SEARCH · PubMed Health

Results for “machine learning algorithms”

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 469 records · Page 26Linked to original sources

PubMed2006

Learning interpretable SVMs for biological sequence classification.

BACKGROUND: Support Vector Machines (SVMs)--using a variety of string kernels--have been successfully applied to biological sequence classification problems. While SVMs achieve high classification accuracy they lack interpretability. In many applications, it does not suffice that an algorithm just detects a biological signal in the sequence, but it should also provide means to interpret its solution in order to gain biological insight. RESULTS: We propose novel and efficient algorithms for solving the so-called Support Vector Multiple Kernel Learning problem. The developed techniques can be used to understand the obtained support vector decision function in order to extract biologically relevant knowledge about the sequence analysis problem at hand. We apply the proposed methods to the task of acceptor splice site prediction and to the problem of recognizing alternatively spliced exons. Our algorithms compute sparse weightings of substring locations, highlighting which parts of the sequence are important for discrimination. CONCLUSION: The proposed method is able to deal with thousands of examples while combining hundreds of kernels within reasonable time, and reliably identifies a few statistically significant positions.

Algorithms↗

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↗

PubMed2004

Finding more needles in the haystack: A simple and efficient method for improving high-throughput docking results.

The technology underpinning high-throughput docking (HTD) has developed over the past few years to where it has become a vital tool in modern drug discovery. Although the performance of various docking algorithms is adequate, the ability to accurately and consistently rank compounds using a scoring function remains problematic. We show that by employing a simple machine learning method (naïve Bayes) it is possible to significantly overcome this deficiency. Compounds from the Available Chemical Directory (ACD), along with known active compounds, were docked into two protein targets using three software packages. In cases where HTD alone was able to show some enrichment, the application of naïve Bayes was able to improve upon the enrichment. The application of this methodology to enrich HTD results can be carried out without a priori knowledge of the activity of compounds and results in superior enrichment of known actives compared to the use of scoring methods alone.

Bayes Theorem↗

PubMed2000

Gait event detection for FES using accelerometers and supervised machine learning.

Rule based detectors were used with a single cluster of accelerometers attached to the shank for the real time detection of the main phases of normal gait during walking. The gait phase detectors were synthesized from two rule induction algorithms, Rough Sets (RS) and Adaptive Logic Networks (ALNs), and compared with to a previously reported stance/swing detector based on a hand crafted, rule based algorithm. Data was sampled at 100 Hz and the detection errors determined at each sample for 50 steps. For three able bodied subjects, the sample by sample accuracy of stance/swing detection ranged within 94-97%, 87-94%, and 87-95% for the RS, ALN, and the handcrafted methods, respectively. A heuristically formulated postdetector filter improved the RS and ALN detectors' accuracy to 98%. RS and ALN also detected five gait phases to an overall accuracy of 82-89% and 86-91%, respectively. The postdetector filter localized the errors to the phase transitions, but did not change the detection accuracy. The average duration of the error at each transition was 40 ms and 23 ms for RS and ALN, respectively. When implemented on a microcontroller, the RS-based detector executed ten times faster and required one tenth of the memory than the ALN-based detector.

Acceleration↗

PubMedDate not supplied

The applicability of recurrent neural networks for biological sequence analysis.

Selection of machine learning techniques requires a certain sensitivity to the requirements of the problem. In particular, the problem can be made more tractable by deliberately using algorithms that are biased toward solutions of the requisite kind. In this paper, we argue that recurrent neural networks have a natural bias toward a problem domain of which biological sequence analysis tasks are a subset. We use experiments with synthetic data to illustrate this bias. We then demonstrate that this bias can be exploitable using a data set of protein sequences containing several classes of subcellular localization targeting peptides. The results show that, compared with feed forward, recurrent neural networks will generally perform better on sequence analysis tasks. Furthermore, as the patterns within the sequence become more ambiguous, the choice of specific recurrent architecture becomes more critical.

Algorithms↗

PubMed1998

Contextual quick-learning and generalization by humans and machines.

In a previous study (1994 Network: Comput. Neural Syst. 5 203-27) we compared human quick-learning and generalization (quick modelling) with that of neural nets (feedforward architectures), symbolic algorithms (decision tree procedures), and pattern classifiers (truth-set descriptors). Those studies raised the question of the role of context in the nature and rapidity of human learning. Here we address that issue in the setting of the same basic experiment (Quinlan classification problem) used for the previous studies. A major implication of our findings is that humans overwhelmingly seek, create, or imagine context in order to provide meaning when presented with abstract or apparently incomplete or contradictory or otherwise untenable situations.

Adolescent↗

PubMed2026

scFANCL: Dual contrastive learning with false-negative correction at cell level for single-cell RNA-seq clustering.

BACKGROUND: Single-cell RNA sequencing (scRNA-seq) enables cellular characterization at single-cell resolution. However, its high dimensionality, sparsity, and noise make clustering challenging. Approaches utilizing contrastive learning and data augmentation have been introduced to improve representation quality for scRNA-seq clustering. In particular, dual contrastive frameworks combining instance- and cluster-level objectives can capture both cell-cell similarities and inter-cluster variations. However, existing dual contrastive frameworks focus primarily on discrete cluster boundaries, neglecting the biological continuity inherent in scRNA-seq data. METHODS: We propose scFANCL, a dual contrastive framework designed to capture biological continuity in scRNA data. Rather than treating all non-augmented samples as negatives, scFANCL applies a cosine-similarity-based threshold to exclude cells of the same type from the negative pool, preserving continuous transcriptional relationships among them while maintaining inter-cluster separation. RESULTS: Extensive experiments across seven publicly available scRNA-seq datasets demonstrated that scFANCL achieves competitive clustering performance compared with existing baseline methods, consistently yielding high ARI and NMI scores across datasets of varying size and complexity. Ablation studies further confirmed the contribution of the false negative filtering component, showing measurable improvements over variants without filtering. Downstream analyses further suggest that the learned embeddings may reflect biologically meaningful transcriptional transitions, including continuous differentiation trajectories within related cell types. The source code is available at https://github.com/mjuailab/scFANCL . CONCLUSIONS: scFANCL addresses a key limitation of conventional contrastive learning by applying a cosine-similarity-based threshold to exclude cells of the same type from the negative pool, thereby preserving biological continuity within cell types while maintaining inter-cluster separation. Evaluations across seven benchmark scRNA-seq datasets demonstrate competitive clustering performance, with learned embeddings capturing biologically meaningful transcriptional structure and characteristics of rare cell populations.

Clustering Algorithms↗

PubMed2005

Implementation of automated signal generation in pharmacovigilance using a knowledge-based approach.

Automated signal generation is a growing field in pharmacovigilance that relies on data mining of huge spontaneous reporting systems for detecting unknown adverse drug reactions (ADR). Previous implementations of quantitative techniques did not take into account issues related to the medical dictionary for regulatory activities (MedDRA) terminology used for coding ADRs. MedDRA is a first generation terminology lacking formal definitions; grouping of similar medical conditions is not accurate due to taxonomic limitations. Our objective was to build a data-mining tool that improves signal detection algorithms by performing terminological reasoning on MedDRA codes described with the DAML+OIL description logic. We propose the PharmaMiner tool that implements quantitative techniques based on underlying statistical and bayesian models. It is a JAVA application displaying results in tabular format and performing terminological reasoning with the Racer inference engine. The mean frequency of drug-adverse effect associations in the French database was 2.66. Subsumption reasoning based on MedDRA taxonomical hierarchy produced a mean number of occurrence of 2.92 versus 3.63 (p < 0.001) obtained with a combined technique using subsumption and approximate matching reasoning based on the ontological structure. Semantic integration of terminological systems with data mining methods is a promising technique for improving machine learning in medical databases.

Adverse Drug Reaction Reporting Systems↗

PubMed2000

Visual management of large scale data mining projects.

This paper describes a unified framework for visualizing the preparations for, and results of, hundreds of machine learning experiments. These experiments were designed to improve the accuracy of enzyme functional predictions from sequence, and in many cases were successful. Our system provides graphical user interfaces for defining and exploring training datasets and various representational alternatives, for inspecting the hypotheses induced by various types of learning algorithms, for visualizing the global results, and for inspecting in detail results for specific training sets (functions) and examples (proteins). The visualization tools serve as a navigational aid through a large amount of sequence data and induced knowledge. They provided significant help in understanding both the significance and the underlying biological explanations of our successes and failures. Using these visualizations it was possible to efficiently identify weaknesses of the modular sequence representations and induction algorithms which suggest better learning strategies. The context in which our data mining visualization toolkit was developed was the problem of accurately predicting enzyme function from protein sequence data. Previous work demonstrated that approximately 6% of enzyme protein sequences are likely to be assigned incorrect functions on the basis of sequence similarity alone. In order to test the hypothesis that more detailed sequence analysis using machine learning techniques and modular domain representations could address many of these failures, we designed a series of more than 250 experiments using information-theoretic decision tree induction and naive Bayesian learning on local sequence domain representations of problematic enzyme function classes. In more than half of these cases, our methods were able to perfectly discriminate among various possible functions of similar sequences. We developed and tested our visualization techniques on this application.

Alcohol Dehydrogenase↗

PubMed2026

Identifying JAK2 and ANXA5 as Key Genes Linking Obstructive Sleep Apnea and Oxidative Stress via Machine Learning and Multilayer Transcriptomic Integration With Functional Validation.

Obstructive sleep apnea (OSA) is a common and severe sleep disorder closely associated with oxidative stress (OS). This study aims to identify and validate potential OS-related genes associated with OSA through bioinformatics methods. We successfully identified OS-related differentially expressed genes (OS-DEGs) by combining the limma test, weighted correlation network analysis (WGCNA), and OS-related genes from the GeneCards database. Key genes and potential biological roles were further identified using Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG), enrichment analysis, protein-protein interaction (PPI) network analysis, Lasso regression analysis, random forest algorithm, and support vector machine recursive feature elimination (SVM-RFE) method. Evaluate and validate the accuracy of key genes through receiver operating characteristic (ROC) curve analysis. The human single-cell RNA sequencing (scRNA-seq) dataset is used for cell classification annotation, analysis of key gene single-cell expression profiles, and virtual gene knockout experiments based on the scTenifoldKnk algorithm. Integrating scRNA-seq sequencing, pseudotime trajectory inference, cell-cell communication analysis, and bulk immune infiltration deconvolution reveals monocyte subtype remodeling in OSA. Finally, the expression levels of key genes in clinical samples were validated using real-time quantitative PCR (RT-qPCR) and Western blotting. A total of 57 common DEGs, indicating significant enrichment in OS, inflammation, and tumor pathways, particularly prominent in the immunometabolism pathway. By integrating DEGs, WGCNA, PPI results, and machine learning methods, key genes Janus kinase 2 (JAK2) and ANXA5 were screened out. JAK2 was significantly upregulated under disease conditions, while ANXA5 was significantly downregulated. ROC curve exhibited high accuracy (area under the curve [AUC] > 0.85). Human scRNA-seq analysis revealed that key genes were predominantly highly expressed in monocytes. Virtual knockout experiments demonstrated that these key genes play a crucial role in regulating immune responses and inflammatory reactions. PPI networks and enrichment analysis verified that downstream genes S100P, ALOX5AP, PROK2, and PADI4 may collaboratively participate in immune response and inflammation regulation. Finally, clinical sample experiment further validated the results of bioinformatics analysis. This study provides new research insights for the diagnosis, mechanism research, and treatment development of OSA in the future by integrating multilayer transcriptomic and machine learning techniques.

Humans↗

PubMed2004

Predicting the efficacy of short oligonucleotides in antisense and RNAi experiments with boosted genetic programming.

MOTIVATION: Both small interfering RNAs (siRNAs) and antisense oligonucleotides can selectively block gene expression. Although the two methods rely on different cellular mechanisms, these methods share the common property that not all oligonucleotides (oligos) are equally effective. That is, if mRNA target sites are picked at random, many of the antisense or siRNA oligos will not be effective. Algorithms that can reliably predict the efficacy of candidate oligos can greatly reduce the cost of knockdown experiments, but previous attempts to predict the efficacy of antisense oligos have had limited success. Machine learning has not previously been used to predict siRNA efficacy. RESULTS: We develop a genetic programming based prediction system that shows promising results on both antisense and siRNA efficacy prediction. We train and evaluate our system on a previously published database of antisense efficacies and our own database of siRNA efficacies collected from the literature. The best models gave an overall correlation between predicted and observed efficacy of 0.46 on both antisense and siRNA data. As a comparison, the best correlations of support vector machine classifiers trained on the same data were 0.40 and 0.30, respectively.

Algorithms↗

PubMedDate not supplied

Electronic van der Waals surface property descriptors and genetic algorithms for developing structure-activity correlations in olfactory databases.

A methodology to facilitate the intelligent design of new odorants (e.g., musks) with specialized properties has been developed as part of an ongoing research effort in machine learning. In a traditional framework, the introduction of a new odorant is a lengthy, costly, and laborious discovery, development, and testing process. We propose to streamline this process utilizing large existing olfactory databases available through the open scientific literature as input for a new structure/activity correlation methodology. The first step in this process is to characterize each molecule in the database by an appropriate set of descriptors. To accomplish this task, an enhanced version of Breneman's Transferable Atom Equivalent (TAE) descriptor methodology will be used to create a large set of electron density derived shape/property hybrid (PEST), wavelet coefficient (WCD), and TAE histogram descriptors. We have chosen these molecular property descriptors to represent the problem because they have been shown to contain pertinent shape and electronic properties of the molecule and correlate with key modes of intermolecular interactions. Traditional QSAR methodologies, which employ fragment based descriptors, have been shown to be effective for QSAR development within homologous sets of molecules but are less effective when applied to data sets containing a great deal of structural variation. In contrast to previous attempts at SAR, our use of shape-aware electron density based molecular property descriptors has removed many of the limitations brought about by the use of descriptors based on substructure fragments, molecular surface properties, or other whole molecule descriptors. Another reason for the mixed success of past QSAR efforts can be traced to the nature of the underlying modeling problem, which is often quite complex. To meet these challenges, a genetic algorithm for pattern recognition analysis has been developed that selects descriptors which create class separation in a plot of the two largest principal components of the data while simultaneously searching for features that increase clustering of the data.

Journal Article↗

PubMed2006

Spectral imaging perspective on cytomics.

BACKGROUND: Cytomics involves the analysis of cellular morphology and molecular phenotypes, with reference to tissue architecture and to additional metadata. To this end, a variety of imaging and nonimaging technologies need to be integrated. Spectral imaging is proposed as a tool that can simplify and enrich the extraction of morphological and molecular information. Simple-to-use instrumentation is available that mounts on standard microscopes and can generate spectral image datasets with excellent spatial and spectral resolution; these can be exploited by sophisticated analysis tools. METHODS: This report focuses on brightfield microscopy-based approaches. Cytological and histological samples were stained using nonspecific standard stains (Giemsa; hematoxylin and eosin (H&E)) or immunohistochemical (IHC) techniques employing three chromogens plus a hematoxylin counterstain. The samples were imaged using the Nuance system, a commercially available, liquid-crystal tunable-filter-based multispectral imaging platform. The resulting data sets were analyzed using spectral unmixing algorithms and/or learn-by-example classification tools. RESULTS: Spectral unmixing of Giemsa-stained guinea-pig blood films readily classified the major blood elements. Machine-learning classifiers were also successful at the same task, as well in distinguishing normal from malignant regions in a colon-cancer example, and in delineating regions of inflammation in an H&E-stained kidney sample. In an example of a multiplexed ICH sample, brown, red, and blue chromogens were isolated into separate images without crosstalk or interference from the (also blue) hematoxylin counterstain. CONCLUSION: Cytomics requires both accurate architectural segmentation as well as multiplexed molecular imaging to associate molecular phenotypes with relevant cellular and tissue compartments. Multispectral imaging can assist in both these tasks, and conveys new utility to brightfield-based microscopy approaches.

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↗

PubMed2006

An adaptive recurrent-neural-network motion controller for X-Y table in CNC machine.

In this paper, an adaptive recurrent-neural-network (ARNN) motion control system for a biaxial motion mechanism driven by two field-oriented control permanent magnet synchronous motors (PMSMs) in the computer numerical control (CNC) machine is proposed. In the proposed ARNN control system, a RNN with accurate approximation capability is employed to approximate an unknown dynamic function, and the adaptive learning algorithms that can learn the parameters of the RNN on line are derived using Lyapunov stability theorem. Moreover, a robust controller is proposed to confront the uncertainties including approximation error, optimal parameter vectors, higher-order terms in Taylor series, external disturbances, cross-coupled interference and friction torque of the system. To relax the requirement for the value of lumped uncertainty in the robust controller, an adaptive lumped uncertainty estimation law is investigated. Using the proposed control, the position tracking performance is substantially improved and the robustness to uncertainties including cross-coupled interference and friction torque can be obtained as well. Finally, some experimental results of the tracking of various reference contours demonstrate the validity of the proposed design for practical applications.

Algorithms↗

PubMed2006

Predicting protein structural class with AdaBoost Learner.

The structural class is an important feature in characterizing the overall topological folding type of a protein or the domains therein. Prediction of protein structural classification has attracted the attention and efforts from many investigators. In this paper a novel predictor, the AdaBoost Learner, was introduced to deal with this problem. The essence of the AdaBoost Learner is that a combination of many 'weak' learning algorithms, each performing just slightly better than a random guessing algorithm, will generate a 'strong' learning algorithm. Demonstration thru jackknife cross-validation on two working datasets constructed by previous investigators indicated that AdaBoost outperformed other predictors such as SVM (support vector machine), a powerful algorithm widely used in biological literatures. It has not escaped our notice that AdaBoost may hold a high potential for improving the quality in predicting the other protein features as well, such as subcellular location and receptor type, among many others. Or at the very least, it will play a complementary role to many of the existing algorithms in this regard.

Algorithms↗

PubMed2004

Image fusion for dynamic contrast enhanced magnetic resonance imaging.

BACKGROUND: Multivariate imaging techniques such as dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) have been shown to provide valuable information for medical diagnosis. Even though these techniques provide new information, integrating and evaluating the much wider range of information is a challenging task for the human observer. This task may be assisted with the use of image fusion algorithms. METHODS: In this paper, image fusion based on Kernel Principal Component Analysis (KPCA) is proposed for the first time. It is demonstrated that a priori knowledge about the data domain can be easily incorporated into the parametrisation of the KPCA, leading to task-oriented visualisations of the multivariate data. The results of the fusion process are compared with those of the well-known and established standard linear Principal Component Analysis (PCA) by means of temporal sequences of 3D MRI volumes from six patients who took part in a breast cancer screening study. RESULTS: The PCA and KPCA algorithms are able to integrate information from a sequence of MRI volumes into informative gray value or colour images. By incorporating a priori knowledge, the fusion process can be automated and optimised in order to visualise suspicious lesions with high contrast to normal tissue. CONCLUSION: Our machine learning based image fusion approach maps the full signal space of a temporal DCE-MRI sequence to a single meaningful visualisation with good tissue/lesion contrast and thus supports the radiologist during manual image evaluation.

Algorithms↗

PubMed1999

Comparing expert systems for identifying chest x-ray reports that support pneumonia.

We compare the performance of four computerized methods in identifying chest x-ray reports that support acute bacterial pneumonia. Two of the computerized techniques are constructed from expert knowledge, and two learn rules and structure from data. The two machine learning systems perform as well as the expert constructed systems. All of the computerized techniques perform better than a baseline keyword search and a lay person, and perform as well as a physician. We conclude that machine learning can be used to identify chest x-ray reports that support pneumonia.

Algorithms↗