Bioinformatics. 2024 Aug 22:btae520. doi: 10.1093/bioinformatics/btae520. Online ahead of print.

ABSTRACT

MOTIVATION: Single-cell RNA sequencing (scRNA-seq) enables comprehensive characterization of the cell state. However, its destructive nature prohibits measuring gene expression changes during dynamic processes such as embryogenesis. Although recent studies integrating scRNA-seq with lineage tracing have provided clonal insights between progenitor and mature cells, challenges remain. Because of their experimental nature, observations are sparse, and cells observed in the early state are not the exact progenitors of cells observed at later time points. To overcome these limitations, we developed LineageVAE, a novel computational methodology that utilizes deep learning based on the property that cells sharing barcodes have identical progenitors.

RESULTS: LineageVAE is a deep generative model that transforms scRNA-seq observations with identical lineage barcodes into sequential trajectories toward a common progenitor in a latent cell state space. This method enables the reconstruction of unobservable cell state transitions, historical transcriptomes, and regulatory dynamics at a single-cell resolution. Applied to hematopoiesis and reprogrammed fibroblast datasets, LineageVAE demonstrated its ability to restore backward cell state transitions and infer progenitor heterogeneity and transcription factor activity along differentiation trajectories.

AVAILABILITY AND IMPLEMENTATION: The LineageVAE model was implemented in Python using the PyTorch deep learning library. The code is available on GitHub at https://github.com/LzrRacer/LineageVAE/.

SUPPLEMENTARY INFORMATION: Available at Bioinformatics online.

PMID:39172488 | DOI:10.1093/bioinformatics/btae520

Brief Bioinform. 2024 Jul 25;25(5):bbae408. doi: 10.1093/bib/bbae408.

ABSTRACT

During the drug discovery and design process, the acid-base dissociation constant (pKa) of a molecule is critically emphasized due to its crucial role in influencing the ADMET (absorption, distribution, metabolism, excretion, and toxicity) properties and biological activity. However, the experimental determination of pKa values is often laborious and complex. Moreover, existing prediction methods exhibit limitations in both the quantity and quality of the training data, as well as in their capacity to handle the complex structural and physicochemical properties of compounds, consequently impeding accuracy and generalization. Therefore, developing a method that can quickly and accurately predict molecular pKa values will to some extent help the structural modification of molecules, and thus assist the development process of new drugs. In this study, we developed a cutting-edge pKa prediction model named GR-pKa (Graph Retention pKa), leveraging a message-passing neural network and employing a multi-fidelity learning strategy to accurately predict molecular pKa values. The GR-pKa model incorporates five quantum mechanical properties related to molecular thermodynamics and dynamics as key features to characterize molecules. Notably, we originally introduced the novel retention mechanism into the message-passing phase, which significantly improves the model's ability to capture and update molecular information. Our GR-pKa model outperforms several state-of-the-art models in predicting macro-pKa values, achieving impressive results with a low mean absolute error of 0.490 and root mean square error of 0.588, and a high R2 of 0.937 on the SAMPL7 dataset.

PMID:39171986 | DOI:10.1093/bib/bbae408

Brief Bioinform. 2024 Jul 25;25(5):bbae405. doi: 10.1093/bib/bbae405.

ABSTRACT

An overwhelming majority of protein-protein interaction (PPI) studies are conducted in a select few model organisms largely due to constraints in time and cost of the associated 'wet lab' experiments. In silico PPI inference methods are ideal tools to overcome these limitations, but often struggle with cross-species predictions. We present INTREPPPID, a method that incorporates orthology data using a new 'quintuplet' neural network, which is constructed with five parallel encoders with shared parameters. INTREPPPID incorporates both a PPI classification task and an orthologous locality task. The latter learns embeddings of orthologues that have small Euclidean distances between them and large distances between embeddings of all other proteins. INTREPPPID outperforms all other leading PPI inference methods tested on both the intraspecies and cross-species tasks using strict evaluation datasets. We show that INTREPPPID's orthologous locality loss increases performance because of the biological relevance of the orthologue data and not due to some other specious aspect of the architecture. Finally, we introduce PPI.bio and PPI Origami, a web server interface for INTREPPPID and a software tool for creating strict evaluation datasets, respectively. Together, these two initiatives aim to make both the use and development of PPI inference tools more accessible to the community.

PMID:39171984 | DOI:10.1093/bib/bbae405

Cancer Med. 2024 Aug;13(16):e70046. doi: 10.1002/cam4.70046.

ABSTRACT

BACKGROUND: To explore the efficacy of a prediction model based on diffusion-weighted imaging (DWI) features extracted from deep learning (DL) and radiomics combined with clinical parameters and apparent diffusion coefficient (ADC) values to identify microsatellite instability (MSI) in endometrial cancer (EC).

METHODS: This study included a cohort of 116 patients with EC, who were subsequently divided into training (n = 81) and test (n = 35) sets. From DWI, conventional radiomics features and convolutional neural network-based DL features were extracted. Random forest (RF) and logistic regression were adopted as classifiers. DL features, radiomics features, clinical variables, ADC values, and their combinations were applied to establish DL, radiomics, clinical, ADC, and combined models, respectively. The predictive performance was evaluated through the area under the receiver operating characteristic curve (AUC), total integrated discrimination index (IDI), net reclassification index (NRI), calibration curves, and decision curve analysis (DCA).

RESULTS: The optimal predictive model, based on an RF classifier, comprised four DL features, three radiomics features, two clinical variables, and an ADC value. In the training and test sets, this model exhibited AUC values of 0.989 (95% CI: 0.935-1.000) and 0.885 (95% CI: 0.731-0.967), respectively, demonstrating different degrees of improvement compared with the clinical, DL, radiomics, and ADC models (AUC-training = 0.671, 0.873, 0.833, and 0.814, AUC-test = 0.685, 0.783, 0.708, and 0.713, respectively). The NRI and IDI analyses revealed that the combined model resulted in improved risk reclassification of the MSI status compared to the clinical, radiomics, DL, and ADC models. The calibration curves and DCA indicated good consistency and clinical utility of this model, respectively.

CONCLUSIONS: The predictive model based on DWI features extracted from DL and radiomics combined with clinical parameters and ADC values could effectively assess the MSI status in EC.

PMID:39171859 | DOI:10.1002/cam4.70046

Nanoscale. 2024 Aug 22. doi: 10.1039/d4nr03081h. Online ahead of print.

ABSTRACT

In nanophotonics, nanohole arrays (NHAs) are periodic arrangements of nanoscale apertures in thin films that provide diverse optical functionalities essential for various applications. Fully studying NHAs' optical properties and optimizing performance demands understanding both materials and geometric parameters, which presents a computational challenge due to numerous potential combinations. Efficient computational modeling is critical for overcoming this challenge and optimizing NHA-based device performance. Traditional approaches rely on time-consuming numerical simulation processes for device design and optimization. However, using a deep learning approach offers an efficient solution for NHAs design. In this work, a deep neural network within the forward modeling framework accurately predicts the optical properties of NHAs by using device structure data such as periodicity and hole radius as model inputs. We also compare three deep learning-based inverse modeling approaches-fully connected neural network, convolutional neural network, and tandem neural network-to provide approximate solutions for NHA structures based on their optical responses. Once trained, the DNN accurately predicts the desired result in milliseconds, enabling repeated use without wasting computational resources. The models are trained using over 6000 samples from a dataset obtained by finite-difference time-domain (FDTD) simulations. The forward model accurately predicts transmission spectra, while the inverse model reliably infers material attributes, lattice geometries, and structural parameters from the spectra. The forward model accurately predicts transmission spectra, with an average Mean Squared Error (MSE) of 2.44 × 10-4. In most cases, the inverse design demonstrates high accuracy with deviations of less than 1.5 nm for critical geometrical parameters. For experimental verification, gold nanohole arrays are fabricated using deep UV lithography. Validation against experimental data demonstrates the models' robustness and precision. These findings show that the trained DNN models offer accurate predictions about the optical behavior of NHAs.

PMID:39171500 | DOI:10.1039/d4nr03081h

Comput Struct Biotechnol J. 2024 Jul 18;23:3020-3029. doi: 10.1016/j.csbj.2024.07.014. eCollection 2024 Dec.

ABSTRACT

Colorectal cancer (CRC) is the third most diagnosed cancer and the second deadliest cancer worldwide representing a major public health problem. In recent years, increasing evidence has shown that microRNA (miRNA) can control the expression of targeted human messenger RNA (mRNA) by reducing their abundance or translation, acting as oncogenes or tumor suppressors in various cancers, including CRC. Due to the significant up-regulation of oncogenic miRNAs in CRC, elucidating the underlying mechanism and identifying dysregulated miRNA targets may provide a basis for improving current therapeutic interventions. In this paper, we proposed Gra-CRC-miRTar, a pre-trained nucleotide-to-graph neural network framework, for identifying potential miRNA targets in CRC. Different from previous studies, we constructed two pre-trained models to encode RNA sequences and transformed them into de Bruijn graphs. We employed different graph neural networks to learn the latent representations. The embeddings generated from de Bruijn graphs were then fed into a Multilayer Perceptron (MLP) to perform the prediction tasks. Our extensive experiments show that Gra-CRC-miRTar achieves better performance than other deep learning algorithms and existing predictors. In addition, our analyses also successfully revealed 172 out of 201 functional interactions through experimentally validated miRNA-mRNA pairs in CRC. Collectively, our effort provides an accurate and efficient framework to identify potential miRNA targets in CRC, which can also be used to reveal miRNA target interactions in other malignancies, facilitating the development of novel therapeutics. The Gra-CRC-miRTar web server can be found at: http://gra-crc-mirtar.com/.

PMID:39171252 | PMC:PMC11338065 | DOI:10.1016/j.csbj.2024.07.014

Radiol Adv. 2024 Jul 4;1(2):umae018. doi: 10.1093/radadv/umae018. eCollection 2024 Jul.

ABSTRACT

BACKGROUND: The classic metaphyseal lesion (CML) is a distinctive fracture highly specific to infant abuse. To increase the size and diversity of the training CML database for automated deep-learning detection of this fracture, we developed a mask conditional diffusion model (MaC-DM) to generate synthetic images with and without CMLs.

PURPOSE: To objectively and subjectively assess the synthetic radiographic images with and without CMLs generated by MaC-DM.

MATERIALS AND METHODS: For retrospective testing, we randomly chose 100 real images (50 normals and 50 with CMLs; 39 infants, male = 22, female = 17; mean age = 4.1 months; SD = 3.1 months) from an existing distal tibia dataset (177 normal, 73 with CMLs), and generated 100 synthetic distal tibia images via MaC-DM (50 normals and 50 with CMLs). These test images were shown to 3 blinded radiologists. In the first session, radiologists determined if the images were normal or had CMLs. In the second session, they determined if the images were real or synthetic. We analyzed the radiologists' interpretations and employed t-distributed stochastic neighbor embedding technique to analyze the data distribution of the test images.

RESULTS: When presented with the 200 images (100 synthetic, 100 with CMLs), radiologists reliably and accurately diagnosed CMLs (kappa = 0.90, 95% CI = [0.88-0.92]; accuracy = 92%, 95% CI = [89-97]). However, they were inaccurate in differentiating between real and synthetic images (kappa = 0.05, 95% CI = [0.03-0.07]; accuracy = 53%, 95% CI = [49-59]). The t-distributed stochastic neighbor embedding analysis showed substantial differences in the data distribution between normal images and those with CMLs (area under the curve = 0.996, 95% CI = [0.992-1.000], P < .01), but minor differences between real and synthetic images (area under the curve = 0.566, 95% CI = [0.486-0.647], P = .11).

CONCLUSION: Radiologists accurately diagnosed images with distal tibial CMLs but were unable to distinguish real from synthetically generated ones, indicating that our generative model could synthesize realistic images. Thus, MaC-DM holds promise as an effective strategy for data augmentation in training machine-learning models for diagnosis of distal tibial CMLs.

PMID:39171131 | PMC:PMC11335364 | DOI:10.1093/radadv/umae018

Chin Med J Pulm Crit Care Med. 2023 Sep 9;1(3):148-160. doi: 10.1016/j.pccm.2023.05.001. eCollection 2023 Sep.

ABSTRACT

Lung cancer has the highest mortality rate among all cancers in the world. Hence, early diagnosis and personalized treatment plans are crucial to improving its 5-year survival rate. Chest computed tomography (CT) serves as an essential tool for lung cancer screening, and pathology images are the gold standard for lung cancer diagnosis. However, medical image evaluation relies on manual labor and suffers from missed diagnosis or misdiagnosis, and physician heterogeneity. The rapid development of artificial intelligence (AI) has brought a whole novel opportunity for medical task processing, demonstrating the potential for clinical application in lung cancer diagnosis and treatment. AI technologies, including machine learning and deep learning, have been deployed extensively for lung nodule detection, benign and malignant classification, and subtype identification based on CT images. Furthermore, AI plays a role in the non-invasive prediction of genetic mutations and molecular status to provide the optimal treatment regimen, and applies to the assessment of therapeutic efficacy and prognosis of lung cancer patients, enabling precision medicine to become a reality. Meanwhile, histology-based AI models assist pathologists in typing, molecular characterization, and prognosis prediction to enhance the efficiency of diagnosis and treatment. However, the leap to extensive clinical application still faces various challenges, such as data sharing, standardized label acquisition, clinical application regulation, and multimodal integration. Nevertheless, AI holds promising potential in the field of lung cancer to improve cancer care.

PMID:39171128 | PMC:PMC11332840 | DOI:10.1016/j.pccm.2023.05.001

Cureus. 2024 Jul 22;16(7):e65122. doi: 10.7759/cureus.65122. eCollection 2024 Jul.

ABSTRACT

Early detection of suspicious pigmented skin lesions is crucial for improving the outcomes and survival rates of skin cancers. However, the accuracy of clinical diagnosis by primary care physicians (PCPs) is suboptimal, leading to unnecessary referrals and biopsies. In recent years, deep learning (DL) algorithms have shown promising results in the automated detection and classification of skin lesions. This systematic review and meta-analysis aimed to evaluate the diagnostic performance of DL algorithms for the detection of suspicious pigmented skin lesions in primary care settings. A comprehensive literature search was conducted using electronic databases, including PubMed, Scopus, IEEE Xplore, Cochrane Central Register of Controlled Trials (CENTRAL), and Web of Science. Data from eligible studies were extracted, including study characteristics, sample size, algorithm type, sensitivity, specificity, diagnostic odds ratio (DOR), positive likelihood ratio (PLR), negative likelihood ratio (NLR), and receiver operating characteristic curve analysis. Three studies were included. The results showed that DL algorithms had a high sensitivity (90%, 95% CI: 90-91%) and specificity (85%, 95% CI: 84-86%) for detecting suspicious pigmented skin lesions in primary care settings. Significant heterogeneity was observed in both sensitivity (p = 0.0062, I2 = 80.3%) and specificity (p < 0.001, I2 = 98.8%). The analysis of DOR and PLR further demonstrated the strong diagnostic performance of DL algorithms. The DOR was 26.39, indicating a strong overall diagnostic performance of DL algorithms. The PLR was 4.30, highlighting the ability of these algorithms to influence diagnostic outcomes positively. The NLR was 0.16, indicating that a negative test result decreased the odds of misdiagnosis. The area under the curve of DL algorithms was 0.95, indicating excellent discriminative ability in distinguishing between benign and malignant pigmented skin lesions. DL algorithms have the potential to significantly improve the detection of suspicious pigmented skin lesions in primary care settings. Our analysis showed that DL exhibited promising performance in the early detection of suspicious pigmented skin lesions. However, further studies are needed.

PMID:39171046 | PMC:PMC11338545 | DOI:10.7759/cureus.65122

Cureus. 2024 Jul 22;16(7):e65134. doi: 10.7759/cureus.65134. eCollection 2024 Jul.

ABSTRACT

Polycystic ovary syndrome (PCOS) is a common endocrine disorder that disrupts reproductive function and hormonal balance. It primarily affects reproductive-aged women and leads to physical, metabolic, and emotional challenges affecting the quality of life. In this study, we develop a machine learning-based model to accurately identify PCOS pelvic ultrasound images from normal pelvic ultrasound images. By leveraging 1,932 pelvic ultrasound images from the Kaggle online platform (Google LLC, Mountain View, CA), we were able to create a model that accurately detected multiple small follicles in the ovaries and an increase in ovarian volume for PCOS pelvic ultrasound images from normal pelvic ultrasound images. Our developed model demonstrated a promising performance, achieving a precision value of 82.6% and a recall value of 100%, including a sensitivity and specificity of 100% each. The value of the overall accuracy proved to be 100% and the F1 score was calculated to be 0.905. As the results garnered from our study are promising, further validation studies are necessary to generalize the model's capabilities and incorporate other diagnostic factors of PCOS such as physical exams and lab values.

PMID:39171041 | PMC:PMC11338641 | DOI:10.7759/cureus.65134

EClinicalMedicine. 2024 Jul 26;75:102772. doi: 10.1016/j.eclinm.2024.102772. eCollection 2024 Sep.

ABSTRACT

BACKGROUND: Acute respiratory distress syndrome (ARDS) is a life-threatening condition with a high incidence and mortality rate in intensive care unit (ICU) admissions. Early identification of patients at high risk for developing ARDS is crucial for timely intervention and improved clinical outcomes. However, the complex pathophysiology of ARDS makes early prediction challenging. This study aimed to develop an artificial intelligence (AI) model for automated lung lesion segmentation and early prediction of ARDS to facilitate timely intervention in the intensive care unit.

METHODS: A total of 928 ICU patients with chest computed tomography (CT) scans were included from November 2018 to November 2021 at three centers in China. Patients were divided into a retrospective cohort for model development and internal validation, and three independent cohorts for external validation. A deep learning-based framework using the UNet Transformer (UNETR) model was developed to perform the segmentation of lung lesions and early prediction of ARDS. We employed various data augmentation techniques using the Medical Open Network for AI (MONAI) framework, enhancing the training sample diversity and improving the model's generalization capabilities. The performance of the deep learning-based framework was compared with a Densenet-based image classification network and evaluated in external and prospective validation cohorts. The segmentation performance was assessed using the Dice coefficient (DC), and the prediction performance was assessed using area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. The contributions of different features to ARDS prediction were visualized using Shapley Explanation Plots. This study was registered with the China Clinical Trial Registration Centre (ChiCTR2200058700).

FINDINGS: The segmentation task using the deep learning framework achieved a DC of 0.734 ± 0.137 in the validation set. For the prediction task, the deep learning-based framework achieved AUCs of 0.916 [0.858-0.961], 0.865 [0.774-0.945], 0.901 [0.835-0.955], and 0.876 [0.804-0.936] in the internal validation cohort, external validation cohort I, external validation cohort II, and prospective validation cohort, respectively. It outperformed the Densenet-based image classification network in terms of prediction accuracy. Moreover, the ARDS prediction model identified lung lesion features and clinical parameters such as C-reactive protein, albumin, bilirubin, platelet count, and age as significant contributors to ARDS prediction.

INTERPRETATION: The deep learning-based framework using the UNETR model demonstrated high accuracy and robustness in lung lesion segmentation and early ARDS prediction, and had good generalization ability and clinical applicability.

FUNDING: This study was supported by grants from the Shanghai Renji Hospital Clinical Research Innovation and Cultivation Fund (RJPY-DZX-008) and Shanghai Science and Technology Development Funds (22YF1423300).

PMID:39170939 | PMC:PMC11338113 | DOI:10.1016/j.eclinm.2024.102772

J Biomed Opt. 2024 Jun;29(Suppl 3):S33309. doi: 10.1117/1.JBO.29.S3.S33309. Epub 2024 Aug 21.

ABSTRACT

SIGNIFICANCE: Monitoring oxygen saturation ( SpO 2 ) is important in healthcare, especially for diagnosing and managing pulmonary diseases. Non-contact approaches broaden the potential applications of SpO 2 measurement by better hygiene, comfort, and capability for long-term monitoring. However, existing studies often encounter challenges such as lower signal-to-noise ratios and stringent environmental conditions.

AIM: We aim to develop and validate a contactless SpO 2 measurement approach using 3D convolutional neural networks (3D CNN) and 3D visible-near-infrared (VIS-NIR) multimodal imaging, to offer a convenient, accurate, and robust alternative for SpO 2 monitoring.

APPROACH: We propose an approach that utilizes a 3D VIS-NIR multimodal camera system to capture facial videos, in which SpO 2 is estimated through 3D CNN by simultaneously extracting spatial and temporal features. Our approach includes registration of multimodal images, tracking of the 3D region of interest, spatial and temporal preprocessing, and 3D CNN-based feature extraction and SpO 2 regression.

RESULTS: In a breath-holding experiment involving 23 healthy participants, we obtained multimodal video data with reference SpO 2 values ranging from 80% to 99% measured by pulse oximeter on the fingertip. The approach achieved a mean absolute error (MAE) of 2.31% and a Pearson correlation coefficient of 0.64 in the experiment, demonstrating good agreement with traditional pulse oximetry. The discrepancy of estimated SpO 2 values was within 3% of the reference SpO 2 for ∼ 80 % of all 1-s time points. Besides, in clinical trials involving patients with sleep apnea syndrome, our approach demonstrated robust performance, with an MAE of less than 2% in SpO 2 estimations compared to gold-standard polysomnography.

CONCLUSIONS: The proposed approach offers a promising alternative for non-contact oxygen saturation measurement with good sensitivity to desaturation, showing potential for applications in clinical settings.

PMID:39170819 | PMC:PMC11338290 | DOI:10.1117/1.JBO.29.S3.S33309

Front Neurosci. 2024 Aug 7;18:1449527. doi: 10.3389/fnins.2024.1449527. eCollection 2024.

ABSTRACT

Facial expression recognition (FER) plays a crucial role in affective computing, enhancing human-computer interaction by enabling machines to understand and respond to human emotions. Despite advancements in deep learning, current FER systems often struggle with challenges such as occlusions, head pose variations, and motion blur in natural environments. These challenges highlight the need for more robust FER solutions. To address these issues, we propose the Attention-Enhanced Multi-Layer Transformer (AEMT) model, which integrates a dual-branch Convolutional Neural Network (CNN), an Attentional Selective Fusion (ASF) module, and a Multi-Layer Transformer Encoder (MTE) with transfer learning. The dual-branch CNN captures detailed texture and color information by processing RGB and Local Binary Pattern (LBP) features separately. The ASF module selectively enhances relevant features by applying global and local attention mechanisms to the extracted features. The MTE captures long-range dependencies and models the complex relationships between features, collectively improving feature representation and classification accuracy. Our model was evaluated on the RAF-DB and AffectNet datasets. Experimental results demonstrate that the AEMT model achieved an accuracy of 81.45% on RAF-DB and 71.23% on AffectNet, significantly outperforming existing state-of-the-art methods. These results indicate that our model effectively addresses the challenges of FER in natural environments, providing a more robust and accurate solution. The AEMT model significantly advances the field of FER by improving the robustness and accuracy of emotion recognition in complex real-world scenarios. This work not only enhances the capabilities of affective computing systems but also opens new avenues for future research in improving model efficiency and expanding multimodal data integration.

PMID:39170679 | PMC:PMC11335721 | DOI:10.3389/fnins.2024.1449527

Heliyon. 2024 Jul 29;10(15):e35242. doi: 10.1016/j.heliyon.2024.e35242. eCollection 2024 Aug 15.

ABSTRACT

Intelligent robotic systems for patients with motor impairments have gained significant interest over the past few years. Various sensor types and human-machine interface (HMI) methods have been developed; however, most research in this area has focused on eye-blink-based binary control with minimal electrode placements. This approach restricts the complexity of HMI systems and does not consider the potential of multiple-activity decoding via static ocular activities. These activities pose a decoding challenge due to non-oscillatory noise components, such as muscle tremors or fatigue. To address this issue, a hybrid preprocessing methodology is proposed that combines harmonic source separation and ensemble empirical mode decomposition in the time-frequency domain to remove percussive and non-oscillatory components of static ocular movements. High-frequency components are included in the harmonic enhancement process. Next, a machine learning model with dual input of time-frequency images and a vectorized feature set of consecutive time windows is employed, leading to a 3.8% increase in performance as compared to without harmonic enhancement in leave-one-session-out cross-validation (LOSO). Additionally, a high correlation is found between the harmonic ratios of the static activities in the Hilbert-Huang frequency spectrum and LOSO performances. This finding highlights the potential of leveraging the harmonic characteristics of the activities as a discriminating factor in machine learning-based classification of EOG-based ocular activities, thus providing a new aspect of activity enrichment with minimal performance loss for future HMI systems.

PMID:39170510 | PMC:PMC11336459 | DOI:10.1016/j.heliyon.2024.e35242

Nat Comput Sci. 2024 Aug 21. doi: 10.1038/s43588-024-00679-4. Online ahead of print.

ABSTRACT

Large-scale drug discovery and repurposing is challenging. Identifying the mechanism of action (MOA) is crucial, yet current approaches are costly and low-throughput. Here we present an approach for MOA identification by profiling changes in mitochondrial phenotypes. By temporally imaging mitochondrial morphology and membrane potential, we established a pipeline for monitoring time-resolved mitochondrial images, resulting in a dataset comprising 570,096 single-cell images of cells exposed to 1,068 United States Food and Drug Administration-approved drugs. A deep learning model named MitoReID, using a re-identification (ReID) framework and an Inflated 3D ResNet backbone, was developed. It achieved 76.32% Rank-1 and 65.92% mean average precision on the testing set and successfully identified the MOAs for six untrained drugs on the basis of mitochondrial phenotype. Furthermore, MitoReID identified cyclooxygenase-2 inhibition as the MOA of the natural compound epicatechin in tea, which was successfully validated in vitro. Our approach thus provides an automated and cost-effective alternative for target identification that could accelerate large-scale drug discovery and repurposing.

PMID:39169261 | DOI:10.1038/s43588-024-00679-4

Commun Med (Lond). 2024 Aug 21;4(1):167. doi: 10.1038/s43856-024-00590-z.

ABSTRACT

BACKGROUND: Predicting diabetic retinopathy (DR) progression could enable individualised screening with prompt referral for high-risk individuals for sight-saving treatment, whilst reducing screening burden for low-risk individuals. We developed and validated deep learning systems (DLS) that predict 1, 2 and 3 year emergent referable DR and maculopathy using risk factor characteristics (tabular DLS), colour fundal photographs (image DLS) or both (multimodal DLS).

METHODS: From 162,339 development-set eyes from south-east London (UK) diabetic eye screening programme (DESP), 110,837 had eligible longitudinal data, with the remaining 51,502 used for pretraining. Internal and external (Birmingham DESP, UK) test datasets included 27,996, and 6928 eyes respectively.

RESULTS: Internal multimodal DLS emergent referable DR, maculopathy or either area-under-the receiver operating characteristic (AUROC) were 0.95 (95% CI: 0.92-0.98), 0.84 (0.82-0.86), 0.85 (0.83-0.87) for 1 year, 0.92 (0.87-0.96), 0.84 (0.82-0.87), 0.85 (0.82-0.87) for 2 years, and 0.85 (0.80-0.90), 0.79 (0.76-0.82), 0.79 (0.76-0.82) for 3 years. External multimodal DLS emergent referable DR, maculopathy or either AUROC were 0.93 (0.88-0.97), 0.85 (0.80-0.89), 0.85 (0.76-0.85) for 1 year, 0.93 (0.89-0.97), 0.79 (0.74-0.84), 0.80 (0.76-0.85) for 2 years, and 0.91 (0.84-0.98), 0.79 (0.74-0.83), 0.79 (0.74-0.84) for 3 years.

CONCLUSIONS: Multimodal and image DLS performance is significantly better than tabular DLS at all intervals. DLS accurately predict 1, 2 and 3 year emergent referable DR and referable maculopathy using colour fundal photographs, with additional risk factor characteristics conferring improvements in prognostic performance. Proposed DLS are a step towards individualised risk-based screening, whereby AI-assistance allows high-risk individuals to be closely monitored while reducing screening burden for low-risk individuals.

PMID:39169209 | DOI:10.1038/s43856-024-00590-z

Sci Rep. 2024 Aug 21;14(1):19361. doi: 10.1038/s41598-024-70367-w.

ABSTRACT

Transcranial magnetic stimulation (TMS) has emerged as a promising neuromodulation technique with both therapeutic and diagnostic applications. As accurate coil placement is known to be essential for focal stimulation, computational models have been established to help find the optimal coil positioning by maximizing electric fields at the cortical target. While these numerical simulations provide realistic and subject-specific field distributions, they are computationally demanding, precluding their use in real-time applications. In this paper, we developed a novel multi-task deep neural network which simultaneously predicts the optimal coil placement for a given cortical target as well as the associated TMS-induced electric field. Trained on large amounts of preceding numerical optimizations, the Attention U-Net-based neural surrogate provided accurate coil optimizations in only 35 ms, a fraction of time compared to the state-of-the-art numerical framework. The mean errors on the position estimates were below 2 mm, i.e., smaller than previously reported manual coil positioning errors. The predicted electric fields were also highly correlated (r> 0.97) with their numerical references. In addition to healthy subjects, we validated our approach also in glioblastoma patients. We first statistically underlined the importance of using realistic heterogeneous tumor conductivities instead of simply adopting values from the surrounding healthy tissue. Second, applying the trained neural surrogate to tumor patients yielded similar accurate positioning and electric field estimates as in healthy subjects. Our findings provide a promising framework for future real-time electric field-optimized TMS applications.

PMID:39169126 | DOI:10.1038/s41598-024-70367-w

Sci Rep. 2024 Aug 21;14(1):19377. doi: 10.1038/s41598-024-69483-4.

ABSTRACT

The reliable operation of power systems while integrating renewable energy systems depends on Optimal Power Flow (OPF). Power systems meet the operational demands by efficiently managing the OPF. Identifying the optimal solution for the OPF problem is essential to ensure voltage stability, and minimize power loss and fuel cost when the power system is integrated with renewable energy resources. The traditional procedure to find the optimal solution utilizes nature-inspired metaheuristic optimization algorithms which exhibit performance drop in terms of high convergence rate and local optimal solution while handling uncertainties and nonlinearities in Hybrid Renewable Energy Systems (HRES). Thus, a novel hybrid model is presented in this research work using Deep Reinforcement Learning (DRL) with Quantum Inspired Genetic Algorithm (DRL-QIGA). The DRL in the proposed model effectively combines the proximal policy network to optimize power generation in real-time. The ability to learn and adapt to the changes in a real-time environment makes DRL to be suitable for the proposed model. Meanwhile, the QIGA enhances the global search process through the quantum computing principle, and this improves the exploitation and exploration features while searching for optimal solutions for the OPF problem. The proposed model experimental evaluation utilizes a modified IEEE 30-bus system to validate the performance. Comparative analysis demonstrates the proposed model's better performance in terms of reduced fuel cost of $620.45, minimized power loss of 1.85 MW, and voltage deviation of 0.065 compared with traditional optimization algorithms.

PMID:39169061 | DOI:10.1038/s41598-024-69483-4

Pathology. 2024 Aug 3:S0031-3025(24)00185-5. doi: 10.1016/j.pathol.2024.05.012. Online ahead of print.

ABSTRACT

There is an urgent clinical demand to explore novel diagnostic and prognostic biomarkers for renal cell carcinoma (RCC). We proposed deep learning-based artificial intelligence strategies. The study included 1752 whole slide images from multiple centres. Based on the pixel-level of RCC segmentation, the diagnosis diagnostic model achieved an area under the receiver operating characteristic curve (AUC) of 0.977 (95% CI 0.969-0.984) in the external validation cohort. In addition, our diagnostic model exhibited excellent performance in the differential diagnosis of RCC from renal oncocytoma, which achieved an AUC of 0.951 (0.922-0.972). The graderisk for the recognition of high-grade tumour achieved AUCs of 0.840 (0.805-0.871) in the Cancer Genome Atlas (TCGA) cohort, 0.857 (0.813-0.894) in the Shanghai General Hospital (General) cohort, and 0.894 (0.842-0.933) in the Clinical Proteomic Tumor Analysis Consortium (CPTAC) cohort, for the recognition of high-grade tumour. The OSrisk for predicting 5-year survival status achieved an AUC of 0.784 (0.746-0.819) in the TCGA cohort, which was further verified in the independent general cohort and the CPTAC cohort, with AUCs of 0.774 (0.723-0.820) and 0.702 (0.632-0.765), respectively. Moreover, the competing-risk nomogram (CRN) showed its potential to be a prognostic indicator, with a hazard ratio (HR) of 5.664 (3.893-8.239, p<0.0001), outperforming other traditional clinical prognostic indicators. Kaplan-Meier survival analysis further illustrated that our CRN could significantly distinguish patients with high survival risk. Deep learning-based artificial intelligence could be a useful tool for clinicians to diagnose and predict the prognosis of RCC patients, thus improving the process of individualised treatment.

PMID:39168777 | DOI:10.1016/j.pathol.2024.05.012

Nihon Hoshasen Gijutsu Gakkai Zasshi. 2024;80(8):861-866. doi: 10.6009/jjrt.2024-2398.

NO ABSTRACT

PMID:39168595 | DOI:10.6009/jjrt.2024-2398