SEARCH · PubMed Health

Results for “machine learning prediction”

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 613 records · Page 34Linked to original sources

PubMedDate not supplied

Prediction of functional class of the SARS coronavirus proteins by a statistical learning method.

The complete genome of severe acute respiratory syndrome coronavirus (SARS-CoV) reveals the existence of putative proteins unique to SARS-CoV. Identification of their function facilitates a mechanistic understanding of SARS infection and drug development for its treatment. The sequence of the majority of these putative proteins has no significant similarity to those of known proteins, which complicates the task of using sequence analysis tools to probe their function. Support vector machines (SVM), useful for predicting the functional class of distantly related proteins, is employed to ascribe a possible functional class to SARS-CoV proteins. Testing results indicate that SVM is able to predict the functional class of 73% of the known SARS-CoV proteins with available sequences and 67% of 18 other novel viral proteins. A combination of the sequence comparison method BLAST and SVMProt can further improve the prediction accuracy of SMVProt such that the functional class of two additional SARS-CoV proteins is correctly predicted. Our study suggests that the SARS-CoV genome possibly contains a putative voltage-gated ion channel, structural proteins, a carbon-oxygen lyase, oxidoreductases acting on the CH-OH group of donors, and an ATP-binding cassette transporter. A web version of our software, SVMProt, is accessible at http://jing.cz3.nus.edu.sg/cgi-bin/svmprot.cgi .

Adenosine Triphosphate↗

PubMed2006

Comparison between neural networks and multiple logistic regression to predict acute coronary syndrome in the emergency room.

OBJECTIVE: Patients with suspicion of acute coronary syndrome (ACS) are difficult to diagnose and they represent a very heterogeneous group. Some require immediate treatment while others, with only minor disorders, may be sent home. Detecting ACS patients using a machine learning approach would be advantageous in many situations. METHODS AND MATERIALS: Artificial neural network (ANN) ensembles and logistic regression models were trained on data from 634 patients presenting an emergency department with chest pain. Only data immediately available at patient presentation were used, including electrocardiogram (ECG) data. The models were analyzed using receiver operating characteristics (ROC) curve analysis, calibration assessments, inter- and intra-method variations. Effective odds ratios for the ANN ensembles were compared with the odds ratios obtained from the logistic model. RESULTS: The ANN ensemble approach together with ECG data preprocessed using principal component analysis resulted in an area under the ROC curve of 80%. At the sensitivity of 95% the specificity was 41%, corresponding to a negative predictive value of 97%, given the ACS prevalence of 21%. Adding clinical data available at presentation did not improve the ANN ensemble performance. Using the area under the ROC curve and model calibration as measures of performance we found an advantage using the ANN ensemble models compared to the logistic regression models. CONCLUSION: Clinically, a prediction model of the present type, combined with the judgment of trained emergency department personnel, could be useful for the early discharge of chest pain patients in populations with a low prevalence of ACS.

Acute Disease↗

PubMed2026

From prediction to mechanism: Explainable AI uncovers plasma and CSF proteomic signatures of Alzheimer's disease.

Alzheimer's disease (AD) plasma and cerebrospinal fluid (CSF) proteomics can distinguish AD from cognitively normal controls, but the generalizability of machine learning performance and the recurrence of biological signals across datasets require cautious interpretation. We developed an explainable artificial intelligence framework spanning two fluids and four ADNI proteomic datasets, covering 2082 modality specific samples, all analysed internally within ADNI. Phase 1 analysed plasma using a 119 analyte NULISA and targeted UPENN panel (n = 727; 216 CE, 511 controls). Phase 2 extended the analysis to CSF using SOMAscan7k, TMT-MS and targeted SET2, with Elecsys Aβ42, Aβ40, total tau and p-tau181 as anchor biomarkers. Only SOMAscan was subject-independent relative to Phase 1 plasma; TMT-MS and SET2 overlapped with Phase 1 for 96.0% and 97.7% of subjects and therefore are not independent replication cohorts. Under subject-level splits with fold internal preprocessing, we compared Elastic Net, Explainable Boosting Machines and gradient boosted trees with SHAP-based explanations. Among the candidate pipelines, we selected the pipeline with the highest held-out test ROC AUC for each platform; the selected values were 0.927 in plasma and 0.954-0.973 across the three CSF datasets. Because the same held out test performance was used for pipeline selection and headline reporting, these are optimistically selected single-holdout estimates, not unbiased estimates of generalizable or clinical performance. Explanations identified five recurring biological axes within ADNI: cholinergic (ACHE), tau/14-3-3 (YWHAG, YWHAZ, YWHAB, YWHAE), neuro-axonal (NEFL, NEFH), microglial/complement (CHIT1, SMOC1, CHI3L1, C7, CFH) and synaptic (NPTXR, NPTX2, DLG4, SYT5, VSNL1, ELAVL2). CSF analyses showed synaptic vesicle-cycle enrichment (q = 2 × 10-6), and CSF YWHAG correlated strongly with total tau (ρ = 0.87). Cross-fluid directional concordance was modest overall (54-57%) but increased to 73-80% among mapped analyte/protein rows reaching q < 0.05 in CSF. These findings provide hypothesis-generating, internally supported evidence within ADNI. Independent external cohorts with locked pipelines are required to evaluate generalizable performance and biological reproducibility; the overlapping TMT-MS and SET2 analyses should not be interpreted as independent replication.

Alzheimer Disease↗

PubMed2026

Integrating structure and experimental data annotations with computational modeling framework for predicting micro-nanoplastics toxicities.

The wide use of plastic materials leads to increased emissions of micro-nanoplastics (MNPs) into the environment, raising significant concerns about their impact on human health. Traditional experimental approaches for assessing MNPs toxicity are costly, time-consuming, and there are no experimental protocols that are universally acceptable. Computational modeling using machine learning (ML) approaches provides an efficient alternative to MNP toxicity assessment. However, most modeling studies of MNPs are limited due to the lack of high-quality data and there are few previous modeling studies considering complex structures of MNPs for model training. To address this challenge, we constructed three MNP datasets with popular toxicity endpoints from various resources and used nanostructure annotation techniques to create virtual MNPs (vMNPs) for all MNP structures. The MNP structures were digitalized from annotated vMNPs, and geometrical descriptors were calculated using the Delaunay Tessellation approach. Moreover, important experimental information, such as concentrations and cell lines, were transformed into extra training variables. Partial least squares regression (PLSR) models were built using both experimental and geometrical descriptors and validated through a leave-one-out cross validation procedure. The resulting models showed reasonable performance in predicting toxicity potentials of MNPs for the three endpoints in the present datasets. Moreover, an additional library of vMNPs with their predicted properties and bioactivities was constructed, directing further research of new MNPs. This study provides three novel ML models for MNPs by integrating geometrical and experimental descriptors, which have the potential to assess new MNPs for their toxicity. The modeling strategy developed in this study can be easily expanded to model other MNP toxicity endpoints and create promising new models for MNP toxicity assessments.

Data annotation↗

PubMed2003

PlantProm: a database of plant promoter sequences.

PlantProm DB, a plant promoter database, is an annotated, non-redundant collection of proximal promoter sequences for RNA polymerase II with experimentally determined transcription start site(s), TSS, from various plant species. The first release (2002.01) of PlantProm DB contains 305 entries including 71, 220 and 14 promoters from monocot, dicot and other plants, respectively. It provides DNA sequence of the promoter regions (-200 : +51) with TSS on the fixed position +201, taxonomic/promoter type classification of promoters and Nucleotide Frequency Matrices (NFM) for promoter elements: TATA-box, CCAAT-box and TSS-motif (Inr). Analysis of TSS-motifs revealed that their composition is different in dicots and monocots, as well as for TATA and TATA-less promoters. The database serves as learning set in developing plant promoter prediction programs. One such program (TSSP) based on discriminant analysis has been created by Softberry Inc. and the application of a support ftp: vector machine approach for promoter identification is under development. PlantProm DB is available at http://mendel.cs.rhul.ac.uk/ and http://www.softberry.com/.

Databases, Nucleic Acid↗

PubMed2026

Long-read based detection of large copy number variants with potential functional significance using the ContextSV structural variant caller.

Long-read sequencing enables improved detection of structural variants (SVs) in the human genome due to its substantially increased read lengths. However, currently widely used long-read SV callers primarily rely on alignment-based evidence, limiting their ability to detect large and complex SVs and potentially missing disease-relevant events. To address these limitations, we developed ContextSV, a framework that integrates alignment evidence with copy number predictions derived from sequencing coverage and single-nucleotide variant allele frequencies to improve SV detection, particularly for large copy number variants (CNVs). We additionally developed ContextScore, a machine learning-based classification model to assign SV confidence scores based on genomic context features and integrated it within ContextSV. Through benchmarking analyses on both simulated and real datasets, we demonstrate that ContextSV improves detection of large CNVs and inversions that may be missed by existing long-read SV callers. We further illustrate its utility by identifying and experimentally validating multiple large SVs in the KOLF2.1J reference stem cell line that were not detected by other methods. Collectively, our results demonstrate that ContextSV serves as a valuable complement to existing long-read SV detection approaches by improving sensitivity for large and clinically relevant SVs.

Humans↗

PubMed2026

Unveiling the Molecular Secrets of Seaweeds: A Comprehensive Review of Bioinformatics Applications in Algal Research.

Recent advances in high-throughput sequencing, bioinformatics, and multi-omics technologies have transformed seaweed research by overcoming long-standing challenges associated with complex genomes, diverse life cycles, and limited genomic resources. This review provides a comprehensive overview of bioinformatics approaches used to investigate seaweed genomics, transcriptomics, proteomics, metabolomics, microbiomes, and functional genomics, with emphasis on the computational tools and databases that support these analyses. Applications of bioinformatics in phylogenetics, drug discovery, microbiome characterization, and the development of biofuels, nutraceuticals, pharmaceuticals, and sustainable agriculture are also discussed. Particular attention is given to emerging strategies involving multi-omics integration, genome editing, artificial intelligence, machine learning, and synthetic biology that are reshaping seaweed research. The review further examines current challenges, including incomplete genomic resources, data standardization, and the need for experimental validation of computational predictions. Collectively, these advances highlight the growing role of bioinformatics in enabling systems-level understanding of seaweed biology and accelerating their translation into sustainable biotechnological and marine bioeconomy applications.

macroalgal genomics↗

PubMed2026

GUANinE v1.1 reveals complementarity of supervised and genomic language models.

There has been much debate about the benefits of supervised versus unsupervised learning on genomes. Determining which is better in what contexts requires developing comprehensive benchmarks spanning functional and evolutionary tasks. Importantly, such benchmarks need large sample sizes to enable well-powered ranking of models. Having developed and applied such a benchmark here (GUANinE v1.1), we conclusively demonstrate each paradigm offers key advantages and outperforms on certain tasks. In accordance with training, supervised sequence-to-function models exhibit strong performance when annotating functional states characterized by chromatin accessibility or histone marks, while self-supervised language models outperform on evolutionary conservation. Our hundreds of new evaluations in this v1.1 expansion provide evidence for a tradeoff between input context size and model parameter count for a fixed compute budget, which we depict with new metrics such as kiloparameters/base pair. We also construct two new large-scale variant interpretation tasks in v1.1: cadd-snv measuring deleteriousness, and clinvar-snv measuring clinical pathogenicity. We find that conservation scores, and by extension, genomic language models, predict deleteriousness well, but successfully translating deleteriousness predictions to pathogenicity remains challenging. GUANinE v1.1 newly evaluates dozens of pretrained genomic models, and we conclude that moderate-context hybrid or post-trained language models may define the next era of machine learning in genomics.

Genomics↗

PubMed2026

MetaFX: feature extraction from whole-genome metagenomic sequencing data.

MOTIVATION: Microbial communities consist of thousands of microorganisms and viruses and have a tight connection with an environment, such as gut microbiota modulation of host body metabolism. However, the direct relationship between the presence of certain microorganism and the host state often remains unknown. Toolkits using reference-based approaches are limited to microbes present in databases. Reference-free methods often require enormous resources for metagenomic assembly or results in many poorly interpretable features based on k-mers. RESULTS: Here we present MetaFX-an open-source library for feature extraction from whole-genome metagenomic sequencing data and classification of groups of samples. Using a large volume of metagenomic samples deposited in databases, MetaFX compares samples grouped by metadata criteria (e.g. disease, treatment, etc.) and constructs genomic features distinct for certain types of communities. Features constructed based on statistical k-mer analysis and de Bruijn graphs partition. Those features are used in machine learning models for classification of novel samples. Extracted features can be visualized on de Bruijn graphs and annotated for providing biological insights. We demonstrate the utility of MetaFX by building classification models for 590 human gut samples with inflammatory bowel disease. Our results outperform the previous research disease prediction accuracy up to 17%, and improves classification results compared to taxonomic analysis by 9±10% on average. AVAILABILITY AND IMPLEMENTATION: MetaFX is a feature extraction toolkit applicable for metagenomic datasets analysis and samples classification. The source code, test data, and relevant information for MetaFX are freely accessible at https://github.com/ctlab/metafx under the MIT License. Alternatively, MetaFX can be obtained via http://doi.org/10.5281/zenodo.16949369.

Metagenomics↗

PubMed1993

Transmembrane segment prediction from protein sequence data.

We consider the automated identification of transmembrane domains in membrane protein sequences. 324 proteins (containing 1585 segments) were examined, representing every protein in the PIR database having the transmembrane domain feature annotation. Machine learning techniques were used to evaluate the efficacy of alternative hydrophobicity measures and windowing techniques. We describe a simpler measure of hydrophobicity and a new variable window size concept. We demonstrate that these techniques are superior to some previous techniques in minimizing the segment error rate. Using these new techniques, we describe an algorithm that has a 7.9% segment error rate on the sampled proteins, while classifying 16.7% of the amino acid residues as transmembrane.

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↗

PubMed2026

Challenges and future directions in AI-driven biomaterials for microbiome-associated oral infectious diseases: A systematic review.

Oral biofilm-induced antimicrobial resistance is the core pathogenic mechanism of microbiome-associated oral infectious diseases (dental caries, periodontitis, peri-implantitis, and endodontic infection). Traditional therapies and biomaterials are limited by poor biofilm penetration, drug resistance induction, single functionality, and inadequate adaptation to dynamic oral microenvironmental changes (e.g., pH fluctuations, salivary rinsing, masticatory stimulation). Artificial intelligence (AI) has transformed the field by integrating materials science, microbiology, and stomatology data. Via machine learning, deep learning, and multi-physics simulation, AI optimizes biomaterial physicochemical properties, decodes microenvironmental signals, constructs precise sensing-response loops, and supports the full chain of material design, performance prediction, and action simulation, advancing treatment from empirical intervention to precision regulation. This systematic review retrieved literature from PubMed, Embase, and Web of Science (January 2016-January 2026) using keywords across three dimensions: AI, biomaterials, and oral microbiome. Following inclusion/exclusion criteria, 99 articles were included. It elaborates on five core mechanisms of AI-driven oral biomaterials (precise oral microbiome analysis, targeted material design/optimization, performance prediction/simulation, targeted delivery/intervention, effect evaluation/dynamic regulation), analyzes their applications in microbiome-targeted biomaterial research and development (R&D) and clinical practice for the four major oral infectious diseases, addresses technical bottlenecks (insufficient targeting specificity and precision of biomaterials, poor stability and durability in complex oral microenvironments, inadequate biofilm disruption capacity, and clinical translation obstacles), and proposes future directions (multimodal design to enhance targeting specificity, structural and component optimization to improve stability/durability, development of multi-mechanism synergistic biofilm disruption strategies, strengthening translational research for clinical application, and deep integration of AI in the full chain of biomaterial R&D). This work provides comprehensive theoretical and practical support for the R&D, optimization, and clinical translation of AI-driven microbiome-targeted oral biomaterials.

Humans↗

PubMed2026

Machine learning-based clinical tool for identifying factors associated with symptomatic knee osteoarthritis: the Nagahama study.

BACKGROUND: A clinical tool that evaluates factors associated with symptomatic knee osteoarthritis (OA) based on modifiable factors is lacking. This study aimed to develop a machine learning-based clinical assessment tool using modifiable factors to identify factors associated with symptomatic knee OA and to determine its accuracy. METHODS: This study included 429 participants (81.8% women; age, 69.0 ± 5.3 years) from the Nagahama Study who were ≥60 years old and had radiographically confirmed knee OA. A Knee Society Knee Scoring System 2011 symptom score of <23 points defined symptomatic knee OA. Participants were randomly assigned to training (70%) and test (30%) datasets. A machine learning model was developed using Extreme Gradient Boosting with 27 variables, and the SHapley Additive exPlanation (SHAP) values were used to assess feature importance. The top 8 features were translated into a 100-point clinical scoring tool weighted by their SHAP contributions. The cutoff value indicating symptomatic knee OA in the clinical assessment tool was determined using receiver operating characteristic analysis, and model performance was evaluated in both datasets. RESULTS: The clinical assessment tool consisted of low back pain, OA severity, depressive tendencies, knee flexion/extension range of motion, knee extension and hip abduction strength, and lower limb muscle quality. The model showed moderate discriminative performance (AUC 0.771 and 0.773 in the training and test datasets, respectively), with a cutoff point of 47. CONCLUSION: The proposed clinical assessment tool may provide a structured framework for assessing modifiable factors associated with symptomatic knee OA, reflecting their contribution to current symptom status.

Humans↗

PubMed2004

Learning to discriminate between ligand-bound and disulfide-bound cysteines.

We present a machine learning method to discriminate between cysteines involved in ligand binding and cysteines forming disulfide bridges. Our method uses a window of multiple alignment profiles to represent each instance and support vector machines with a polynomial kernel as the learning algorithm. We also report results obtained with two new kernel functions based on similarity matrices. Experimental results indicate that binding type can be predicted at significantly higher accuracy than using PROSITE patterns.

Algorithms↗

PubMed2025

Multi-Omics and Integrative Analytics in Natural Products Discovery.

Natural products (NPs) have long been an essential source of new bioactive compounds for drug discovery; however, traditional methods for screening and isolating these compounds can be slow and often yield diminishing returns. Fortunately, advanced multi-omics and computational approaches present powerful solutions to these challenges. This review highlights innovative methodologies that integrate metabolomics, genomics, transcriptomics, and proteomics with bioinformatics and analytical chemistry to accelerate NP discovery. For instance, untargeted metabolomics platforms like high-resolution liquid chromatography-tandem mass spectrometry (LC-MS/MS) and Global Natural Products Social (GNPS) molecular networking allow for comprehensive profiling of new compounds, while targeted isotope-labeling strategies enhance this process. Additionally, genome and metagenome mining tools such as antibiotics and secondary metabolite analysis shell (antiSMASH), Deep Biosynthetic Gene Cluster (DeepBGC), and Pipeline for Reconstructing Integrated Syntheses of Metabolites (PRISM) quickly identify biosynthetic gene clusters (BGCs) in both cultured and uncultured organisms, often using heterologous expression to validate products. Transcriptomic analyses, including RNA sequencing (RNA-seq), co-expression networks, and fluxomics, help clarify how pathways are regulated, while quantitative proteomics techniques like tandem mass tags/isobaric tags for relative and absolute quantitation (TMT/iTRAQ) and label-free methods, along with chemoproteomics approaches such as cellular thermal shift assay and thermal proteome profiling (TPP), uncover molecular targets and their mechanisms of action. This review also places significant emphasis on the role of artificial intelligence (AI) and machine learning (ML) in integrating multi-omics data, spanning activities from constructing gene-metabolite correlation networks to leveraging knowledge graphs and graph neural networks for data fusion and functional prediction. Finally, this review concludes by discussing the synergistic benefits of multi-omics for natural-product discovery, addressing current technical challenges, and exploring future directions toward high-throughput, intelligent data integration for next-generation NP research.

Biological Products↗

PubMed2026

A machine learning approach to identify key epigenetic transcripts for ageing research in human blood (Epitage).

DNA methylation is an established biomarker of human ageing and is used by a variety of tools to identify meaningful epigenetic signals. We investigated whether analysing CpGs grouped by transcript as functional units could generate a ranked list of transcripts most correlated with age that might otherwise be overlooked in genome-wide CpG-based studies. Here we present Epitage ( https://github.com/a00s/epitage ), a continuously updated ranked list of transcripts built from the GSE87571 dataset (714 whole-blood samples, ages 14-94 years) through intensive testing with machine-learning models. To support reproducible analyses, we developed ugPlot ( https://github.com/a00s/ugplot ), an open-source R/Shiny tool with a graphical user interface that automates model training, testing, and comparison. Initially, we identified 48 transcripts across 13 genes, with some transcripts from the genes OBSCN, PRRT1, and SPTBN4 showing better predictive performance when multiple associated CpGs were analysed together rather than individually. In contrast, for the majority of transcripts, a dominant individual CpG still showed a higher Spearman correlation with age, as seen in established ageing genes such as ELOVL2, FHL2, and TRIM59. Epitage is a transcript-ranking list based on the methylation patterns observed in the analysed dataset. It provides a reproducible framework for prioritising transcripts associated with human ageing and for guiding future epigenetic studies.

Humans↗

PubMed2003

Combining the performance strengths of the logistic regression and neural network models: a medical outcomes approach.

The assessment of medical outcomes is important in the effort to contain costs, streamline patient management, and codify medical practices. As such, it is necessary to develop predictive models that will make accurate predictions of these outcomes. The neural network methodology has often been shown to perform as well, if not better, than the logistic regression methodology in terms of sample predictive performance. However, the logistic regression method is capable of providing an explanation regarding the relationship(s) between variables. This explanation is often crucial to understanding the clinical underpinnings of the disease process. Given the respective strengths of the methodologies in question, the combined use of a statistical (i.e., logistic regression) and machine learning (i.e., neural network) technology in the classification of medical outcomes is warranted under appropriate conditions. The study discusses these conditions and describes an approach for combining the strengths of the models.

Artificial Intelligence↗

PubMed1996

The dynamics of discrete-time computation, with application to recurrent neural networks and finite state machine extraction.

Recurrent neural networks (RNNs) can learn to perform finite state computations. It is shown that an RNN performing a finite state computation must organize its state space to mimic the states in the minimal deterministic finite state machine that can perform that computation, and a precise description of the attractor structure of such systems is given. This knowledge effectively predicts activation space dynamics, which allows one to understand RNN computation dynamics in spite of complexity in activation dynamics. This theory provides a theoretical framework for understanding finite state machine (FSM) extraction techniques and can be used to improve training methods for RNNs performing FSM computations. This provides an example of a successful approach to understanding a general class of complex systems that has not been explicitly designed, e.g., systems that have evolved or learned their internal structure.

Neural Networks, Computer↗