Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “active learning”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

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

At least 19 recordsLinked to original sources
PubMed2025

Active learning of enhancers and silencers in the developing neural retina.

Deep learning is a promising strategy for modeling cis-regulatory elements. However, models trained on genomic sequences often fail to explain why the same transcription factor can activate or repress transcription in different contexts. To address this limitation, we developed an active learning approach to train models that distinguish between enhancers and silencers composed of binding sites for the photoreceptor transcription factor cone-rod homeobox (CRX). After training the model on nearly all bound CRX sites from the genome, we coupled synthetic biology with uncertainty sampling to generate additional rounds of informative training data. This allowed us to iteratively train models on data from multiple rounds of massively parallel reporter assays. The ability of the resulting models to discriminate between CRX sites with identical sequence but opposite functions establishes active learning as an effective strategy to train models of regulatory DNA. A record of this paper's transparent peer review process is included in the supplemental information.

Retina↗
PubMed2023

Active learning of enhancer and silencer regulatory grammar in photoreceptors.

Cis-regulatory elements (CREs) direct gene expression in health and disease, and models that can accurately predict their activities from DNA sequences are crucial for biomedicine. Deep learning represents one emerging strategy to model the regulatory grammar that relates CRE sequence to function. However, these models require training data on a scale that exceeds the number of CREs in the genome. We address this problem using active machine learning to iteratively train models on multiple rounds of synthetic DNA sequences assayed in live mammalian retinas. During each round of training the model actively selects sequence perturbations to assay, thereby efficiently generating informative training data. We iteratively trained a model that predicts the activities of sequences containing binding motifs for the photoreceptor transcription factor Cone-rod homeobox (CRX) using an order of magnitude less training data than current approaches. The model's internal confidence estimates of its predictions are reliable guides for designing sequences with high activity. The model correctly identified critical sequence differences between active and inactive sequences with nearly identical transcription factor binding sites, and revealed order and spacing preferences for combinations of motifs. Our results establish active learning as an effective method to train accurate deep learning models of cis-regulatory function after exhausting naturally occurring training examples in the genome.

Journal Article↗
PubMed2025

Boolean matrix logic programming for active learning of gene functions in genome-scale metabolic network models.

Reasoning about hypotheses and updating knowledge through empirical observations are central to scientific discovery. In this work, we applied logic-based machine learning methods to drive biological discovery by guiding experimentation. Genome-scale metabolic network models (GEMs) - comprehensive representations of metabolic genes and reactions - are widely used to evaluate genetic engineering of biological systems. However, GEMs often fail to accurately predict the behaviour of genetically engineered cells, primarily due to incomplete annotations of gene interactions. The task of learning the intricate genetic interactions within GEMs presents computational and empirical challenges. To efficiently predict using GEM, we describe a novel approach called Boolean Matrix Logic Programming (BMLP) by leveraging Boolean matrices to evaluate large logic programs. We developed a new system, [Formula: see text], which guides cost-effective experimentation and uses interpretable logic programs to encode a state-of-the-art GEM of a model bacterial organism. Notably, [Formula: see text] successfully learned the interaction between a gene pair with fewer training examples than random experimentation, overcoming the increase in experimental design space. [Formula: see text] enables rapid optimisation of metabolic models to reliably engineer biological systems for producing useful compounds. It offers a realistic approach to creating a self-driving lab for biological discovery, which would then facilitate microbial engineering for practical applications.

Active learning↗
PubMed1979

[Rat brain nuclease activity during learning with emotionally different reinforcement].

Acid and alkaline activity of nucleases of the rats trained with emotional positive or negative reinforcement was estimated in the neocortex, hippocampus, midbrain, and in caudal portions of the brain-stem, using native and denaturated DNA as a substrate. The results showed the total increase in nuclease activity during learning. Nevertheless the dynamics of enzyme activation was different depending on the emotional state of rats during learning. The most active enzyme was found in the caudal portion of the brain-stem.

Animals↗
PubMed1975

[On the effect of some inhibitors of proteinbiosynthesis on activity and learning behavior of goldfish (Carassius auratus auratus L)].

Concerning the problems of learning and memory there is a distinction of a short term memory (STM) and a long term memory (LTM). It is supposed that the STM is an electrical phenomenon, whereas the LTM depends on material changes. The assumed materials are RNA, proteins, lipids, amines etc, and the primary carrier of the information is DNA. But there is a discrepancy: learning-specificity is based on environmental changes, but not the structure of DNA. For the investigation of this, we trained goldfish in a shock-free task to take food from coloured cups under the influence of inhibitors of the proteinbiosynthesis. There was no inhibition on memory-processes in our experiments.

Animals↗
PubMed2026

Artificial intelligence for anticancer drug discovery from natural products of macroalgae and sponges: A systematic review.

Marine natural products (MNPs) from macroalgae and marine sponges have inspired clinically important anticancer agents, including the cytarabine pharmacophore and the eribulin scaffold, while cyanobacterial dolastatin chemistry supplies the auristatin payloads of several marine-inspired antibody-drug conjugates (ADCs) such as brentuximab vedotin. Artificial intelligence (AI) methods, encompassing both classical machine learning (ML) with hand-engineered features and modern deep learning (DL) with many-layered neural networks, are increasingly supporting key decisions in natural-product anticancer drug discovery, including bioactivity prediction, target identification, absorption, distribution, metabolism, excretion and toxicity (ADMET) filtering, generative analogue design, and the selection of preclinical candidates. DL architectures relevant to this field include graph neural networks, transformer-based molecular generators, diffusion models for protein-ligand docking, and convolutional networks for mass spectrometry, while classical ML contributes interpretable fingerprint-based bioactivity models and molecular networking for dereplication. This review follows a systematic literature review methodology to organize the landscape of AI methods now applied to MNP anticancer discovery, distinguishing ML and DL approaches where relevant, situating them within the chemical context of macroalgal and sponge-derived oncology leads, and critically examining published case studies, including validation level (computational, in vitro, in vivo, clinical). The principal bottleneck for medical translation has shifted partly from algorithmic capability toward data infrastructure and experimental validation. Sparse, heterogeneous, and taxonomically biased bioactivity records limit what current models can learn and reduce the reliability of AI-prioritized candidates entering the preclinical pipeline. A roadmap is proposed that prioritizes open MNP-specific benchmarks, symbiont-aware modeling, and active learning loops with synthesizability and ADMET constraints. These AI workflows may accelerate the prioritization of marine-derived anticancer leads and support earlier, more evidence-based translational decisions in oncology drug development.

Biological Products↗
PubMed2026

Individual differences in brain dynamics across a social cognition network induced by cortico-cerebellar tDCS in adults with autism spectrum disorder (ASD).

Autism spectrum disorder (ASD) is a neurodevelopmental condition with core diagnostic domains of social communication impairments, restricted interests and repetitive behaviors. Idiosyncratic brain organization is a potential hallmark of ASD. Previous transcranial direct current stimulation (tDCS) studies often targeted dorsolateral prefrontal cortex, with changes oin brain dynamics averaged across the cohort. We utilized a magnetoencephalographic (MEG) array to characterize individual differences in brain dynamics induced by cortico-cerebellar tDCS across nodes of a social cognition network. A randomized, sham-controlled, double-blind, within-subject clinical trial was conducted in a cohort of 24 young adults with ASD or high autistic traits. Two separate sessions of computerized social learning activities were combined with verum/sham tDCS, with anodal electrode over right temporoparietal junction (TPJ) and cathode on right deltoid. Following stimulation, theta- and alpha-band activity were evaluated within nodes of a social cognition network: bilateral TPJ, fusiform, medial prefrontal cortex and Crus I/II of cerebellum. Idiosyncratic participant-specific up- and down-regulation of theta- and alpha-band activity occurred across the network. Activity in right Crus I/II, a region inundated by the stimulation current, strongly correlated with the change of activity summed across all cerebral cortical nodes in theta- but not alpha-band. Intrinsic theta-band activity is believed to mediate input/output relationships in cerebellar cortex and to drive synaptic plasticity. These results suggest that theta-band stimulation of cerebellar cortex might be an effective therapy for individuals on the autism spectrum who present with cerebellar hyperactivity.

Humans↗
PubMed1976

Teratopsychogenetic effects apparently produced by nonphysiological neurotransmitter concentrations during brain differentiation.

In male rats treated with pargyline, reserpine or pyridostigmine during neonatal life significant permanent changes of sexual behaviour and conditioned learning behaviour were observed in juvenile and/or adult life. Male sexual activity and learning capacity were permanently decreased in neonatally pargyline- or reserpine-treated animals, but permanently increased in neonatally pyridostigmine-treated rats. These findings suggest that nonphysiological concentrations and/or turnover rates of neurotransmitters, if produced during a critical period of brain differentiation, are able to induce lifelond effective behavioural changes, i.e. teratopsychogenetic effects.

Animals↗
PubMed2025

APNet, an explainable sparse deep learning model to discover differentially active drivers of severe COVID-19.

MOTIVATION: Computational analyses of bulk and single-cell omics provide translational insights into complex diseases, such as COVID-19, by revealing molecules, cellular phenotypes, and signalling patterns that contribute to unfavourable clinical outcomes. Current in silico approaches dovetail differential abundance, biostatistics, and machine learning, but often overlook nonlinear proteomic dynamics, like post-translational modifications, and provide limited biological interpretability beyond feature ranking. RESULTS: We introduce APNet, a novel computational pipeline that combines differential activity analysis based on SJARACNe co-expression networks with PASNet, a biologically informed sparse deep learning model, to perform explainable predictions for COVID-19 severity. The APNet driver-pathway network ingests SJARACNe co-regulation and classification weights to aid result interpretation and hypothesis generation. APNet outperforms alternative models in patient classification across three COVID-19 proteomic datasets, identifying predictive drivers and pathways, including some confirmed in single-cell omics and highlighting under-explored biomarker circuitries in COVID-19. AVAILABILITY AND IMPLEMENTATION: APNet's R, Python scripts, and Cytoscape methodologies are available at https://github.com/BiodataAnalysisGroup/APNet.

COVID-19↗
PubMed2026

Advancing nursing education through social and emotional learning: A systematic review guided by the Collaborative for Academic, Social, and Emotional Learning framework.

BACKGROUND: With Generation Z entering the nursing workforce in growing numbers, strengthening social and emotional learning is critical for academic success, professional adaptation, and safe practice. However, the existing evidence remains fragmented because of varied interventions and inconsistent approaches. OBJECTIVES: This systematic review examined (1) the social and emotional learning essential for nursing students and nurses within the Collaborative for Academic, Social, and Emotional Learning framework, (2) their impact on educational and clinical outcomes, and (3) implications for advancing nursing education and practice. METHODS: Following Joanna Briggs Institute methodology and Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, five international (PubMed, EMBASE, CINAHL, PsycINFO, Cochrane) and three Korean (RISS, KoreaMed, KMBASE) databases were searched up to June 2025. Eighteen studies involving 2,952 participants met the inclusion criteria, including quasi-experimental quantitative studies, descriptive quantitative studies, qualitative studies, and mixed-methods studies. The methodological quality of the included studies was appraised using the Mixed Methods Appraisal Tool. RESULTS: Within the Collaborative for Academic, Social, and Emotional Learning framework, relationship skills and self-management were the most frequently studied competencies, emphasizing teamwork, communication, and stress regulation. Self-awareness and social awareness were underexplored, despite their importance in empathy, resilience, and reflective practice. Responsible decision-making was the least studied competency, despite its importance in ethical reasoning. Social and emotional learning was consistently associated with enhanced adaptation, communication, leadership, relationships, and clinical performance. Effective strategies included blended learning, simulation, reflective activities, and mentorship, which are aligned with Generation Z's learning preferences. CONCLUSION: Although social and emotional learning integration is associated with improvements in educational and clinical outcomes in nursing, current research has largely centered on relational and stress-related competencies while underrepresenting responsible decision-making. To cultivate reflective, empathetic, and ethically grounded nurses, curricula should integrate social and emotional learning through a balanced and structured approach. REGISTRATION: This study was registered on PROSPERO (ID: CRD420251005683).

Humans↗
PubMed1976

[Assessment of the biological age in the animal-experiment (author's transl)].

Experimental investigations of internal and external factors presumably influencing the aging process require an objective assessment of the biological age or vitality respectively by means of as many age parameters as possible. Using the rat, a valuable test animal in experimental gerontology, whose life expectancy of about 40 month allows longitudinal studies, a standard test programm for the estimation of the biological age has been developed. The age parameters used originate from investigations of 1. the tail tendon collagen, 2. the skin, 3. the aorta, 4. the ECG, 5. the lipofuscin content of brain and heart, 6. the tissue respiration of various organs, 7, the motor activity and 8. learning and memory. Using the above-mentioned age parameters a statistical measure for the biological age will be calculated by means of multivariate analysis and will allow the comparison of differeent age-and experimental-groups.

Aging↗
PubMed2026

Activity-dependent DNA methylation and demethylation: epigenetic regulators of learning and memory.

Learning and memory are fundamental cognitive processes that rely on activity-dependent epigenetic mechanisms to shape synaptic and neuronal plasticity. Among these, DNA methylation and demethylation have emerged as pivotal regulators that convert transient neural activity into enduring transcriptional programs. In mammals, DNA methylation marks include 5-methylcytosine (5mC) as well as the less well-established N6-methyladenine (6mA) and the more enigmatic N4-methylcytosine (4mC). Compared with 5mC, the abundance, genomic distribution, and regulatory role of 6mA and 4mC remain incompletely defined, partly due to low abundance and technical challenges, yet these non-canonical marks may provide an additional regulatory layer in specific biological contexts. Accordingly, this review focuses on the best-characterized pathway in the nervous system, 5mC and its activity-regulated oxidative turnover. This system comprises a dynamic spectrum of cytosine modifications, including 5mC, 5-hydroxymethylcytosine (5hmC), 5-formylcytosine (5fC), and 5-carboxylcytosine (5caC), orchestrated by distinct enzyme families such as DNMTs, TETs, and TDG. We review current insights about how these regulators shape activity-induced gene expression programs underlying learning and memory, and we discuss how dysregulated DNA (de) methylation contributes to impaired transcriptional control and cognitive decline in neurodegenerative diseases, particularly Alzheimer's disease. Finally, we highlight recent advances in high-resolution mapping technologies for DNA modifications, which are expanding our ability to resolve cell type- and locus-specific epigenetic dynamics in the brain. A deeper understanding of these pathways may inform targeted strategies to preserve or restore cognitive function in neurological disorders.

Alzheimer’s disease↗
PubMed2026

Investigating the relationship between Toll-like receptor activity, low-grade inflammation, cognitive deficits, and antipsychotic drug dose in schizophrenia patients: a moderation analysis.

BACKGROUND: Schizophrenia (SZ) is a debilitating psychiatric disorder where patients experience cognitive decline. Antipsychotic drugs alleviate positive symptoms but do not improve cognitive performance. We previously demonstrated that Toll-like receptors (TLRs), involved in cytokine production, can predict cognitive deficits in SZ patients. In this study, we aim to investigate the potential moderating effects of antipsychotic drugs on the associations between cytokines, TLRs, and cognition. METHODS: In total, 280 participants (201 controls and 79 cases of SZ) were recruited in Ireland. Venous blood from the participants was stimulated with TLR ligands. Levels of cytokines were measured from plasma and post-blood stimulation. The participants were administered a battery of cognitive tasks using the Cambridge Neuropsychological Test Automated Battery and Wechsler Adult Intelligence Scale-IIIR. Olanzapine equivalents were calculated using the defined daily dose method. RESULTS: The results indicate that antipsychotic drug dose does not predict TLR activity or cognition, indicating that antipsychotic drug dose does not have a direct effect on cognition or TLR activity. However, the relationship between TLR4 activity and visual learning and memory is moderated by the antipsychotic drug dose (B&#xa0;=&#xa0;-0.065; p&#xa0;<&#xa0;0.001), where increasing doses have a decreasing impact on their relationship. CONCLUSIONS: Our data indicate that the dose of antipsychotic drugs alone cannot predict changes in cognitive performance and TLR4-activity. It also suggests that antipsychotic drug doses significantly affect TLR activity and its relationship with cognition. These effects are more pronounced on some domains than others. These findings open up new avenues for understanding the complex interplay between antipsychotic drugs, TLRs, and cognitive deficits in SZ.

Humans↗
PubMed2025

Refining sequence-to-activity models by increasing model resolution.

Decoding the cis-regulatory syntax that controls gene expression is essential for improving our understanding of cell differentiation and disease. To identify regulatory motifs and their regulatory syntax, deep learning based sequence-to-activity (S2A) models learn transcription factor binding motifs and their combinations from DNA sequence by modeling measured chromatin accessibility. Previously, we developed AI-TAC, a S2A model that predicts chromatin accessibility across various immune cell types in multi-task fashion, effectively decoding the regulatory syntax underlying immune cell differentiation. While ATAC-seq is commonly used to measure regional accessibility, it also provides high-resolution profiles, the distribution of Tn5 insertion sites, that offer additional insights into the precise location and strength of TF binding sites. Here we demonstrate that modeling ATAC-seq profiles alongside accessibility consistently improves predictions of differential chromatin accessibility across cell types. Moreover, we also find that multi-task learning across related immune cell types consistently outperforms single-task models. To understand what additional information bpAITAC learns from ATAC-seq profiles, we systematically compare sequence attributions from models trained with and without ATAC-seq profiles. We identify novel motifs with strong effect sizes that emerge only when profile data is included. Our findings suggest that modeling ATAC-seq at base-pair resolution enables the model to learn a more nuanced and sensitive representation of the cis-regulatory syntax driving immune cell-specific chromatin landscapes.

ATAC-seq↗
PubMed1975

Auto-tutorial method for teaching manual skills.

This paper describes a self-learning method for teaching craft and activity techniques developed by the faculty at St. Mary's Junior College, Minneapolis. The basic assumption is that, in order for learning to take place, the student must be actively involved in the learning-teaching process. Personalized instruction was simulated in an auto-tutorial laboratory where the student was responsible for organizing his time and for mastering specified craft and activity techniques.

Audiovisual Aids↗
PubMed2025

DeepWheat: predicting the effects of genomic variants on gene expression and regulatory activities across tissues and varieties in wheat using deep learning.

Spatiotemporal gene expression shapes key agronomic traits, yet tissue-specific prediction remains challenging in complex crops. We present DeepWheat, a broadly applicable deep learning framework comprising DeepEXP and DeepEPI, for accurate, tissue-specific gene expression prediction. DeepEXP integrates sequence and epigenomic features to predict gene expression (PCC 0.82-0.88), while DeepEPI predicts epigenomic maps from DNA sequence to support model transfer across varieties. Validations in five wheat cultivars confirm robustness and accuracy. DeepWheat also identifies regulatory variants with strong expression effects, enabling targeted cis-regulatory elements editing and offering a powerful tool for crop functional genomics and breeding.

Triticum↗
PubMed2025

Stochastic epigenetic mutation profiles as biomarkers of clinical activity in juvenile idiopathic arthritis: a multi-omic machine learning approach for gene prioritization.

BACKGROUND: Juvenile idiopathic arthritis (JIA) is a rare autoimmune disease arising from a complex interplay between genetic and environmental factors. Epigenetic modifications such as DNA methylation (DNAm) have been described as potential mediators in gene-environment interactions, contributing to immune system dysregulation. Emerging evidence suggests that DNAm profiles also predict therapeutic responses in autoimmune diseases. This study aims to identify epigenetic biomarkers and epigenetic-driven gene expression changes associated with JIA clinical activity. METHODS: We reanalyzed a publicly available dataset of 44 JIA patients, with whole-genome DNAm and gene expression from CD4&#x2009;+&#x2009;T cells measured at two points: at anti-TNF therapy withdrawal (T0) and eight months later (Tend). At Tend, 30 patients maintained inactive disease (ID) while 14 did not (NO ID). We investigated differences between ID and NO ID patients in the epigenetic mutation load and various epigenetic clocks through linear regression models, and prioritized genomic regions with significantly higher number of epimutations in NO ID patients through machine learning. RESULTS: We found a higher mutation load in NO ID than ID patients, both at T0 and at Tend, with the differences at Tend reaching statistical significance (p&#x2009;=&#x2009;0.02). In contrast, we found no evidence of association between epigenetic clocks and JIA clinical activity. Using a multi-omic approach, we identified a List of candidate epigenetically-driven differentially expressed genes, 80 up-regulated and 77 down-regulated, in NO ID patients. Finally, comparing our candidate gene list with the Connectivity Map database, we identified new candidate potential therapeutic targets. Key findings were validated in independent datasets: DNAm profiles from CD4&#x2009;+&#x2009;T cells (56 JIA patients, 57 controls) and transcriptomic data from PBMCs of JIA patients with active or inactive disease, confirming dysregulation of pathways such as TNF-&#x3b1; signaling via NF-kB and TGF-&#x3b2; signaling among others. CONCLUSIONS: We described a significant association of epigenetic mutations with JIA clinical activity, indicating that epigenetic changes might precede clinical symptoms and may serve as biomarkers for early disease monitoring. Further, our results shed light on biomolecular mechanisms of JIA, supporting the development of more effective treatments.

Humans↗