, demonstrating its potential for efficient grape disease classification.

PMID:38914605 | DOI:10.1038/s41598-024-64072-x

Genome Res. 2024 Jun 24:gr.278606.123. doi: 10.1101/gr.278606.123. Online ahead of print.

ABSTRACT

3'-end cleavage and polyadenylation is an essential process for eukaryotic mRNA maturation. In yeast species, the polyadenylation signals that recruit the processing machinery are degenerate and remain poorly characterized compared to the well-defined regulatory elements in mammals. Here we address this question by developing deep learning models to deconvolute degenerate cis-regulatory elements and quantify their positional importance in mediating yeast poly(A) site formation, cleavage heterogeneity, and strength. In S. cerevisiae, cleavage heterogeneity is promoted by the depletion of U-rich elements around poly(A) sites as well as multiple occurrences of upstream UA-rich elements. Sites with high cleavage heterogeneity show overall lower strength. The site strength and tandem site distances modulate alternative polyadenylation (APA) under the diauxic stress. Finally, we develop a deep learning model to reveal the distinct motif configuration of S. pombe poly(A) sites, which show more precise cleavage than S. cerevisiae Altogether, our deep learning models provide unprecedented insights into poly(A) site formation of yeast species, and our results highlight divergent poly(A) signals across distantly related species.

PMID:38914436 | DOI:10.1101/gr.278606.123