Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Machine learning model”

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 523 records · Page 29Linked to original sources
PubMed2025

MetaChrome: An Open-Source, User-Friendly Tool for Automated Metaphase Chromosome Analysis.

DNA Fluorescence In Situ Hybridization (FISH) is an essential technique to study chromosome biology and genetics, enabling precise visualization of specific genomic loci to study structural abnormalities, gene mapping, and chromosomal rearrangements. High-Throughput Imaging (HTI) can automate the analysis of DNA-FISH chromosome images, but the accurate and automated segmentation of mitotic chromosomes and simultaneous colocalization of FISH signals remains a challenge. While several commercial automated karyotyping tools partially solve these issues, open-source software that effectively combines robust chromosome segmentation with comprehensive colocalization analysis capabilities remains necessary. To address this unmet need, we developed MetaChrome, an open-source software platform built around a graphical user interface and explicitly designed for automated metaphase chromosome analysis. MetaChrome leverages fine-tuned deep learning models to automate metaphase chromosome segmentation, together with colocalization analysis of chromosome-specific FISH probes and immunofluorescent-labeled proteins. Importantly, MetaChrome achieves enhanced segmentation accuracy compared to traditional image processing methods by adopting a Cellpose segmentation model fine-tuned with manually annotated metaphase chromosome datasets. The fine-tuned model ensures precise assignment of DNA-FISH spots to individual chromosomes in an automated manner. This facilitates rapid identification of chromosomal abnormalities, reduces human error, and advances high-throughput chromosome analysis workflows, addressing a key bottleneck in chromosome biology research.

Chromosome segmentation↗
PubMed2025

Knowledge-enhanced protein subcellular localization prediction from 3D fluorescence microscope images.

MOTIVATION: Pinpointing the subcellular location of proteins is essential for studying protein function and related diseases. Advances in spatial proteomics have shown that automatic recognition of protein subcellular localization from images could highly facilitate protein translocation analysis and biomarker discovery, but existing machine-learning works have been mostly limited to processing 2D images. By contrast, 3D images have higher spatial resolution and allow researchers to observe cellular structures in their natural context, but currently, there are only a few studies of 3D image processing for protein distribution analysis due to the lack of data and complexity of modeling. RESULTS: We developed a knowledge-enhanced protein subcellular localization model, KE3DLoc, which could recognize distribution patterns in 3D fluorescence microscope images using deep learning methods. The model designs an image feature extraction module that incorporates information from 3D and 2D projected cells and implements asymmetric loss and confidence weights to address data imbalance and weak cell annotation issues. Besides, considering that the biological knowledge in the Gene Ontology (GO) database can provide valuable support for protein location understanding, the KE3DLoc model incorporates a novel knowledge enhancement module that optimizes the protein representation by related knowledge graphs derived from the GO. Since the image module and the knowledge module calculate features from different levels, KE3DLoc designs protein ID aggregation to enhance the consistency of protein features across different cells. Experimental results on three public datasets have demonstrated that the KE3DLoc significantly outperforms existing methods and provides valuable insights for spatial proteomics research. AVAILABILITY AND IMPLEMENTATION: All datasets and codes used in this study are available at GitHub: https://github.com/PRBioimages/KE3DLoc.

Microscopy, Fluorescence↗
PubMed2025

Application of causal discovery of factors driving dissolved oxygen in estuarine environments.

Dissolved oxygen (DO) concentrations in estuarine bottom waters are a manifestation of multiple, interacting physical and biogeochemical processes, yet identifying their independent contributions remains challenging. Here, we analyze monthly water quality monitoring data from eight stations across Long Island Sound from 1994 to 2022 using a causal discovery framework (PCMCI+) and transformation of forcing variables. Our goal is to identify and isolate variables that causally influence bottom DO and improve predictive models by minimizing overfitting and multicollinearity. PCMCI+ reveals surface-layer temperature as the most important and consistent negative driver of bottom DO, followed by stratification. Wind events exhibit only brief relief by advection and mixing, while river discharge shows no direct causal link to DO, making it less influential than previously thought. Biogeochemical variables, including chlorophyll-a (Chl-a), nitrate and nitrite, and particulate carbon, influence DO through both contemporaneous and time-lagged pathways, often with signs that shift depending on the process. The derived models were evaluated by comparing skill scores, mean squared error, and Akaike Information Criterion. Both model types perform well, with coefficient of determination values exceeding 0.90 at multiple stations using only 3-5 predictors. Our analysis reveals that the best causal predictors are surface-layer temperature, stratification, Chl-a, and particle carbon. This approach provides a scalable framework for improving prediction models and understanding the mechanistic links that control the seasonal variability of DO in estuarine systems.

Estuaries↗
PubMed2026

Divergent microbial preludes to necrotising enterocolitis defined by gut phages and bacterial resistomes.

BACKGROUND: Translating microbiome correlations into robust predictive features for complex gut disorders remains elusive, partly due to oversimplified models of pathogenesis and neglect of the virome, a key player in microbial ecosystems. Necrotising enterocolitis (NEC), a devastating disease of preterm infants with no reliable clinical predictors, exemplifies this challenge. OBJECTIVE: To determine the predictive potential of the gut prophageome and polymicrobial aetiologies for NEC. DESIGN: We applied integrated metagenomic and metatranscriptomic analyses and machine learning to 1825 longitudinal stool samples from 43 preterm infants who later developed NEC and 86 gestational age-matched and birthweight-matched controls across three US hospitals. We characterised gut prophageome acquisitions and their association with clinical exposures, including antibiotics, diet and pharmacotherapies. To predict NEC risk, we integrated pre-onset prophageome, antibacterial resistome and bacteriome profiles with neonatal pathology, stratifying the cohort by disease onset timing (early: ≤40 days; late: >40 days) for separate analysis. RESULTS: NEC cases exhibited distinct viral diversity trajectories before disease onset. Early-onset NEC was best predicted by phage-bacterial interaction signatures (75% accuracy, 81% sensitivity). Metatranscriptomics revealed increased phage DNA abundance with low gene expression, suggesting a lysogenic lifestyle that may stabilise pathobionts. These phages encode metabolic genes potentially enhancing pathobiont resilience. Late-onset NEC was best predicted by antibacterial resistome profiles (83% accuracy). CONCLUSION: The gut prophageome serves as both a source of pre-symptomatic predictive signals and an active modulator of NEC pathogenesis, with distinct microbial mechanisms driving early-onset and late-onset disease. These polymicrobial etiologies inform strategies for early detection, risk stratification and the development of microbiome-targeted preventive and therapeutic interventions.

BIOMARKERS↗
PubMed2001

A knowledge model for the interpretation and visualization of NLP-parsed discharged summaries.

At our institution, a Natural Language Processing (NLP) tool called MedLEE is used on a daily basis to parse medical texts including complete discharge summaries. MedLEE transforms written text into a generic structured format, which preserves the richness of the underlying natural language expressions by the use of concept modifiers (like change, certainty, degree and status). As a tradeoff, extraction of application-specific medical information is difficult without a clear understanding of how these modifiers combine. We report on a knowledge model for MedLEE modifiers that is helpful for a high level interpretation of NLP data and is used for the generation of two distinct views on NLP-parsed discharge summaries: A physician view offering a condensed overview of the severity of patient problems and a data mining view featuring binary problem states useful for machine learning.

Artificial Intelligence↗
PubMed2002

DNA splice site detection: a comparison of specific and general methods.

In an era when whole organism genomes are being routinely sequenced, the problem of gene finding has become a key issue on the road to understanding. For eukaryotic organisms a large part of locating the genes is accomplished by predicting the likely location of splice sites on a DNA strand. This problem of splice site location has been ap- proached using a number of machine learning or statistical methods tailored more or less specifically to the nature of the problem. Recently large margin classifiers and boosting methods have been found to give improvements over more traditional methods in a number of areas. Here we compare large margin classifiers (SVM and CMLS) and boosted decision trees with the three most common models used for splice site detection (WMM, WAM, and MDT). We find that the newer methods compare favorably in all cases and can yield significant improvement in some cases.

Algorithms↗
PubMed2003

Machine learning approaches to lung cancer prediction from mass spectra.

We addressed the problem of discriminating between 24 diseased and 17 healthy specimens on the basis of protein mass spectra. To prepare the data, we performed mass to charge ratio (m/z) normalization, baseline elimination, and conversion of absolute peak height measures to height ratios. After preprocessing, the major difficulty encountered was the extremely large number of variables (1676 m/z values) versus the number of examples (41). Dimensionality reduction was treated as an integral part of the classification process; variable selection was coupled with model construction in a single ten-fold cross-validation loop. We explored different experimental setups involving two peak height representations, two variable selection methods, and six induction algorithms, all on both the original 1676-mass data set and on a prescreened 124-mass data set. Highest predictive accuracies (1-2 off-sample misclassifications) were achieved by a multilayer perceptron and Naïve Bayes, with the latter displaying more consistent performance (hence greater reliability) over varying experimental conditions. We attempted to identify the most discriminant peaks (proteins) on the basis of scores assigned by the two variable selection methods and by neural network based sensitivity analysis. These three scoring schemes consistently ranked four peaks as the most relevant discriminators: 11683, 1403, 17350 and 66107.

Algorithms↗
PubMed2025

GRUMB: a genome-resolved metagenomic framework for monitoring urban microbiomes and diagnosing pathogen risk.

SUMMARY: Urban infrastructure hosts dynamic microbial communities that complicate biosurveillance and AMR monitoring. Existing tools rarely combine genome-resolved reconstruction with ecological modeling and batch-aware analytics tailored to infrastructure-scale studies. We present GRUMB (Genome-Resolved Urban Microbiome Biosurveillance), an open-source, SLURM-compatible pipeline that reconstructs high-quality metagenome-assembled genomes (MAGs) from shotgun sequencing reads and integrates taxonomic/functional annotation (CARD, VFDB), batch-aware normalization, ecological diagnostics and machine learning classification of environment types with uncertainty and risk scoring. GRUMB accepts either SRA project accessions or paired-end FASTQ files with metadata, and produces assemblies, MAGs, taxonomic and functional profiles, ecological outputs and risk-informed classification. Its modular design enables reproducible, infrastructure-scale biosurveillance across diverse environments. AVAILABILITY AND IMPLEMENTATION: GRUMB is freely available under the MIT License at: https://github.com/SuleimanAminu/genome-resolved-urban-microbiome-biosurveillance; Zenodo DOI: https://doi.org/10.5281/zenodo.15505402. Requirements: Linux (Ubuntu 20.04+), Python 3.11, R 4.2+, SLURM. Issues and feature requests are tracked on GitHub.

Microbiota↗
PubMed2003

Functional discrimination of gene expression patterns in terms of the gene ontology.

The ever-growing amount of experimental data in molecular biology and genetics requires its automated analysis, by employing sophisticated knowledge discovery tools. We use an Inductive Logic Programming (ILP) learner to induce functional discrimination rules between genes studied using microarrays and found to be differentially expressed in three recently discovered subtypes of adenocarcinoma of the lung. The discrimination rules involve functional annotations from the Proteome HumanPSD database in terms of the Gene Ontology, whose hierarchical structure is essential for this task. While most of the lower levels of gene expression data (pre)processing have been automated, our work can be seen as a step toward automating the higher level functional analysis of the data. We view our application not just as a prototypical example of applying more sophisticated machine learning techniques to the functional analysis of genes, but also as an incentive for developing increasingly more sophisticated functional annotations and ontologies, that can be automatically processed by such learning algorithms.

Adenocarcinoma↗
PubMed1998

Neural network mosaic model for pupillary responses to spatial stimuli.

A neural network mosaic model was developed to investigate the spatial-temporal properties of the human pupillary control system. It was based on the double-layer neural network model developed by Cannon and Robinson and the pupillary dual-path model developed by Sun and Stark. The neural network portion of the model received its input from a sensor array and consisted of a retina-like two-dimensional neuronal layer. The dual-path portion of the model was composed of interconnections of the neurons that formed a mosaic of AC transient and DC sustained paths. The spatial aggregates of the AC and DC signals were input to the AC and DC summing neurons, respectively. Finally, the weighted sum of the aggregate AC and DC signals provided the output for driving the pupillary response. An important property of the model was that it could adaptively learn from training samples by adjustment of the weights. The neural network mosaic model showed excellent performance in simulating both the traditional pupillary phenomena and the new spatial stimulation findings such as responses to change in stimulus pattern and shift of light spot. Moreover, the model could also be used for the diagnosis of clinical deficits and image processing in machine vision.

Brain Stem↗
PubMedDate not supplied

A teaching and research simulator for therapeutic embolization.

A teaching machine that simulates intravascular conditions found during a human therapeutic embolization has been constructed. A submersible pump drives fluid through a circuit of tubing. One limb of a Y (a vascular bifurcation) located in this circuit leads to a model arteriovenous malformation. Catheters placed in this limb may introduce embolic materials by various techniques, and those techniques may be learned and practiced under safe and stress-free conditions. Loss of an embolus into the other limb which supposedly leads to normal tissues is caught and displayed by a sieve, providing immediate feedback that a technique error has occurred.

Embolization, Therapeutic↗
PubMed1986

Long-term depression as a memory process in the cerebellum.

When details of neuronal network structures of the cerebellum were uncovered in the 1960's, a hope emerged that functions of the cerebellum would eventually be explained in terms of operation of the cerebellar neuronal network. While various network models were proposed, involvement of synaptic plasticity in the cerebellar neuronal network as a memory process became a focus of discussion. The characteristic dual inputs to Purkinje cells, one from parallel fibers (axons of granule cells) and the other from climbing fibers, were suggested to represent such synaptic plasticity, and under this assumption, the cerebellar cortex was envisaged as a learning machine for pattern recognition. Despite these theoretical suggestions, earlier efforts to reveal the postulated synaptic plasticity in the cerebellar cortex were unsuccessful. It had then to wait for a decade before long-term depression (LTD) was finally found as its possible substrate. LTD is a long-lasting depression of parallel fiber-to-Purkinje cell transmission that occurs following conjunctive activation of parallel fibers and a climbing fiber both converging onto one and the same Purkinje cell. LTD has now been established by means of various testing methods, and recent efforts have been directed toward its molecular mechanisms. Efforts have also been devoted to demonstrate roles of LTD in motor learning through studies of adaptation of the vestibulo-ocular reflex, adaptive adjustment of hand movement, and more recently eyelid blink conditioned reflex. This article reviews recent efforts to characterize the LTD as a memory process, presumably the major, in the cerebellum.

Animals↗
PubMed1998

Medical diagnostic system using Fuzzy Coloured Petri Nets under uncertainty.

We propose a medical diagnostic system using Fuzzy Coloured Petri Nets (FCPN) in this paper. For complex real-world knowledge Fuzzy Petri Net (FPN) models have been proposed to perform fuzzy reasoning automatically. However, in the Petri Net we have to represent all kinds of processes by separate subnets even though the process has the same behavior of other one. Real-world knowledge often contains many parts which are similar, but not identical. This means that the total PTN becomes very large. The kind of problems may be annoying for a small system, and it may be catastrophic for the description of large-scale system. To avoid this kind of problems we propose a learning and reasoning method using FCPNs under uncertainty. On the other hand to correct the rules of knowledge-based system hand-built classifier and empirical learning method both based on domain theory have been proposed as machine learning methods, where there is a significant gap between the knowledge-intensive approach in the former and the virtually knowledge-free approach in the later. To resolve such problems simultaneously we propose a hybrid learning method which is built on the top of knowledge-based FCPN and Genetic Algorithms (GA). To verify the validity and the effectiveness of the proposed system, we have successfully applied it to the diagnosis of intervertebral diseases.

Algorithms↗
PubMed2026

CAKR: commutative algebra k-mer representations for genomics.

Despite the availability of various sequence analysis models, comparative genomic analysis remains a challenge in genomics, genetics, and phylogenetics. Commutative algebra, a fundamental tool in algebraic geometry and number theory, has rarely been used in data and biological sciences. In this study, we introduce commutative algebra k-mer representations as a nonlinear algebraic framework for analyzing genomic sequences. This representation bridges commutative algebra, algebraic topology, combinatorics, and machine learning to establish a mathematical framework for comparative genomic analysis. We evaluate its effectiveness on three tasks including genetic variant classification, phylogenetic tree reconstruction, and viral classification, typically requiring alignment-based, alignment-free, and machine-learning approaches, respectively. In this work, we show that commutative algebra k-mer representations outperform five state-of-the-art sequence analysis methods across twelve primary datasets, with two additional supplementary fragment-placement benchmarks, especially in viral classification, and maintain relatively stable predictive accuracy as dataset size increases, underscoring scalability and robustness.

Genomics↗
PubMed2001

Warmr: a data mining tool for chemical data.

Data mining techniques are becoming increasingly important in chemistry as databases become too large to examine manually. Data mining methods from the field of Inductive Logic Programming (ILP) have potential advantages for structural chemical data. In this paper we present Warmr, the first ILP data mining algorithm to be applied to chemoinformatic data. We illustrate the value of Warmr by applying it to a well studied database of chemical compounds tested for carcinogenicity in rodents. Data mining was used to find all frequent substructures in the database, and knowledge of these frequent substructures is shown to add value to the database. One use of the frequent substructures was to convert them into probabilistic prediction rules relating compound description to carcinogenesis. These rules were found to be accurate on test data, and to give some insight into the relationship between structure and activity in carcinogenesis. The substructures were also used to prove that there existed no accurate rule, based purely on atom-bond substructure with less than seven conditions, that could predict carcinogenicity. This results put a lower bound on the complexity of the relationship between chemical structure and carcinogenicity. Only by using a data mining algorithm, and by doing a complete search, is it possible to prove such a result. Finally the frequent substructures were shown to add value by increasing the accuracy of statistical and machine learning programs that were trained to predict chemical carcinogenicity. We conclude that Warmr, and ILP data mining methods generally, are an important new tool for analysing chemical databases.

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↗
PubMed2003

Multidimensional signal exploration using multiple correspondence analysis. An example of a load lifting study.

Most empirical studies concerning rehabilitation yield numerous multidimensional signals (dozens of time variables are obtained for dozens of empirical situations). The purpose of this paper is to suggest a statistical analysis procedure based on: 1) space-time fuzzy windowing; 2) signal behavior characterization within the windows using membership value averages (MVA); and 3) MVA analysis using the multiple correspondence analysis (MCA). A load lifting study provided an example of 78 multidimensional signals including 89 time variables (forces, energy indicators, linear and angular positions, speeds, and accelerations). The main goal of MCA was to compare and contrast biomechanical signals from two lifting modes: "free" and "isokinetic." In the first mode, three loads were tested--light, medium, and heavy. In the second, three speeds were tested--slow, medium, and fast. Thirteen male individuals without disabilities participated in this study. The MCA showed that most of the free load-lifting strategies cannot be used in isokinetic lifting because the constraints of the subject and the environment are different. In addition, as the level of difficulty increases, free lifting became more economical while isokinetic lifting became less economical. These results would appear to indicate that movement strategies used for free lifting cannot be learned using an isokinetic machine during rehabilitation sessions for chronic low back pain. MCA was also suggested as a tool for comparing patients with control individuals. To achieve this aim, the notion of "supplementary data" was introduced.

Adult↗
PubMed2003

PicSOr: an objective test of perceptual skill that predicts laparoscopic technical skill in three initial studies of laparoscopic performance.

BACKGROUND: Laparoscopic surgery requires surgeons to infer the shape of 3-D structures, such as the internal organs of patients, from 2-D displays on a video monitor. Recent evidence indicates that the issue is not resolved by the use of contemporary 3-D camera systems. It is therefore crucial to find ways of measuring differences in aptitude for recovering 3-D structure from 2-D images, and assessing its impact on performance. Our aim was to test empirically for a relationship between laparoscopic ability and the perceptual skill of recovering information about 3-D structures from 2-D monitor displays. METHODS: Participants in three studies completed a simulated laparoscopic cutting task as well as the Pictorial Surface Orientation (PicSOr)3 Test. In studies 1 (n = 48) and 2 (n = 32) both groups were laparoscopic novices, and in study 3 (n = 34) 18 of the participants were experienced laparoscopic surgeons. FINDINGS: All three studies showed that PicSOr consistently predicted the laparoscopic performance of participants on the laparoscopic cutting task (study 1, r = 0.5, p < 0.0003; study 2, r = 0.5, p < 0.004; and study 3, r = 0.42, p = 0.017). Furthermore, it was also a significant predictor of laparoscopic surgeons' performance (r = 0.54, p = 0.047). INTERPRETATIONS: This is the first objective perceptual psychometric test to reliably predict laparoscopic technical skills. PicSOr provides a tool for assessing which trainees have the potential to learn minimal access surgery.

Adult↗