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 559 records · Page 31Linked to original sources

PubMed2001

Ockham's razor modeling of the matrisome channels of the basal ganglia thalamocortical loops.

A functional model of the basal ganglia-thalamocortical (BTC) loops is described. In our modeling effort, we try to minimize the complexity of our starting hypotheses. For that reason, we call this type of modeling Ockham's razor modeling. We have the additional constraint that the starting assumptions should not contradict experimental findings about the brain. First assumption: The brain lacks direct representation of paths but represents directions (called speed fields in control theory). Then control should be concerned with speed-field tracking (SFT). Second assumption: Control signals are delivered upon differencing in competing parallel channels of the BTC loops. This is modeled by extending SFT with differencing that gives rise to the robust Static and Dynamic State (SDS) feedback-controlling scheme. Third assumption: Control signals are expressed in terms of a gelatinous medium surrounding the limbs. This is modeled by expressing parameters of motion in parameters of the external space. We show that corollaries of the model fit properties of the BTC loops. The SDS provides proper identification of motion related neuronal groups of the putamen. Local minima arise during the controlling process that works in external space. The model explains the presence of parallel channels as the means to avoiding such local minima. Stability conditions of the SDS predict that the initial phase of learning is mostly concerned with selection of sign for the inverse dynamics. The model provides a scalable controller. State description in external space instead of configurational space reduces the dimensionality problem. Falsifying experiment is suggested. Computer experiments demonstrate the feasibility of the approach. We argue that the resulting scheme has a straightforward connectionist representation exhibiting population coding and Hebbian learning properties.

Basal Ganglia↗

PubMed2024

PredIL13: Stacking a variety of machine and deep learning methods with ESM-2 language model for identifying IL13-inducing peptides.

Interleukin (IL)-13 has emerged as one of the recently identified cytokine. Since IL-13 causes the severity of COVID-19 and alters crucial biological processes, it is urgent to explore novel molecules or peptides capable of including IL-13. Computational prediction has received attention as a complementary method to in-vivo and in-vitro experimental identification of IL-13 inducing peptides, because experimental identification is time-consuming, laborious, and expensive. A few computational tools have been presented, including the IL13Pred and iIL13Pred. To increase prediction capability, we have developed PredIL13, a cutting-edge ensemble learning method with the latest ESM-2 protein language model. This method stacked the probability scores outputted by 168 single-feature machine/deep learning models, and then trained a logistic regression-based meta-classifier with the stacked probability score vectors. The key technology was to implement ESM-2 and to select the optimal single-feature models according to their absolute weight coefficient for logistic regression (AWCLR), an indicator of the importance of each single-feature model. Especially, the sequential deletion of single-feature models based on the iterative AWCLR ranking (SDIWC) method constructed the meta-classifier consisting of the top 16 single-feature models, named PredIL13, while considering the model's accuracy. The PredIL13 greatly outperformed the-state-of-the-art predictors, thus is an invaluable tool for accelerating the detection of IL13-inducing peptide within the human genome.

Humans↗

PubMed2026

Integrating histology and spatial transcriptomics via multimodal transformers and contrastive representation learning for accurate gene expression prediction.

Predicting spatial gene expression from Histological images is a fundamental task in understanding tissue organization and molecular phenotypes. However, existing methods often rely on single-model representations or lack effective alignment between image and transcriptomic features. To address these limitations, we propose a unified multimodal learning framework that integrates histological imaging and spatial transcriptomics through a shared latent representation space. Specifically, histological H&E images are encoded by a ResNet50-based convolutional stem and a MobileViT Transformer backbone to extract hierarchical visual representations. Both modalities are projected into a shared latent space via linear-GELU-dropout transformation blocks, enabling cross-modal alignment through a contrastive learning objective that maximizes agreement between the corresponding image and the spot embeddings. Experimental results on the 10x Genomics Visium dataset of human liver tissue demonstrate that MViTGene achieves significantly higher prediction accuracy than existing methods across multiple gene subsets, with improvements of 20%, 33%, and 12% in predicting marker genes, highly expressed genes, and highly variable genes, respectively. The significant improvement in relevance indicates that the model can more accurately capture the true correspondence between tissue morphology and gene expression, therefore enabling more reliable biological interpretation. It provides a computational tool for high-throughput spatial gene expression prediction that balances performance and interpretability.

Humans↗

PubMed2026

Predicting genome-wide functional constraints with GPN-Star.

Genomic language models have emerged as a powerful approach for learning genome-wide functional constraints directly from DNA sequences1. However, standard genomic language models adapted from natural language processing often require large model sizes and computational resources, yet still fall short of classical evolutionary models in predictive tasks2-4. Here we introduce a genomic pretrained network with species tree and alignment representations (GPN-Star), which is a biologically grounded genomic language model featuring a phylogeny-aware architecture that leverages whole-genome alignments and species trees to model evolutionary relationships explicitly. Trained on alignments spanning vertebrate, mammal and primate evolutionary timescales, GPN-Star achieves state-of-the-art performance across a wide range of variant effect prediction tasks in both coding and non-coding regions of the human genome. Analyses across timescales show task-dependent advantages of modelling more recent versus deeper evolution. To demonstrate its potential to advance human genetics, we show that GPN-Star substantially outperforms previous methods in prioritizing pathogenic and fine-mapped genome-wide association study variants, yields strong enrichments of complex trait heritability and improves power in rare variant association testing5. Extending beyond humans, we train GPN-Star for five model organisms-Mus musculus, Gallus gallus, Drosophila melanogaster, Caenorhabditis elegans and Arabidopsis thaliana-demonstrating the robustness and generalizability of the framework. Taken together, these results position GPN-Star as a scalable, powerful and flexible tool for genome interpretation, well suited to leverage the growing abundance of comparative genomics data.

Journal Article↗

PubMed2006

Gaze following: why (not) learn it?

We propose a computational model of the emergence of gaze following skills in infant-caregiver interactions. The model is based on the idea that infants learn that monitoring their caregiver's direction of gaze allows them to predict the locations of interesting objects or events in their environment (Moore & Corkum, 1994). Elaborating on this theory, we demonstrate that a specific Basic Set of structures and mechanisms is sufficient for gaze following to emerge. This Basic Set includes the infant's perceptual skills and preferences, habituation and reward-driven learning, and a structured social environment featuring a caregiver who tends to look at things the infant will find interesting. We review evidence that all elements of the Basic Set are established well before the relevant gaze following skills emerge. We evaluate the model in a series of simulations and show that it can account for typical development. We also demonstrate that plausible alterations of model parameters, motivated by findings on two different developmental disorders - autism and Williams syndrome - produce delays or deficits in the emergence of gaze following. The model makes a number of testable predictions. In addition, it opens a new perspective for theorizing about cross-species differences in gaze following.

Animals↗

PubMed2001

Investigating the role of context in learning to read: a direct test of Goodman's model.

The much discussed 'whole language' or 'real books' approach to children's reading is based on a theory which makes two quite separate predictions: (1) that children will read difficult words more successfully in context than in isolation, and (2) that contextual experience of words will lead to greater improvements in word reading than isolated experience of words. We report a study which tests both predictions and supports the first but not the second.

Child↗

PubMed2005

Another look at retroactive and proactive interference: a quantitative analysis of conversion processes.

Traditionally, the causes of interference phenomena were sought in "real" or "hard" memory processes such as unlearning, response competition, or inhibition, which serve to reduce the accessibility of target items. I propose an alternative approach which does not deny the influence of such processes but highlights a second, equally important, source of interference-the conversion (Tulving, 1983) of accessible memory information into memory performance. Conversion is conceived as a problem-solving-like activity in which the rememberer tries to find solutions to a memory task. Conversion-based interference effects are traced to different conversion processes in the experimental and control conditions of interference designs. I present a simple theoretical model that quantitatively predicts the resulting amount of interference. In two paired-associate learning experiments using two different types of memory tests, these predictions were corroborated. Relations of the present approach to traditional accounts of interference phenomena and implications for eyewitness testimony are discussed.

Adult↗

PubMed2002

Initiation and maintenance of exercise behavior in older women: predictors from the social learning model.

The purpose of the present study was to determine the extent to which modifiable social learning constructs predicted long-term adherence to an exercise program in older individuals. Participants were 189 women aged 59 to 78 years and diagnosed with low bone density. Exercise behavior was assessed at 3-month intervals. Self-efficacy, readiness for change, orientation toward exercise, social support in general, and support specifically for exercise were measured at baseline and at 12-month follow-up. Analyses indicated that initial adoption of exercise behavior was best predicted by readiness to change. Maintenance was predicted by self-efficacy for exercise, and exercise behavior at 12 months was predicted by social support for exercise. The results were seen as supportive of the stages and processes of change model of health behavior change. Implications of the findings for interventions to enhance adoption and maintenance of exercise programs by older women are discussed.

Aged↗

PubMed2025

Predicting functional constraints across evolutionary timescales with phylogeny-informed genomic language models.

Genomic language models (gLMs) have emerged as a powerful approach for learning genome-wide functional constraints directly from DNA sequences. However, standard gLMs adapted from natural language processing often require extremely large model sizes and computational resources, yet still fall short of classical evolutionary models in predictive tasks. Here, we introduce GPN-Star (Genomic Pretrained Network with Species Tree and Alignment Representation), a biologically grounded gLM featuring a phylogeny-aware architecture that leverages whole-genome alignments and species trees to model evolutionary relationships explicitly. Trained on alignments spanning vertebrate, mammalian, and primate evolutionary timescales, GPN-Star achieves state-of-the-art performance across a wide range of variant effect prediction tasks in both coding and non-coding regions of the human genome. Analyses across timescales reveal task-dependent advantages of modeling more recent versus deeper evolution. To demonstrate its potential to advance human genetics, we show that GPN-Star substantially outperforms prior methods in prioritizing pathogenic and fine-mapped GWAS variants; yields unprecedented enrichments of complex trait heritability; and improves power in rare variant association testing. Extending beyond humans, we train GPN-Star for five model organisms - Mus musculus, Gallus gallus, Drosophila melanogaster, Caenorhabditis elegans, and Arabidopsis thaliana - demonstrating the robustness and generalizability of the framework. Taken together, these results position GPN-Star as a scalable, powerful, and flexible new tool for genome interpretation, well suited to leverage the growing abundance of comparative genomics data.

Journal Article↗

PubMed2026

pKAKA: a protein language model for prioritizing kinase-disrupting variants in diseases.

Protein kinases are pivotal regulators of cellular signaling, and their genetic variations are frequently implicated in diseases. Although numerous kinase mutations have been identified as drivers of altered activity, with a few successfully targeted therapeutically, the functional impact of most variants remains uncharacterized. To bridge this gap, we curate a comprehensive dataset that contains 2553 experimentally validated kinase activity-related key alterations (KAKAs) from the literature. While many mutations outside canonical functional regions are known to affect kinase activity, systematic methods to predict their functional consequences are lacking. Consequently, we develop a computational method to predict potential KAKAs, leveraging transfer learning on the pre-trained protein language model ProtBert. Our model, termed pKAKA, achieves an impressive AUC score of 0.9593 and outperforms the AlphaMissense benchmark in comparative testing. Systematic analysis of kinase missense mutations underscores the critical role of KAKAs in pathogenesis, with highlights including JAK2 V617F in atherosclerotic cardiovascular disease, LRRK2 G2385R in Parkinson's disease, EGFR L858R in lung adenocarcinoma, and EGFR G598V in glioma. Overall, this study significantly advances our understanding of how mutations that influence kinase activity contribute to disease mechanisms.

Humans↗

PubMed2003

Gene networks inference using dynamic Bayesian networks.

This article deals with the identification of gene regulatory networks from experimental data using a statistical machine learning approach. A stochastic model of gene interactions capable of handling missing variables is proposed. It can be described as a dynamic Bayesian network particularly well suited to tackle the stochastic nature of gene regulation and gene expression measurement. Parameters of the model are learned through a penalized likelihood maximization implemented through an extended version of EM algorithm. Our approach is tested against experimental data relative to the S.O.S. DNA Repair network of the Escherichia coli bacterium. It appears to be able to extract the main regulations between the genes involved in this network. An added missing variable is found to model the main protein of the network. Good prediction abilities on unlearned data are observed. These first results are very promising: they show the power of the learning algorithm and the ability of the model to capture gene interactions.

Algorithms↗

PubMed1991

Effects of early common features on form perception.

Recognizing forms may involve a contingency in which later processing is modified, depending on the results of early analyses. This hypothesis can be distinguished from feature models, in which features (including early global features) accumulate over time. In four experiments, shape primes were presented briefly, followed immediately and in the same location by a similarly or differently shaped target, and then a mask. Accuracy was measured with a two-alternative forced-choice discrimination. The primes facilitated discriminations between a similarly shaped target and differently shaped foil, as would be expected. More important is that the primes also facilitated discriminations between similarly shaped targets and similarly shaped foils, even though the primes contained only features common to the alternatives and thus provided no discrimination-relevant information. The facilitation effect was constant over variations in the size of the target set, the type of mask, and the type of baseline condition. This result is consistent with the idea of early-to-late contingencies in processing but was not predicted by feature models.

Adult↗

PubMed2006

When more is less: negative exposure effects in unsupervised learning.

In this article, two broad classes of models of unsupervised learning are compared: correlation tracking models, according to which learning is expected to increase monotonically with exposure to instances, and category invention models, which can accommodate specific violations of monotonicity (negative exposure effects). In two experiments, increasing the number of training instances had a negative rather than a positive effect on unsupervised learning, a clear violation of monotonicity. The results of these experiments are then compared with the predictions of two computational models, one a category invention model and the other a correlation tracking model. The category invention model was able to reproduce the qualitative pattern of results from the human data, whereas the correlation tracking model was not. Overall, these results provide strong evidence for the existence of a discrete category invention process in unsupervised learning.

Affect↗

PubMed1991

Two-stage model for order discrimination.

Ulrich (1987), exploring the shapes of psychometric functions obtained in the ternary-response paradigm, indicated several inconsistencies between observed and predicted relationships providing evidence against most popular models of temporal-order judgment. In this paper, a new model is presented. It assumes that there are two mechanisms involved in the order discrimination task: one is responsible for the recognition of whether or not the stimuli are successive, and the second is able to determine their order. The model was tested using Allan's (1975a, 1975b) and Ulrich's (1987) data; the model predictions were found to be consistent with the experimental results.

Attention↗

PubMed2003

Transitivity, flexibility, conjunctive representations, and the hippocampus. II. A computational analysis.

A computational neural network model is presented that explains how the hippocampus can contribute to transitive inference performance observed in rats (Dusek and Eichenbaum, 1997. Proc Natl Acad Sci U S A 94:7109-7114; Van Elzakker et al., 2003. Hippocampus 12:this issue). In contrast to existing theories that emphasize the idea that the hippocampus contributes by flexibly relating previously encoded memories, we find that the hippocampus contributes by altering the elemental associative weights of individual stimulus elements during learning. We use this model to account for a range of existing data and to make a number of distinctive predictions that clearly contrast these two views.

Animals↗

PubMed2005

Flow rate of some pharmaceutical diluents through die-orifices relevant to mini-tableting.

The effects of cylindrical orifice length and diameter on the flow rate of three commonly used pharmaceutical direct compression diluents (lactose, dibasic calcium phosphate dihydrate and pregelatinised starch) were investigated, besides the powder particle characteristics (particle size, aspect ratio, roundness and convexity) and the packing properties (true, bulk and tapped density). Flow rate was determined for three different sieve fractions through a series of miniature tableting dies of different orifice diameter (0.4, 0.3 and 0.2 cm) and thickness (1.5, 1.0 and 0.5 cm). It was found that flow rate decreased with the increase of the orifice length for the small diameter (0.2 cm) but for the large diameter (0.4 cm) was increased with the orifice length (die thickness). Flow rate changes with the orifice length are attributed to the flow regime (transitional arch formation) and possible alterations in the position of the free flowing zone caused by pressure gradients arising from the flow of self-entrained air, both above the entrance in the die orifice and across it. Modelling by the conventional Jones-Pilpel non-linear equation and by two machine learning algorithms (lazy learning, LL, and feed-forward back-propagation, FBP) was applied and predictive performance of the fitted models was compared. It was found that both FBP and LL algorithms have significantly higher predictive performance than the Jones-Pilpel non-linear equation, because they account both dimensions of the cylindrical die opening (diameter and length). The automatic relevance determination for FBP revealed that orifice length is the third most influential variable after the orifice diameter and particle size, followed by the bulk density, the difference between bulk and tapped densities and the particle convexity.

Algorithms↗

PubMedDate not supplied

[The role of type 2 serotonin receptors, 5-HT2A and 5-HT2C, in depressive disorders: effect of medifoxamine].

The serotonin (5-HT) is implicated in many centrally-regulated functions and has shown to be involved in affective disorders, such as depression and anxiety disorders. Recent progress in pharmacology and molecular neurobiology have confirmed the concept of the heterogeneity of 5-HT receptors and permitted reformulation of new hypothesis concerning antidepressant mechanisms of action, in particular those concerning serotoninergic receptors. Up to date, among the 5-HT defined sites, only 13 have been cloned, and several subfamilies have been described. Particularly, the 5-HT1 family containing receptors: 5-HT1A, 5-HT1B/1D, 5-HT1E and 5-HT1F. The 5-HT2 family includes receptors that stimulate phospholipase C: 5-HT2A (previously termed 5-HT2), 5-HT2B and 5-HT2C (previously termed 5-HT1C). Concerning 5-HT2 family, it is possible that some 5-HT binding drugs properties initially attributed to 5-HT2A receptors, might well be mediated by 5-HT2C receptors. Recently, medifoxamine (Cledial) activities on 5-HT systems have been shown. In particular, these activities are related on 5-HT2C and/or 5-HT2A binding sites. Results indicate that, in vitro, medifoxamine affinities (Ki) are near to 1 microM, for both 5-HT2C and 5-HT2A sites (ratio = 1.42). On the other hand, m-CPP, an 5-HT2C agonist, considered as a reference compound, has the same affinities that medifoxamine, but a higher one for 5-HT2A (ratio = 3.42). In animals models considered as predictive for psychotropic activity in human, we investigate in rat the impact of medifoxamine on 5-HT2C receptors, using Learned-Helplessness model (LH) and the social interaction test.(ABSTRACT TRUNCATED AT 250 WORDS)

Animals↗

PubMed2004

Role of hippocampal CA3 mu-opioid receptors in spatial learning and memory.

The dorsal CA3 region of the hippocampus is unique in its connectivity, sensitivity to neurotoxic lesions, and its ability to encode and retrieve episodic memories. Computational models of the CA3 region predict that blocking mossy-fiber and/or perforant path activity to CA3 would cause impairments in learning and recall of spatial memory, respectively. Because the CA3 region contains micro-opioid receptors and receives inputs from the mossy-fiber and lateral perforant pathways, both of which contain and release opioid peptides, we tested the hypothesis that inactivating micro-opioid receptors in the CA3 region would cause spatial learning and memory impairments and retrieval deficits. In this study, male Sprague Dawley rats were trained in a Morris water maze after a single bilateral intrahippocampal injection of either saline or the selective and irreversible micro-opioid receptor antagonist beta-funaltrexamine (beta-FNA) into area CA3. We found that micro-opioid receptor binding decreased 24 hr after beta-FNA injection and returned to control levels 11 d after injection. Injections of beta-FNA into the CA3 region, but not into the ventricles, caused a significant impairment in the acquisition of spatial learning without causing sensory or motor deficits. New learning was not affected once micro-opioid receptor levels replenished (>11 d after injection). In pretrained animals, beta-FNA significantly impaired spatial memory retrieval and new (reversal) learning. These data are consistent with theoretical models of CA3 function and suggest that CA3 micro-opioid receptors play an important role in the acquisition and retrieval of spatial memory.

Animals↗