SEARCH · PubMed Health

Results for “Predictive Learning Models”

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 379 records · Page 21Linked to original sources

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↗

PubMed2026

Metagenomic polymorphic toxin effector and immunity profiling predicts microbiome development and disease-related dysbiosis.

Bacteria use antagonistic interbacterial weapons, such as polymorphic toxin secretion systems (TSS), to compete for niches in the human gut microbiome. We hypothesized that TSS influence gut microbiome development and disease-related dysbiosis. We developed a bioinformatic marker gene approach (PolyProf) to quantify TSS including ~200 effector and immunity genes and applied it to ~15,000 publicly available human metagenomes. PolyProf alpha and beta diversity readily distinguished 12 different human disease states and enabled the construction of highly accurate linear regression classifier machine learning models. Elastic net machine learning models integrating bacterial taxonomy with PolyProf had strong predictive value for 12 disease states, outperforming models utilizing taxonomy alone. During microbiome development in the first year of life, PolyProf alpha diversity increases, and beta diversity becomes increasingly like the maternal microbiome, influenced by vertical transfer, delivery mode, and breastfeeding. PolyProf is related to strain sharing among adults through social interactions. In summary, TSS genes strongly correlate with microbiome development and interpersonal strain sharing, suggesting roles for interbacterial antagonism. Since PolyProf distinguishes diverse adult disease statuses, these dynamics may contribute to non-genetic inheritance.IMPORTANCEPrevious research has demonstrated that bacteria compete within the gut microbiome using toxin secretion systems (TSS). How TSS contribute to human microbiome development and the microbiome alterations observed in human diseases is not known. This study develops a new bioinformatic tool for profiling TSS-related genes in metagenomic data. Application of this approach to large-scale human fecal metagenomic data demonstrates the dynamic association of TSS during microbiome development, including the exchange of strains among social contacts. TSS gene abundance patterns are highly predictive of 12 disease states. This study advances the field by enabling TSS profiling in metagenomes and by identifying disease and microbiome development biomarkers that provide hypotheses for future mechanistic studies and may be useful for disease diagnosis.

Dysbiosis↗

PubMed2006

A cerebellar model for predictive motor control tested in a brain-based device.

The cerebellum is known to be critical for accurate adaptive control and motor learning. We propose here a mechanism by which the cerebellum may replace reflex control with predictive control. This mechanism is embedded in a learning rule (the delayed eligibility trace rule) in which synapses onto a Purkinje cell or onto a cell in the deep cerebellar nuclei become eligible for plasticity only after a fixed delay from the onset of suprathreshold presynaptic activity. To investigate the proposal that the cerebellum is a general-purpose predictive controller guided by a delayed eligibility trace rule, a computer model based on the anatomy and dynamics of the cerebellum was constructed. It contained components simulating cerebellar cortex and deep cerebellar nuclei, and it received input from a middle temporal visual area and the inferior olive. The model was incorporated in a real-world brain-based device (BBD) built on a Segway robotic platform that learned to traverse curved paths. The BBD learned which visual motion cues predicted impending collisions and used this experience to avoid path boundaries. During learning, the BBD adapted its velocity and turning rate to successfully traverse various curved paths. By examining neuronal activity and synaptic changes during this behavior, we found that the cerebellar circuit selectively responded to motion cues in specific receptive fields of simulated middle temporal visual areas. The system described here prompts several hypotheses about the relationship between perception and motor control and may be useful in the development of general-purpose motor learning systems for machines.

Cerebellum↗

PubMed2003

The trichotomous model and investment in learning to prepare for a sport test: a mediational analysis.

BACKGROUND: Contemporary views on motivation suggest that the approach-avoidance achievement goals conceptualization--namely the trichotomous model--can shed light on the important issue of student motivation. AIMS: To test the predictive value of the trichotomous model on the investment in learning a sport task for test preparation, and to validate a model which included a set of psychological processes (i.e., state anxiety and competence valuation) which mediate the relationship between the three goals (i.e., performance-approach, performance-avoidance, and mastery goals) and test preparation. The study was designed to investigate the direct and mediational effects of three experimental goal conditions on the time in which pupils prepared for a sport test. SAMPLE: French male school pupils (N = 75). Pupils were aged 13-15 years and attended schools in southern France. METHOD: Pupils prepared themselves for a sport task with a 5-minute period of training, and performed in one of three experimental conditions to which they were randomly assigned: a performance goal with a positive outcome focus (performance-approach), a performance goal with a negative outcome focus (performance-avoidance), or a mastery goal. RESULTS: Pupils in the performance-avoidance group reported higher state anxiety and lower competence valuation than those in the performance-approach and mastery groups, and this psychological state was associated with less time taken to prepare for the test. CONCLUSION: School pupils placed in an examination preparation context that elicits a performance goal with a negative outcome focus (performance-avoidance) show motivational deficits which manifest themselves in less time spent practising. The trichotomous model appears to be valid for the study of motivational processes in school physical education.

Adolescent↗

PubMed2026

dsRNAscan maps human dsRNAome, revealing conservation, intermolecular dsRNA, and correlates of ADAR dependency.

The human transcriptome contains millions of A-to-I editing sites arising from an unclear number of poorly characterized dsRNAs. Editing sites reveal the presence of dsRNA, but this method is limited by transcription levels, read depth, and ADAR expression and cannot identify unedited dsRNA. To address these limitations, we developed dsRNAscan. Applying dsRNAscan to the human genome predicted 5 million dsRNAs, mostly in repetitive and intergenic regions. Machine learning models trained on A-to-I editing and RNA structure-probing data identified ∼2.4 million high-confidence predictions, which were enriched at dsRNA-binding protein binding sites. Additionally, we predicted hundreds of dsRNAs conserved across vertebrates and observed thousands of editing-enriched regions suspected to arise from intermolecular dsRNAs formed with sense-antisense transcripts. Quantifying expression of intramolecular and intermolecular dsRNAs accessible to cytoplasmic immune sensors revealed that their ratio correlated with ADAR dependency across cancer cell lines. The human dsRNAome is available as a resource at https://dsrna.chpc.utah.edu/.

A-to-I RNA editing↗

PubMed1996

An analysis of errors in the learning, overlearning, and forgetting of sequences.

This paper investigates the effects upon delayed recall of errors made during learning. Subjects learn a sequence of wagons in a model train over repeated presentation and test cycles. The recall of the same sequence is unexpectedly tested one week later. The results show that the errors subjects make during learning are a significant factor in predicting which elements of the sequence are forgotten. Learning is modelled by a population of discrete traces, accumulated during learning, which has two characteristics: First, many of the traces duplicate information encoded in other traces; and second, representations of the correct sequence coexist with traces containing incorrect information about the same elements of the sequence. Forgetting is modelled by the accretion of null traces that compete with correct traces of retrieval and the increasing inability with time to discriminate correct representations in memory from erroneous records. This model is shown to provide a good fit to the experimental results and suggests a strong link between the complete history of learning new material (including errors) and its subsequent likelihood of forgetting.

Attention↗

PubMed1989

Learning and recall in a dynamic theory of coordination patterns.

A dynamic theory of learning and recall of coordination patterns is developed in the context of relative timing skills. Characterizing the coordination patterns in such skills by the collective variable, relative phase, we choose a model system in which the intrinsic pattern dynamics as well as the influence of environmental and memorized information are well understood from previous experimental and theoretical work. To describe learning we endow memorized information with dynamics which is determined by a phenomenological strategy. Similarly, additional degrees of freedom must be introduced to understand recall. As such recall variables we choose the relative strengths with which each memorized pattern acts on the pattern dynamics and model their dynamics phenomenologically. The resulting dynamical system that resembles models used in pattern recognition theory is shown to adequately describe the learning and recall processes. Moreover, due to the operational character of the theory, several predictions emerge that are open to experimental test. In particular, we show under which conditions phase transitions occur in the dynamics of the coordination patterns during learning and during recall. Considering different time scales and their relations we demonstrate how these phase transitions can be identified and observed. Other predictions include the influence of the intrinsic pattern dynamics on the recall process and the existence of history and hysteresis effects in recall. We discuss different forms of "forgetting" and differentiation of memorized information. The results show how a new theoretical view of learning and recall as change of behavioral dynamics can lead to a different understanding of these processes by providing testable predictions.

Extremities↗

PubMed2001

What happens when we relearn part of what we previously knew? Predictions and constraints for models of long-term memory.

Part-set relearning studies examine whether relearning a subset of previously learned items impairs or improves memory for other items in memory that are not relearned. Atkins and Murre have examined part-set relearning using multi-layer networks that learn by optimizing performance on a complete set of items. For this paper, four computer models that learn each item additively and separately were tested using the part-set relearning procedure (Hebbian network, CHARM, MINERVA 2, and SAM). Optimization models predict that part-set relearning should improve memory for items not relearned, while additive models make the opposite prediction. This distinction parallels the relative ability of these models to account for interference phenomena. Part-set relearning provides another source of evidence for choosing between optimization and additive models of long-term memory. A new study suggests that the predictions of the additive models are broadly supported.

Humans↗

PubMed1999

Isokinetic elbow joint torques estimation from surface EMG and joint kinematic data: using an artificial neural network model.

Because the relations between electromyographic signal (EMG) and anisometric joint torque remain unpredictable, the aim of this study was to determine the relations between the EMG activity and the isokinetic elbow joint torque via an artificial neural network (ANN) model. This 3-layer feed-forward network was constructed using an error back-propagation algorithm with an adaptive learning rate. The experimental validation was achieved by rectified, low-pass filtered EMG signals from the representative muscles, joint angle and joint angular velocity and measured torque. Learning with a limited set of examples allowed accurate prediction of isokinetic joint torque from novel EMG activities, joint position, joint angular velocity. Sensitivity analysis of the hidden node numbers during the learning and testing phases demonstrated that the choice of numbers of hidden node was not critical except at extreme values of those parameters. Model predictions were well correlated with the experimental data (the mean root-mean-square-difference and correlation coefficient gamma in learning were 0.0290 and 0.998, respectively, and in three different speed testings were 0.1413 and 0.900, respectively). These results suggested that an ANN model can represent the relations between EMG and joint torque/moment in human isokinetic movements. The effect of different adjacent electrode sites was also evaluated and showed the location of electrodes was very important to produce errors in the ANN model.

Adult↗

PubMedDate not supplied

Data mining and machine learning techniques for the identification of mutagenicity inducing substructures and structure activity relationships of noncongeneric compounds.

This paper explores the utility of data mining and machine learning algorithms for the induction of mutagenicity structure-activity relationships (SARs) from noncongeneric data sets. We compare (i) a newly developed algorithm (MOLFEA) for the generation of descriptors (molecular fragments) for noncongeneric compounds with traditional SAR approaches (molecular properties) and (ii) different machine learning algorithms for the induction of SARs from these descriptors. In addition we investigate the optimal parameter settings for these programs and give an exemplary interpretation of the derived models. The predictive accuracies of models using MOLFEA derived descriptors is approximately 10-15%age points higher than those using molecular properties alone. Using both types of descriptors together does not improve the derived models. From the applied machine learning techniques the rule learner PART and support vector machines gave the best results, although the differences between the learning algorithms are only marginal. We were able to achieve predictive accuracies up to 78% for 10-fold cross-validation. The resulting models are relatively easy to interpret and usable for predictive as well as for explanatory purposes.

Algorithms↗

PubMed2001

Predicting gene function from gene expressions and ontologies.

We introduce a methodology for inducing predictive rule models for functional classification of gene expressions from microarray hybridisation experiments. The basic learning method is the rough set framework for rule induction. The methodology is different from the commonly used unsupervised clustering approaches in that it exploits background knowledge of gene function in a supervised manner. Genes are annotated using Ashburner's Gene Ontology and the functional classes used for learning are mined from these annotations. From the original expression data, we extract a set of biologically meaningful features that are used for learning. A rule model is induced from the data described in terms of these features. Its predictive quality is fine-turned via cross-validation on subsets of the known genes prior to classification of unknown genes. The predictive and descriptive quality of such a rule model is demonstrated on the fibroblast serum response data previously analysed by Iyer et. al. Our analysis shows that the rules are capable of representing the complex relationship between gene expressions and function, and that it is possible to put forward high quality hypotheses about the function of unknown genes.

Algorithms↗

PubMed1996

Context codes and the effect of noisy learning on a simplified hippocampal CA3 model.

This paper investigates how noise affects a minimal computational model of the hippocampus and, in particular, region CA3. The architecture and physiology employed are consistent with the known anatomy and physiology of this region. Here, we use computer simulations to demonstrate and quantify the ability of this model to create context codes in sequential learning problems. These context codes are mediated by local context neurons which are analogous to hippocampal place-coding cells. These local context neurons endow the network with many of its problem-solving abilities. Our results show that the network encodes context on its own and then uses context to solve sequence prediction under ambiguous conditions. Noise during learning affects performance, and it also affects the development of context codes. The relationship between noise and performance in a sequence prediction is simple and corresponds to a disruption of local context neuron firing. As noise exceeds the signal, sequence completion and local context neuron firing are both lost. For the parameters investigated, extra learning trials and slower learning rates do not overcome either of the effects of noise. The results are consistent with the important role played, in this hippocampal model, by local context neurons in sequence prediction and for disambiguation across time.

Artifacts↗

PubMed2025

A robust transfer learning approach for high-dimensional linear regression to support integration of multi-source gene expression data.

Transfer learning aims to integrate useful information from multi-source datasets to improve the learning performance of target data. This can be effectively applied in genomics when we learn the gene associations in a target tissue, and data from other tissues can be integrated. However, heavy-tail distribution and outliers are common in genomics data, which poses challenges to the effectiveness of current transfer learning approaches. In this paper, we study the transfer learning problem under high-dimensional linear models with t-distributed error (Trans-PtLR), which aims to improve the estimation and prediction of target data by borrowing information from useful source data and offering robustness to accommodate complex data with heavy tails and outliers. In the oracle case with known transferable source datasets, a transfer learning algorithm based on penalized maximum likelihood and expectation-maximization algorithm is established. To avoid including non-informative sources, we propose to select the transferable sources based on cross-validation. Extensive simulation experiments as well as an application demonstrate that Trans-PtLR demonstrates robustness and better performance of estimation and prediction when heavy-tail and outliers exist compared to transfer learning for linear regression model with normal error distribution. Data integration, Variable selection, T distribution, Expectation maximization algorithm, Genotype-Tissue Expression, Cross validation.

Linear Models↗

PubMed1997

Improved disability population estimates of functional limitation among American children aged 5-17.

OBJECTIVES: This paper (a) creates and validates measures for population survey data to assess functional limitation in mobility, self-care, communication, and learning ability for school-age American children; (b) calculates rates of functional limitation using these measures, and provides population estimates of the number of children with limitations; and (c) examines these limitations as a function of socioeconomic factors. METHOD: The study is based on data for children aged 5-17 collected in the 1994 National Health Interview Survey on Disability. Ordinal values are assigned to survey items in the four functional areas and analyzed to produce scales of high reliability. These measures are used to identify within a 95% confidence interval the number of children with these limitations. Ordered logistic regression models measure the effects of functional limitations on disability and societal limitation. Socioeconomic differences are measured with an ordered logistic regression model that predicts severity and comorbidity. RESULTS: Limitations in learning ability (10.6%) and communication (5.5%) are the most common, with mobility (1.3%) and self-care (0.9%) occurring less often. Six percent of children have one serious functional limitation and 2.0% have two or more serious functional limitations. This corresponds to 4.0 million school-age American children with serious functional limitations. Functional limitation is strongly linked to socioeconomic disadvantage and to residence in single-mother households. CONCLUSIONS: Future population research should use multiple-item scales for four distinct areas of functional limitation, and a summary that takes into account both severity and comorbidity. The improved estimates of the number of school-age children with functional limitation in this paper may help contribute to a more informed scientific and policy discussion of functional limitation and disability among American school-age children. Future research on the disability process among children must consider the role of socioeconomic disadvantage and family structure.

Activities of Daily Living↗

PubMed2026

BaGGLS: a Bayesian shrinkage framework for interpretable modeling of interactions in high-dimensional biological data.

MOTIVATION: Biological data is often high dimensional, noisy, and governed by complex interactions among sparse signals. This poses major challenges for interpretability and reliable feature selection. Tasks such as identifying motif interactions in genomics exemplify these difficulties, as only a small subset of biologically relevant features (e.g. motifs) are typically active, and their effects are often non-linear and context-dependent. While statistical approaches often result in more interpretable models, deep learning models have proven effective in modeling complex interactions and prediction accuracy, yet their black-box nature limits interpretability. RESULTS: We introduce BaGGLS, a flexible and interpretable probabilistic binary regression model designed for high-dimensional biological inference involving feature interactions. BaGGLS incorporates a Bayesian group global-local shrinkage prior, aligned with the group structure introduced by interaction terms. This prior encourages sparsity while retaining interpretability, helping to isolate meaningful signals and suppress noise. To enable scalable inference, we employ a partially factorized variational approximation that captures posterior skewness and supports efficient learning even in large feature spaces. In extensive simulations, we compare BaGGLS to frequentist probit regressions (unconstrained and with L1-penalty) as well as a probit model with Markov Chain Monte Carlo (MCMC) sampling under a horseshoe prior. We can show that BaGGLS outperforms the other methods with regard to interaction detection and is many times faster than MCMC sampling under the horseshoe prior. We also demonstrate the usefulness of BaGGLS in the context of interaction discovery from motif scanner outputs (e.g. Find Individual Motif Occurrences (FIMO)) and noisy attribution scores from deep learning models. This shows that BaGGLS is a promising approach for uncovering biologically relevant interaction patterns, with potential applicability across a range of high-dimensional tasks in computational biology. AVAILABILITY: Code is available at gitlab.com/dacs-hpi/baggls.

Bayes Theorem↗

PubMed2003

Chaotic itinerancy in coupled dynamical recognizers.

We argue that chaotic itinerancy in interaction between humans originates in the fluctuation of predictions provided by the nonconvergent nature of learning dynamics. A simple simulation model called the coupled dynamical recognizer is proposed to study this phenomenon. Daily cognitive phenomena provide many examples of chaotic itinerancy, such as turn taking in conversation. It is therefore an interesting problem to bridge two chaotic itinerant phenomena. A clue to solving this is the fluctuation of prediction, which can be translated as "hot prediction" in the context of cognitive theory. Hot prediction is simply defined as a prediction based on an unstable model. If this approach is correct, the present simulation will reveal some dynamic characteristics of cognitive interactions.

Cognition↗

PubMed2025

A comparative study highlights superiority of LSTM in crop genomic prediction.

We systematically evaluated three key determinants affecting prediction accuracy and the algorithm performance differences based on fifteen state-of-the-art GP methods, and found LSTM suitable for capturing additive and epistatic effects. Genomic prediction (GP) has been developed as an important method supporting crop breeding. By utilizing the phenotype values result from GP, breeders could make decisions in the seedling stage that consequently benefit for cost saving. In recent years, machine learning emerged as an efficient technology to solve modeling problems in many fields, including crop breeding. However, numerous modeling approaches have hindered the application of GP since breeders struggle to choose. Therefore, a comprehensively methodological research with guiding significance is extremely necessary. In the present study, we systematically evaluated three key determinants affecting prediction accuracy and the algorithm performance differences based on fifteen state-of-the-art GP methods. As for genomic feature processing, we found feature selection (SNP filtering approach) performed better than feature extraction (PCA method). Specifically, the feature relationship dependent methods (GBLUP, RNN, and LSTM) as well as DNN architecture showed superior performance with feature selection. Marker density analysis showed positive correlation with prediction accuracy in a limited threshold. Comparison on effect of population size demonstrated a positive correlation between trait genetic complexity and the optimal population size required. By testing fifteen modeling methods, we found LSTM network displayed superior performance, achieving the highest average STScore (0.967) across six datasets. Further research using all cell states or the latest cell states of LSTM inputs demonstrated its architecture particularly adept with capturing additive and epistatic QTL effects among SNPs. In conclusion, our findings provide basic principles for implementing GP in breeding project to maximize prediction accuracy while maintaining cost-effectiveness.

Plant Breeding↗

PubMed1997

Protein kinase C, learning and memory: a circular determinism between physiology and behaviour.

1. In vertebrates as in invertebrates, protein kinase C appears to have a key role in learning and memory, probably given its involvement in synaptic plasticity. 2. Hippocampal PKC in mammalians is activated by learning in a large variety of memory tasks. However, the kind of information processed, the type of task, and the dynamics of learning processes all induce differential changes in the mode of PKC activation and in its anatomy. 3. The behaviourally induced changes in PKC activity are often varying in their magnitude. Inter-individual differences in PKC basal activity are generally correlated to the ability to learn. 4. Pharmacologic activation and inhibition of brain PKC shows that PKC activation plays an important role in cognitive function. 5. Basal PKC stores characterising each individual could be determined by genetic factors and modulated through life by individual experience. 6. The issue of PKC and memory relationships is reformulated through a comprehensive interactionist model which leads to formulating some new testable predictions.

Animals↗