Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Machine learning.”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

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

At least 757 records · Page 42Linked to original sources
PubMed2004

Using unsupervised learning with variational bayesian mixture of factor analysis to identify patterns of glaucomatous visual field defects.

PURPOSE: To determine whether an unsupervised machine learning classifier can identify patterns of visual field loss in standard visual fields consistent with typical patterns learned by decades of human experience. METHODS: Standard perimetry thresholds for 52 locations plus age from one eye of each of 156 patients with glaucomatous optic neuropathy (GON) and 189 eyes of healthy subjects were clustered with an unsupervised machine classifier, variational Bayesian mixture of factor analysis (vbMFA). RESULTS: The vbMFA formed five distinct clusters. Cluster 5 held 186 of 189 fields from normal eyes plus 46 from eyes with GON. These fields were then judged within normal limits by several traditional methods. Each of the other four clusters could be described by the pattern of loss found within it. Cluster 1 (71 GON + 3 normal optic discs) included early, localized defects. A purely diffuse component was rare. Cluster 2 (26 GON) exhibited primarily deep superior hemifield defects, and cluster 3 (10 GON) held deep inferior hemifield defects only or in combination with lesser superior field defects. Cluster 4 (6 GON) showed deep defects in both hemifields. In other words, visual fields within a given cluster had similar patterns of loss that differed from the predominant pattern found in other clusters. The classifier separated the data based solely on the patterns of loss within the fields, without being guided by the diagnosis, placing 98.4% of the healthy eyes within the same cluster and spreading 70.5% of the eyes with GON across the other four clusters, in good agreement with a glaucoma expert and pattern standard deviation. CONCLUSIONS: Without training-based diagnosis (unsupervised learning), the vbMFA identified four important patterns of field loss in eyes with GON in a manner consistent with years of clinical experience.

Algorithms↗
PubMed2005

Stochastic complexities of reduced rank regression in Bayesian estimation.

Reduced rank regression extracts an essential information from examples of input-output pairs. It is understood as a three-layer neural network with linear hidden units. However, reduced rank approximation is a non-regular statistical model which has a degenerate Fisher information matrix. Its generalization error had been left unknown even in statistics. In this paper, we give the exact asymptotic form of its generalization error in Bayesian estimation, based on resolution of learning machine singularities. For this purpose, the maximum pole of the zeta function for the learning theory is calculated. We propose a new method of recursive blowing-ups which yields the complete desingularization of the reduced rank approximation.

Artificial Intelligence↗
PubMed2026

A leakage-aware genomic prediction pipeline for meropenem resistance in Klebsiella pneumoniae using transformer-based resistome representation learning.

MOTIVATION: Antimicrobial resistance (AMR) in Klebsiella pneumoniae, particularly to carbapenems such as meropenem, is a major global health problem. Machine learning is increasingly used to predict resistance from genomic markers; however, many models fail to capture high-level gene-gene interactions and may exhibit inflated performance due to lineage-biased prediction. Existing genomic prediction models largely rely on flat feature representations that fail to capture epistatic gene interactions, and commonly suffer from inflated performance estimates due to phylogenetic data leakage. To address these limitations simultaneously, a leakage-aware hybrid TabTransformer-CatBoost pipeline was developed, combining self-attention-based resistome representation learning with gradient boosting classification under clade-aware data partitioning. A self-attention encoder converts sparse gene presence-absence profiles into contextualized latent embeddings, which are subsequently classified using gradient boosting to capture lineage-aware AMR patterns. RESULTS: The proposed architecture outperformed classical baselines including Logistic Regression, Random Forest, XGBoost, and optimized CatBoost models. Internal accuracy reached 92.59% for the Chained Hybrid configuration (area under the receiver operating characteristic curve, AUROC = 0.8670, F1 = 0.8537). Performance gains primarily originated from the embedding stage, as confirmed by ablation analysis. External validation across independent multinational cohorts (n = 305) demonstrated generalizability (AUROC = 0.8105; F1 = 0.7552). Permutation testing produced near-zero Matthews Correlation Coefficient (MCC) = 0.0091, indicating predictions reflect genuine biological signal rather than noise. These results establish attention-based genomic embedding with gradient boosting as a scalable, interpretable, and leakage-aware framework for clinical AMR prediction. AVAILABILITY AND IMPLEMENTATION: The source code for the TabTransformer-CatBoost framework, including preprocessing pipelines and pre-trained embeddings, is available at https://github.com/SibelKervanci/kp-meropenem-tabtransformer.

Journal Article↗
PubMed2006

Incremental nonlinear dimensionality reduction by manifold learning.

Understanding the structure of multidimensional patterns, especially in unsupervised cases, is of fundamental importance in data mining, pattern recognition, and machine learning. Several algorithms have been proposed to analyze the structure of high-dimensional data based on the notion of manifold learning. These algorithms have been used to extract the intrinsic characteristics of different types of high-dimensional data by performing nonlinear dimensionality reduction. Most of these algorithms operate in a "batch" mode and cannot be efficiently applied when data are collected sequentially. In this paper, we describe an incremental version of ISOMAP, one of the key manifold learning algorithms. Our experiments on synthetic data as well as real world images demonstrate that our modified algorithm can maintain an accurate low-dimensional representation of the data in an efficient manner.

Algorithms↗
PubMed2006

More complete gene silencing by fewer siRNAs: transparent optimized design and biophysical signature.

Highly accurate knockdown functional analyses based on RNA interference (RNAi) require the possible most complete hydrolysis of the targeted mRNA while avoiding the degradation of untargeted genes (off-target effects). This in turn requires significant improvements to target selection for two reasons. First, the average silencing activity of randomly selected siRNAs is as low as 62%. Second, applying more than five different siRNAs may lead to saturation of the RNA-induced silencing complex (RISC) and to the degradation of untargeted genes. Therefore, selecting a small number of highly active siRNAs is critical for maximizing knockdown and minimizing off-target effects. To satisfy these needs, a publicly available and transparent machine learning tool is presented that ranks all possible siRNAs for each targeted gene. Support vector machines (SVMs) with polynomial kernels and constrained optimization models select and utilize the most predictive effective combinations from 572 sequence, thermodynamic, accessibility and self-hairpin features over 2200 published siRNAs. This tool reaches an accuracy of 92.3% in cross-validation experiments. We fully present the underlying biophysical signature that involves free energy, accessibility and dinucleotide characteristics. We show that while complete silencing is possible at certain structured target sites, accessibility information improves the prediction of the 90% active siRNA target sites. Fast siRNA activity predictions can be performed on our web server at http://optirna.unl.edu/.

Artificial Intelligence↗
PubMed2005

Multiclass molecular cancer classification by kernel subspace methods with effective kernel parameter selection.

Microarray techniques provide new insights into molecular classification of cancer types, which is critical for cancer treatments and diagnosis. Recently, an increasing number of supervised machine learning methods have been applied to cancer classification problems using gene expression data. Support vector machines (SVMs), in particular, have become one of the most effective and leading methods. However, there exist few studies on the application of other kernel methods in the literature. We apply a kernel subspace (KS) method to multiclass cancer classification problems, and assess its validity by comparing it with multiclass SVMs. Our comparative study using seven multiclass cancer datasets demonstrates that the KS method has high performance that is comparable to multiclass SVMs. Furthermore, we propose an effective criterion for kernel parameter selection, which is shown to be useful for the computation of the KS method.

Artificial Intelligence↗
PubMed2005

A hierarchical Bayesian model for learning nonlinear statistical regularities in nonstationary natural signals.

Capturing statistical regularities in complex, high-dimensional data is an important problem in machine learning and signal processing. Models such as principal component analysis (PCA) and independent component analysis (ICA) make few assumptions about the structure in the data and have good scaling properties, but they are limited to representing linear statistical regularities and assume that the distribution of the data is stationary. For many natural, complex signals, the latent variables often exhibit residual dependencies as well as nonstationary statistics. Here we present a hierarchical Bayesian model that is able to capture higher-order nonlinear structure and represent nonstationary data distributions. The model is a generalization of ICA in which the basis function coefficients are no longer assumed to be independent; instead, the dependencies in their magnitudes are captured by a set of density components. Each density component describes a common pattern of deviation from the marginal density of the pattern ensemble; in different combinations, they can describe nonstationary distributions. Adapting the model to image or audio data yields a nonlinear, distributed code for higher-order statistical regularities that reflect more abstract, invariant properties of the signal.

Bayes Theorem↗
PubMed2004

What can we learn from noncoding regions of similarity between genomes?

BACKGROUND: In addition to known protein-coding genes, large amounts of apparently non-coding sequence are conserved between the human and mouse genomes. It seems reasonable to assume that these conserved regions are more likely to contain functional elements than less-conserved portions of the genome. METHODS: Here we used a motif-oriented machine learning method based on the Relevance Vector Machine algorithm to extract the strongest signal from a set of non-coding conserved sequences. RESULTS: We successfully fitted models to reflect the non-coding sequences, and showed that the results were quite consistent for repeated training runs. Using the learned models to scan genomic sequence, we found that they often made predictions close to the start of annotated genes. We compared this method with other published promoter-prediction systems, and showed that the set of promoters which are detected by this method is substantially similar to that detected by existing methods. CONCLUSIONS: The results presented here indicate that the promoter signal is the strongest single motif-based signal in the non-coding functional fraction of the genome. They also lend support to the belief that there exists a substantial subset of promoter regions which share several common features including, but not restricted to, a relative abundance of CpG dinucleotides. This subset is detectable by a variety of distinct computational methods.

Animals↗
PubMed2005

Boosted ARTMAP: modifications to fuzzy ARTMAP motivated by boosting theory.

In this paper, several modifications to the Fuzzy ARTMAP neural network architecture are proposed for conducting classification in complex, possibly noisy, environments. The goal of these modifications is to improve upon the generalization performance of Fuzzy ART-based neural networks, such as Fuzzy ARTMAP, in these situations. One of the major difficulties of employing Fuzzy ARTMAP on such learning problems involves over-fitting of the training data. Structural risk minimization is a machine-learning framework that addresses the issue of over-fitting by providing a backbone for analysis as well as an impetus for the design of better learning algorithms. The theory of structural risk minimization reveals a trade-off between training error and classifier complexity in reducing generalization error, which will be exploited in the learning algorithms proposed in this paper. Boosted ART extends Fuzzy ART by allowing the spatial extent of each cluster formed to be adjusted independently. Boosted ARTMAP generalizes upon Fuzzy ARTMAP by allowing non-zero training error in an effort to reduce the hypothesis complexity and hence improve overall generalization performance. Although Boosted ARTMAP is strictly speaking not a boosting algorithm, the changes it encompasses were motivated by the goals that one strives to achieve when employing boosting. Boosted ARTMAP is an on-line learner, it does not require excessive parameter tuning to operate, and it reduces precisely to Fuzzy ARTMAP for particular parameter values. Another architecture described in this paper is Structural Boosted ARTMAP, which uses both Boosted ART and Boosted ARTMAP to perform structural risk minimization learning. Structural Boosted ARTMAP will allow comparison of the capabilities of off-line versus on-line learning as well as empirical risk minimization versus structural risk minimization using Fuzzy ARTMAP-based neural network architectures. Both empirical and theoretical results are presented to enhance the understanding of these architectures.

Artificial Intelligence↗
PubMed2003

Supervised classification for gene network reconstruction.

One of the central problems of functional genomics is revealing gene expression networks - the relationships between genes that reflect observations of how the expression level of each gene affects those of others. Microarray data are currently a major source of information about the interplay of biochemical network participants in living cells. Various mathematical techniques, such as differential equations, Bayesian and Boolean models and several statistical methods, have been applied to expression data in attempts to extract the underlying knowledge. Unsupervised clustering methods are often considered as the necessary first step in visualization and analysis of the expression data. As for supervised classification, the problem mainly addressed so far has been how to find discriminative genes separating various samples or experimental conditions. Numerous methods have been applied to identify genes that help to predict treatment outcome or to confirm a diagnosis, as well as to identify primary elements of gene regulatory circuits. However, less attention has been devoted to using supervised learning to uncover relationships between genes and/or their products. To start filling this gap a machine-learning approach for gene networks reconstruction is described here. This approach is based on building classifiers--functions, which determine the state of a gene's transcription machinery through expression levels of other genes. The method can be applied to various cases where relationships between gene expression levels could be expected.

Genes↗
PubMed2025

Learning neural dynamics through instructive signals.

Rapid learning is essential for flexible behavior, but its basis in the brain remains unknown. Here we introduce the PRISM plasticity rule, a unifying mechanistic model of three well-established, fast-acting synaptic plasticity rules-in hippocampus, cerebellum and mushroom body-which relies exclusively on pre-synaptic activity and an "instructive signal" from another brain area. Using a multi-region network model we show that guiding PRISM plasticity with instructive signals enables the network to quickly learn extremely flexible nonlinear dynamics underlying behaviorally relevant computations, as well as to emulate unknown external system dynamics from real-time error signals, which we demonstrate with comprehensive simulations supported by exact mathematical theory. Thus, PRISM plasticity guided by instructive signals is well-suited to rapidly learn general-purpose neural computations-in contrast to canonical Hebbian rules. Finally, we show how including this plasticity rule in artificial learning algorithms can solve long-range temporal credit assignment, a long-standing challenge in machine learning.

cerebellum↗
PubMed1993

New concepts in cerebellar function.

In the past 3 decades our knowledge of the cerebellum has increased enormously and yielded important new concepts which include the parasagittal band organization of the cerebellum, synaptic plasticity, motor learning, etc. Very recently, knowledge of the cerebellum at the levels of ion channels, receptors and messengers has advanced greatly and is expanding at the level of gene regulation. Our knowledge about the cerebellum at systems level has also advanced and facilitated theoretical modelling of the cerebellum as a complex learning machine. The cerebellum acquires and retains the dynamics, or inverse dynamics, of a control object by learning. By using this "dynamics memory" it permits automatic, precise and smooth execution of learned movements. It is postulated that this control principle may also apply to the brain mechanisms underlying human thought, in which ideas and concepts are "manipulated", as opposed to limbs as in movement. Finally, the control system scheme of the cerebellum will be generalized to encompass the whole learned behavior including movements and thoughts.

Adaptation, Physiological↗
PubMed2025

Efficient detection and characterization of targets of natural selection using transfer learning.

Natural selection leaves detectable patterns of altered spatial diversity within genomes, and identifying affected regions is crucial for understanding species evolution. Recently, machine learning approaches applied to raw population genomic data have been developed to uncover these adaptive signatures. Convolutional neural networks (CNNs) are particularly effective for this task, as they handle large data arrays while maintaining element correlations. However, shallow CNNs may miss complex patterns due to their limited capacity, while deep CNNs can capture these patterns but require extensive data and computational power. Transfer learning addresses these challenges by utilizing a deep CNN pre-trained on a large dataset as a feature extraction tool for downstream classification and evolutionary parameter prediction. This approach reduces extensive training data generation requirements and computational needs while maintaining high performance. In this study, we developed TrIdent, a tool that uses transfer learning to enhance detection of adaptive genomic regions from image representations of multilocus variation. We evaluated TrIdent across various genetic, demographic, and adaptive settings, in addition to unphased data and other confounding factors. TrIdent demonstrated improved detection of adaptive regions compared to recent methods using similar data representations. We further explored model interpretability through class activation maps and adapted TrIdent to infer selection parameters for identified adaptive candidates. Using whole-genome haplotype data from European and African populations, TrIdent effectively recapitulated known sweep candidates and identified novel cancer, and other disease-associated genes as potential sweeps.

Journal Article↗
PubMed2004

Binary halftone image resolution increasing by decision tree learning.

This paper presents a new, accurate, and efficient technique to increase the spatial resolution of binary halftone images. It makes use of a machine learning process to automatically design a zoom operator starting from pairs of input-output sample images. To accurately zoom a halftone image, a large window and large sample images are required. Unfortunately, in this case, the execution time required by most of the previous techniques may be prohibitive. The new solution overcomes this difficulty by using decision tree (DT) learning. Original DT learning is modified to obtain a more efficient technique (WZDT learning). It is useful to know, a priori, sample complexity (the number of training samples needed to obtain, with probability 1 - delta, an operator with accuracy epsilon): we use the probably approximately correct (PAC) learning theory to compute the sample complexity. Since the PAC theory usually yields an overestimated sample complexity, statistical estimation is used to evaluate, a posteriori, a tight error bound. Statistical estimation is also used to choose an appropriate window and to show that DT learning has good inductive bias. The new technique is more accurate than a zooming method based on simple inverse halftoning techniques. The quality of the proposed solution is very close to the theoretical optimal obtainable quality for a neighborhood-based zooming process using the Hamming distance to quantify the error.

Algorithms↗
PubMed2000

Boosting neural networks.

Boosting is a general method for improving the performance of learning algorithms. A recently proposed boosting algorithm, AdaBoost, has been applied with great success to several benchmark machine learning problems using mainly decision trees as base classifiers. In this article we investigate whether AdaBoost also works as well with neural networks, and we discuss the advantages and drawbacks of different versions of the AdaBoost algorithm. In particular, we compare training methods based on sampling the training set and weighting the cost function. The results suggest that random resampling of the training data is not the main explanation of the success of the improvements brought by AdaBoost. This is in contrast to bagging, which directly aims at reducing variance and for which random resampling is essential to obtain the reduction in generalization error. Our system achieves about 1.4% error on a data set of on-line handwritten digits from more than 200 writers. A boosted multilayer network achieved 1.5% error on the UCI letters and 8.1% error on the UCI satellite data set, which is significantly better than boosted decision trees.

Algorithms↗
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↗
PubMed2000

A probabilistic learning approach to whole-genome operon prediction.

We present a computational approach to predicting operons in the genomes of prokaryotic organisms. Our approach uses machine learning methods to induce predictive models for this task from a rich variety of data types including sequence data, gene expression data, and functional annotations associated with genes. We use multiple learned models that individually predict promoters, terminators and operons themselves. A key part of our approach is a dynamic programming method that uses our predictions to map every known and putative gene in a given genome into its most probable operon. We evaluate our approach using data from the E. coli K-12 genome.

Gene Expression Profiling↗
PubMed2006

Towards automated classification of intensive care nursing narratives.

Nursing narratives are an important part of patient documentation, but the possibilities to utilize them in the direct care process are limited due to the lack of proper tools. One solution to facilitate the utilization of narrative data could be to classify them according to their content. In this paper, we addressed two issues related to designing an automated classifier: domain experts' agreement on the content of the classes into which the data are to be classified, and the ability of the machine-learning algorithm to perform the classification on an acceptable level. The data we used were a set of Finnish intensive care nursing narratives. By using Cohen's kappa, we assessed the agreement of three nurses on the content of the classes Breathing, Blood Circulation and Pain, and by using the area under ROC curve (AUC), we measured the ability of the Least Squares Support Vector Machine (LS-SVM) algorithm to learn the classification patterns of the nurses. On average, the values of kappa were around 0.8. The agreement was highest in the class Blood Circulation, and lowest in the class Breathing. The LS-SVM algorithm was able to learn the classification patterns of the three nurses on an acceptable level; the values of AUC were generally around 0.85. Our results indicate that one way to develop electronic patient records could be tools that handle the free text in nursing documentation.

Algorithms↗