Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Ensemble 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 163 records · Page 9Linked to original sources
PubMedDate not supplied

Stimulus information and habituation of the visual event related potential and the skin conductance reaction under task-relevance conditions.

The influence of information value of visual stimuli on habituation of event related potentials (ERPs) at Fz, Cz, Pz and Oz and of the skin conductance reaction (SRC) was investigated under task-relevance condition. An improved Wiener filter was used to reduce the number of stimulus presentations to estimate an ERP. Twenty-six subjects received two times a block of 36 stimulus presentations. Half of the subjects received a stimulus with a high information value in terms of complexity and then a stimulus with a low information value. The other half of the subjects received the reversed order. Wiener filtered ERPs and SCRs were determined over ensembles of six stimulus presentations. The habituation of the P300 component was restricted to the fronto-central leads, and was delayed when compared to the results of a former study (Woestenburg, Verbaten and Slangen, 1981b) where non-signal stimuli were used. Also information effects were noticed on these fronto-central leads, but not on the SCR. This reaction habituated as in the former non-signal study. The P300 at the parieto-occipital leads showed larger amplitudes than the fronto-central P300 and these components did not habituate. At the Oz lead early waves habituated and late waves increased during ensemble 1 to 6.

Adult↗
PubMed2026

Artificial intelligence (AI) uses in stereotactic radiosurgery (SRS): diagnosis with brain metastasis (BM) - A systematic review.

BACKGROUND: Brain metastases (BM) are the most common intracranial tumors in adults, and stereotactic radiosurgery (SRS) has become a mainstay of management. However, several diagnostic challenges persist in the SRS pathway, particularly the differentiation of radiation necrosis (RN) from true tumor progression, which conventional MRI and even advanced imaging techniques often cannot reliably resolve. Recent advances in artificial intelligence (AI) offer the potential to address these diagnostic limitations. This systematic review synthesizes current literature on AI applications for MRI-based diagnostic decision support in BM patients undergoing SRS, with a focus on radiomics and deep learning tools for distinguishing RN from progression, classifying molecular and histologic subtypes, and predicting treatment response. METHODS: A systematic review was performed in accordance with PRISMA guidelines. PubMed, Web of Science, and Scopus were searched using a targeted query combining terms related to AI, brain metastasis, diagnosis or imaging, and SRS. After screening 483 records and applying strict inclusion and exclusion criteria, 18 studies published between 2015 and 2025 were included. Data were extracted on study design, cohort characteristics, imaging modality, AI methodology, validation strategy, and reported diagnostic performance. RESULTS: Among the 18 included studies, AI models demonstrated strong performance across diagnostic tasks in the BM-SRS pathway. The differentiation of RN from true tumor progression was the most extensively studied application, addressed by 14 of 18 studies, with reported AUCs ranging from 0.71 to 0.94. Support vector machines, random-forest ensembles, convolutional neural networks, and transformer-based multimodal architectures were widely used. The literature evolved from single-sequence radiomic classifiers in 2018 to multimodal deep learning frameworks fusing imaging with clinical and genomic data in 2025. Contrast-enhanced T1-weighted MRI was the dominant imaging input, and texture-based radiomic features (GLCM, GLSZM, GLDM, and wavelet-derived features) were the most consistently predictive. The highest-performing models reached AUCs of 0.85-0.91 through multimodal integration of imaging with clinical and genomic features, and consistently outperformed expert neuroradiologist read on matched cases. Remaining studies addressed longitudinal segmentation-based detection of local failure and adverse radiation effects, BRAF mutation status in melanoma BM, early Gamma Knife treatment response, and primary tumor histology classification, with more variable performance. CONCLUSION: AI models, particularly those integrating MRI-derived radiomic features with clinical and genomic data, show high accuracy in supporting diagnostic decisions for BM patients treated with SRS. The post-SRS differentiation of radiation necrosis from true tumor progression has reached the greatest level of maturity and is closest to clinical translation, with potential to reduce unnecessary biopsies, personalize surveillance intervals, and rationalize treatment-pathway decisions. Other diagnostic applications, including molecular subtyping and primary tumor histology classification, remain exploratory and require further multicenter validation. Integration of AI tools into multidisciplinary tumor-board workflows, combined with prospective validation and standardized reporting, will be essential to realize the full clinical benefits of AI in SRS for brain metastases.

Humans↗
PubMed2000

Unsupervised learning of binary vectors: a Gaussian scenario.

We study a model of unsupervised learning where the real-valued data vectors are isotropically distributed, except for a single symmetry-breaking binary direction Bin¿-1,+1¿(N), onto which the projections have a Gaussian distribution. We show that a candidate vector J undergoing Gibbs learning in this discrete space, approaches the perfect match J=B exponentially. In addition to the second-order "retarded learning" phase transition for unbiased distributions, we show that first-order transitions can also occur. Extending the known result that the center of mass of the Gibbs ensemble has Bayes-optimal performance, we show that taking the sign of the components of this vector (clipping) leads to the vector with optimal performance in the binary space. These upper bounds are shown generally not to be saturated with the technique of transforming the components of a special continuous vector, except in asymptotic limits and in a special linear case. Simulations are presented which are in excellent agreement with the theoretical results.

Bayes Theorem↗
PubMed2026

Biophysical mechanisms underlying the generation and maintenance of rule-learning engram.

Training rodents in a particularly difficult olfactory-discrimination task results with acquisition of high-skill to perform the task superbly, termed 'rule-learning'. We show that rule-learning occurs abruptly, in a "light-bulb moment". Using whole-cell patch-clamp recordings from the piriform cortex (PC) of Fos2A-iCreER/TRAP2 mice, we target activated-neurons, expressing immediate early genes (IEG). We notice, from the onset of training, IEG-positive neurons from trained animals display enhanced intrinsic excitability. Subsequently, synaptic excitation and inhibition are enhanced in these neurons, in a coordinated, cell-wide process. Additionally, in parallel, we detect the density of IEG-expressing neurons sharply declines. Double labeling with TRAP and c-Fos reveal that nearly two-thirds of the rule-memory cell ensemble neurons are activated from the beginning of training. Silencing TRAP-expressing neurons using inhibitory DREADD leads to a complete loss of rule memory. Hence, we propose that rule learning occurs at a discrete moment and is developed through a gradual process that stabilizes the memory of the rule.

Animals↗
PubMed2026

Seeing and Feeling DNA Methylation: Single-Molecule Biophysics Meets Machine Learning.

DNA methylation at 5-methylcytosine (5mC) is crucial for embryonic development and cellular function, while aberrant patterns strongly drive disease onset and progression. Its reversible nature offers substantial therapeutic potential, emphasizing the need for precise, context-specific genome wide 5mC mapping. Conventional techniques such as bisulfite sequencing and ensemble biosensor assays are hindered by DNA degradation, amplification bias, high cost, and inability to resolve single-molecule structural and mechanical effects of methylation. This review examines advances in single-molecule biophysical methods (nanopore sensing, smFRET, optical/magnetic tweezers, and AFM) that provide direct, label-free/minimally invasive 5mC detection, along with quantitative insights into DNA conformation, mechanics, and protein-DNA interactions. These techniques complement traditional methylome mapping by linking genomic localization to molecular mechanisms. Emerging machine-learning approaches are revolutionizing analysis, particularly in nanopore sensing, while promising applications in smFRET, tweezers, and AFM address throughput and reproducibility challenges. Their convergence promises scalable, high-resolution epigenetic profiling, advancing precision epigenomics toward clinical application.

DNA Methylation↗
PubMed2006

Gradual translocation of spatial correlates of neuronal firing in the hippocampus toward prospective reward locations.

In a continuous T-maze alternation task, CA1 complex-spike neurons in the hippocampus differentially fire as the rat traverses overlapping segments of the maze (i.e., the stem) repeatedly via alternate routes. The temporal dynamics of this phenomenon were further investigated in the current study. Rats learned the alternation task from the first day of acquisition and the differential firing pattern in the stem was observed accordingly. More importantly, we report a phenomenon in which spatial correlates of CA1 neuronal ensembles gradually changed from their original firing locations, shifting toward prospective goal locations in the continuous T-maze alternation task. The relative locations of simultaneously recorded firing fields, however, were preserved within the ensemble spatial representation during this shifting. The within-session shifts in preferred firing locations in the absence of any changes in the environment suggest that certain cognitive factors can significantly alter the location-bound coding scheme of hippocampal neurons.

Animals↗
PubMed2002

Bayesian A* tree search with expected O(N) node expansions: applications to road tracking.

Many perception, reasoning, and learning problems can be expressed as Bayesian inference. We point out that formulating a problem as Bayesian inference implies specifying a probability distribution on the ensemble of problem instances. This ensemble can be used for analyzing the expected complexity of algorithms and also the algorithm-independent limits of inference. We illustrate this problem by analyzing the complexity of tree search. In particular, we study the problem of road detection, as formulated by Geman and Jedynak (1996). We prove that the expected convergence is linear in the size of the road (the depth of the tree) even though the worst-case performance is exponential. We also put a bound on the constant of the convergence and place a bound on the error rates.

Algorithms↗
PubMed2026

Integrating machine learning and GWAS for variant prioritization in the INCIPE cohort highlights ABC transporter genes in chronic kidney disease.

INTRODUCTION: Chronic kidney disease (CKD) is a major public health challenge, affecting approximately 674 million people worldwide and representing one of the fastest-growing causes of mortality. Since CKD is frequently asymptomatic in its early stages, the identification of novel genetic biomarkers may improve early detection and risk stratification. Genome-Wide Association Studies (GWAS) have identified numerous genetic loci associated with CKD and related traits; however, their performance is often limited in small and imbalanced cohorts, where reduced statistical power increases both false-positive and false-negative findings. Machine learning (ML) approaches can complement conventional GWAS by prioritizing biologically relevant genetic signals from high-dimensional genomic data. METHODS: In this study, we implemented a nested ensemble (NCBC) model composed of an undersampler and a CatBoostClassifier (CBC) to prioritize candidate genetic variants associated with CKD in the INCIPE cohort. Prioritized variants were functionally annotated and evaluated through enrichment analyses, GTEx gene expression profiling, and protein-protein interaction network analyses. Genes identified by the CKDGen Consortium were analysed as an external reference set and used to validate the biological relevance of the prioritized results. RESULTS: The NCBC model outperformed conventional ML classifiers, achieving a ROC AUC score of 87.77%, compared to 50%-53% for the other evaluated models. Among the prioritized genes, 56.25% showed protein-protein interactions with genes previously reported by the CKDGen Consortium, whereas only 1.9% of randomly generated gene sets showed interactions. DISCUSSION: Our study demonstrates that the NCBC model improves the prioritization of biologically plausible candidate variants in a small and imbalanced CKD cohort. Functional analyses suggested ABC transporter-related genes, including ABCA13, ABCA4, and ABCC4 genes, as promising candidate for future validation, with ABCA4 showing substantial expression in kidney tissues. Overall, these findings support the integration of ML with GWAS to prioritize candidate genes and investigate the genetic architecture of complex diseases.

SNP prioritization↗
PubMed1986

Some principles in the brain analysis of important signals: mapping and stimulus recognition.

This essay addresses two questions: What are the meanings of different kinds of brain maps? Can the recognition of important communicative signals and other stimuli known to the system be adequately explained by an ensemble code? Several kinds and grades of brain maps are distinguished. Before we can properly state the meaning, especially of the higher forms of multiple and multifactor maps, we need to learn where they project. At the higher levels this is a labor-intensive task, requiring also ingenuity and ethological thinking to devise stimuli. The neuronal basis of recognition in those cases where behavior or perception is triggered in an either-or manner has chiefly been attributed to one or the other of two classes of models: a large spatiotemporal configuration of many kinds of cells in which there is little convergence of input, and a small set of nearly equivalent cells after successive convergences. The latter is known to exist but it is not clear how far it goes or for what classes of stimuli. The former is a more popular view but carries several burdens in required assumptions and is essentially not demonstrable or disprovable. I believe both exist and operate in sequence: specific ensembles are inputs to small sets of equivalent recognition units and specific arrays of different recognition units at higher and higher levels of abstraction may constitute the specific configurations for the most sophisticated recognitions. Our information base is pitifully small, especially in comparative physiology of higher integrative functions of the brain and in comparative behaviour.

Afferent Pathways↗
PubMed1999

The effects of fabric air permeability and moisture absorption on clothing microclimate and subjective sensation in sedentary women at cyclic changes of ambient temperatures from 27 degrees C to 33 degrees C.

The present paper aimed at learning the effects of two different levels of air permeability and moisture absorption on clothing microclimate and subjective sensation in sedentary women. Three kinds of clothing ensemble were investigated: 1) polyester clothing with low moisture absorption and low air permeability (A clothing); 2) polyester clothing with low moisture absorption and high air permeability (B clothing); and 3) cotton clothing with high moisture absorption and high air permeability (C clothing). After 20 min of dressing time, the room temperature and humidity began to rise from 27 degrees C and 50% rh to 33 degrees C and 70% rh over 20 min, and it was maintained for 30 min (Section I); it then began to fall to 27 degrees C and 50% rh over 20 min, and it was maintained there for 20 min (Section II). The subject sat quietly on a chair for 110 min. The main findings are summarized as follows: 1) The clothing surface temperature was significantly higher in C clothing than in B clothing during section I, but it was significantly higher in B clothing than in C clothing during section II. 2) Although the positive relationship between the microclimate humidity and forearm sweat rate was significantly confirmed in all three kinds of clothing, the microclimate humidity at the chest for the same sweat rate was lower in C clothing than in A and B clothing. These results were discussed in terms of thermal physiology.

Adult↗
PubMed2025

Structural basis of differential gene expression at eQTLs loci from high-resolution ensemble models of 3D single-cell chromatin conformations.

MOTIVATION: Techniques such as high-throughput chromosome conformation capture (Hi-C) have provided a wealth of information on nucleus organization and genome important for understanding gene expression regulation. Genome-Wide Association Studies have identified numerous loci associated with complex traits. Expression quantitative trait loci (eQTL) studies have further linked the genetic variants to alteration in expression levels of associated target genes across individuals. However, the functional roles of many eQTLs in noncoding regions remain unclear. Current joint analyses of Hi-C and eQTLs data lack advanced computational tools, limiting what can be learned from these data. RESULTS: We developed a computational method for simultaneous analysis of Hi-C and eQTL data, capable of identifying a small set of nonrandom interactions from all Hi-C interactions. Using these nonrandom interactions, we reconstructed large ensembles (×105) of high-resolution single-cell 3D chromatin conformations with thorough sampling, accurately replicating Hi-C measurements. Our results revealed many-body interactions in chromatin conformation at the single-cell level within eQTL loci, providing a detailed view of how 3D chromatin structures form the physical foundation for gene regulation, including how genetic variants of eQTLs affect the expression of associated eGenes. Furthermore, our method can deconvolve chromatin heterogeneity and investigate the spatial associations of eQTLs and eGenes at subpopulation level, revealing their regulatory impacts on gene expression. Together, ensemble modeling of thoroughly sampled single-cell chromatin conformations combined with eQTL data, helps decipher how 3D chromatin structures provide the physical basis for gene regulation, expression control, and aid in understanding the overall structure-function relationships of genome organization. AVAILABILITY AND IMPLEMENTATION: It is available at https://github.com/uic-liang-lab/3DChromFolding-eQTL-Loci.

Quantitative Trait Loci↗
PubMed2002

An emerging molecular and cellular framework for memory processing by the hippocampus.

The hippocampus plays a central role in memory consolidation, a process for converting short-term memory into cortically stored, long-lasting memory in the mammalian brain. Here, we review recent data and discuss the 'synaptic re-entry reinforcement' (SRR) hypothesis, which can account for the role of the hippocampus in memory consolidation at both the molecular and systems levels. The central idea of the SRR hypothesis is that reactivation of neural ensembles in the hippocampus during the consolidation period results in multiple rounds of NMDA-receptor-dependent synaptic reinforcement of the hippocampal memory traces created during initial learning. In addition, such reactivation and reinforcement processes permit the hippocampus to act as a 'coincidence regenerator', providing coordinated input that drives the coherent reactivation of cortical neurons, resulting in the progressive strengthening of cortical memory traces through reactivation of cortical NMDA receptors.

Animals↗
PubMed2005

Pattern-dependent, simultaneous plasticity differentially transforms the input-output relationship of a feedforward circuit.

Memories are believed to be encoded by changes in the synaptic connections between neurons. Although many forms of synaptic plasticity have been identified, it remains unknown how such changes affect local circuits. Feedforward inhibitory networks are a common type of local circuitry and occur when principal neurons and their afferent inhibitory interneurons receive the same input. Using slices of cerebellar cortex, we explored how synaptic plasticity at multiple sites within a feedforward inhibitory network consisting of parallel fibers, interneurons, and Purkinje neurons alters the output of this circuit. We found that stimuli resembling baseline activity potentiated feedforward excitatory and simultaneously depressed feedforward inhibitory pathways. In contrast, stimuli resembling sensory-evoked patterns of firing potentiated both types of feedforward connections. These distinct forms of ensemble plasticity change the way Purkinje neurons subsequently respond to inputs. Such concerted changes in the circuitry of cerebellar cortex may contribute to certain forms of sensorimotor learning.

Animals↗
PubMed2005

Post-training intra-amygdala amphetamine injections given during acquisition of a stimulus-response (S-R) habit task enhance the expression of stimulus-reward learning: further evidence for incidental amygdala learning.

The effect of post-training intra-amygdala amphetamine injections was examined on the acquisition and expression of a visual discrimination task. Rats were trained to enter four lit arms for food (stimulus-response) and avoid unlit arms on an eight-arm radial maze visual discrimination task. Post-training intra-amygdala amphetamine injections (10 microg) were given for 4 consecutive days during the mid-point of training (days 20-23). The number of lit arm entries was used as a measure of stimulus-response habit learning 24 h after each injection. Twenty-four hours after the last injection, a transfer test was run to assess the effect of the same post-training manipulation. This transfer test assessed the amount of time spent in the lit arms and was used as a measure of stimulus-reward learning. Compared to saline-injected rats, rats that received post-training amphetamine spent more time in lit as opposed to dark arms during the transfer test. This occurred in the absence of an increase in the number of correct arm entries during visual discrimination training. This suggests that post-training amphetamine strengthened a stimulus-reward association that did not immediately affect behavioral output. This association may reflect a mnemonic representation stored in an ensemble of amygdala neurons.

Amphetamine↗
PubMed1979

[Changes in the ultrastructure and protein fractions of the cortex of the motor and visual analyzers during conditioned reflex avoidance reactions].

In avoidance conditioning, rats developed changes in the range of electrophoretic proteins as well as subcellular reconstructions in neurons and synapses which enabled them to fulfill specific functions on the basis of genetically fixed biochemical processes and ultrastructures. This corroborates ideas of information storage in the c. n. s. on the basis of formation of certain neuronal ensembles by means of changes in neurons' synapses facilitating the conduction.

Animals↗
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↗
PubMedDate not supplied

[Collective behavior of cortical neurons upon long-term reinforcement].

The differential equation describing behaviour of a large ensemble of cortical cells under the extended action of positive or negative reinforcement is derived. The equation is based on the concept that the reinforcement changes synaptic effectiveness in the learning process and a sign of this change depends on an average pulse frequency of a presynaptic neuron and a reinforcement sign. This equation turns out to be identical to the equation which was derived by us earlier based on the ideas that the reinforcement influences on a threshold of neuronal excitation. The comparison of the equation solution with our experimental data lends support for the solution and enables to believe that the serotoninergic system of the brain is a terminal link of the positive reinforcement system and that the noradrenalinergic one is a terminal link of the negative reinforcement.

Cerebral Cortex↗