PubMed Health⌕ Search

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 253 records · Page 14Linked to original sources
PubMed2025

An updated compendium and reevaluation of the evidence for nuclear transcription factor occupancy over the mitochondrial genome.

In most eukaryotes, mitochondrial organelles contain their own genome, usually circular, which is the remnant of the genome of the ancestral bacterial endosymbiont that gave rise to modern mitochondria. Mitochondrial genomes are dramatically reduced in their gene content due to the process of endosymbiotic gene transfer to the nucleus; as a result most mitochondrial proteins are encoded in the nucleus and imported into mitochondria. This includes the components of the dedicated mitochondrial transcription and replication systems and regulatory factors, which are entirely distinct from the information processing systems in the nucleus. However, since the 1990s several nuclear transcription factors have been reported to act in mitochondria, and previously we identified 8 human and 3 mouse transcription factors (TFs) with strong localized enrichment over the mitochondrial genome using ChIP-seq (Chromatin Immunoprecipitation) datasets from the second phase of the ENCODE (Encyclopedia of DNA Elements) Project Consortium. Here, we analyze the greatly expanded in the intervening decade ENCODE compendium of TF ChIP-seq datasets (a total of 6,153 ChIP experiments for 942 proteins, of which 763 are sequence-specific TFs) combined with interpretative deep learning models of TF occupancy to create a comprehensive compendium of nuclear TFs that show evidence of association with the mitochondrial genome. We find some evidence for chrM occupancy for 50 nuclear TFs and two other proteins, with bZIP TFs emerging as most likely to be playing a role in mitochondria. However, we also observe that in cases where the same TF has been assayed with multiple antibodies and ChIP protocols, evidence for its chrM occupancy is not always reproducible. In the light of these findings, we discuss the evidential criteria for establishing chrM occupancy and reevaluate the overall compendium of putative mitochondrial-acting nuclear TFs.

Genome, Mitochondrial↗
PubMed2026

Graph neural network-based risk stratification of prostate cancer using gene expression and SHAP interpretability.

Accurate risk stratification is essential for guiding treatment decisions and preventing over treatment of prostate cancer, which remains one of the most prevalent cancers among adult men. While the Gleason score, obtained from prostate biopsies, is routinely used to assess tumor aggressiveness, the biopsy procedure carries risks such as pain, infection, and, in some cases, serious complications such as sepsis. In this study, we proposed an artificial intelligence-based framework that integrates mRNA expression profiles with functional interaction networks to classify prostate cancer patients into low-, medium-, and high-risk groups defined by Gleason scores. The pipeline comprised five steps: (1) data collection from The Cancer Genome Atlas (TCGA), (2) preprocessing of gene expression data, (3) two-stage feature selection to identify informative biomarkers, (4) risk classification using a dual-branch graph neural network (GNN) that combines gene-gene interaction graphs with sample-level expression features, and (5) model interpretation using SHAP to quantify feature contributions. Differentially expressed genes were identified in the High (ASPN, GMNN, PEBP4, C2, KNCK17), Medium (C2, IGSF1, ASPN, CDKN3, AMH), and Low (TNMD, VWA5B2, ST6GALNAC5, CYP3A5, PHGR1) risk groups, underscoring the molecular heterogeneity of disease progression. On an independent held-out test set, the model achieved AUCs of 0.86, 0.88, and 0.95 for the low-, medium-, and high-risk groups, respectively, with an overall accuracy of 80%. These results suggest that combining GNN-based modeling with explainable AI can capture both global and local molecular patterns relevant to tumor aggressiveness. However, as the model was developed and evaluated solely on the TCGA cohort, the findings should be regarded as exploratory, and external validation will be required to establish generalizability. Within these limitations, the proposed framework highlights the potential of molecular profiling and graph-based deep learning to support more precise, potentially less invasive, risk assessment and individualized treatment planning in prostate cancer.

Prostatic Neoplasms↗
PubMed2026

AI-Driven Precision Medicine in Alzheimer's Disease: Drug Repurposing, Digital Therapeutics and Clinical Decision Support.

Alzheimer's Disease (AD) is a neurodegenerative disease that causes significant clinical, social, and economic burden worldwide. Despite improvements in understanding its multifaceted pathogenesis, current treatments are mostly symptomatic and ineffective across varied patient populations. To overcome these constraints, AI-driven precision medicine allows tailored risk assessment, treatment selection, and disease monitoring. This review covers AI's role in AD precision medicine, focusing on drug repurposing, digital therapies and clinical decision support systems. Machine and deep learning models are used to predict medication response, integrate heterogeneous data sources such as genomics, transcriptomics, neuroimaging and electronic health records, and uncover pharmacogenomic treatment success factors. The paper covers AIenabled precision pharmacology, including tailored dosing algorithms, adaptive therapeutic monitoring, and adverse drug reaction prediction. Bioinformatics-based target identification, network pharmacology, graphbased AI models, virtual screening, and real-world and clinical data validation are emphasized in AI-driven medication repurposing. AI-powered digital treatments like personalized cognitive training platforms, wearable- derived digital biomarkers, virtual and mixed reality interventions, adherence monitoring, and digital twins for therapy optimization have been discussed. AI-based clinical decision support systems are also thoroughly assessed for clinical value, accuracy, and explainability in disease subtyping, trajectory prediction, and risk stratification in preclinical and prodromal AD. Despite these promises, data heterogeneity, algorithmic bias, legal barriers, and privacy concerns exist. Federated learning enables safe multi-center collaboration and hybrid AI-human approaches, and it represents the future. AI's ability to alter AD care opens the door to precision medicine paradigms that use repurposed medications, digital tools and intelligent decision-making to improve patient outcomes.

Alzheimer’s disease↗
PubMed2026

Artificial Intelligence for Natural Products Discovery and Development.

Natural products (NPs) remain a cornerstone of modern drug discovery, offering stereochemical complexity and diverse bioactivities that precisely modulate therapeutic targets, refined through billions of years of evolution. However, their research has long been hindered by inefficient, empirical workflows, high resource consumption, structural complexity, and the "multicomponent, multi-target" nature of their mechanisms. The exponential growth of genomic, metabolomic, and spectral data has overwhelmed conventional analytical methods, exposing critical bottlenecks in handling high-dimensional, heterogeneous datasets that exceed human interpretive capacity. Artificial intelligence (AI) is emerging as a transformative paradigm to address these challenges, integrating multi-omics and chemical data to shift NP research from fragmented empiricism toward mechanism-driven, precision-oriented development. By leveraging deep learning architectures- including graph neural networks, Transformers, and diffusion-based generative models-AI enables systematic decoding of NP biosynthesis, automated structure elucidation, rational target identification, knowledge extraction from vast unstructured scientific literature, and de novo molecular design. This review comprehensively surveys recent advances in AI applications across the full NP discovery and development pipeline, encompassing genome mining, structure-based and ligand-based virtual screening, multimodal structural characterization, lead optimization, and biosynthetic pathway engineering. We further examine the emerging roles of protein-centric, molecule- centric, and multimodal foundation models, as well as large language models, in bridging genotype-to-chemotype gaps and unlocking unstructured scientific knowledge. Finally, we discuss critical challenges including data scarcity, representational limitations for complex stereochemistry, physical plausibility in generative models, and the urgent need for experimental validation, while outlining future directions toward autonomous experimentation, closed-loop optimization, and human-AI collaborative discovery.

Artificial intelligence↗
PubMed2026

A voyage of reprogrammable metabolic bioengineering reshapes plant defense: from editing tools to synthetic systems.

Metabolic bioengineering has emerged as a transformative approach for reshaping plant defense by targeting intrinsic biosynthetic pathways to enhance immunity in modern agriculture. Moving beyond proof-of-concept metabolomics to broad-spectrum programmable pathway engineering addresses gaps in plant rational design and optimizes resilience in response to diverse environmental cues. This review aims to comprehensively highlight the transition of innovative approaches to phenolics, alkaloids, flavonoids, terpenoids, and benzoxazinoids, inferring adaptive reprogramming that mediates the growth-defense balance and functions as molecular sentinels in plants. Furthermore, decoding the volatile metabolome reveals a dynamic signaling interface that influences defense responses and stress-induced plant-microbe interactions, with the shikimate, jasmonate, and salicylate pathways functioning as central hubs for microbial deterrence and priming immune memory. Recent developments in multi-scalar genome-editing strategies, including CRISPR-driven combinatorial edits, enzyme orthogonalization, fluxomics, and spatially resolved multi-omics, reconfigure central and specialized metabolic fluxes toward improved defense function and regulation. Additionally, emerging tools, such as WUSCHEL2 and BABY BOOM transcriptional modules, and artificial engineering strategies integrating deep learning model-driven predictions facilitate rapid development of synthetic genetic circuits and support a predictive engineering of plants. Moreover, Mass spectrometry imaging (MSI) in spatial metabolomics enables to obtain structures and locations of unidentified endogenous metabolites within cells and tissues. Overall, this review emphasizes a diverse array of primary and secondary metabolites, spanning molecular concepts to recent advances in plant immune mechanisms. It also illustrates new frontiers in programmable metabolic engineering that accelerate the understanding of plant-microbe-metabolite cross-talks, offering strategies to improve plant resistance and advance sustainable agricultural solutions.

metabolic bioengineering↗
PubMed2026

Cross-Device Adaptation of Mirai for Mammography-Based Breast Cancer Risk Prediction.

Fine-tuning can adapt pretrained medical imaging models to new clinical datasets, but device-specific domain shifts may limit generalizability. We evaluated Mirai, a mammography-based deep learning model for breast cancer risk prediction, in a large screening cohort containing Hologic and General Electric (GE) full-field digital mammography systems, including GE Premium View (GE PV) and Tissue Equalization (GE TE) post-processing software. Native Mirai showed lower performance on TE images than on Hologic or PV images. Fine-tuning on TE images improved TE performance, particularly for short-term risk prediction, but substantially reduced performance on Hologic images, consistent with catastrophic forgetting. To mitigate this effect, we developed a device-invariant model using interleaved multi-device sampling and conditional adversarial training. This approach largely restored Hologic performance while maintaining improved TE performance, providing better robustness across heterogeneous imaging platforms. Comparison of cumulative and annual risk AUCs over a five-year time horizon further showed that performance gains were driven mainly by short- and intermediate-term predictions. These findings highlight both the value and dangers of device-specific fine-tuning and support balanced domain-adaptation strategies for deploying mammography-based risk models across diverse clinical imaging environments.

Journal Article↗
PubMed2005

Ambulatory teaching: do approaches to learning predict the site and preceptor characteristics valued by clerks and residents in the ambulatory setting?

BACKGROUND: In a study to determine the site and preceptor characteristics most valued by clerks and residents in the ambulatory setting we wished to confirm whether these would support effective learning. The deep approach to learning is thought to be more effective for learning than surface approaches. In this study we determined how the approaches to learning of clerks and residents predicted the valued site and preceptor characteristics in the ambulatory setting. METHODS: Postal survey of all medical residents and clerks in training in Ontario determining the site and preceptor characteristics most valued in the ambulatory setting. Participants also completed the Workplace Learning questionnaire that includes 3 approaches to learning scales and 3 workplace climate scales. Multiple regression analysis was used to predict the preferred site and preceptor characteristics as the dependent variables by the average scores of the approaches to learning and perception of workplace climate scales as the independent variables. RESULTS: There were 1642 respondents, yielding a 47.3% response rate. Factor analysis revealed 7 preceptor characteristics and 6 site characteristics valued in the ambulatory setting. The Deep approach to learning scale predicted all of the learners' preferred preceptor characteristics (beta = 0.076 to beta = 0.234, p < .001). Valuing preceptor Direction was more strongly associated with the Surface Rational approach (beta = .252, p < .001) and with the Surface Disorganized approach to learning (beta = .154, p < 001) than with the Deep approach. The Deep approach to learning scale predicted valued site characteristics of Office Management, Patient Logistics, Objectives and Preceptor Interaction (p < .001). The Surface Rational approach to learning predicted valuing Learning Resources and Clinic Set-up (beta = .09, p = .001; beta = .197, p < .001). The Surface Disorganized approach to learning weakly negatively predicted Patient Logistics (beta = -.082, p = .003) and positively the Learning Resources (beta = .088, p = .003). Climate factors were not strongly predictive for any studied characteristics. Role Modeling and Patient Logistics were predicted by Supportive Receptive climate (beta = .135, p < .001, beta = .118, p < .001). CONCLUSION: Most site and preceptor characteristics valued by clerks and residents were predicted by their Deep approach to learning scores. Some characteristics reflecting the need for good organization and clear direction are predicted by learners' scores on less effective approaches to learning.

Adult↗
PubMed2002

Postal survey of approaches to learning among Ontario physicians: implications for continuing medical education.

OBJECTIVES: To understand the approaches to learning of practising physicians in their workplace and to assess the relation of these approaches to their motivation for, preferred methods of, and perceived barriers to continuing medical education. DESIGN: Postal survey of 800 Ontario physicians. PARTICIPANTS: 373 physicians who responded. MAIN OUTCOME MEASURES: Correlations of approaches to learning and perceptions of workplace climate with methods, motives, and barriers to continuing medical education. RESULTS: Perceived heavy workload was significantly associated with the surface disorganised (r=0.463, P<0.01) and surface rational approach (r=0.135, P<0.05) to learning. The deep approach to learning was significantly correlated with a perception of choice-independence and a supportive-receptive climate at work (r=0.341 and 0.237, P<0.01). Physicians who adopt a deep approach to learning seem to be internally motivated to learn, whereas external motivation is associated with surface approaches to learning. Heavy workload and a surface disorganised approach to learning were correlated with every listed barrier to continuing medical education. The deep approach to learning was associated with independent learning activities and no barriers. CONCLUSIONS: Perception of the workplace climate affects physicians' approaches to learning at work and their motivation for and perceived barriers to continuing medical education. Younger, rural, family physicians may be most vulnerable to feeling overworked and adopting less effective approaches to learning. Further work is required to determine if changing the workplace environment will help physicians learn more effectively.

Attitude of Health Personnel↗
PubMed2006

Deep dissection: motivating students beyond rote learning in veterinary anatomy.

The profusion of descriptive, factual information in veterinary anatomy inevitably creates pressure on students to employ surface learning approaches and "rote learning." This phenomenon may contribute to negative perceptions of the relevance of anatomy as a discipline. Thus, encouraging deep learning outcomes will not only lead to greater satisfaction for both instructors and learners but may have the added effect of raising the profile of and respect for the discipline. Consideration of the literature reveals the broad scope of interventions required to motivate students to go beyond rote learning. While many of these are common to all disciplines (e.g., promoting active learning, making higher-order goals explicit, reducing content in favor of concepts, aligning assessment with outcomes), other factors are peculiar to anatomy, such as the benefits of incorporating clinical tidbits, "living anatomy," the anatomy museum, and dissection classes into a "learning context" that fosters deep approaches. Surprisingly, the 10 interventions discussed focus more on factors contributing to student perceptions of the course than on drastic changes to the anatomy course itself. This is because many traditional anatomy practices, such as dissection and museum-based classes, are eminently compatible with active, student-centered learning strategies and the adoption of deep learning approaches by veterinary students. Thus the key to encouraging, for example, dissection for deep learning ("deep dissection") lies more in student motivation, personal engagement, curriculum structure, and "learning context" than in the nature of the learning activity itself.

Anatomy↗
PubMed2006

The use of deep and surface learning strategies among students learning English as a foreign language in an Internet environment.

BACKGROUND: The learning context is learning English in an Internet environment. The examination of this learning process was based on the Biggs and Moore's teaching-learning model (Biggs & Moore, 1993). AIM: The research aims to explore the use of the deep and surface strategies in an Internet environment among EFL students who come from different socio-economic backgrounds. The results of the research may add an additional level to the understanding of students' functioning in the Internet environment. SAMPLE: One hundred fourty-eight Israeli junior and high school students participated in this research. METHODS: The methodology was based on special computer software: Screen Cam, which recorded the students' learning process. In addition, expert judges completed a questionnaire which examined and categorized the students' learning strategies. RESULTS: The research findings show a clear preference of participants from all socio-economic backgrounds towards the surface learning strategy. The findings also showed that students from the medium to high socio-economic background used both learning strategies more frequently than low socio-economic students. CONCLUSIONS: The results reflect the habits that students acquire during their adjustment process throughout their education careers. A brief encounter with the Internet learning environment apparently cannot change norms or habits, which were acquired in the non-Internet learning environment.

Female↗
PubMed2006

Learning-induced plasticity in deep cerebellar nucleus.

Evidence that cerebellar learning involves more than one site of plasticity comes from, in part, pavlovian eyelid conditioning, where disconnecting the cerebellar cortex abolishes one component of learning, response timing, but spares the expression of abnormally timed short-latency responses (SLRs). Here, we provide evidence that SLRs unmasked by cerebellar cortex lesions are mediated by an associative form of learning-induced plasticity in the anterior interpositus nucleus (AIN) of the cerebellum. We used pharmacological inactivation and/or electrical microstimulation of various sites afferent and efferent to the AIN to systematically eliminate alternative candidate sites of plasticity upstream or downstream from this structure. Collectively, the results suggest that cerebellar learning is mediated in part by plasticity in target nuclei downstream of the cerebellar cortex. These data demonstrate an instance in which an aspect of associative learning, SLRs, can be used as an index of plasticity at a specific site in the brain.

Animals↗
PubMed2006

Portfolio as a method for continuous assessment in an undergraduate health education programme.

A portfolio assessment system has been introduced into a biomedical science programme to promote both continuous learning and deep approaches to learning. Attention has been focused on creating harmony between the assessment system and the PBL curriculum of the programme. Biomedicine and laboratory work are central in the curriculum. The portfolio included evidence of laboratory work, personal reflections and certificates from the PBL tutor. The portfolio was assessed on three occasions over 20 weeks. The grades were 'pass' or 'fail'. The tutor certificate appeared to be a crucial part of the portfolio since a 'fail' in this part usually led to an overall 'fail'. Both students and teachers were concerned about ensuring that enough factual knowledge, as measured by a traditional test, had been achieved. The agreement was good enough for the pass or fail level but some expected differences were found at the detailed level. The course, including the portfolio, was evaluated orally during weekly whole-group meetings and using a questionnaire at the end. The students felt comfortable with the portfolio system and preferred it to a traditional test. The teachers felt that they needed to develop their teacher-student discussion skills and to improve their feedback on the reflections. Peer assessment between students is proposed as a line of action to enhance the credibility of the crucial tutor certificate. The portfolio might be an efficient tool for the students to concentrate their efforts on the most central concepts of medical laboratory work. The model will be developed through further discussions and better consensus among faculty.

Adult↗
PubMed2025

Transfer learning with multiomics integration and deep neural networks reveals drug resistance mechanisms in cancer.

Drug resistance remains one of the primary challenges in effective cancer therapy. In this study, we employed a deep neural network (DNN)-based transfer learning (TL) approach to predict drug response and uncover drug resistance mechanisms. We integrated gene expression, somatic mutation, and copy number aberration (CNA) data with drug response profiles using multi-omics integration (MI). We used the Genomics of Drug Sensitivity in Cancer (GDSC) data for training and incorporated drugs with same pathways into the training models. We then evaluated drug response predictions on independent in-vivo PDX Encyclopedia (PDX) and ex-vivo the Cancer Genome Atlas (TCGA) datasets. In addition, we conducted pathway enrichment analyses to elucidate the mechanisms underlying drug resistance for paclitaxel, 5-fluorouracil (5-FU), gemcitabine, and cetuximab. We also applied Fisher's exact test (FET) to assess potential associations between drug resistance and the presence of mutations or CNAs. Our pan-drug models outperformed other methods based on the area under the precision-recall curve (AUCPR). Our pathway enrichment analyses revealed LDHB-mediated pyruvate metabolism and FYN-mediated focal adhesion might have pivotal roles in paclitaxel resistance, while PINK1-mediated mitophagy might be critical in 5-FU resistance. In addition to transcriptional activation, FET suggested that CNAs in LDHB and PINK1 may also be associated with resistance to paclitaxel and 5-FU, respectively. Furthermore, enrichment results for paclitaxel and cetuximab indicated shared resistance mechanisms between the two drugs. Importantly, our findings are consistent with prior experimental studies, providing literature-based validation of our results. Overall, our DNN-based TL approach achieved strong predictive performance across PDX & TCGA datasets and enrichment analyses provided valuable biological insights into drug resistance mechanisms.

Humans↗
PubMed1998

Differential roles of cerebellar cortex and deep cerebellar nuclei in learning and retention of a spatial task: studies in intact and cerebellectomized lurcher mutant mice.

Lurcher mutant mice (+/Lc) exhibit a massive loss of neurons in the cerebellar cortex and the inferior olivary nucleus, while deep cerebellar nuclei are essentially intact. To discriminate the relative participation of the cerebellar cortex and deep structures in learning and memory, 3 to 6-month-old +/Lc mice were subjected to a spatial learning task derived from the Morris water escape. They were able to learn to escape as well as their strain-matched controls (+/+). Seven days later, their scores showed that they had memorized the spatial environment but not as accurately as +/+ mice. Cerebellectomy before training did not significantly alter the escape learning capabilities of either group, whereas cerebellectomy performed after learning completely abolished retention in +/+, as well as in +/Lc, mice. These results suggest that the cerebellum, although not necessary for learning a spatial task, plays a crucial role in its retention, and that the storing structure of spatial information differs in +/+ and +/Lc mice.

Analysis of Variance↗
PubMed2005

Can we influence medical students' approaches to learning?

Students use three approaches to learning and studying: deep, surface and strategic. These are influenced by the learning environment. In response to the General Medical Council's report 'Tomorrow's Doctors', the second year of the medical course at the University of Edinburgh was changed to promote deep learning, with learning objectives constructed according to the SOLO taxonomy, learning methods such as problem-based learning and constructively aligned written assignments and examinations. The Approaches to Study Skills Inventory for Students (ASSIST) was used to evaluate the effect of these changes. Scores were highest for deep approaches and lowest for surface approaches and showed almost no change during the course. There are various possible explanations. The students already scored highly on deep approaches at the beginning of Year 2 and it may be difficult to increase the deep scores further, particularly over the relatively short period of the study. Alternatively, the effect of the changes in learning environment may not be strong enough to change entrenched approaches which have hitherto been successful.

Cohort Studies↗
PubMed2005

A comparison of responses to group learning between first-year Asian and first-year Australian veterinary science students.

INTRODUCTION: Group learning has been used to enhance deep (long-term) learning and promote life skills, such as decision making, communication, and interpersonal skills. However, with increasing multiculturalism in higher education, there is little information available as to the acceptance of this form of learning by Asian students or as to its value to them. METHODOLOGY: Group-learning projects, incorporating a seminar presentation, were used in first-year veterinary anatomical science classes over two consecutive years (2003 and 2004) at the School of Veterinary Science, University of Queensland. Responses of Australian and Asian students to survey forms evaluating the learning experience were analyzed and compared. RESULTS: All students responded positively to the group learning, indicating that it was a useful learning experience and a great method for meeting colleagues. There were no significant differences between Asian and Australian students in overall responses to the survey evaluating the learning experience, except where Asian students responded significantly higher than Australian students in identifying specific skills that needed improving. CONCLUSIONS: Group learning can be successfully used in multicultural teaching to enhance deep learning. This form of learning helps to remove cultural barriers and establish a platform for continued successful group learning throughout the program.

Adult↗