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 235 records · Page 13Linked to original sources

PubMed2026

Profiler: an open web platform for multi-omics analysis.

MOTIVATION: High-throughput multi-omics technologies produce increasingly large and heterogeneous datasets that are difficult to analyze without advanced computational expertise. Existing bioinformatics tools are often fragmented or limited to specific omics types, hindering reproducibility and accessibility. There is a critical need for an integrated, user-friendly, and scalable platform capable of supporting multi-omics analyses across different data modalities. RESULTS: We present Profiler, an open-source, modular platform that unifies data import, quality control, preprocessing, statistical testing, machine and deep learning, biomarker discovery, pathway and drug-target enrichment, and survival modeling within a single reproducible environment. Built in Python with Streamlit, Profiler is available as both a web-based platform deployed on high-performance computing and a desktop version for local execution, enabling flexible usage across computational infrastructures. Profiler supports diverse omics modalities, including proteomics, transcriptomics, lipidomics, and electroencephalogram data. Through applications to glioblastoma proteomic, pancancer, and multi-omics datasets, Profiler reproduced known molecular subtypes, revealed potential therapeutic targets, and generated fully traceable analysis reports within minutes. By integrating advanced analytics behind an intuitive interface, Profiler democratizes multi-omics analysis and provides a robust, scalable foundation for systems biology and precision medicine research. AVAILABILITY AND IMPLEMENTATION: Profiler is open-source and freely available via its web platform (https://prism-profiler.univ-lille.fr) and GitHub (web version: https://github.com/yanisZirem/Profiler_v1_requests_datatests, desktop version: https://github.com/yanisZirem/prism-profiler), and archived on Zenodo (DOI: https://doi.org/10.5281/zenodo.17478158).

Software↗

PubMed2026

How negative sampling shapes the performance of transcription factor binding site prediction models.

MOTIVATION: Transcription factors (TFs) are key players in gene regulation and development, where they activate and repress gene expression through DNA binding. Predicting transcription factor binding sites (TFBSs) has long been an active area of research, with many deep learning methods developed to tackle this problem. These models are often trained on TF ChIP-seq data, which is generally seen as only providing positive samples. The choice of datasets and negative sampling techniques is a critical yet often overlooked aspect of this work. RESULTS: In this study, we investigate the impact of different negative sampling techniques on TFBS prediction performance. We create high-quality test datasets based on ChIP-seq and ATAC-seq data, where true negatives can be identified as positions that are accessible but not bound by the TF in question. We then train models using various negative sampling techniques, including genomic sampling, shuffling, dinucleotide shuffling, neighborhood sampling, and cell line specific sampling, simulating cases where matching ATAC-seq data is not available. Our results show that, generally, metrics calculated on training datasets give inflated performance scores. Of the tested techniques, genomic sampling of negatives based on similarity to the positives performed by far the best, although still not reaching the performance of baseline models trained on high-quality datasets. Models trained on dinucleotide shuffled negatives performed poorly, despite being a common practice in the field. Our findings highlight the importance of carefully selecting negative sampling techniques for TFBS prediction, as they can significantly impact model performance and the interpretation of results. AVAILABILITY AND IMPLEMENTATION: The code used in this study is available at https://github.com/NatanTourne/TFBS-negatives (DOI: 10.5281/zenodo.18007567).

Binding Sites↗

PubMed2026

A novel transformer model of protein domains for viral taxonomy classification.

MOTIVATION: Viruses with carefully curated taxonomic assignments (such as those in the ICTV taxonomy) still represent only a small fraction of viruses identified through sequencing data from virome or microbiome projects. It is therefore critical to develop methods that can assign viruses at multiple taxonomic ranks, so that a virus deemed novel at a given rank may still be placed into a higher-level taxon. Sequence-similarity-based approaches can classify viruses that share substantial genomic similarity with known viruses (e.g. those belonging to the same species or genus); however, their performance drops significantly when applied to more divergent viruses. Recent deep learning models, such as ViTax, which utilize DNA language models, aim to address these limitations, but their performance also degrades when applied to novel viruses lacking genus-level similarity to known references. Proteins are more conserved than genomic sequences, and the multiple proteins encoded by a virus can be leveraged to reveal evolutionary relationships among viruses. RESULTS: We propose a new tool, D2T (Domain-to-Taxonomy), that leverages recent advances in protein language models to improve viral taxonomic assignment. D2T represents a virus as a sequence of protein domain tokens and learns a transformer-based model for taxonomic classification. Experiments on multiple closed-set and open-set datasets show that D2T excels at assigning higher-level taxonomic labels (family and above). Furthermore, by combining D2T with Kraken2, which performs well at the genus level, the hybrid method (K+D2T) achieves accurate viral taxonomic classification across multiple taxonomic ranks. AVAILABILITY AND IMPLEMENTATION: D2T is available as a GitHub repository at https://github.com/mgtools/D2T.

Viruses↗

PubMed2026

Artificial Intelligence for Diagnosing Meibomian Gland Dysfunction: A Systematic Review and Meta-Analysis of Diagnostic Test Accuracy Studies.

PURPOSE: To identify, appraise, and synthesize the performance of artificial intelligence-based meibography reading as compared with human graders in diagnosing meibomian gland dysfunction. METHODS: We followed Cochrane methodology and reporting guidelines for diagnostic test accuracy reviews. To assess potential risk of bias and applicability, we used a modified Quality Assessment of Diagnostic Accuracy Studies-2 checklist. We applied bivariate logistic models to estimate summary sensitivity and specificity when appropriate and used the GRADE framework to rate the certainty of the evidence. RESULTS: We identified 14 eligible studies involving 5511 predominantly middle-aged participants (average age: 27-55 years) who were primarily female (≥54.5%). A total of 18,926 meibography images were obtained through noncontact infrared (11 studies) or in vivo confocal microscopy (three studies). Two studies reported external validation of deep learning models, 12 reported internally validated models, and one reported both. All but one study had high risk of bias in at least one domain; 12 studies raised high or intermediate concern about applicability. Based on three external evaluations, the summary sensitivity and specificity for diagnosing meibomian gland dysfunction from normal glands were 97.5% (95% confidence interval: 77.5%-99.8%) and 85.5% (95% confidence interval: 47.3%-97.5%). Sources of heterogeneity in internally validated models included study population, case mix, and others. The overall evidence was very low to low certainty because of imprecision, high risk of bias, and concerns about applicability. CONCLUSIONS: Artificial intelligence-based meibography grading appears less accurate than human graders. Future studies should adopt rigorous designs, including a more diverse participant pool (or image set), and external validation.

Humans↗

PubMed2024

DeepSomatic: Accurate somatic small variant discovery for multiple sequencing technologies.

Somatic variant detection is an integral part of cancer genomics analysis. While most methods have focused on short-read sequencing, long-read technologies now offer potential advantages in terms of repeat mapping and variant phasing. We present DeepSomatic, a deep learning method for detecting somatic SNVs and insertions and deletions (indels) from both short-read and long-read data, with modes for whole-genome and exome sequencing, and able to run on tumor-normal, tumor-only, and with FFPE-prepared samples. To help address the dearth of publicly available training and benchmarking data for somatic variant detection, we generated and make openly available a dataset of five matched tumor-normal cell line pairs sequenced with Illumina, PacBio HiFi, and Oxford Nanopore Technologies, along with benchmark variant sets. Across samples and technologies (short-read and long-read), DeepSomatic consistently outperforms existing callers, particularly for indels.

Journal Article↗

PubMed2025

Carafe enables high quality in silico spectral library generation for data-independent acquisition proteomics.

Data-independent acquisition (DIA)-based mass spectrometry is becoming an increasingly popular mass spectrometry acquisition strategy for carrying out quantitative proteomics experiments. Most of the popular DIA search engines make use of in silico generated spectral libraries. However, the generation of high-quality spectral libraries for DIA data analysis remains a challenge, particularly because most such libraries are generated directly from data-dependent acquisition (DDA) data or are from in silico prediction using models trained on DDA data. In this study, we developed Carafe, a tool that generates high-quality experiment-specific in silico spectral libraries by training deep learning models directly on DIA data. We demonstrate the performance of Carafe on a wide range of DIA datasets, where we observe improved fragment ion intensity prediction and peptide detection relative to existing pretrained DDA models. To make Carafe more accessible to the community, we have integrated Carafe into the widely used Skyline tool.

Journal Article↗

PubMed2025

OpenSpliceAI: An efficient, modular implementation of SpliceAI enabling easy retraining on non-human species.

The SpliceAI deep learning system is currently one of the most accurate methods for identifying splicing signals directly from DNA sequences. However, its utility is limited by its reliance on older software frameworks and human-centric training data. Here we introduce OpenSpliceAI, a trainable, open-source version of SpliceAI implemented in PyTorch to address these challenges. OpenSpliceAI supports both training from scratch and transfer learning, enabling seamless retraining on species-specific datasets and mitigating human-centric biases. Our experiments show that it achieves faster processing speeds and lower memory usage than the original SpliceAI code, allowing large-scale analyses of extensive genomic regions on a single GPU. Additionally, OpenSpliceAI's flexible architecture makes for easier integration with established machine learning ecosystems, simplifying the development of custom splicing models for different species and applications. We demonstrate that OpenSpliceAI's output is highly concordant with SpliceAI. In silico mutagenesis (ISM) analyses confirm that both models rely on similar sequence features, and calibration experiments demonstrate similar score probability estimates.

Journal Article↗

PubMed2025

Integrating Imaging-Derived Clinical Endotypes with Plasma Proteomics and External Polygenic Risk Scores Enhances Coronary Microvascular Disease Risk Prediction.

Coronary microvascular disease (CMVD) is an underdiagnosed but significant contributor to the burden of ischemic heart disease, characterized by angina and myocardial infarction. The development of risk prediction models such as polygenic risk scores (PRS) for CMVD has been limited by a lack of large-scale genome-wide association studies (GWAS). However, there is significant overlap between CMVD and enrollment criteria for coronary artery disease (CAD) GWAS. In this study, we developed CMVD PRS models by selecting variants identified in a CMVD GWAS and applying weights from an external CAD GWAS, using CMVD-associated loci as proxies for the genetic risk. We integrated plasma proteomics, clinical measures from perfusion PET imaging, and PRS to evaluate their contributions to CMVD risk prediction in comprehensive machine and deep learning models. We then developed a novel unsupervised endotyping framework for CMVD from perfusion PET-derived myocardial blood flow data, revealing distinct patient subgroups beyond traditional case-control definitions. This imaging-based stratification substantially improved classification performance alongside plasma proteomics and PRS, achieving AUROCs between 0.65 and 0.73 per class, significantly outperforming binary classifiers and existing clinical models, highlighting the potential of this stratification approach to enable more precise and personalized diagnosis by capturing the underlying heterogeneity of CMVD. This work represents the first application of imaging-based endotyping and the integration of genetic and proteomic data for CMVD risk prediction, establishing a framework for multimodal modeling in complex diseases.

Cardiovascular Disease↗

PubMed2025

Integration of Gene Expression and Digital Histology to Predict Treatment-Specific Responses in Breast Cancer.

Deep learning models applied to digital histology can predict gene expression signatures (GES) and offer a low-cost, rapidly available alternative to molecular testing at the time of diagnosis. We optimized transformer-based models to infer GES results and applied this approach to pre-treatment H&E-stained biopsies from 1,940 breast cancer patients treated with neoadjuvant chemotherapy in clinical trial and real-world cohorts. The most predictive histology-derived GES for pathologic complete response (pCR) in the I-SPY2 trial was validated in four external cohorts: CALGB 40601, CALGB 40603, a trial of durvalumab plus CT, and standard-of-care CT-treated patients from the University of Chicago. Among HER2-negative patients, a transformer-based model trained using a signature composed of estrogen-regulated genes, proliferation, apoptosis, and interferon response genes predicted pCR with an AUC of 0.794, outperforming models based on clinical features alone (AUC 0.704, p = 0.001), pathologist TIL assessment, and a model trained directly to predict response from I-SPY2 cases. Tertiles of this signature stratify patients into clinically relevant groups with increasing likelihood of complete response, with pCR rates ≥50% in the top tertile regardless of treatment or hormone receptor status. Additional transformer-based signature models predicted response to specific therapies (but not chemotherapy alone), including a HER2 signaling signature in IO-treated patients, and a claudin-low signature in bevacizumab treated patients. In HER2- cohorts with available gene expression data and histology, models trained on expression data performed similarly to digital histology predictions, but the combination of gene expression and histology outperformed histology alone. These findings suggest that histology-based GES provides additive information to RNA sequencing data and can inform precision treatment selection across breast cancer subtypes.

Journal Article↗

PubMed2025

Enhancer-targeting CRISPR screens at coronary artery disease loci suggest shared mechanisms of disease risk.

To systematically identify causal genetic mechanisms that confer risk for coronary artery disease (CAD) in GWAS loci, we mapped genome-wide variant-to-enhancer-to-gene (V2E2G) links in vascular smooth muscle cells (SMC). Enhancers identified by active chromatin features, and further prioritized by base-resolution deep learning models of chromatin accessibility in 108 CAD loci, were studied with CRISPRi targeting and Direct-Capture Targeted Perturb-seq (DC-TAP-seq) evaluation of 470 genes. Seventy-six V2E2G links were identified for 59 candidate CAD genes representing gene programs including epithelial-mesenchymal transformation, ubiquitination, and protein folding as well as BMP and TGFB signaling. Similar methods employed with an independent focused screen targeting one candidate locus at 9p21.3 identified 10 enhancers regulating expression of multiple genes at this location. Detailed molecular studies revealed that two enhancers mediating transcription factor binding and transcriptional regulation contribute to ancestry-specific and sex-specific risk for CAD and the surrogate biomarker vascular calcification. Together, these studies advance our identification of GWAS CAD V2E2G links across the genome, and specific mechanisms of risk at the complex 9p21.3 locus.

Journal Article↗

PubMed2025

MetaChrome: An Open-Source, User-Friendly Tool for Automated Metaphase Chromosome Analysis.

DNA Fluorescence In Situ Hybridization (FISH) is an essential technique to study chromosome biology and genetics, enabling precise visualization of specific genomic loci to study structural abnormalities, gene mapping, and chromosomal rearrangements. High-Throughput Imaging (HTI) can automate the analysis of DNA-FISH chromosome images, but the accurate and automated segmentation of mitotic chromosomes and simultaneous colocalization of FISH signals remains a challenge. While several commercial automated karyotyping tools partially solve these issues, open-source software that effectively combines robust chromosome segmentation with comprehensive colocalization analysis capabilities remains necessary. To address this unmet need, we developed MetaChrome, an open-source software platform built around a graphical user interface and explicitly designed for automated metaphase chromosome analysis. MetaChrome leverages fine-tuned deep learning models to automate metaphase chromosome segmentation, together with colocalization analysis of chromosome-specific FISH probes and immunofluorescent-labeled proteins. Importantly, MetaChrome achieves enhanced segmentation accuracy compared to traditional image processing methods by adopting a Cellpose segmentation model fine-tuned with manually annotated metaphase chromosome datasets. The fine-tuned model ensures precise assignment of DNA-FISH spots to individual chromosomes in an automated manner. This facilitates rapid identification of chromosomal abnormalities, reduces human error, and advances high-throughput chromosome analysis workflows, addressing a key bottleneck in chromosome biology research.

Chromosome segmentation↗

PubMed2025

Predicting emergent phenotypes from single cell populations using CELLECTION.

Biological systems exhibit emergent phenotypes that arise from the collective behavior of individual components, such as whole-organ functions that arise from the coordinated activity of its individual cells, or organism-level phenotypes that result from the functional interplay of collections of genes in the genome. We present CELLECTION, a deep learning framework that learns to associate subgroups of instances with different emergent phenotypes. We show CELLECTION enables interpretable predictions for heterogeneous tasks, including disease classification, identification of disease-associated cell subtypes, alignment of developmental stages between human model systems, and even predicting relative hand-wing indices across the avian lineage. CELLECTION therefore provides a scalable and flexible framework for identifying key cellular or genetic signatures underlying complex traits in development, disease, and evolution.

Journal Article↗

PubMed2025

Sensitive, direct detection of non-coding off-target base editor unwinding and editing in primary cells.

Base editors create precise nucleotide changes in DNA, but their off-target activity remains challenging to quantify. Here, we develop and deploy a direct, in cellulo sequencing assay that simultaneously measures both Cas9-mediated unwinding and deaminase editing of genomic DNA (beCasKAS). Our strategy nominates >460-fold more potential off-target sites than other methods by enriching for Cas9-dependent R-loops immediately preceding editing. Using beCasKAS in primary human T-cells, we observe that mRNA-encoded ABE8e and PAMless ABE8e-SpRY base editors have distinct off-target profiles that can be mitigated by optimizing mRNA dose. Finally, we combine beCasKAS with base-resolution deep learning models to risk-stratify off-target edits by their likelihood of epigenetic dysregulation. Collectively, beCasKAS offers a sensitive and facile tool to optimize the balance between base editor on- and off-target activity.

Journal Article↗

PubMed2026

Linking cortical structure and delirium in the elderly: insights from cohort study and shared genetic risk analysis.

BACKGROUND: This study aimed to assess the association between regional cortical changes measured via baseline magnetic resonance imaging (MRI) and the incidence of delirium. METHODS: Observational associations were assessed using a prospective cohort from the UK Biobank and an independent clinical cohort. The population-based study included participants aged 60 years or older who had undergone structural brain MRI since 2014. Regional cortical volume, mean thickness, and surface area were extracted based on the Desikan-Killiany cortical atlas. Delirium was defined using ICD-10 diagnostic codes. Additionally, preoperative brain MRI images from participants in another cohort were collected and automatically segmented using deep learning algorithms to obtain cortical measurements. Logistic analysis was performed to investigate the associations between cerebral cortical structure and delirium risk. Lastly, genome-wide association study data derived from the ENIGMA Consortium and FinnGen Biobank were utilized to conduct conditional/conjunctional false discovery rate (cond/conjFDR) analyses to identify shared genetic loci associated with cortical structures and delirium. RESULTS: This observational analysis included 31,890 participants from the UK Biobank and 152 participants from an independent cohort. In the UK Biobank cohort, decreased cortical thickness in the 17 regions was associated with a significantly increased risk of delirium. Similarly, a preoperative reduction in cortical volume in 7 regions was associated with an increased risk of delirium in the independent cohort. Besides, 100 single-nucleotide polymorphisms (SNPs) were identified as significantly associated with cortical structures when conditioned on delirium. Finally, colocalization analysis demonstrated that these pleiotropic risk loci modulated the expression of NT5C2, RGP1, CCDC25, TPM2, EEF1AKMT2, IQANK1 and LHPP in blood and brain tissues. CONCLUSION: Regional cortical atrophy is associated with an increased risk of delirium in the elderly. Brain MRI examinations may be beneficial for preoperative delirium risk assessment in elderly individuals undergoing elective surgery.

Humans↗

PubMed2026

Haplotype-aware long-read error correction.

Error correction of long reads is an important initial step in genome assembly workflows. For organisms with ploidy greater than one, it is important to preserve haplotype-specific variation during read correction. This challenge has driven the development of several haplotype-aware correction methods. However, existing methods are based on either ad-hoc heuristics or deep learning approaches. In this paper, we introduce a rigorous formulation for this problem. Our approach builds on the minimum error correction framework used in reference-based haplotype phasing. We prove that the proposed formulation for error correction of reads in de novo context, i.e., without using a reference genome, is NP-hard. To make our exact algorithm scale to large datasets, we introduce practical heuristics. Experiments using PacBio HiFi sequencing datasets from human and plant genomes show that our approach achieves accuracy comparable to state-of-the-art methods. Implementation: https://github.com/at-cg/HALE .

Clustering↗

PubMed2026

The Landmark Series: Mutation-Based Therapy of Pancreatic Cancer.

BACKGROUND: Pancreatic ductal adenocarcinoma (PDAC) remains a highly lethal malignancy with limited long-term survival despite advances in surgery and systemic therapy. PATIENTS: The population of interest comprises patients with PDAC characterized by targetable molecular alterations and biologically distinct transcriptomic subtypes. METHODS: We performed a narrative review of landmark and contemporary clinical trials, translational studies, and emerging molecular-classification platforms relevant to precision oncology in PDAC. RESULTS: Growing understanding of PDAC molecular biology has identified putative genetic mutations, including homologous recombination repair deficiency, mismatch repair deficiency, and mutated KRAS, enabling the development of targeted therapies and precision treatment strategies. Concurrently, transcriptomic profiling has revealed biologically distinct molecular subtypes associated with differences in prognosis and therapeutic response. Emerging tools such as molecular classifiers, deep learning models, and multiomic platforms may further refine patient selection and treatment personalization. CONCLUSIONS: This review highlights contemporary efforts of novel targeted therapies, ongoing advances in molecular subtyping, and the evolving role of precision oncology in improving outcomes for patients with PDAC.

Genomic alterations↗

PubMed2025

Capturing continuous, long timescale behavioral changes in Drosophila melanogaster postural data.

Animal behavior spans many timescales, from short, seconds-scale actions to daily rhythms over many hours to life-long changes during aging. To access longer timescales of behavior, we continuously recorded individual Drosophila melanogaster at 100 frames per second for up to 7 days at a time in featureless arenas on sucrose-agarose media. We use the deep learning framework SLEAP to produce a full-body postural dataset for 47 individuals resulting in nearly 2 billion pose instances. We identify stereotyped behaviors such as grooming, proboscis extension, and locomotion and use the resulting ethograms to explore how the flies' behavior varies across time of day and days in the experiment. We find distinct daily patterns in all stereotyped behaviors, adding specific information about trends in different grooming modalities, proboscis extension duration, and locomotion speed to what is known about the D. melanogaster circadian cycle. Using our holistic measurements of behavior, we find that the hour after dawn is a unique time point in the flies' daily pattern of behavior, and that the behavioral composition of this hour tracks well with other indicators of health such as locomotion speed and the fraction of time spend moving vs. resting. The method, data, and analysis presented here give us a new and clearer picture of D. melanogaster behavior across timescales, revealing novel features that hint at unexplored underlying biological mechanisms.

Animals↗

PubMed2025

NextVir: Enabling classification of tumor-causing viruses with genomic foundation models.

MOTIVATION: Oncoviruses, pathogens known to cause or increase the risk of cancer, include both common viruses such as human papillomaviruses and rarer pathogens such as human T-lymphotropic viruses. Computational methods for detecting viral DNA from data acquired by modern DNA sequencing technologies have enabled studies of the association between oncoviruses and cancers. Those studies are rendered particularly challenging when multiple species of oncovirus are present in a tumor sample. In such scenarios, merely detecting the presence of a sequencing read of viral origin is insufficiently informative-instead, a more precise characterization of the viral content in the sample is required. RESULTS: We address this need with NextVir, to our knowledge the first multi-class viral classification framework that adapts genomic foundation models to detecting and classifying sequencing reads of oncoviral origin. Specifically, NextVir explores several foundation models-DNABERT-S, Nucelotide Transformer, and HyenaDNA-and efficiently fine-tunes them to enable accurate identification of the sequencing reads' origin. The results demonstrate superior performance of the proposed framework over existing deep learning methods and suggest downstream potential for foundational models in genomics.

Humans↗