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 1,747 records · Page 97Linked to original sources

PubMed2006

Spatial memory deficits in middle-aged mice correlate with lower exploratory activity and a subordinate status: role of hippocampal neurotrophins.

The aim of the present work was to relate age-related individual differences in cognitive function with behavioural strategies employed in social and non-social challenges. To this purpose, the behaviour of adult (5-month-old) and middle-aged (13-month-old) CD-1 mice was scored in the social interaction, plus-maze, Morris water maze (MWM) and open-field tests. In addition, brain levels of nerve growth factor and brain-derived neurotrophic factor (BDNF) were analysed and correlated with the behaviours scored. Compared to adults, middle-aged mice showed greater anxiety in both non-social and social situations, spending less time in the open arms of the plus-maze and performing more freezing behaviour in response to aggression. Based upon their behaviour in the social interaction test, adult and middle-aged subjects were classified as dominant or subordinate and their behaviour in the open field, plus-maze and MWM tests subjected to factor analysis, taking into account age and social status. Results highlighted meaningful differences in exploratory strategies as a function of social status only in middle-aged subjects. In particular, middle-aged dominants were, overall, more explorative than same-aged subordinates, spending less time in peripheral areas and approaching more readily a novel object. Interestingly, in middle-aged mice, superior performance in the MWM task was associated with exploratory strategies exploited by dominants. At adulthood, BDNF hippocampal levels, but not specific behaviours, were positively correlated with the ability to learn a spatial task. Overall, data indicate that, in middle-aged subjects individual differences in exploratory strategies, rather than neurotrophin levels, are able to predict the degree of impairment in a spatial learning task.

Age Factors↗

PubMed2000

Middle-ear disease in remote Aboriginal Australia: a field assessment of surgical outcomes.

Chronic middle-ear disease is highly prevalent among Australian Aboriginal people, and many undergo surgical treatment. However, the outcomes of surgery in this group have not been fully evaluated. This is a descriptive study of operations for middle-ear disease (excluding grommets) on Aboriginal patients in Kimberley hospitals between 1 October 1986 and 31 December 1995. Logistic regression was used to model predictors of surgical outcome. Success was defined by an intact tympanic membrane and air-bone gap of < or = 25 dB at review at, or later than, six months post-operation. A success rate of 53 per cent was observed; increasing age was the only variable predictive of success. Successful outcomes were more likely in adults and children aged > 10 years, however, this does not take into account the necessity of hearing for language acquisition and learning. Dedicated resources must be allocated for post-operative follow-up of Aboriginal patients so that much-needed, rigorous evaluations of ENT surgery can be conducted.

Adolescent↗

PubMed2004

Mismatch string kernels for discriminative protein classification.

MOTIVATION: Classification of proteins sequences into functional and structural families based on sequence homology is a central problem in computational biology. Discriminative supervised machine learning approaches provide good performance, but simplicity and computational efficiency of training and prediction are also important concerns. RESULTS: We introduce a class of string kernels, called mismatch kernels, for use with support vector machines (SVMs) in a discriminative approach to the problem of protein classification and remote homology detection. These kernels measure sequence similarity based on shared occurrences of fixed-length patterns in the data, allowing for mutations between patterns. Thus, the kernels provide a biologically well-motivated way to compare protein sequences without relying on family-based generative models such as hidden Markov models. We compute the kernels efficiently using a mismatch tree data structure, allowing us to calculate the contributions of all patterns occurring in the data in one pass while traversing the tree. When used with an SVM, the kernels enable fast prediction on test sequences. We report experiments on two benchmark SCOP datasets, where we show that the mismatch kernel used with an SVM classifier performs competitively with state-of-the-art methods for homology detection, particularly when very few training examples are available. Examination of the highest-weighted patterns learned by the SVM classifier recovers biologically important motifs in protein families and superfamilies.

Algorithms↗

PubMed1997

Empirical parameterization of a model for predicting peptide helix/coil equilibrium populations.

A modification of the Lifson-Roig formulation of helix/coil transitions is presented; it (1) incorporates end-capping and coulombic (salt bridges, hydrogen bonding, and side-chain interactions with charged termini and the helix dipole) effects, (2) helix-stabilizing hydrophobic clustering, (3) allows for different inherent termination probabilities of individual residues, and (4) differentiates helix elongation in the first versus subsequent turns of a helix. Each residue is characterized by six parameters governing helix formation. The formulation of the conditional probability of helix initiation and termination that we developed is essentially the same as one presented previously (Shalongo W, Stellwagen, E. 1995. Protein Sci 4:1161-1166) and nearly the mathematical equivalent of the new capping formulation incorporated in the model presented by Rohl et al. (1996. Protein Sci 5:2623-2637). Side-chain/side-chain interactions are, in most cases, incorporated as context dependent modifications of propagation rather than nucleation parameters. An alternative procedure for converting [theta]221 values to experimental fractional helicities ( ) is presented. Tests of the program predictions suggest this method may have some advantages both for designed peptides and for the analysis of secondary structure preferences that could drive the formation of molten-globule intermediates on protein folding pathways. The model predicts the fractional helicity of 385 peptides with a root-mean-square deviation (RMSD) of 0.050 and locates (with precise definition of the termini in many cases) helices in proteins as well as competing methods. The propagation and nucleation parameters were derived from NMR data and from the CD data for a 79 peptide "learning set" for which an excellent fit resulted (RMSD = 0.0295). The current set of parameter corrections for capping boxes, helix dipole interactions, and side-chain/side-chain interactions (coulombic, hydrogen bonding and hydrophobic clustering), although still under development provide a significant improvement in both helix/coil equilibrium prediction for peptides and helix location in protein sequences. This is clearly evident in the rms deviations between CD measures and calculated values of fractional helicity for different classes of peptides before and after applying the corrections: for peptides lacking capping boxes and i/i + 3 and i/i + 4 side-chain/side-chain interactions RMSD = 0.044 (n = 164) versus RMSD = 0.054 (0.172 without the corrections, n = 221) for peptides that required context-dependent corrections of the parameters. If we restrict the analysis to N-acylated peptides with helix stabilizing side-chain/side-chain interactions (including N-capping boxes), the degree to which our corrections account for the stabilizing interaction can be judged from the change in helicity underestimation, ( calc- CD): -0.15 +/- 0.10, which is reduced to -0.018 +/- 0.048 (n = 191) upon applying the corrections.

Algorithms↗

PubMed2026

ChromBERT-tools: a versatile toolkit for context-specific regulatory representations of transcription regulators across different cell types.

SUMMARY: Representations that encode the genome-wide regulatory behavior of transcription regulators provide a foundation for flexible transcription modeling and in silico regulatory analysis. Existing regulator representations are commonly derived from gene co-expression, motif annotations, or static protein features, which capture useful but limited aspects of regulator identity but do not directly model how regulators participate in region-specific regulatory programs across the genome. ChromBERT addresses this gap by learning context-aware regulatory representations from large-scale ChIP-seq data. However, routine bioinformatics applications require lightweight, accessible, and modular tools for generating, adapting, and interpreting these representations in user-defined biological contexts. Here, we present ChromBERT-tools, a user-oriented toolkit built upon ChromBERT that converts its regulatory representation framework into practical workflows for customizable analysis across cellular contexts. ChromBERT-tools provides command-line interfaces and Python APIs organized into three functional layers: representation generation, predictive modeling, and regulatory interpretation. The representation generation layer produces representations of genomic regions and transcription regulators. The predictive modeling layer fine-tunes ChromBERT for genome-wide regulatory activity prediction through classification or regression tasks, with optimized implementation to reduce running time and computational resource requirements. The regulatory interpretation layer supports inference of the context-specific roles of cis-regulatory elements and transcription regulators. These modules can be used independently or integrated into end-to-end workflows, enabling flexible analyses across diverse datasets. ChromBERT-tools lowers the barrier to applying context-specific regulatory representations in routine genomic analyses. AVAILABILITY AND IMPLEMENTATION: ChromBERT-tools is freely available at https://github.com/TongjiZhanglab/ChromBERT-tools, with documentation at https://chrombert-tools.readthedocs.io/en/latest/. A frozen archival snapshot is available on Zenodo under DOI: 10.5281/zenodo.20094206.

Software↗

PubMed1998

A comparison of statistical learning methods on the Gusto database.

We apply a battery of modern, adaptive non-linear learning methods to a large real database of cardiac patient data. We use each method to predict 30 day mortality from a large number of potential risk factors, and we compare their performances. We find that none of the methods could outperform a relatively simple logistic regression model previously developed for this problem.

Databases as Topic↗

PubMed2001

How valuable are animal models in defining antidepressant activity?

Animal models of depression have been utilised to screen novel compounds with antidepressant potential although uncertainty lingers concerning their clinical relevance. In order for a model to be considered of any value, it must possess predictive validity (does drug action in the model correspond to that in the clinic?), face validity (are there phenomenological similarities between the model and the clinic?) and construct validity (does the model possess a strong theoretical rationale?). On the one hand, there are models based on stress such as the learned helplessness model, the forced swimming test and the chronic mild stress model and, on the other hand, models based on neuronal deficits such as the olfactory bulbectomy model. To date, among models more frequently used in depression, none of them meet all these criteria. Moreover, improvements to tests are often poorly validated and estimating time of onset of action of antidepressants remains a major challenge in animal model research. Finally, reproducing the tests outside the laboratory of origin continues to be problematic and leads to variability in results. Although animal models of depression fail to be unequivocally valid, they represent the best tool to define potential antidepressant activity of drugs, to investigate their mechanism of action and, to a greater extent, explore this complex heterogeneous illness. Copyright 2001 John Wiley & Sons, Ltd.

Journal Article↗

PubMed1990

Trajectory formation of arm movement by cascade neural network model based on minimum torque-change criterion.

We proposed that the trajectory followed by human subject arms tended to minimize the time integral of the square of the rate of change of torque (Uno et al. 1987). This minimum torque-change model predicted and reproduced human multi-joint movement data quite well (Uno et al. 1989). Here, we propose a neural network model for trajectory formation based on the minimum torque-change criterion. Basic ideas of information representation and algorithm are (i) spatial representation of time, (ii) learning of forward dynamics and kinetics model and (iii) relaxation computation based on the acquired model. The model can resolve ill-posed inverse kinematics and inverse dynamics problems for redundant controlled object as well as ill-posed trajectory formation problems. By computer simulation, we show that the model can produce a multi-joint arm trajectory while avoiding obstacles or passing through viapoints.

Algorithms↗

PubMed2006

Cheminformatics analysis and learning in a data pipelining environment.

Workflow technology is being increasingly applied in discovery information to organize and analyze data. SciTegic's Pipeline Pilot is a chemically intelligent implementation of a workflow technology known as data pipelining. It allows scientists to construct and execute workflows using components that encapsulate many cheminformatics based algorithms. In this paper we review SciTegic's methodology for molecular fingerprints, molecular similarity, molecular clustering, maximal common subgraph search and Bayesian learning. Case studies are described showing the application of these methods to the analysis of discovery data such as chemical series and high throughput screening results. The paper demonstrates that the methods are well suited to a wide variety of tasks such as building and applying predictive models of screening data, identifying molecules for lead optimization and the organization of molecules into families with structural commonality.

Anti-Infective Agents↗

PubMed2002

Spike-timing-dependent synaptic plasticity - the long road towards understanding neuronal mechanisms of learning and memory.

Depending on the precise temporal relationship between their spiking activities, connections between neurons could be modified in opposite directions. Although the functional implications of this spike-timing-dependent plasticity are not clear, several theoretical studies have indicated that it could underlie important effects such as sequence learning, predictive learning and balancing excitation and inhibition. To explore fully this novel form of synaptic plasticity, it is crucial to understand how the modification builds up over the consecutive spikes of presynaptic and postsynaptic neurons. In the absence of solid data, many theorists assumed a linear summation model. However, recent experiments specifically devised to study this issue have demonstrated that the effects of the consecutive spikes on the overall modification steadily decline, indicating strong non-linearities in the corresponding learning rules.

Animals↗

PubMed2004

The impact of HIV-associated neuropsychological impairment on everyday functioning.

HIV-1 infection can be associated with neuropsychological (NP) deficits ranging from subtle to severe. The purpose of this study was to evaluate the functional, or "real-world" impact of HIV-associated NP impairment in a group of 267 HIV-infected participants. All participants received comprehensive NP, neuromedical, and standardized functional evaluations that included laboratory measures of shopping, cooking, financial management, medication management and vocational abilities. Compared to NP-normal participants, those with NP impairment performed significantly worse on all laboratory measures of everyday functioning. Multivariate analyses revealed that the NP ability domains of Abstraction/Executive Function, Learning, Attention/Working Memory and Verbal abilities most strongly and consistently predicted failures on the functional battery. Both NP impairment and impairment on the functional battery were significantly associated with subjective experiences of cognitive difficulties, as well as unemployment and increased dependence in activities of daily living; multivariate prediction models that also considered depressed mood and biological measures of disease progression revealed that impairment on the functional battery and depression were the only unique predictors of all three indicators of "real-world" functioning. The current results add to growing evidence concerning the clinical significance of HIV-associated NP impairment. Objective, laboratory based functional measures, such as those used here, may compliment NP testing in future studies directed at understanding the impact on life quality of central nervous system disorders and their treatments. Finally, there is a need for additional research investigating the apparently independent effect of depression on level of everyday functioning in HIV infected persons.

Activities of Daily Living↗

PubMed2005

Neuroanatomic correlates of CVLT-C performance following pediatric traumatic brain injury.

Traumatic brain injury (TBI) frequently results in memory problems, and the degree of memory impairment is related to injury severity and is commonly associated with lesions in frontal and temporal brain areas. This study examined the relationship among injury severity, brain lesions, and memory in children with moderate to severe TBI using Donders' (1999) 5-factor model of performance on the California Verbal Learning Test-Children's Version (CVLT-C). Seventy-six children underwent magnetic resonance imaging (MRI) scans 3 months post-TBI and testing 1 year post-TBI. Results showed injury severity (Glasgow Coma Scale) was not predictive of performance on 4 of the 5 factors. Volume of frontal and/or temporal brain lesions was significantly predictive of performance on 3 of the 5 factors. Unexpectedly, lesion volume outside these areas (extra-frontotemporal) was predictive of performance on all 5 factors. In contrast, Verbal IQ at 1 year was most strongly associated with preinjury factors (socioeconomic status and special education involvement), although extra-frontotemporal lesions also contributed to the variability in this measure. Results suggest that in children with moderate to severe TBI, extra-frontal/temporal lesions are predictive of memory outcome 1 year postinjury above and beyond initial severity or frontal/temporal contusions. This finding may relate to widespread diffuse axonal injury, which potentially disconnects brain circuits mediating memory following moderate to severe TBI.

Adolescent↗

PubMedDate not supplied

Results of a new classification algorithm combining K nearest neighbors and recursive partitioning.

We present results of a new computational learning algorithm combining favorable elements of two well-known techniques: K nearest neighbors and recursive partitioning. Like K nearest neighbors, the method provides an independent prediction for each test sample under consideration, while like recursive partitioning, it incorporates an automatic selection of important input variables for model construction. The new method is applied to the problem of correctly classifying a set of chemical data samples designated as being either active or inactive in a biological screen. Training is performed at varying levels of intrinsic model complexity, and classification performance is compared to that of both K nearest neighbor and recursive partitioning models trained using the identical protocol. We find that the cross-validated performance of the new method outperforms both of these standard techniques over a considerable range of user parameters. We discuss advantages and drawbacks of the new method, with particular emphasis on its parameter robustness, required training time, and performance with respect to chemical structural class.

Journal Article↗

PubMed1994

Artificial intelligence in molecular biology: a review and assessment.

Over the past ten years, molecular biologists and computer scientists have experimented with various computational methods developed in artificial intelligence (AI). AI research has yielded a number of novel technologies, which are typified by an emphasis on symbolic (non-numerical) programming methods aimed at problems which are not amenable to classical algorithmic solutions. Prominent examples include knowledge-based and expert systems, qualitative simulation and artificial neural networks and other automated learning techniques. These methods have been applied to problems in data analysis, construction of advanced databases and modelling of biological systems. Practical results are now being obtained, notably in the recognition of active genes in genomic sequences, the assembly of physical and genetic maps and protein structure prediction. This paper outlines the principal methods, surveys the findings to date, and identifies the promising trends and current limitations.

Algorithms↗

PubMed2025

Landscape of essential growth and fluconazole-resistance genes in the human fungal pathogen Cryptococcus neoformans.

Fungi can cause devastating invasive infections, typically in immunocompromised patients. Treatment is complicated both by the evolutionary similarity between humans and fungi and by the frequent emergence of drug resistance. Studies in fungal pathogens have long been slowed by a lack of high-throughput tools and community resources that are common in model organisms. Here we demonstrate a high-throughput transposon mutagenesis and sequencing (TN-seq) system in Cryptococcus neoformans that enables genome-wide determination of gene essentiality. We employed a random forest machine learning approach to classify the C. neoformans genome as essential or nonessential, predicting 1,465 essential genes, including 302 that lack human orthologs. These genes are ideal targets for new antifungal drug development. TN-seq also enables genome-wide measurement of the fitness contribution of genes to phenotypes of interest. As proof of principle, we demonstrate the genome-wide contribution of genes to growth in fluconazole, a clinically used antifungal. We show a novel role for the well-studied RIM101 pathway in fluconazole susceptibility. We also show that insertions of transposons into the 5' upstream region can drive sensitization of essential genes, enabling screenlike assays of both essential and nonessential components of the genome. Using this approach, we demonstrate a role for mitochondrial function in fluconazole sensitivity, such that tuning down many essential mitochondrial genes via 5' insertions can drive resistance to fluconazole. Our assay system will be valuable in future studies of C. neoformans, particularly in examining the consequences of genotypic diversity.

Cryptococcus neoformans↗

PubMed1999

Stress, anxiety and performance.

Research which has examined the catastrophe models of anxiety and performance is discussed. The conclusion drawn is that the evidence supports the notion of hysteresis, and partially supports the interactive effects prediction of the catastrophe models. Two potential explanations of anxiety induced performance catastrophes are then examined, processing efficiency theory and the conscious processing hypothesis. Process efficiency theory proposes that, as well as reducing attentional resources, cognitive anxiety can also lead performers to invest additional effort in the task in an attempt to allay their concerns and fears. Thus, performance may be maintained (or even enhanced), but at an increased physiological cost. Evidence is presented in support of the prediction that cognitive anxiety leads to increased effort. The conscious processing hypothesis proposes that anxious performers regress to an earlier stage of learning when they controlled movements using conscious processes and explicit knowledge. Evidence is presented from a number of recent studies which at least partially support this notion. Finally, it is suggested that these two different explanations are not necessarily mutually exclusive.

Anxiety↗

PubMed2004

Phonetic perceptual identification by native- and second-language speakers differentially activates brain regions involved with acoustic phonetic processing and those involved with articulatory-auditory/orosensory internal models.

This experiment investigates neural processes underlying perceptual identification of the same phonemes for native- and second-language speakers. A model is proposed implicating the use of articulatory-auditory and articulatory-orosensory mappings to facilitate perceptual identification under conditions in which the phonetic contrast is ambiguous, as in the case of second-language speakers. In contrast, native-language speakers are predicted to use auditory-based phonetic representations to a greater extent for perceptual identification than second-language speakers. The English /r-l/ phonetic contrast, although easy for native English speakers, is extremely difficult for native Japanese speakers who learned English as a second language after childhood. Twenty-two native English and twenty-two native Japanese speakers participated in this study. While undergoing event-related fMRI, subjects were aurally presented with syllables starting with a /r/, /l/, or a vowel and were required to rapidly identify the phoneme perceived by pushing one of three buttons with the left thumb. Consistent with the proposed model, the results show greater activity for second- over native-language speakers during perceptual identification of /r/ and /l/ relative to vowels in brain regions implicated with instantiating forward and inverse articulatory-auditory articulatory-orosensory models [Broca's area, anterior insula, anterior superior temporal sulcus/gyrus (STS/G), planum temporale (PT), superior temporal parietal area (Stp), SMG, and cerebellum]. The results further show that activity in brain regions implicated with instantiating these internal models is correlated with better /r/ and /l/ identification performance for second-language speakers. Greater activity found for native-language speakers especially in the anterior STG/S for /r/ and /l/ perceptual identification is consistent with the hypothesis that native-language speakers use auditory phonetic representations more extensively than second-language speakers.

Adult↗

PubMed2026

Integrated transcriptome analysis and machine learning to construct a homeostatic model of acetylation for bladder cancer and validate the key gene CES1.

BACKGROUND: Bladder cancer (BLCA) is one of the most common malignant tumors of the urinary system. Protein acetylation (PA) plays a critical role in regulating multiple biological processes (BPs), cellular homeostasis, and cancer-related signaling pathways. This study aimed to construct a homeostatic model of acetylation for BLCA using integrated transcriptome analysis and machine learning and to validate the key gene CES1. METHODS: RNA sequencing (RNA-seq) and clinical data were obtained from The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) databases. Acetylation-related differentially expressed genes (DEGs) in BLCA were screened using differential expression analysis (DEA). An acetylation homeostatic model was constructed via univariate, machine learning-based least absolute shrinkage and selection operator (LASSO) and multivariate Cox regression analyses, followed by validation in multiple cohorts. Single-cell RNA-seq analysis was used to explore gene expression patterns in diverse cell types. Enrichment analysis (EA), immune infiltration, and drug sensitivity analysis (DSA) were performed to characterize molecular features of different risk groups. Finally, the biological function of CES1 as the key gene was verified by in vitro knockdown experiments. RESULTS: We established a robust acetylation homeostatic model consisting of five genes, which effectively predicted overall survival (OS) and served as an independent prognostic factor in BLCA. High-risk patients showed significantly poorer prognosis, distinct immune infiltration profiles, and differential drug sensitivity. CES1 was identified and validated as the key gene in this model, which was highly expressed in BLCA and associated with poor prognosis. Knockdown of CES1 markedly suppressed cell proliferation, invasion, and migration, and reduced intracellular coenzyme A (CoA) levels, thereby regulating PA homeostasis. CONCLUSIONS: We developed and validated a novel acetylation homeostatic model for survival stratification and personalized treatment guidance in BLCA, based on integrated transcriptome analysis and machine learning. CES1 is closely associated with intracellular CoA levels and the malignant progression of BLCA. Its potential association with PA homeostasis requires further mechanistic validation, and it may act as a candidate therapeutic biomarker for BLCA.

Bladder cancer (BLCA)↗