SEARCH · PubMed Health

Results for “Deep Learning”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 91 records · Page 5Linked to original sources

PubMed2025

Integrating RNA sequencing with deep learning-based metabolic toxicity prediction: A new perspective on screening prioritized liquid crystal monomers.

Nearly 99 % of liquid crystal monomers (LCMs) toxicological data remains gaps, especially to aquatic organisms. Herein, this study proposes a rapid and high-throughput screening method for identifying priority LCMs in natural water. Using six fluorinated LCMs (LCMsF) with significant enrichment characteristics in zebrafish as examples, RNA sequencing revealed that LCMsF-induced metabolic disturbances are predominant, including 28 Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway abnormalities attributed to 498 differentially expressed genes. Notably, the intricate sequencing process resulted in the inability to rapid identify additional 857 LCMsF that may induce metabolic disturbances. To address this, LCMsT-MTP, a predictive deep learning model based on RNA sequencing, was developed. This model integrates a comprehensive representation of LCMsF structures and metabolic toxicity target sequences. LCMsT-MTP improves upon traditional methods that are limited to single targets and mechanisms by facilitating the simultaneous identification of 21 metabolic toxicities induced by LCMsF. In addition, the LCMsT-MTP model was further applied to non-fluorinated LCMs (LCMsNone F) that satisfy the applicability domains test. Accordingly, a metabolic toxicity priority list of LCMs was proposed, with ∼95 % of LCMs classified as high or medium risk. Priority list validation by molecular dynamics confirmed that the interactions of LCMsF/LCMsNone F and metabolic toxicity targets in representative KEGG pathways were distinct.

Animals↗

PubMed2025

Deep learning-based annotation of plant abiotic stress resistance genes for crops.

The declining costs of DNA sequencing have expanded genomic data, crucial for understanding plant abiotic stress responses and crop improvement. However, accurate gene annotation remains challenging. To address this limitation, we propose the PASRGA, a deep learning approach that leverages transfer learning and contrastive learning to annotate genes related to drought, salt, cold, and UV resistance. PASRGA achieves high F1-scores, area under the receiver operating characteristic (AUROC), area under the precision-recall curve (AUPRC), and Matthews correlation coefficient (MCC) in annotating stress resistance genes, significantly outperforming the general protein annotation model CLEAN, the plant phosphatase gene annotation model PF-NET, the top-ranked model in the CAFA5 challenge NetGO 4.0, and four traditional machine learning methods. Its effectiveness was further validated with a salt stress treatment experiment in Eutrema salsugineum. To facilitate crop breeding practices, we utilized PASRGA to annotate the genomes of 17 major crops. To improve accessibility and utility, we incorporated both manually curated and PASRGA-predicted gene data, together with the PASRGA tool, into the PlantASRG database (https://bioinfor.nefu.edu.cn/PlantASRG/). This comprehensive resource aims to support crop breeding initiatives and ensure food security.

Crops, Agricultural↗

PubMed2026

A novel deep learning-driven framework for improving lncRNA comprehensive annotation with LncADeep 2.0.

MOTIVATION: Long non-coding RNAs (lncRNAs) have emerged as crucial players in diverse physiological and pathological processes, yet the biological mechanisms of the vast majority of lncRNAs remain elusive. To fill this gap, it is necessary to improve the accuracy of lncRNA identification and functional annotation. RESULTS: Here, we introduce LncADeep 2.0, an integrated deep learning framework designed to meet these needs. In the identification module, LncADeep 2.0 incorporated novel peptide features along with sequence and structural information, demonstrating superior performance over our previous LncADeep and other existing tools on both annotated transcripts from GENCODE and RNA-seq data. For functional annotation, LncADeep 2.0 leveraged lncRNA-centric interaction networks and gene ontology terms through the transfer learning strategy to achieve robust annotation performance with limited functional data. Compared to LncADeep, LncADeep 2.0 could accurately elucidate the general functions of given lncRNA sequences, predict tissue- or cell-type-specific functions from bulk and single-cell RNA-seq data, and establish connections between tumor-associated lncRNAs and genomic markers. Overall, LncADeep 2.0 stands out as an efficient and reliable tool for lncRNA identification and functional annotation across a wide spectrum of biological processes. AVAILABILITY AND IMPLEMENTATION: LncADeep 2.0 is available for use at https://github.com/Jefferson-Chou/LncADeep2 and https://doi.org/10.5281/zenodo.17164767.

RNA, Long Noncoding↗

PubMed2026

MegaPlantTF: a machine learning framework for comprehensive identification and classification of plant transcription factors.

MOTIVATION: Understanding the role of transcription factors (TFs) in plants is essential for the study of gene regulation and various biological processes. However, both TF detection and classification remain challenging due to the great diversity and complexity of these proteins. Conventional approaches, such as BLAST, often suffer from high computational complexity and limited performance on less common TF families. RESULTS: We introduce MegaPlantTF, the first comprehensive machine learning and deep learning framework for the prediction (TF versus non-TF) and classification (family-level) of plant TFs. Our method employs k-mer-based protein representations and a two-stage architecture combining a deep feed-forward neural network with a stacking ensemble classifier. To ensure robust performance assessment, we report micro-, macro-, and weighted-average performance metrics, providing a holistic evaluation of both frequent and underrepresented TF families. Additionally, we employ threshold-based evaluation to calibrate confidence in TF detection. The results show that MegaPlantTF achieves strong accuracy and precision, particularly with a k-mer size of 3 and a classification threshold of 0.5, and maintains stable performance even under stringent thresholds. In addition to the standard cross-validation tests, a use case study on Sorghum bicolor confirms that our method performs strongly in the genome-wide analysis, making it highly suitable for large-scale TF identification and classification tasks. MegaPlantTF represents a novel contribution by integrating k-mer encoding, binary family-specific classifiers, and a two-stage stacking ensemble into a unified, reproducible framework for large-scale plant TF identification and classification. AVAILABILITY AND IMPLEMENTATION: MegaPlantTF is freely accessible through a public web server available at https://bioinformatics.um6p.ma/MegaPlantTF. The complete source code, including pretrained models and example datasets, is available at https://github.com/Bioinformatics-UM6P/MegaPlantTF.

Transcription Factors↗

PubMed2025

Deep learning-based assessment of missense variants in the COG4 gene presented with bilateral congenital cataract.

OBJECTIVE: We compared the protein structure and pathogenicity of clinically relevant variants of the COG4 gene with AlphaFold2 (AF2), Alpha Missense (AM), and ThermoMPNN for the first time. METHODS AND ANALYSIS: The sequences of clinically relevant Cog4 missense variants (one novel identified p.Y714F and three pre-existing p.G512R, p.R729W and p.L769R from Uniprot Q9H9E3) were imported into AF2 for protein structural prediction, and the pathogenicity was estimated using AM and ThermoMPNN. Different pathogenicity metrics were aggregated with principal component analysis (PCA) and further analysed at three levels (amino acid position, substitution and post-translation) based on all possible Cog4 missense variants (n=14 915). RESULTS: Localised protein structural impact including change of conformation and amino acid polarity, breakage of hydrogen bond and salt-bridge, and formation of alpha-helix were identified among clinically relevant Cog4 variants. The global structural comparison with multidimensional scaling demonstrated variants with similar protein structures (AF2) tended to exhibit similar clinical and biological phenotypes. The Cog4 p.Y714F variant exhibited greater protein structural similarity to mutated Cog4 found in Saul‒Wilson syndrome (p.G512R) and shared similar clinical phenotype (congenital cataract and psychomotor retardation). PCA of included pathogenic metrics demonstrated p.Y714F occurred at a critical position in Cog4 amino acid sequence with disrupted post-translational phosphorylation. CONCLUSION: Deep learning algorithms, including AF2, AM and ThermoMPNN, can be useful for evaluating variant of uncertain significance (VUS) by structural and pathogenicity prediction. Despite classified as VUS (American College of Medical Genetics and Genomics criteria: PM1, PP4), the pathogenicity in this Cog4 variant cannot be ruled out and warrants further investigation.

Mutation, Missense↗

PubMed2025

Automated Deep Learning-Based Detection of Early Atherosclerotic Plaques in Carotid Ultrasound Imaging.

BACKGROUND: Carotid plaque presence is associated with cardiovascular risk, even among asymptomatic individuals. While deep learning has shown promise for carotid plaque phenotyping in patients with advanced atherosclerosis, its application in population-based settings of asymptomatic individuals remains unexplored. METHODS: We developed a YOLOv8-based model for plaque detection using carotid ultrasound images from 19,499 participants of the population-based UK Biobank (UKB) and fine-tuned it for external validation in the BiDirect study (N = 2,105). Cox regression was used to estimate the impact of plaque presence and count on major cardiovascular events. To explore the genetic architecture of carotid atherosclerosis, we conducted a genome-wide association study (GWAS) meta-analysis of the UKB and CHARGE cohorts. Mendelian randomization (MR) assessed the effect of genetic predisposition to vascular risk factors on carotid atherosclerosis. RESULTS: Our model demonstrated high performance with accuracy, sensitivity, and specificity exceeding 85%, enabling identification of carotid plaques in 45% of the UKB population (aged 47-83 years). In the external BiDirect cohort, a fine-tuned model achieved 86% accuracy, 78% sensitivity, and 90% specificity. Plaque presence and count were associated with risk of major adverse cardiovascular events (MACE) over a follow-up of up to seven years, improving risk reclassification beyond the Pooled Cohort Equations. A GWAS meta-analysis of carotid plaques uncovered two novel genomic loci, with downstream analyses implicating targets of investigational drugs in advanced clinical development. Observational and MR analyses showed associations between smoking, LDL cholesterol, hypertension, and odds of carotid atherosclerosis. CONCLUSIONS: Our model offers a scalable solution for early carotid plaque detection, potentially enabling automated screening in asymptomatic individuals and improving plaque phenotyping in population-based cohorts. This approach could advance large-scale atherosclerosis research.

atherosclerosis↗

PubMed2025

Colorectal Liver Metastasis Pathomics Model: Integrating Single-Cell and Spatial Transcriptome Analysis With Pathomics for Predicting Liver Metastasis in Colorectal Cancer.

The liver is the primary target organ for hematologic metastasis of colorectal cancer (CRC), and CRC liver metastasis (CRLM) often precludes radical resection, making it the leading cause of death in patients with CRC. To improve the identification and prediction of liver metastasis risk, we identified a cell type of liver metastasis--triggering malignant cells (LMTMCs) through integrating single-cell RNA sequencing and spatial transcriptome analysis. Multiomics cell communication analysis indicated that the interaction between fibroblasts and LMTMCs through the COL1A1-CD44/SDC4 and LAMA4-CD44 signaling axes could promote CRLM. By applying the one-class logistic regression algorithm, we developed a CRLM scoring system in the bulk RNA-sequencing data according to the abundance of LMTMCs in each individual. Using the grouping labels derived from the CRLM scoring system in the bulk data and the corresponding whole-slide images without any manual annotations at the region or pixel level, processed via slide-level weakly supervised learning, a deep-learning model based on the ResNet18 architecture, called Colorectal Liver Metastasis Pathomics Model, was developed to predict the risk of liver metastasis in patients with CRC. The Colorectal Liver Metastasis Pathomics Model achieved an area under the curve of 0.84 at the internal test set of The Cancer Genome Atlas-CRC histology images. In the external independent validation sets, namely the Affiliated Hospital of Southwest Medical University and the Affiliated Traditional Chinese Medicine Hospital of Southwest Medical University cohorts, the areas under the curve were 0.89 and 0.72, respectively, indicating effective classification performances. This study provided new insights and tools for the early identification of CRLM and demonstrated the potential of combining multiomics with deep learning-based pathomics in cancer research.

Humans↗

PubMed2025

Computational Pathology for Accurate Prediction of Breast Cancer Recurrence: Development and Validation of a Deep Learning-Based Tool.

Accurate recurrence risk stratification is crucial for optimizing treatment plans for breast cancer patients. Current prognostic tools like Oncotype DX offer valuable genomic insights into hormone receptor-positive and human epidermal growth factor receptor-negative patients but are limited by cost and accessibility, particularly in underserved populations. In this study, we present Deep-Breast-Cancer-Recurrence (BCR)-Auto, a deep learning-based computational pathology approach that predicts breast cancer recurrence risk from routine hematoxylin and eosin-stained whole slide images. Our methodology was validated on 2 independent cohorts: The Cancer Genome Atlas Program breast cancer data set and an in-house data set from The Ohio State University. Deep-BCR-Auto demonstrated robust performance in stratifying patients into low- and high-recurrence risk categories. On The Cancer Genome Atlas Program breast cancer data set, the model achieved an area under the receiver operating characteristic curve of 0.827, significantly outperforming the existing weakly supervised models (P = .041). In the independent The Ohio State University data set, Deep-BCR-Auto maintained strong generalizability, achieving an area under the receiver operating characteristic curve of 0.832, along with 82.0% accuracy, 85.0% specificity, and 67.7% sensitivity. These findings highlight the potential of computational pathology as a cost-effective alternative for recurrence risk assessment, broadening access to personalized treatment strategies. This study underscores the clinical utility of integrating deep learning-based computational pathology into routine pathological assessment for breast cancer prognosis across diverse clinical settings.

Humans↗

PubMed2026

miRNA Target Prediction: An Overview of the Past and Current Tools.

MicroRNAs (miRNAs) are among the most studied molecules in recent years, and since their discovery, many miRNAs have been identified across various species. As members of the non-coding RNA family, miRNAs are key players in post-transcriptional gene regulation. These molecules can inhibit translation or promote degradation of messenger RNA (mRNA) by binding to the 3' untranslated region (UTR) of mRNA, thereby influencing almost all biological processes. To identify a miRNA's biological role, it is essential to predict the target sites to which it binds, a goal made possible through bioinformatics tools. This chapter discusses the bioinformatics tools commonly used for this purpose. Also, it analyzes the main factors considered in target prediction, such as seed match, free energy, conservation, site accessibility, multiple binding site contribution, and machine learning and deep learning approaches. Understanding the principles underlying these predictive methodologies is crucial for advancing one's biological research on miRNAs.

MicroRNAs↗

PubMed2026

Integrative proteomics and bioinformatics pipelines for PTM profiling.

Post-translational modifications (PTMs) regulate protein function across all life forms and allow plants to respond rapidly to biotic and abiotic stress. Over 450 PTM types have been described across organisms, of which 23-33 have been experimentally confirmed in plants, including phosphorylation, acetylation, methylation, glycosylation, ubiquitination, and sumoylation. These modifications are highly dynamic and often reversible, and frequently act in combination, or "crosstalk," to fine-tune cellular processes. Advances in high-resolution mass spectrometry and large-scale genome sequencing continue to expand the catalogue of known PTM sites, while machine learning and deep learning approaches increasingly support prediction of PTM site localization and function. Unlike broader surveys of plant PTMs, this review focuses specifically on O-phosphorylation and Lys-N(ε)-acetylation, the two best-characterized and most extensively crosstalking PTMs in plants, and integrates four perspectives: the historical development of proteomic and bioinformatics approaches to these modifications; current mass spectrometry-based workflows and enrichment strategies; the bioinformatics tools and databases available for their analysis; and the technical and species-related challenges, particularly in non-model plants, that currently limit their study. We close by outlining priority directions for future research, including multi-omics integration, AI-based prediction, and the translation of PTM knowledge into crop stress resilience and breeding applications.

Protein Processing, Post-Translational↗

PubMed2026

Decoding cancer with artificial intelligence: Transforming research, diagnosis, and therapy with future insights.

Cancer remains one of the leading global health burdens, with increasing complexity in genomic, imaging, and clinical datasets presenting significant challenges for effective management. Artificial intelligence (AI) has emerged as a powerful tool to address these challenges by enabling pattern recognition, knowledge integration, and data-driven decision-making. This review highlights recent advances in the application of AI across cancer research, diagnosis, and therapy. In research, AI accelerates drug discovery and repurposing, enhances genomic data interpretation, and facilitates biomarker identification through multi-omics integration. In diagnosis, AI has demonstrated high technical performance in radiology for lesion detection and image segmentation, in pathology for tumour grading and molecular prediction, and in liquid biopsy for non-invasive biomarker analysis. In therapy, AI supports precision medicine by predicting treatment responses, monitoring disease progression, and optimizing clinical trial design. Despite these advances, barriers such as data heterogeneity, algorithmic bias, interpretability, and regulatory challenges remain. Future directions, including explainable AI, federated learning, multimodal modelling, and digital twins, hold promise for translating AI-driven innovations into routine oncology practice. Significance Statement This review provides a timely synthesis of recent (2020-2025) advances in artificial intelligence across cancer research, diagnosis, and therapy, highlighting applications in drug discovery, genomics, multi-omics biomarker identification, and clinical decision-making. By integrating technological progress with translational and clinical relevance, this work serves as a valuable resource for bridging AI innovation with precision oncology practice. As a narrative review, the literature was identified through targeted PubMed, Scopus, and Google Scholar searches, combining terms for artificial intelligence, machine learning, and deep learning with cancer-related keywords, with priority given to peer-reviewed studies published between 2020 and 2025, seminal earlier works, and official regulatory or guideline documents. Within each domain, representative studies were selected to illustrate methodological diversity, clinical context, and current translational readiness rather than to provide exhaustive coverage of an extremely rapidly evolving field.

Artificial intelligence↗

PubMed2026

Spectral Transforms as a Tool to Optimize Digital Phenotyping in Biological Images.

Modern livestock breeding has mastered genotyping. Genome-wide association studies, genomic selection, and SNP arrays enable genetic merit prediction at lower cost. However, phenotyping remains the bottleneck, as manual measurement is slow, expensive, subjective, and unable to capture spatial or temporal trait organization. Digital phenotyping via artificial intelligence could resolve this, but deep learning requires thousands of labelled examples, impractical when phenotyping cost itself limits datasets to hundreds of individuals. This creates a paradox: AI could accelerate phenotyping but requires large numbers of samples to train the models. Here, we demonstrate that integrating computer vision with machine learning offers sample-efficient digital phenotyping using eggshell colour as a model system. Rather than learning features from scratch (deep learning), we engineer physically motivated features via Wavelet transforms that decompose images into multi-scale spatial components. Wavelet features captured 14.2 percentage points more variance (R2 = 0.976 vs. 0.834, p < 0.001) than standard colorimetry, with 50% better sample efficiency (achieving at n = 60 what colorimetry required n = 120). Variance decomposition revealed 77% of discriminative capacity derives from spatial patterns (bands, spots, gradients) invisible to scalar averages. Additionally, we identified "cryptic phenotypes" (3.3%) where spatial patterns contradicted average colour, cases where colorimeters failed but Wavelets succeeded. The underlying principle-that spatial decomposition can recover organizational information lost by scalar averaging-may be applicable to other traits with spatial or temporal structure, such as marbling, dermatitis, or pigmentation rhythms, although whether comparable performance gains would be observed remains to be tested empirically. Hence, for breeding programs implementing genomic selection, computer vision-based digital phenotyping captures complex trait variation without massive training datasets, addressing the bottleneck that increasingly limits genetic progress as genotyping becomes trivial.

Wavelet transform↗

PubMed2025

Artificial intelligence in healthcare and medicine: clinical applications, therapeutic advances, and future perspectives.

Healthcare systems worldwide face growing challenges, including rising costs, workforce shortages, and disparities in access and quality, particularly in low- and middle-income countries. Artificial intelligence (AI) has emerged as a transformative tool capable of addressing these issues by enhancing diagnostics, treatment planning, patient monitoring, and healthcare efficiency. AI's role in modern medicine spans disease detection, personalized care, drug discovery, predictive analytics, telemedicine, and wearable health technologies. Leveraging machine learning and deep learning, AI can analyze complex data sets, including electronic health records, medical imaging, and genomic profiles, to identify patterns, predict disease progression, and recommend optimized treatment strategies. AI also has the potential to promote equity by enabling cost-effective, resource-efficient solutions in low-resource and remote settings, such as mobile diagnostics, wearable biosensors, and lightweight algorithms. Successful deployment requires addressing critical challenges, including data privacy, algorithmic bias, model interpretability, regulatory oversight, and maintaining human clinical oversight. Emphasizing scalable, ethical, and evidence-driven implementation, key strategies include clinician training in AI literacy, adoption of resource efficient tools, global collaboration, and robust regulatory frameworks to ensure transparency, safety, and accountability. By complementing rather than replacing healthcare professionals, AI can reduce errors, optimize resources, improve patient outcomes, and expand access to quality care. This review emphasizes the responsible integration of AI as a powerful catalyst for innovation, sustainability, and equity in healthcare delivery worldwide.

Humans↗

PubMed2025

Hepatocyte proteome destabilization and novel targets for PFASs unveiled through combined thermal proteome profiling and deep transfer learning.

Identifying protein targets for per- and polyfluoroalkyl substances (PFASs) is essential to understand their toxicity and health risks. However, knowledge about their interacting proteins is limited since reliable identification methods are lacking. We developed an integrated approach combining thermal proteome profiling (TPP) and deep transfer learning (DTL) modeling to efficiently identify cellular targets of PFAS. TPP measured PFAS binding proteins and the affinities by nanospray liquid chromatography tandem mass spectrometry, while DTL models were constructed to predict PFAS-protein affinities using neural network algorithms. TPP results revealed that PFASs uniquely destabilized the proteome of HepG2 cells, unlike the stabilizing effects by other xenobiotics. Key protein targets for three representative PFASs (PFOA, GenX and Novec 649) were identified, which exhibited weak binding affinities (median EC50 ≈ 30 μM). The number of protein targets increased with molecular weights among the three PFASs. The DTL model achieved a higher Pearson correlation coefficient of 0.89, and reduced mean squared errors by 54 % over previous models for drug-protein interactions. Notably, TPP and DTL jointly pinpointed ribosomal proteins as novel targets of GenX, potentially linking it to cell apoptosis through disrupted protein synthesis. Biolayer interferometry validated GenX binding to RPL4 protein, driven by electrostatic interactions and halogen bonds. This integrated approach effectively uncovers novel PFASs targets, advancing insights into their adverse health effects.

Humans↗

PubMed2026

Artificial intelligence in treatment prediction for skeletal Class III malocclusion: A systematic review.

In skeletal Class III patients, treatment options range from orthodontics to orthognathic surgery. Choosing the optimal approach requires a comprehensive clinical evaluation, which may be supported by AI tools. The aim of this study was to assess the performance of AI models in predicting the need for orthognathic surgery and in identifying predictors influencing treatment decisions. A PRISMA-guided electronic database search (PubMed, Web of Science; 2009-2024; English/French) was performed to identify studies using machine learning (ML) or deep learning (DL) on cephalometric and clinical data. After screening and assessment for eligibility, 15 studies were critically appraised. Model performance was summarized using accuracy, sensitivity, specificity, and the area under the curve (AUC). ML algorithms (particularly Random Forest and XGBoost) and DL models (ResNet-based convolutional neural networks (CNNs)) achieved high accuracy for predicting surgical need. Frequently selected predictors included Wits appraisal, ANB angle, the maxillomandibular ratio (Mx/Md), overjet, and the divergence of the lower gonial angle. AI methods show promise for assisting treatment decisions in Class III malocclusion, with Random Forest and XGBoost performing well on tabular cephalometric data and CNNs on imaging. Larger, multicentre datasets and external validation are needed to improve reliability, address bias, and support clinical implementation.

Humans↗

PubMed2025

DeepES: deep learning-based enzyme screening to identify orphan enzyme genes.

MOTIVATION: Progress in sequencing technology has led to determination of large numbers of protein sequences, and large enzyme databases are now available. Although many computational tools for enzyme annotation were developed, sequence information is unavailable for many enzymes, known as orphan enzymes. These orphan enzymes hinder sequence similarity-based functional annotation, leading gaps in understanding the association between sequences and enzymatic reactions. RESULTS: Therefore, we developed DeepES, a deep learning-based tool for enzyme screening to identify orphan enzyme genes, focusing on biosynthetic gene clusters and reaction class. DeepES uses protein sequences as inputs and evaluates whether the input genes contain biosynthetic gene clusters of interest by integrating the outputs of the binary classifier for each reaction class. The validation results suggested that DeepES can capture functional similarity between protein sequences, and it can be implemented to explore orphan enzyme genes. By applying DeepES to 4744 metagenome-assembled genomes, we identified candidate genes for 236 orphan enzymes, including those involved in short-chain fatty acid production as a characteristic pathway in human gut bacteria. AVAILABILITY AND IMPLEMENTATION: DeepES is available at https://github.com/yamada-lab/DeepES. Model weights and the candidate genes are available at Zenodo (https://doi.org/10.5281/zenodo.11123900).

Deep Learning↗

PubMed2026

AI-driven diagnostic and prognostic models for metabolic dysfunction-associated steatotic liver disease: insights from clinical, imaging, and multi-omics studies-a scoping review.

Metabolic dysfunction-associated steatotic liver disease (MASLD), formerly known as non-alcoholic fatty liver disease (NAFLD), is the most common chronic liver disease around the world, affecting 33.6% of the adult population (95% CI: 28.1%-39.5%; I 2 = 99.9%), or roughly one in three. The extent of the liver damage is variable, from simple steatosis to metabolic dysfunction-associated steatohepatitis (MASH, formerly NASH), cirrhosis and hepatocellular carcinoma (HCC). Early diagnosis is essential to prevent serious liver damage. Traditional diagnostic techniques such as liver biopsy, imaging, and biomarker testing are all invasive, costly, reduced sensitive to early-stage disease, and they also have variability among observers. Modern diagnostic and prognostic approaches based on the principles of Artificial Intelligence (AI) and specifically on machine learning (ML) and deep learning (DL) have enabled multimodal approaches integrating clinical, imaging and molecular data. This scoping review conducted per PRISMA-ScR guidelines, synthesizes findings from 73 studies (search window 2020-2026) across three dimensions: clinical data driven models, imaging-based classifiers (ultrasound, CT and MRI), and multi-omics (genomics, transcriptomics and proteomics) techniques. Moreover, emergence of models such as U-Net and LiverNet 2.x, classification models like DeepLiverNet and BiLSTM models, as well as transformer frameworks and the identification of biomarkers models are also described. This study also investigates challenges such as data heterogeneity, data interpretability, fairness and real-world clinical application. Finally, important areas of research opportunities and future directions are highlighted to present a developing clinically applicable, explainable and ethical AI solutions to manage MASLD.

MASLD↗

PubMed2026

Overcoming Artificial Structures in Resolution-Enhanced Hi-C Data by Signal Decomposition and Multi-Scale Attention.

Computational enhancement is an important strategy for inferring high-resolution features from genome-wide chromosome conformation capture (Hi-C) data, which typically have limited resolution. Deep learning has been highly successful in this task but we show that it creates prevalent artificial structures in the enhanced data due to the need to divide the large contact matrix into small patches. In addition, previous deep learning methods largely focus on local patterns, which cannot fully capture the complexity of Hi-C data. Here we propose Smooth, High-resolution, and Accurate Reconstruction of Patterns (SHARP) for enhancing Hi-C data. It uses the novel approach of decomposing the data into three types of signals, due to one-dimensional proximity, contiguous domains, and other fine structures, respectively, and applies deep learning only to the third type of signals, such that enhancement of the first two is unaffected by the patches. For the deep learning part, SHARP uses both local and global attention mechanisms to capture multi-scale contextual information. We compare SHARP with state-of-the-art methods extensively, including application to data from new samples and another species, and show that SHARP has superior performance in terms of resolution enhancement accuracy, avoiding creation of artificial structures, identifying significant interactions, and enrichment in chromatin states.

Hi‐C↗