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.

SourceResearch connectionFrom yearThrough year

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

At least 199 records · Page 11Linked to original sources

PubMed1993

Dynamics of the hippocampal ensemble code for space.

Ensemble recordings of 73 to 148 rat hippocampal neurons were used to predict accurately the animals' movement through their environment, which confirms that the hippocampus transmits an ensemble code for location. In a novel space, the ensemble code was initially less robust but improved rapidly with exploration. During this period, the activity of many inhibitory cells was suppressed, which suggests that new spatial information creates conditions in the hippocampal circuitry that are conducive to the synaptic modification presumed to be involved in learning. Development of a new population code for a novel environment did not substantially alter the code for a familiar one, which suggests that the interference between the two spatial representations was very small. The parallel recording methods outlined here make possible the study of the dynamics of neuronal interactions during unique behavioral events.

Animals↗

PubMed2026

CLASPP: A unified model for predicting post-translational modifications.

Post-Translational Modifications (PTMs) are a fundamental mechanism for regulating cellular pathways and increasing the functional diversity of the proteome. Accurately predicting the PTM types that are likely to occur at a given site in the primary sequence is a key challenge in functional proteomics. Existing PTM prediction models predominantly focus on either single PTM types or employ ensemble methods that combine multiple models to predict different PTM types. This fragmentation is largely driven by the vast imbalance in data availability across PTM types, making it difficult to predict multiple PTM types with a single model. To address this limitation, we present the Contrastively Learned Attention-based Stratified PTM Predictor (CLASPP), a unified PTM prediction model. CLASPP addresses imbalance challenges by leveraging unsupervised clustering-based undersampling and a novel contrastive learning framework tailored to PTM data. Additionally, our hierarchical data organization and curation are shown to improve CLASPP's performance by balancing the representation of individual PTM types and provides a standardized dataset to train and validate future model designs. Drawing inspiration from advancements in image and natural language processing, the CLASPP model employs a multi-stage training strategy and a high-quality, curated training dataset to improve PTM prediction performance. To uncover what is learned during the contrastive learning stage, the CLASPP model is shown to distinguish known protein kinase substrate specificity profiles as a form of explainability. Finally, we evaluate the application of CLASPP in predicting PTMs in different model organisms and experimentally validated ubiquitination sites in the understudied DCLK3 kinase. Overall, CLASPP represents a unified model for PTM prediction that addresses key bottlenecks in data imbalance and offers new strategies for biological data curation, thereby improving PTM-type prediction performance across diverse organisms.

Protein Processing, Post-Translational↗

PubMed2006

Optimal classification of long echo time in vivo magnetic resonance spectra in the detection of recurrent brain tumors.

We describe the optimal high-level postprocessing of single-voxel (1)H magnetic resonance spectra and assess the benefits and limitations of automated methods as diagnostic aids in the detection of recurrent brain tumor. In a previous clinical study, 90 long-echo-time single-voxel spectra were obtained from 52 patients and classified during follow-up (30/28/32 normal/non-progressive tumor/tumor). Based on these data, a large number of evaluation strategies, including both standard resonance line quantification and algorithms from pattern recognition and machine learning, were compared in a quantitative evaluation. Results from linear and non-linear feature extraction, including ICA, PCA and wavelet transformations, and also the data from resonance line quantification were combined systematically with different classifiers such as LDA, chemometric methods (PLS, PCR), support vector machines and ensemble methods. Classification accuracy was assessed using a leave-one-out cross-validation scheme and the area under the curve (AUC) of the receiver operator characteristic (ROC). A regularized linear regression on spectra with binned channels reached 91% classification accuracy compared with 83% from quantification. Interpreting the loadings of these regressions, we find that lipid and lactate signals are too unreliable to be used in a simple machine rule. Choline and NAA are the main source of relevant information. Overall, we find that fully automated pattern recognition algorithms perform as well as, or slightly better than, a manually controlled and optimized resonance line quantification.

Algorithms↗

PubMed2004

Long-term memory for elementary visual percepts: memory psychophysics of context and acquisition effects.

In the first phase of each of two experiments, participants learned to associate a set of labels (i.e., consonant-vowel-consonant [CVC]) with a set of line lengths by using a paired-associate learning procedure. In the second phase of each experiment, these learned labels were used as memorial standards in the method of constant stimuli. Psychometric functions and the associated indices of discriminative performance (i.e., Weber fractions [WFs], just noticeable difference, and point of subjective equality) were then obtained for the remembered standards. In Experiment 1, WFs (i.e., the indices of memory precision) obtained with remembered standards were found to be higher (i.e., had poorer discriminability) than were WFs obtained with perceptual standards. In addition, WFs obtained with the remembered standards exhibited serial position effects (i.e., poorer discriminability for central items in the memory ensemble) and systematically varied with set size (i.e., the number of standards in the memory set), but WFs obtained with perceptual standards did not depend on serial position or set size. In Experiment 2, increasing the number of acquisition trials reduced WFs and diminished serial position effects. In addition, WFs did not vary systematically with the "physical" spacing between the standards in memory, but they did with the ordinal spacing. The results are consistent with a noisy analogue representation of remembered magnitudes, whereby central items in a memory ensemble are subject to lateral inhibition and thus reduced discriminability. Finally, presentation order effects, as defined by the classic time-order error, were observed with purely perceptual comparisons but not with comparisons involving a remembered standard. This latter finding is inconsistent with a strong form of the functional equivalence view of perception and memory.

Humans↗

PubMed2026

A cfDNA fragmentomics classifier for noninvasive differentiation of benign and malignant renal masses.

Noninvasive differentiation of malignant and benign renal masses remains a major clinical challenge, particularly for radiologically indeterminate lesions. Here, we developed and validated a plasma cell-free DNA (cfDNA) fragmentomics-based machine learning classifier for renal mass characterization. The model was trained on 331 participants (171 cancer, 160 benign) and independently validated on 144 participants (73 cancer, 71 benign). Three cfDNA fragmentation features, including copy number variation (CNV), fragmentation-based methylation (FRAGMA), and nucleosome footprint (NF), derived from low-pass whole-genome sequencing, were integrated into an ensemble framework. The model achieved strong discriminative performance, with area under the curve (AUC) values of 0.956 in the training cohort and 0.946 in the validation cohort, outperforming individual feature-based models. At a predefined operating threshold corresponding to 90% sensitivity, specificity reached 0.90 and 0.87, respectively. Notably, most cancer samples exhibited low tumor fraction (TF < 3%), yet the model maintained robust performance in low-TF samples (AUCs: 0.952 and 0.941, respectively). Performance remained consistent across tumor stage, grade, and histological subtypes. The classifier also demonstrated potential clinical utility in diagnostically challenging settings, including lipid-poor angiomyolipoma and oncocytoma, with 12 of 13 oncocytoma samples correctly classified in an independent cohort. In addition, the model correctly identified 85.3% of benign masses > 4 cm, for which surgical intervention is more commonly considered, and 84.6% of malignant tumors ≤ 4 cm, for which management can be challenging. Collectively, these findings support cfDNA fragmentomics as a promising noninvasive liquid biopsy approach for renal mass evaluation and clinical decision-making.

Humans↗

PubMed2004

Bioinformatics in proteomics: application, terminology, and pitfalls.

Bioinformatics applies data mining, i.e., modern computer-based statistics, to biomedical data. It leverages on machine learning approaches, such as artificial neural networks, decision trees and clustering algorithms, and is ideally suited for handling huge data amounts. In this article, we review the analysis of mass spectrometry data in proteomics, starting with common pre-processing steps and using single decision trees and decision tree ensembles for classification. Special emphasis is put on the pitfall of overfitting, i.e., of generating too complex single decision trees. Finally, we discuss the pros and cons of the two different decision tree usages.

Computational Biology↗

PubMedDate not supplied

Multiple views of the response of an ensemble of spectro-temporal features support concurrent classification of utterance, prosody, sex and speaker identity.

Models of auditory processing, particularly of speech, face many difficulties. These difficulties include variability among speakers, variability in speech rate and robustness to moderate distortions such as time compression. In contrast to the 'invariance of percept' (across different speakers, of different sexes, using different intonation, and so on) is the observation that we are sensitive to the identity, sex and intonation of the speaker. In previous work we have reported that a model based on ensembles of spectro-temporal feature detectors, derived from onset sensitive pre-processing of a limited class of stimuli, preserves significant information about the stimulus class. We have also shown that this is robust with respect to the exact choice of feature set, moderate time compression in the stimulus and speaker variation. Here we extend these results to show a) that by using a classifier based on a network of spiking neurons with spike-driven plasticity, the output of the ensemble constitutes an effective rate coding representation of complex sounds; and b) that the same set of spectro-temporal features concurrently preserve information about a range of qualitatively different classes into which the stimulus might fall. We show that it is possible for multiple views of the same pattern of responses to generate different percepts. This is consistent with suggestions that multiple parallel processes exist within the auditory 'what' pathway with attentional modulation enhancing the task-relevant classification type. We also show that the responses of the ensemble are sparse in the sense that a small number of features respond for each stimulus type. This has implications for the ensembles' ability to generalise, and to respond differentially to a wide variety of stimulus classes.

Acoustic Stimulation↗

PubMed2005

Tandem machine learning for the identification of genes regulated by transcription factors.

BACKGROUND: The identification of promoter regions that are regulated by a given transcription factor has traditionally relied upon the identification and distributions of binding sites recognized by the factor. In this study, we have developed a tandem machine learning approach for the identification of regulatory target genes based on these parameters and on the corresponding binding site information contents that measure the affinities of the factor for these cognate elements. RESULTS: This method has been validated using models of DNA binding sites recognized by the xenobiotic-sensitive nuclear receptor, PXR/RXRalpha, for target genes within the human genome. An information theory-based weight matrix was first derived and refined from known PXR/RXRalpha binding sites. The promoter region of candidate genes was scanned with the weight matrix. A novel information density-based clustering algorithm was then used to identify clusters of information rich sites. Finally, transformed data representing metrics of location, strength and clustering of binding sites were used for classification of promoter regions using an ensemble approach involving neural networks, decision trees and Naïve Bayesian classification. The method was evaluated on a set of 24 known target genes and 288 genes known not to be regulated by PXR/RXRalpha. We report an average accuracy (proportion of correctly classified promoter regions) of 71%, sensitivity of 73%, and specificity of 70%, based on multiple cross-validation and the leave-one-out strategy. The performance on a test set of 13 genes showed that 10 were correctly classified. CONCLUSION: We have developed a machine learning approach for the successful detection of gene targets for transcription factors with high accuracy. The method has been validated for the transcription factor PXR/RXRalpha and has the potential to be extended to other transcription factors.

Algorithms↗

PubMed1996

Modeling motor cortical operations by an attractor network of stochastic neurons.

Understanding the neural computations performed by the motor cortex requires biologically plausible models that account for cell discharge patterns revealed by neurophysiological recordings. In the present study the motor cortical activity underlying movement generation is modeled as the dynamic evolution of a large fully recurrent network of stochastic spiking neurons with noise superimposed on the synaptic transmission. We show that neural representations of the learned movement trajectories can be stored in the connectivity matrix in such a way that, when activated, a particular trajectory evolves in time as a dynamic attractor of the system while individual neurons fire irregularly with large variability in their interspike intervals. Moreover, the encoding of trajectories as attractors ensures high stability of the ensemble dynamics in the presence of synaptic noise. In agreement with neurophysiological findings, the suggested model can provide a wide repertoire of specific motor behaviors, whereas the number of specialized cells and specific connections may be negligibly small if compared with the whole population engaged in trajectory retrieving. To examine the applicability of the model we study quantitatively the relationship between local geometrical and kinematic characteristics of the trajectories generated by the network. The relationship obtained as a result of simulations is close to the '2/3 power law' established by psychophysical and neurophysiological studies.

Animals↗

PubMed2002

Functional significance of climbing-fiber synchrony: a population coding and behavioral analysis.

Population coding and behavioral approaches were taken toward analyzing the functional significance of the climbing-fiber system. Analyses of neuronal interaction using the joint peristimulus time histogram showed that given a low rate of firing, the climbing-fiber system organizes itself to fire synchronously during movement--a feature that bears little or no relationship to the modulation in firing rate during movement or whether olivary neurons respond to a sensory stimulus. Moreover, the climbing-fiber system avoids synchrony during a passive sensory response but actively makes a transition into synchrony as a movement is initiated. Thus, from a functional viewpoint, the active feature of the climbing-fiber system to organize into synchronously firing cell ensembles is uniquely motor. Analyses of behaving rats without an inferior olive revealed that the climbing-fiber system optimizes the timing of skilled movement by reducing reaction time and the interval between repetitive movements by 100 milliseconds. Finally, using classical delay eyeblink conditioning, it was found that the inferior olive is essential for learning about rapid sequences of events but not the same event sequence when given more slowly. It was concluded that the climbing-fiber system exerts its function through synchrony, which provides a 100 ms advantage in movement speed and the ability to learn about events that are rapidly presented in time.

Action Potentials↗

PubMed2003

The mind through chick eyes: memory, cognition and anticipation.

To understand the animal mind, we have to reconstruct how animals recognize the external world through their own eyes. For the reconstruction to be realistic, explanations must be made both in their proximate causes (brain mechanisms) as well as ultimate causes (evolutionary backgrounds). Here, we review recent advances in the behavioral, psychological, and system-neuroscience studies accomplished using the domestic chick as subjects. Diverse behavioral paradigms are compared (such as filial imprinting, sexual imprinting, one-trial passive avoidance learning, and reinforcement operant conditioning) in their behavioral characterizations (development, sensory and motor aspects of functions, fitness gains) and relevant brain mechanisms. We will stress that common brain regions are shared by these distinct paradigms, particularly those in the ventral telencephalic structures such as AIv (in the archistriatum) and LPO (in the medial striatum). Neuronal ensembles in these regions could code the chick's anticipation for forthcoming events, particularly the quality/quantity and the temporal proximity of rewards. Without the internal representation of the anticipated proximity in LPO, behavioral tolerance will be lost, and the chick makes impulsive choice for a less optimized option. Functional roles of these regions proved compatible with their anatomical counterparts in the mammalian brain, thus suggesting that the neural systems linking between the memorized past and the anticipated future have remained highly conservative through the evolution of the amniotic vertebrates during the last 300 million years. With the conservative nature in mind, research efforts should be oriented toward a unifying theory, which could explain behavioral deviations from optimized foraging, such as "naïve curiosity," "contra-freeloading," "Concorde fallacy," and "altruism."

Animals↗

PubMed2004

caGEDA: a web application for the integrated analysis of global gene expression patterns in cancer.

The explosion of microarray data from pilot studies, basic research and large-scale clinical trials requires the development of integrative computational tools that can not only analyse gene expression patterns but that can also evaluate the methods of analysis adopted and then provide a boost to post-analysis translational interpretation of those patterns. We have developed a web application called caGEDA (cancer gene expression data analyzer) that can: (1) upload gene expression profiles from cDNA or oligonucleotide microarrays; (2) conduct a diverse range of serial linear normalisations; (3) identify differentially expressed genes using a variety of tests - either threshold or permutation tests; (4) produce tables of literature references to papers reporting that specific genes (identified by accession numbers) are up- or down-regulated in specific cancers; (5) estimate the error of sample class prediction using the significant gene set for features; (6) perform low-bias and accurate validated learning using three computational validation techniques (leave-one out validation, k-fold validation, random re-sampling validation); and (7) validate a classifier with a randomly selected or user-defined validation set. Significant genes are reported in a table of links to entries in the following databases: Locus Link, Genome View, UCSC, Ensembl, UniGene, dbSNP, AmiGO and OMIM. caGEDA is seamlessly integrated via embedded forms with UCSD's (University of California at San Diego) 2HAPI server (for medical subject heading (MeSH) term exploration) and EZ-Retrieve (to identify common transcription factors located upstream of sets of genes that exhibit similar modes of differential expression). caGEDA offers a variety of previously described and novel tests for differentially expressed genes, most notably the permutation percentile separability test, which is most appropriate for identifying genes that are significantly differentially expressed in a subset of patients. caGEDA, which is open source and free to academic users, will soon be greatly enhanced by operating with the components of the National Cancer Institute's new cancer bioinformatics grid (caBIG).

Biomarkers, Tumor↗

PubMed2004

Reproducible sequence generation in random neural ensembles.

Little is known about the conditions that neural circuits have to satisfy to generate reproducible sequences. Evidently, the genetic code cannot control all the details of the complex circuits in the brain. In this Letter, we give the conditions on the connectivity degree that lead to reproducible and robust sequences in a neural population of randomly coupled excitatory and inhibitory neurons. In contrast to the traditional theoretical view we show that the sequences do not need to be learned. In the framework proposed here just the averaged characteristics of the random circuits have to be under genetic control. We found that rhythmic sequences can be generated if random networks are in the vicinity of an excitatory-inhibitory synaptic balance. Reproducible transient sequences, on the other hand, are found far from a synaptic balance.

Action Potentials↗

PubMed2000

Age-related differences in the use of contextual information in recognition memory: a global matching approach.

Age differences in the processing of contextual information were investigated using the Item, associated Context, and Ensemble (ICE) model (K. Murnane, M. P. Phelps, & K. Malmberg, 1999), a general global matching model of recognition memory. In two experiments, young and older adults studied words in environmental contexts and were tested in both the same and different contexts. Patterns of context effects for hit rate, false alarm rate, and d' suggest that older adults process associated context, but have difficulties integrating items and context into an ensemble. Thus, older adults appear to have a specific, rather than a general, deficit in processing contextual information. A deficiency in ensemble processing may be responsible for the prevalent finding that older adults show poorer recognition memory performance than young adults.

Adolescent↗

PubMed2025

Modeling Alternative Conformational States in CASP16.

The CASP16 Ensemble Prediction experiment assessed advances in methods for modeling proteins, nucleic acids, and their complexes in multiple conformational states. Targets included systems with experimental structures determined in two or three states, evaluated by direct comparison to experimental coordinates, as well as domain-linker-domain (D-L-D) targets assessed against statistical models from NMR and SAXS data. This paper focuses on the former class of multi-state targets. Ten ensembles were released as community challenges, including ligand-induced conformational changes, protein-DNA complexes, a trimeric protein, a stem-loop RNA, and multiple oligomeric states of a single RNA. For five targets, some groups produced reasonably accurate models of both reference states (best TM-score >0.75). However, with the exception of one protein-ligand complex (T1214), where an apo structure was available as a template, predictors generally failed to capture key structural details distinguishing the states. Overall, accuracy was significantly lower than for single-state targets in other CASP experiments. The most successful approaches generated multiple AlphaFold2 models using enhanced multiple sequence alignments and sampling protocols, followed by model quality based selection. While the AlphaFold3 server performed well on several targets, individual groups outperformed it in specific cases. By contrast, predictions for one protein-DNA complex, three RNA targets, and multiple oligomeric RNA states consistently fell short (TM-score <0.75). These results highlight both progress and persistent challenges in multi-state prediction. Despite recent advances, accurate modeling of conformational ensembles, particularly RNA and large multimeric assemblies, remains a critical frontier for structural biology.

AlphaFold2↗

PubMed2024

Deep-Learning Model for Tumor-Type Prediction Using Targeted Clinical Genomic Sequencing Data.

UNLABELLED: Tumor type guides clinical treatment decisions in cancer, but histology-based diagnosis remains challenging. Genomic alterations are highly diagnostic of tumor type, and tumor-type classifiers trained on genomic features have been explored, but the most accurate methods are not clinically feasible, relying on features derived from whole-genome sequencing (WGS), or predicting across limited cancer types. We use genomic features from a data set of 39,787 solid tumors sequenced using a clinically targeted cancer gene panel to develop Genome-Derived-Diagnosis Ensemble (GDD-ENS): a hyperparameter ensemble for classifying tumor type using deep neural networks. GDD-ENS achieves 93% accuracy for high-confidence predictions across 38 cancer types, rivaling the performance of WGS-based methods. GDD-ENS can also guide diagnoses of rare type and cancers of unknown primary and incorporate patient-specific clinical information for improved predictions. Overall, integrating GDD-ENS into prospective clinical sequencing workflows could provide clinically relevant tumor-type predictions to guide treatment decisions in real time. SIGNIFICANCE: We describe a highly accurate tumor-type prediction model, designed specifically for clinical implementation. Our model relies only on widely used cancer gene panel sequencing data, predicts across 38 distinct cancer types, and supports integration of patient-specific nongenomic information for enhanced decision support in challenging diagnostic situations. See related commentary by Garg, p. 906. This article is featured in Selected Articles from This Issue, p. 897.

Humans↗

PubMed2005

Theta rhythm of navigation: link between path integration and landmark navigation, episodic and semantic memory.

Five key topics have been reverberating in hippocampal-entorhinal cortex (EC) research over the past five decades: episodic and semantic memory, path integration ("dead reckoning") and landmark ("map") navigation, and theta oscillation. We suggest that the systematic relations between single cell discharge and the activity of neuronal ensembles reflected in local field theta oscillations provide a useful insight into the relationship among these terms. In rats trained to run in direction-guided (1-dimensional) tasks, hippocampal cell assemblies discharge sequentially, with different assemblies active on opposite runs, i.e., place cells are unidirectional. Such tasks do not require map representation and are formally identical with learning sequentially occurring items in an episode. Hebbian plasticity, acting within the temporal window of the theta cycle, converts the travel distances into synaptic strengths between the sequentially activated and unidirectionally connected assemblies. In contrast, place representations by hippocampal neurons in 2-dimensional environments are typically omnidirectional, characteristic of a map. Generation of a map requires exploration, essentially a dead reckoning behavior. We suggest that omnidirectional navigation through the same places (junctions) during exploration gives rise to omnidirectional place cells and, consequently, maps free of temporal context. Analogously, multiple crossings of common junction(s) of episodes convert the common junction(s) into context-free or semantic memory. Theta oscillation can hence be conceived as the navigation rhythm through both physical and mnemonic space, facilitating the formation of maps and episodic/semantic memories.

Animals↗

PubMed2006

A comparison of optimal MIMO linear and nonlinear models for brain-machine interfaces.

The field of brain-machine interfaces requires the estimation of a mapping from spike trains collected in motor cortex areas to the hand kinematics of the behaving animal. This paper presents a systematic investigation of several linear (Wiener filter, LMS adaptive filters, gamma filter, subspace Wiener filters) and nonlinear models (time-delay neural network and local linear switching models) applied to datasets from two experiments in monkeys performing motor tasks (reaching for food and target hitting). Ensembles of 100-200 cortical neurons were simultaneously recorded in these experiments, and even larger neuronal samples are anticipated in the future. Due to the large size of the models (thousands of parameters), the major issue studied was the generalization performance. Every parameter of the models (not only the weights) was selected optimally using signal processing and machine learning techniques. The models were also compared statistically with respect to the Wiener filter as the baseline. Each of the optimization procedures produced improvements over that baseline for either one of the two datasets or both.

Action Potentials↗