Chaos. 2025 Jan 1;35(1):013125. doi: 10.1063/5.0233275.

ABSTRACT

Stock trend prediction is a significant challenge due to the inherent uncertainty and complexity of stock market time series. In this study, we introduce an innovative dual-branch network model designed to effectively address this challenge. The first branch constructs recurrence plots (RPs) to capture the nonlinear relationships between time points from historical closing price sequences and computes the corresponding recurrence quantifification analysis measures. The second branch integrates transposed transformers to identify subtle interconnections within the multivariate time series derived from stocks. Features extracted from both branches are concatenated and fed into a fully connected layer for binary classification, determining whether the stock price will rise or fall the next day. Our experimental results based on historical data from seven randomly selected stocks demonstrate that our proposed dual-branch model achieves superior accuracy (ACC) and F1-score compared to traditional machine learning and deep learning approaches. These findings underscore the efficacy of combining RPs with deep learning models to enhance stock trend prediction, offering considerable potential for refining decision-making in financial markets and investment strategies.

PMID:39792696 | DOI:10.1063/5.0233275

Adv Sci (Weinh). 2025 Jan 10:e2408451. doi: 10.1002/advs.202408451. Online ahead of print.

ABSTRACT

Human epidermal growth factor receptor 2 (HER2) positive gastric cancer (GC) shows a robust response to the combined therapy based HER2-targeted therapy. The application of these therapies is highly dependent on the evaluation of tumor HER2 status. However, there are many risks and challenges in HER2 assessment in GC. Therefore, an economically viable and readily available instrument is requisite for distinguishing HER2 status among patients diagnosed with GC. The study has innovatively developed a deep learning model, HER2Net, which can predict the HER2 status by quantitatively calculating the proportion of HER2 high-expression regions. The HER2Net is trained on an internal training set derived from 531 hematoxylin & eosin (H&E) whole slide images (WSI) of 520 patients. Subsequently, the performance of HER2Net is validated on an internal test set from 115 H&E WSI of 111 patients and an external multi-center test set from 102 H&E WSI of 101 patients. The HER2Net achieves an accuracy of 0.9043 on the internal test set, and an accuracy of 0.8922 on an external test set from multiple institutes. This discovery indicates that the HER2Net can potentially offer a novel methodology for the identification of HER2-positive GC.

PMID:39792693 | DOI:10.1002/advs.202408451

J Magn Reson Imaging. 2025 Jan 10. doi: 10.1002/jmri.29686. Online ahead of print.

ABSTRACT

BACKGROUND: Deep learning-based segmentation of brain metastases relies on large amounts of fully annotated data by domain experts. Semi-supervised learning offers potential efficient methods to improve model performance without excessive annotation burden.

PURPOSE: This work tests the viability of semi-supervision for brain metastases segmentation.

STUDY TYPE: Retrospective.

SUBJECTS: There were 156, 65, 324, and 200 labeled scans from four institutions and 519 unlabeled scans from a single institution. All subjects included in the study had diagnosed with brain metastases.

FIELD STRENGTH/SEQUENCES: 1.5 T and 3 T, 2D and 3D T1-weighted pre- and post-contrast, and fluid-attenuated inversion recovery (FLAIR).

ASSESSMENT: Three semi-supervision methods (mean teacher, cross-pseudo supervision, and interpolation consistency training) were adapted with the U-Net architecture. The three semi-supervised methods were compared to their respective supervised baseline on the full and half-sized training.

STATISTICAL TESTS: Evaluation was performed on a multinational test set from four different institutions using 5-fold cross-validation. Method performance was evaluated by the following: the number of false-positive predictions, the number of true positive predictions, the 95th Hausdorff distance, and the Dice similarity coefficient (DSC). Significance was tested using a paired samples t test for a single fold, and across all folds within a given cohort.

RESULTS: Semi-supervision outperformed the supervised baseline for all sites with the best-performing semi-supervised method achieved an on average DSC improvement of 6.3% ± 1.6%, 8.2% ± 3.8%, 8.6% ± 2.6%, and 15.4% ± 1.4%, when trained on half the dataset and 3.6% ± 0.7%, 2.0% ± 1.5%, 1.8% ± 5.7%, and 4.7% ± 1.7%, compared to the supervised baseline on four test cohorts. In addition, in three of four datasets, the semi-supervised training produced equal or better results than the supervised models trained on twice the labeled data.

DATA CONCLUSION: Semi-supervised learning allows for improved segmentation performance over the supervised baseline, and the improvement was particularly notable for independent external test sets when trained on small amounts of labeled data.

PLAIN LANGUAGE SUMMARY: Artificial intelligence requires extensive datasets with large amounts of annotated data from medical experts which can be difficult to acquire due to the large workload. To compensate for this, it is possible to utilize large amounts of un-annotated clinical data in addition to annotated data. However, this method has not been widely tested for the most common intracranial brain tumor, brain metastases. This study shows that this approach allows for data efficient deep learning models across multiple institutions with different clinical protocols and scanners.

LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY: Stage 2.

PMID:39792624 | DOI:10.1002/jmri.29686

Proc Natl Acad Sci U S A. 2025 Jan 7;122(1):e2413191121. doi: 10.1073/pnas.2413191121. Epub 2024 Dec 30.

ABSTRACT

In species with genetic sex determination (GSD), the sex identity of the soma determines germ cell fate. For example, in mice, XY germ cells that enter an ovary differentiate as oogonia, whereas XX germ cells that enter a testis initiate differentiation as spermatogonia. However, numerous species lack a GSD system and instead display temperature-dependent sex determination (TSD). In the red-eared slider turtle, Trachemys scripta, a TSD model species with a warm female promoting temperature (FPT) and cool male promoting temperature (MPT) system, temperature directly affects germ cell number. In this study, we examined whether temperature directly affects other aspects of germ cell differentiation/sex identity. We uncoupled temperature and the sexual fate of the gonad by incubating eggs at MPT and treating with 17β-estradiol, a scheme that invariably produces ovaries. Through analysis of meiotic spreads, we showed that germ cells in FPT ovaries follow the typical pattern of initiating meiosis and progress through prophase I. However, in E2-induced ovaries that incubated at MPT, germ cells entered prophase I yet fail to exhibit synapsis. These results, combined with our single-cell transcriptome analysis, reveal a direct effect of temperature on germ cell sexual differentiation independent of its effect on the gonadal soma. These results imply that not all events of meiosis are under somatic control, at least not in this TSD species.

PMID:39793067 | DOI:10.1073/pnas.2413191121

Proc Natl Acad Sci U S A. 2025 Jan 7;122(1):e2417941121. doi: 10.1073/pnas.2417941121. Epub 2024 Dec 30.

ABSTRACT

Neurotransmitter release is triggered in microseconds by Ca2+-binding to the Synaptotagmin-1 C2-domains and by SNARE complexes that form four-helix bundles between synaptic vesicles and plasma membranes, but the coupling mechanism between Ca2+-sensing and membrane fusion is unknown. Release requires extension of SNARE helices into juxtamembrane linkers that precede transmembrane regions (linker zippering) and binding of the Synaptotagmin-1 C2B domain to SNARE complexes through a "primary interface" comprising two regions (I and II). The Synaptotagmin-1 Ca2+-binding loops were believed to accelerate membrane fusion by inducing membrane curvature, perturbing lipid bilayers, or helping bridge the membranes, but SNARE complex binding through the primary interface orients the Ca2+-binding loops away from the fusion site, hindering these putative activities. To clarify this paradox, we have used NMR and fluorescence spectroscopy. NMR experiments reveal that binding of C2B domain arginines to SNARE acidic residues at region II remains after disruption of region I, and that a mutation that impairs spontaneous and Ca2+-triggered neurotransmitter release enhances binding through region I. Moreover, fluorescence assays show that Ca2+ does not induce dissociation of Synaptotagmin-1 from membrane-anchored SNARE complex but causes reorientation of the C2B domain. Based on these results and electrophysiological data described by Toulme et al. (https://doi.org/10.1073/pnas.2409636121), we propose that upon Ca2+ binding the Synaptotagmin-1 C2B domain reorients on the membrane and dissociates from the SNAREs at region I but not region II, acting remotely as a lever that pulls the SNARE complex and facilitates linker zippering or other SNARE structural changes required for fast membrane fusion.

PMID:39793049 | DOI:10.1073/pnas.2417941121

Sci Immunol. 2025 Jan 10;10(103):eadq1697. doi: 10.1126/sciimmunol.adq1697. Epub 2025 Jan 10.

ABSTRACT

Human recombination-activating gene (RAG) deficiency can manifest with distinct clinical and immunological phenotypes. By applying a multiomics approach to a large group of RAG-mutated patients, we aimed at characterizing the immunopathology associated with each phenotype. Although defective T and B cell development is common to all phenotypes, patients with hypomorphic RAG variants can generate T and B cells with signatures of immune dysregulation and produce autoantibodies to a broad range of self-antigens, including type I interferons. T helper 2 (TH2) cell skewing and a prominent inflammatory signature characterize Omenn syndrome, whereas more hypomorphic forms of RAG deficiency are associated with a type 1 immune profile both in blood and tissues. We used cellular indexing of transcriptomes and epitopes by sequencing (CITE-seq) analysis to define the cell lineage-specific contribution to the immunopathology of the distinct RAG phenotypes. These insights may help improve the diagnosis and clinical management of the various forms of the disease.

PMID:39792639 | DOI:10.1126/sciimmunol.adq1697

Int J Environ Health Res. 2025 Jan 10:1-11. doi: 10.1080/09603123.2025.2451623. Online ahead of print.

ABSTRACT

This study utilized a validated questionnaire that aimed to assess pharmacists' awareness and attitude towards drug repurposing for antimicrobial use. Despite the reasonable awareness, pharmacists reported unfavourable attitudes. Pharmacists with a B.Pharm. or Pharm.D. degree reported less awareness than pharmacists with a master's or PhD degree. In contrast, pharmacists who dispensed fewer than 10 prescriptions or 10-29 prescriptions had significantly higher awareness than those who dispensed 30 prescriptions daily or more. Pharmacists who had 1-5 years of experience and those who dispensed less than 10 prescriptions daily had significantly lower attitude scores than their counterpats. The most reported facilitator was the reduced risk of antimicrobial resistance, while the most reported barrier was patient safety. Pharmacists' perception of drug repurposing for antimicrobial needs to improve via implementing educational sessions that highlight the impact of drug repurposing on supporting the fight against antimicrobial resistance and promoting a more sustainable and resilient healthcare system.

PMID:39792370 | DOI:10.1080/09603123.2025.2451623

Nicotine Tob Res. 2025 Jan 10:ntaf009. doi: 10.1093/ntr/ntaf009. Online ahead of print.

ABSTRACT

INTRODUCTION: Varenicline is an α4β2 nicotinic acetylcholine receptor partial agonist with the highest therapeutic efficacy of any pharmacological smoking cessation aid and a 12-month cessation rate of 26%. Genetic variation may be associated with varenicline response, but to date no genome-wide association studies of varenicline response have been published.

METHODS: In this study, we investigated the genetic contribution to varenicline effectiveness using two electronic health record-derived phenotypes. We defined short-term varenicline effectiveness (SVE) and long-term varenicline effectiveness (LVE) by assessing smoking status at 3 and 12 months, respectively, after initiating varenicline treatment. In Stage 1, comprising five European cohort studies, we tested genome-wide associations with SVE (1,405 cases, 2,074 controls) and LVE (1,576 cases, 2,555 controls), defining sentinel variants (the most strongly associated variant within 1 megabase) with p-value <5×10-6 to follow up in Stage 2. In Stage 2, we tested association between sentinel variants and comparable smoking cessation endpoints in varenicline randomised controlled trials. We subsequently meta-analysed Stages 1 and 2.

RESULTS: No variants reached genome-wide significance in the meta-analysis. In Stage 1, 10 sentinel variants were associated with SVE and five with LVE at a suggestive significance threshold (p-value <5×10-6); none of these sentinels were previously implicated in varenicline-aided smoking cessation or in genetic studies of smoking behaviour.

CONCLUSIONS: We provide initial insights into the biological underpinnings of varenicline-aided smoking cessation, through implicating genes involved in various processes, including gene expression, cilium assembly and early-stage development.

IMPLICATIONS: Leveraging electronic health records, we undertook the largest genetic study of varenicline-aided smoking cessation to date, and the only such study to test genome-wide associations. We showed distinct genetic variants associated (p-value <5×10-6) with varenicline-aided smoking cessation which implicate diverse cellular functions, including transcriptional regulation, RNA modification and cilium assembly. These provide insights which, if independently corroborated, will improve understanding of varenicline response. The growing availability of biobank resources with genetic and varenicline response data will provide future opportunities for larger studies using the approach we developed.

PMID:39792440 | DOI:10.1093/ntr/ntaf009

J Appl Genet. 2025 Jan 10. doi: 10.1007/s13353-024-00930-8. Online ahead of print.

ABSTRACT

Gilles de la Tourette syndrome (GTS) and other tic disorders (TDs) have a substantial genetic component with their heritability estimated at between 60 and 80%. Here we propose an oligogenic risk score of TDs using whole-genome sequencing (WGS) data from a group of Polish GTS patients, their families, and control samples (n = 278). In this study, we first reviewed the literature to obtain a preliminary list of 84 GTS/TD candidate genes. From this list, 10 final risk score genes were selected based on single-gene burden tests (SKAT p < 0.05) between unrelated GTS cases (n = 37) and synthetic control samples based on a database of local allele frequencies. These 10 genes were CHADL, DRD2, MAOA, PCDH10, HTR2A, SLITRK5, SORCS3, KCNQ5, CDH9, and CHD8. Variants in and in the vicinity (± 20 kbp) of the ten risk genes (n = 7654) with a median minor allele frequency in the non-Finnish European population of 0.02 were integrated into an additive classifier. This risk score was then applied to healthy and GTS-affected individuals from 23 families and 100 unrelated healthy samples from the Polish population (AUC-ROC = 0.62, p = 0.02). Application of the algorithm to a group of patients with other tic disorders revealed a continuous increase of the oligogenic score with healthy individuals with the lowest mean, then patients with other tic disorders, then GTS patients, and finally with severe GTS cases with the highest oligogenic score. We have further compared our WGS results with the summary statistics of the Psychiatric Genomics Consortium genome-wide association study (PGC GWAS) of TDs and found no signal overlap except for the CHADL gene locus. Polygenic risk scores from common variants of GTS GWAS show no difference between patient and control groups, except for the comparison between patients with non-GTS TDs and patients with severe GTS. Overall, we leveraged WGS data to construct a GTS/TD risk score based on variants that may cooperatively contribute to the aetiology of these disorders. This study provides evidence that typical and severe adult GTS as well as other tic disorders may exist on a single spectrum in terms of their genetic background.

PMID:39792217 | DOI:10.1007/s13353-024-00930-8

Expert Opin Drug Metab Toxicol. 2025 Jan 10. doi: 10.1080/17425255.2025.2451440. Online ahead of print.

ABSTRACT

INTRODUCTION: The prevalence of polypharmacy and the increasing availability of pharmacogenetic information in clinical practice have raised the prospect of data-driven clinical decision making when addressing the issues of drug-drug interactions and genetic polymorphisms in metabolizing enzymes. Inhibition of metabolizing enzymes in drug interactions can lead to genotype-phenotype discrepancies (phenoconversion) that reduce the relevance of individual pharmacogenetic information.

AREAS COVERED: The aim of this review is to provide an overview on existing models of phenoconversion and we discuss how phenoconversion models may be developed to estimate joint drug-interactions and genetic effects. Based on a literature search in PubMed, Google Scholar and reference lists from review articles, we provide an overview on the current models of phenoconversion. The currently applied phenoconversion models are presented, and discussed to predict effects of drug-drug interactions while accounting for the pharmacogenetic status of patients.

EXPERT OPINION: While pharmacogenetic dose recommendations alone are most relevant for rare and extreme genotypes, phenoconversion may increase the prevalence of these phenotypes. Therefore, in polypharmacy conditions, phenoconversion assessment is especially important for personalized drug therapy.

PMID:39791881 | DOI:10.1080/17425255.2025.2451440

Antimicrob Agents Chemother. 2025 Jan 10:e0104024. doi: 10.1128/aac.01040-24. Online ahead of print.

ABSTRACT

Tobramycin dosing in patients with cystic fibrosis (CF) is challenged by its high pharmacokinetic (PK) variability and narrow therapeutic window. Doses are typically individualized using two-sample log-linear regression (LLR) to quantify the area under the concentration-time curve (AUC). Bayesian model-informed precision dosing (MIPD) may allow dose individualization with fewer samples; however, the relative performance of these methods is unknown. This single-center retrospective analysis included adult patients with CF receiving tobramycin from 2015 to 2022. Tobramycin concentrations were predicted using LLR or Bayesian estimation with two population PK models (Hennig and Alghanem). Then, both methods were used to estimate the AUC for simulated patients. For Bayesian estimation, AUC estimation with flattened priors and limited sampling strategies were also assessed. Predictions were evaluated using normalized root mean square error (nRMSE), mean percent error (MPE), and accuracy. The data set included 70 treatment courses, with 32 not evaluable by LLR due to detection limits or timing issues. Bayesian estimation demonstrated worse accuracy (47.1%-50.7% vs 75.7%), higher MPE (24.2%-32.4% vs -2.4%), and higher nRMSE (35.0%-39.4% vs 24.8%) than LLR for peak concentrations but performed better on troughs (accuracy: 92.0%-92.9% vs 84.6%). Bayesian estimation with flattened priors and a single sample at 4 h was comparable to LLR performance, with better accuracy (42.9%-68.0% vs 41.1% LLR), comparable MPE (-2.3% to -3.7% vs -0.5%) and nRMSE (11.3%-21.6% vs 17.3%). Bayesian estimation with one concentration and flattened priors can match LLR prediction accuracy. However, popPK models must be improved to better estimate peak samples.

PMID:39791873 | DOI:10.1128/aac.01040-24

Healthcare (Basel). 2024 Dec 24;13(1):4. doi: 10.3390/healthcare13010004.

ABSTRACT

Background/Objectives: Exercise for children with cystic fibrosis leads to well-known health benefits. However, maintaining regular activity is challenging due to the daily demands of academics, clinical care, and family tasks. Home-based exercise programs offer a more adaptable alternative, fitting into family schedules. This study evaluated the effectiveness of the "KidMove" program, a parent-supervised, tailored, home exercise regimen. Methods: A quasi-experimental study was conducted with an intervention group (IG) and a wait-list control group (CG). The "KidMove" program lasted 12 weeks and included 35 exercises targeting endurance, resistance, flexibility, and neuromotor training. The primary outcome, endurance, was measured with the Modified Shuttle Walking Test, while secondary outcomes included body composition, resistance, flexibility, postural control, respiratory function, and health-related quality of life. Data were collected at baseline and post-intervention. A per-protocol analysis was conducted with generalized estimating equations (GEEs). Results: Forty-six children aged 10 ± 4 years (6 to 18 years), mostly male (n = 24; 52.2%), participated. Significant improvements were observed in the Modified Shuttle Walking Test [Wald χ2 = 14.24, p < 0.001], postural control [Wald χ2 = 3.89, p = 0.048], knee flexibility [Wald χ2 = 5.58, p = 0.018], and emotional functioning [Wald χ2 = 9.34, p = 0.002] categories. Conclusions: The "KidMove" program offers a practical, family friendly alternative to center-based exercise by empowering parents to support their children's physical activity at home, endurance, flexibility, and emotional well-being, while reducing the logistical challenges.

PMID:39791611 | DOI:10.3390/healthcare13010004

J Magn Reson Imaging. 2025 Jan 10. doi: 10.1002/jmri.29710. Online ahead of print.

ABSTRACT

Osteoarthritis (OA) is heterogeneous and involves structural changes in the whole joint, such as cartilage, meniscus/labrum, ligaments, and tendons, mainly with short T2 relaxation times. Detecting OA before the onset of irreversible changes is crucial for early proactive management and limit growing disease burden. The more recent advanced quantitative imaging techniques and deep learning (DL) algorithms in musculoskeletal imaging have shown great potential for visualizing "pre-OA." In this review, we first focus on ultrashort echo time-based magnetic resonance imaging (MRI) techniques for direct visualization as well as quantitative morphological and compositional assessment of both short- and long-T2 musculoskeletal tissues, and second explore how DL revolutionize the way of MRI analysis (eg, automatic tissue segmentation and extraction of quantitative image biomarkers) and the classification, prediction, and management of OA. PLAIN LANGUAGE SUMMARY: Detecting osteoarthritis (OA) before the onset of irreversible changes is crucial for early proactive management. OA is heterogeneous and involves structural changes in the whole joint, such as cartilage, meniscus/labrum, ligaments, and tendons, mainly with short T2 relaxation times. Ultrashort echo time-based magnetic resonance imaging (MRI), in particular, enables direct visualization and quantitative compositional assessment of short-T2 tissues. Deep learning is revolutionizing the way of MRI analysis (eg, automatic tissue segmentation and extraction of quantitative image biomarkers) and the detection, classification, and prediction of disease. They together have made further advances toward identification of imaging biomarkers/features for pre-OA. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY: Stage 2.

PMID:39792443 | DOI:10.1002/jmri.29710

J Chem Inf Model. 2025 Jan 10. doi: 10.1021/acs.jcim.4c01913. Online ahead of print.

ABSTRACT

Antimicrobial peptides (AMPs) are small peptides that play an important role in disease defense. As the problem of pathogen resistance caused by the misuse of antibiotics intensifies, the identification of AMPs as alternatives to antibiotics has become a hot topic. Accurately identifying AMPs using computational methods has been a key issue in the field of bioinformatics in recent years. Although there are many machine learning-based AMP identification tools, most of them do not focus on or only focus on a few functional activities. Predicting the multiple activities of antimicrobial peptides can help discover candidate peptides with broad-spectrum antimicrobial ability. We propose a two-stage AMP predictor deep-AMPpred, in which the first stage distinguishes AMP from other peptides, and the second stage solves the multilabel problem of 13 common functional activities of AMP. deep-AMPpred combines the ESM-2 model to encode the features of AMP and integrates CNN, BiLSTM, and CBAM models to discover AMP and its functional activities. The ESM-2 model captures the global contextual features of the peptide sequence, while CNN, BiLSTM, and CBAM combine local feature extraction, long-term and short-term dependency modeling, and attention mechanisms to improve the performance of deep-AMPpred in AMP and its function prediction. Experimental results demonstrate that deep-AMPpred performs well in accurately identifying AMPs and predicting their functional activities. This confirms the effectiveness of using the ESM-2 model to capture meaningful peptide sequence features and integrating multiple deep learning models for AMP identification and activity prediction.

PMID:39792442 | DOI:10.1021/acs.jcim.4c01913

Technol Health Care. 2025;33(1):695. doi: 10.3233/THC-249001.

NO ABSTRACT

PMID:39792355 | DOI:10.3233/THC-249001

Esophagus. 2025 Jan 10. doi: 10.1007/s10388-025-01106-x. Online ahead of print.

ABSTRACT

BACKGROUND: Neoadjuvant chemotherapy is standard for advanced esophageal squamous cell carcinoma, though often ineffective. Therefore, predicting the response to chemotherapy before treatment is desirable. However, there is currently no established method for predicting response to neoadjuvant chemotherapy. This study aims to build a deep-learning model to predict the response of esophageal squamous cell carcinoma to preoperative chemotherapy by utilizing multimodal data integrating esophageal endoscopic images and clinical information.

METHODS: 170 patients with locally advanced esophageal squamous cell carcinoma were retrospectively studied, and endoscopic images and clinical information before neoadjuvant chemotherapy were collected. Endoscopic images alone and endoscopic images plus clinical information were each analyzed with a deep-learning model based on ResNet50. The clinical information alone was analyzed using logistic regression machine learning models, and the area under a receiver operating characteristic curve was calculated to compare the accuracy of each model. Gradient-weighted Class Activation Mapping was used on the endoscopic images to analyze the trend of the regions of interest in this model.

RESULTS: The area under the curve by clinical information alone, endoscopy alone, and both combined were 0.64, 0.55, and 0.77, respectively. The endoscopic image plus clinical information group was statistically more significant than the other models. This model focused more on the tumor when trained with clinical information.

CONCLUSIONS: The deep-learning model developed suggests that gastrointestinal endoscopic imaging, in combination with other clinical information, has the potential to predict the efficacy of neoadjuvant chemotherapy in locally advanced esophageal squamous cell carcinoma before treatment.

PMID:39792350 | DOI:10.1007/s10388-025-01106-x

Mol Divers. 2025 Jan 10. doi: 10.1007/s11030-024-11065-7. Online ahead of print.

ABSTRACT

Identifying drug-target binding affinity (DTA) plays a critical role in early-stage drug discovery. Despite the availability of various existing methods, there are still two limitations. Firstly, sequence-based methods often extract features from fixed length protein sequences, requiring truncation or padding, which can result in information loss or the introduction of unwanted noise. Secondly, structure-based methods prioritize extracting topological information but struggle to effectively capture sequence features. To address these challenges, we propose a novel deep learning model named GraphkmerDTA, which integrates Kmer features with structural topology. Specifically, GraphkmerDTA utilizes graph neural networks to extract topological features from both molecules and proteins, while fully connected networks learn local sequence patterns from the Kmer features of proteins. Experimental results indicate that GraphkmerDTA outperforms existing methods on benchmark datasets. Furthermore, a case study on lung cancer demonstrates the effectiveness of GraphkmerDTA, as it successfully identifies seven known EGFR inhibitors from a screening library of over two thousand compounds. To further assess the practical utility of GraphkmerDTA, we integrated it with network pharmacology to investigate the mechanisms underlying the therapeutic effects of Lonicera japonica flower in treating Alzheimer's disease. Through this interdisciplinary approach, three potential compounds were identified and subsequently validated through molecular docking studies. In conclusion, we present not only a novel AI model for the DTA task but also demonstrate its practical application in drug discovery by integrating modern AI approaches with traditional drug discovery methodologies.

PMID:39792322 | DOI:10.1007/s11030-024-11065-7

Environ Monit Assess. 2025 Jan 10;197(2):155. doi: 10.1007/s10661-024-13431-2.

ABSTRACT

Recent advancements in satellite technology have greatly expanded data acquisition capabilities, making satellite imagery more accessible. Despite these strides, unlocking the full potential of satellite images necessitates efficient interpretation. Image classification, a widely adopted for extracting valuable information, has seen a surge in the application of deep learning methodologies due to their effectiveness. However, the success of deep learning is contingent upon the quality of the training data. In our study, we compared the efficiency of pixel-based and object-based classifications in Sentinel-2 satellite imagery using the Deeplabv3 deep learning method. The image sharpness was enhanced through a high-pass filter, aiding in data visualization and preparation. Deeplabv3 underwent training, leading to the development of classifiers following the extraction of training samples from the enhanced image. The majority zonal statistic method was implemented to assign class values to objects in the workflow. The accuracy of pixel-based and object-based classification was 83.1% and 83.5%, respectively, with corresponding kappa values of 0.786 and 0.791. These accuracies highlighted the efficient performance of the object-based method when integrated with a deep learning classifier. These results can serve as a valuable reference for future studies, aiding in the improvement of accuracy while potentially saving time and effort. By evaluating this nuanced impact pixel and object-based classification as well as on class-specific accuracy, this research contributes to the ongoing refinement of satellite image interpretation techniques in environmental applications.

PMID:39792312 | DOI:10.1007/s10661-024-13431-2

Insights Imaging. 2025 Jan 10;16(1):10. doi: 10.1186/s13244-024-01817-2.

ABSTRACT

INTRODUCTION: A large number of middle-aged and elderly patients have an insufficient understanding of osteoporosis and its harm. This study aimed to establish and validate a convolutional neural network (CNN) model based on unenhanced chest computed tomography (CT) images of the vertebral body and skeletal muscle for opportunistic screening in patients with osteoporosis.

MATERIALS AND METHODS: Our team retrospectively collected clinical information from participants who underwent unenhanced chest CT and dual-energy X-ray absorptiometry (DXA) examinations between January 1, 2022, and December 31, 2022, at four hospitals. These participants were divided into a training set (n = 581), an external test set 1 (n = 229), an external test set 2 (n = 198) and an external test set 3 (n = 118). Five CNN models were constructed based on chest CT images to screen patients with osteoporosis and compared with the SMI model to predict the performance of osteoporosis patients.

RESULTS: All CNN models have good performance in predicting osteoporosis patients. The average F1 score of Densenet121 in the three external test sets was 0.865. The area under the curve (AUC) of Desenet121 in external test set 1, external test set 2, and external test set 3 were 0.827, 0.859, and 0.865, respectively. Furthermore, the Densenet121 model demonstrated a notably superior performance compared to the SMI model in predicting osteoporosis patients.

CONCLUSIONS: The CNN model based on unenhanced chest CT vertebral and skeletal muscle images can opportunistically screen patients with osteoporosis. Clinicians can use the CNN model to intervene in patients with osteoporosis and promptly avoid fragility fractures.

CRITICAL RELEVANCE STATEMENT: The CNN model based on unenhanced chest CT vertebral and skeletal muscle images can opportunistically screen patients with osteoporosis. Clinicians can use the CNN model to intervene in patients with osteoporosis and promptly avoid fragility fractures.

KEY POINTS: The application of unenhanced chest CT is increasing. Most people do not consciously use DXA to screen themselves for osteoporosis. A deep learning model was constructed based on CT images from four institutions.

PMID:39792306 | DOI:10.1186/s13244-024-01817-2

World J Urol. 2025 Jan 10;43(1):65. doi: 10.1007/s00345-025-05440-8.

ABSTRACT

PURPOSE: To develop a deep learning (DL) model based on primary tumor tissue to predict the lymph node metastasis (LNM) status of muscle invasive bladder cancer (MIBC), while validating the prognostic value of the predicted aiN score in MIBC patients.

METHODS: A total of 323 patients from The Cancer Genome Atlas (TCGA) were used as the training and internal validation set, with image features extracted using a visual encoder called UNI. We investigated the ability to predict LNM status while assessing the prognostic value of aiN score. External validation was conducted on 139 patients from Renmin Hospital of Wuhan University (RHWU; Wuhan, China).

RESULTS: The DL model achieved area under the receiver operating characteristic curves of 0.79 (95% confidence interval [CI], 0.69-0.88) in the internal validation set for predicting LNM status, and 0.72 (95% CI, 0.68-0.75) in the external validation set. In multivariable Cox analysis, the model-predicted aiN score emerged as an independent predictor of survival for MIBC patients, with a hazard ratio of 1.608 (95% CI, 1.128-2.291; p = 0.008) in the TCGA cohort and 2.746 (95% CI, 1.486-5.076; p < 0.001) in the RHWU cohort. Additionally, the aiN score maintained prognostic value across different subgroups.

CONCLUSION: In this study, DL-based image analysis showed promising results by directly extracting relevant prognostic information from H&E-stained histology to predict the LNM status of MIBC patients. It might be used for personalized management of MIBC patients following prospective validation in the future.

PMID:39792275 | DOI:10.1007/s00345-025-05440-8