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 721 records · Page 40Linked to original sources

PubMed2026

Rhizosphere Dialogue: Microorganisms Mediated by Root Exudates Alleviate Drought Stress in Grasses.

Drought stress threatens the ecological functions and economic value of grasses, posing a major challenge to their sustainable production. Plants co-evolve with rhizosphere microbial communities, sometimes described as the plant's second genome, that can contribute to drought adaptation. Drought alters root architecture, hormonal and redox regulation and belowground carbon allocation, thereby modifying the quantity and composition of root exudation and reshaping the rhizosphere environment. This review uses the rhizosphere dialogue as an integrative framework to link these plant responses with microbial recruitment and subsequent feedback to the host. We summarise three linked stages of this dialogue: drought-induced changes in root exudation; microbial recruitment and colonisation through chemotaxis, attachment, biofilm formation, and root colonisation; and microbiome-mediated feedback that improves plant water relations, hormonal and redox homoeostasis, nutrient acquisition, and root function. We highlight microbial extracellular polymeric substances, 1-aminocyclopropane-1-carboxylate deaminase, and microbial volatile organic compounds as key mediators of drought alleviation. We then discuss how this framework may inform rational synthetic microbial community (SynCom) design, microbiome-informed breeding, artificial intelligence and machine-learning assisted strain prioritisation, rhizosphere legacy effects, and real-time monitoring. Future work should distinguish active exudate-mediated recruitment from drought-driven environmental filtering and integrate multi-omics, plant genetics, functional validation, and multi-location field trials to determine whether rhizosphere dialogue can become a predictive framework for climate-resilient grass production.

drought stress↗

PubMed2026

RAS signaling in lung adenocarcinoma is defined by lineage context and DUSP4 loss.

BACKGROUNDThe molecular landscape of lung adenocarcinoma (LUAD) is often illustrated as a driver-oncogene pie chart, but identical mutations exhibit heterogeneous signaling shaped by comutations, transcriptional programs, and lineage context. We propose a lineage-integrated signaling framework using an EGFR mutation signature (mSig).METHODSWe defined EGFR mSig using differentially expressed genes in EGFR-mutant (EGFR-mt) LUADs. Semisupervised clustering and machine learning models were used to test reproducibility in different combinations of datasets. We analyzed molecular subtypes, lineage markers, co-occurring mutations, and EGFR copy number alterations in EGFR mSig-defined subtypes of LUAD.RESULTSEGFR mSig showed robust classification performance (area under receiver operating characteristic curve = 0.83-0.95; mean negative predictive value = 96.3%). Validated gene expression subtypes and lung lineage markers were closely aligned with EGFR mSig status. Most EGFR mSig+ tumors, including many without EGFR mutations, belonged to the bronchioid subtype. A subset of canonical RAS mutations were mSig+ and mirrored the EGFR mutation pattern. EGFR WT/mSig- tumors were enriched for nonbronchioid subtypes and had comutations in TP53 or RAS/RAF/RTKs. We highlight a parsimonious collection of coordinated mutations, including RAS, KEAP1, STK11, TP53, and CDKN2A, that taken together suggest coordination of tumor signaling previously suggested but now reproduced and expanded.CONCLUSIONA potentially novel EGFR mSig that captures the transcriptional footprint of EGFR activation revealed a subset of EGFR WT LUADs with mt-like features. mSig refines LUAD taxonomy beyond mutation-only pie-chart models by incorporating lineage and comutation context. Lineage-directed stratification with coalteration identifies clinically relevant groups across EGFR and RAS states and highlights treatment opportunities for patients currently considered oncogene-negative.FUNDINGNational Cancer Institute (NCI) U01CA272541, R01CA262296, U24CA264021, UG1CA233333, R01CA211939.

Humans↗

PubMed2003

Genomic data sampling and its effect on classification performance assessment.

BACKGROUND: Supervised classification is fundamental in bioinformatics. Machine learning models, such as neural networks, have been applied to discover genes and expression patterns. This process is achieved by implementing training and test phases. In the training phase, a set of cases and their respective labels are used to build a classifier. During testing, the classifier is used to predict new cases. One approach to assessing its predictive quality is to estimate its accuracy during the test phase. Key limitations appear when dealing with small-data samples. This paper investigates the effect of data sampling techniques on the assessment of neural network classifiers. RESULTS: Three data sampling techniques were studied: Cross-validation, leave-one-out, and bootstrap. These methods are designed to reduce the bias and variance of small-sample estimations. Two prediction problems based on small-sample sets were considered: Classification of microarray data originating from a leukemia study and from small, round blue-cell tumours. A third problem, the prediction of splice-junctions, was analysed to perform comparisons. Different accuracy estimations were produced for each problem. The variations are accentuated in the small-data samples. The quality of the estimates depends on the number of train-test experiments and the amount of data used for training the networks. CONCLUSION: The predictive quality assessment of biomolecular data classifiers depends on the data size, sampling techniques and the number of train-test experiments. Conservative and optimistic accuracy estimations can be obtained by applying different methods. Guidelines are suggested to select a sampling technique according to the complexity of the prediction problem under consideration.

Computational Biology↗

PubMedDate not supplied

Learning to think like a user: using cognitive task analysis to meet today's health care design challenges.

The growing role of information technology in our society has changed the very nature of many of the tasks that workers are called on to perform. Technology has resulted in a dramatic reduction in the number of proceduralized, rote tasks that workers must face. The impact of technology on many tasks and functions has been to greatly increase demands on the cognitive skills of workers. More procedural or predictable tasks are now handled by smart machines, while workers are responsible for tasks that require inference, diagnosis, judgment, and decision making. The increase in the cognitive demands placed on workers and the redistribution of tasks have created a need for a better understanding of the cognitive components of many tasks. This need has been recognized by many in the health care domain, including the U.S. Food and Drug Administration (FDA). Recent FDA regulations encourage the use of human factors in the development of medical devices, instruments, and systems. One promising set of methods for filling this need is cognitive task analysis.

Biomedical Engineering↗

PubMed2025

APNet, an explainable sparse deep learning model to discover differentially active drivers of severe COVID-19.

MOTIVATION: Computational analyses of bulk and single-cell omics provide translational insights into complex diseases, such as COVID-19, by revealing molecules, cellular phenotypes, and signalling patterns that contribute to unfavourable clinical outcomes. Current in silico approaches dovetail differential abundance, biostatistics, and machine learning, but often overlook nonlinear proteomic dynamics, like post-translational modifications, and provide limited biological interpretability beyond feature ranking. RESULTS: We introduce APNet, a novel computational pipeline that combines differential activity analysis based on SJARACNe co-expression networks with PASNet, a biologically informed sparse deep learning model, to perform explainable predictions for COVID-19 severity. The APNet driver-pathway network ingests SJARACNe co-regulation and classification weights to aid result interpretation and hypothesis generation. APNet outperforms alternative models in patient classification across three COVID-19 proteomic datasets, identifying predictive drivers and pathways, including some confirmed in single-cell omics and highlighting under-explored biomarker circuitries in COVID-19. AVAILABILITY AND IMPLEMENTATION: APNet's R, Python scripts, and Cytoscape methodologies are available at https://github.com/BiodataAnalysisGroup/APNet.

COVID-19↗

PubMed2005

Comprehensive bioinformatic analysis of the specificity of human immunodeficiency virus type 1 protease.

Rapidly developing viral resistance to licensed human immunodeficiency virus type 1 (HIV-1) protease inhibitors is an increasing problem in the treatment of HIV-infected individuals and AIDS patients. A rational design of more effective protease inhibitors and discovery of potential biological substrates for the HIV-1 protease require accurate models for protease cleavage specificity. In this study, several popular bioinformatic machine learning methods, including support vector machines and artificial neural networks, were used to analyze the specificity of the HIV-1 protease. A new, extensive data set (746 peptides that have been experimentally tested for cleavage by the HIV-1 protease) was compiled, and the data were used to construct different classifiers that predicted whether the protease would cleave a given peptide substrate or not. The best predictor was a nonlinear predictor using two physicochemical parameters (hydrophobicity, or alternatively polarity, and size) for the amino acids, indicating that these properties are the key features recognized by the HIV-1 protease. The present in silico study provides new and important insights into the workings of the HIV-1 protease at the molecular level, supporting the recent hypothesis that the protease primarily recognizes a conformation rather than a specific amino acid sequence. Furthermore, we demonstrate that the presence of 1 to 2 lysine residues near the cleavage site of octameric peptide substrates seems to prevent cleavage efficiently, suggesting that this positively charged amino acid plays an important role in hindering the activity of the HIV-1 protease.

Algorithms↗

PubMed2002

A bi-recursive neural network architecture for the prediction of protein coarse contact maps.

Prediction of contact maps may be seen as a strategic step towards the solution of fundamental open problems in structural genomics. In this paper we focus on coarse grained maps that describe the spatial neighborhood relation between secondary structure elements (helices, strands, and coils) of a protein. We introduce a new machine learning approach for scoring candidate contact maps. The method combines a specialized noncausal recursive connectionist architecture and a heuristic graph search algorithm. The network is trained using candidate graphs generated during search. We show how the process of selecting and generating training examples is important for tuning the precision of the predictor.

Algorithms↗

PubMed2005

Support vector machines for learning to identify the critical positions of a protein.

A method for identifying the positions in the amino acid sequence, which are critical for the catalytic activity of a protein using support vector machines (SVMs) is introduced and analysed. SVMs are supported by an efficient learning algorithm and can utilize some prior knowledge about the structure of the problem. The amino acid sequences of the variants of a protein, created by inducing mutations, along with their fitness are required as input data by the method to predict its critical positions. To investigate the performance of this algorithm, variants of the beta-lactamase enzyme were created in silico using simulations of both mutagenesis and recombination protocols. Results from literature on beta-lactamase were used to test the accuracy of this method. It was also compared with the results from a simple search algorithm. The algorithm was also shown to be able to predict critical positions that can tolerate two different amino acids and retain function.

Algorithms↗

PubMed2006

Optimized multilayer perceptrons for molecular classification and diagnosis using genomic data.

MOTIVATION: Multilayer perceptrons (MLP) represent one of the widely used and effective machine learning methods currently applied to diagnostic classification based on high-dimensional genomic data. Since the dimensionalities of the existing genomic data often exceed the available sample sizes by orders of magnitude, the MLP performance may degrade owing to the curse of dimensionality and over-fitting, and may not provide acceptable prediction accuracy. RESULTS: Based on Fisher linear discriminant analysis, we designed and implemented an MLP optimization scheme for a two-layer MLP that effectively optimizes the initialization of MLP parameters and MLP architecture. The optimized MLP consistently demonstrated its ability in easing the curse of dimensionality in large microarray datasets. In comparison with a conventional MLP using random initialization, we obtained significant improvements in major performance measures including Bayes classification accuracy, convergence properties and area under the receiver operating characteristic curve (A(z)). SUPPLEMENTARY INFORMATION: The Supplementary information is available on http://www.cbil.ece.vt.edu/publications.htm

Biomarkers, Tumor↗

PubMed2026

Identifying fundamental gaps in functional metagenomics: a step towards unlocking microbiome research potential.

Incomplete functional annotation limits biological interpretation in microbiome studies and their translational potential. Poor annotation arises from multiple causes, with incomplete gene-protein-reaction mapping being one tractable yet under-examined contributor. We address this gap by developing a comprehensive hierarchical framework that systematically integrates gene families in UniRef, proteins in UniProt, and metabolic reactions in MetaCyc and BioCyc through UniProtKB accession, EC number, and Pfam-domain matching. Applied to a human gut metagenome dataset via HUMAnN3, our MetaCyc-based mapping recovers up to 2.3-fold more unique reaction identifiers than the default pipeline and increases reaction prevalence across samples from ≈32% to 52% core reactions, addressing the data sparsity that limits statistical and machine-learning applications in microbiome research. Biological plausibility for the tested functions was supported by positive and negative controls: gut-microbial hormone-metabolism reactions previously linked to this dataset were recovered, while vertebrate-specific hormone-metabolism reactions remained correctly undetected. These gains derive from systematic database integration alone, without predictive algorithms, indicating that a tractable, mapping-related component of functional dark matter and data sparsity in microbiome studies is directly addressable. Because Pfam- and BioCyc-derived mappings trade specificity for coverage, confidence in any individual reaction assignment depends on the supporting evidence tier and source database.

Humans↗

PubMed2026

Quality over quantity: biopsy-anchored CT radiogenomics models outperform all-lesion training in a multi-tumour cohort despite a smaller sample size.

OBJECTIVE: Radiogenomics aims to non-invasively predict tumour genotypes from imaging, but most studies assume molecular homogeneity by assigning a single biopsy-derived label to all lesions within a patient. This approach risks substantial label noise given well-documented interlesional heterogeneity. We investigated whether anchoring training to biopsy-confirmed lesions improves radiogenomic model performance and generalisability. MATERIALS AND METHODS: We retrospectively analysed 1646 patients (11473 segmented lesions) with contrast-enhanced CT and EGFR mutation status from next-generation sequencing at the Netherlands Cancer Institute, alongside an external NSCLC radiogenomics cohort (n = 158). All visible lesions were segmented, and the exact biopsy site was matched to its segmentation. Radiomic features were extracted, and machine learning models were trained with three lesion selection strategies: all lesions, non-biopsied lesions only, and biopsy-confirmed lesions only. To disentangle label quality from sample size, we created size-matched variants (one lesion per patient) for all-lesion and non-biopsied strategies. RESULTS: All models achieved significant discrimination of EGFR status on internal validation (AUC = 0.62-0.68). However, performance of the all-lesion and non-biopsied models declined on external validation (AUC = 0.55-0.63), while the biopsy-anchored model maintained stable performance (AUC = 0.62), despite having only 1/10th of the training sample size. When training sets were size-matched, the biopsy-anchored approach significantly outperformed a model trained on all available lesions on external validation (p = 0.037). CONCLUSIONS: Radiogenomic models trained on biopsy-confirmed lesions outperform conventional all-lesion strategies in external validation, despite using an order of magnitude fewer samples. Prioritising lesion-level label fidelity can mitigate heterogeneity-driven noise, enhancing robustness and clinical translation of imaging-based genomic prediction. KEY POINTS: Question Does assigning biopsy-derived molecular labels to all lesions introduce heterogeneity-driven label noise that reduces the generalisability of radiogenomic models? Findings Models trained exclusively on biopsy-confirmed lesions demonstrated superior external generalisability compared with all-lesion approaches, despite being trained on substantially fewer samples. Clinical relevance Biopsy-anchored radiogenomics improves the reliability of non-invasive mutation prediction by accounting for tumour heterogeneity, potentially supporting clinical decision-making when tissue sampling is limited or molecular results are discordant across lesions.

Humans↗

PubMed2026

Use of synthetic data, a novel paradigm for immunopathology.

The complexity and heterogeneity of autoimmune diseases are only partially captured by current analytic tools, even when deep learning techniques are employed to intercept patterns beyond existing dogma. Synthetic data offer a newer paradigm through machine-generated reconstructions of real-world data that faithfully attempt to recapitulate biological and clinical patterns without creating duplicates and maintaining the privacy of the original ones. Synthetic data act as a magnifying lens, allowing predictions otherwise not possible on disease classification, progression, and therapeutic response. This approach has several advantages and is currently underutilized. Firstly, it provides cohort enrichment and equilibrates group imbalances. Second, it generates synthetic arms for both in vitro studies and human clinical trials, relevant to disentangle the rarity and heterogeneity of autoimmune diseases. Third, the platform allows applications beyond tabular registries, including medical images, genomics, and flow cytometry data. Last, 'digital twins' act through dynamic bidirectional links with the biological/clinical system counterpart, lending themselves to transformative opportunities for precision medicine. Herein, we discuss the current status of this fast-moving novel component of artificial intelligence and its implications for autoimmune diseases.

Humans↗

PubMed2006

Quantitative structure-toxicity relationships (QSTRs): a comparative study of various non linear methods. General regression neural network, radial basis function neural network and support vector machine in predicting toxicity of nitro- and cyano- aromatics to Tetrahymena pyriformis.

Prediction of toxicity of 203 nitro- and cyano-aromatic chemicals to Tetrahymena pyriformis was carried out by radial basis function neural network, general regression neural network and support vector machine, in non-linear response surface methodology. Toxicity was predicted from hydrophobicity parameter (log Kow) and maximum superdelocalizability (Amax). Special attention was drawn to prediction ability and robustness of the models, investigated both in a leave-one-out and 10-fold cross validation (CV) processes. The influence that the corresponding changes in the learning sets during these CV processes could have on a common external test set including 41 compounds was also examined. This allowed us to establish the stability of the models. The non linear results slightly outperform (as expected) multilinear relationships (MLR) and also favourably compete with various other non linear approaches recently proposed by Ren (J. Chem. Inf. Comput. Sci., 43 1679 (2003)).

Animals↗

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↗

PubMed2026

A mechanism-guided framework for prioritizing membrane-interaction anti-Vibrio peptides from peptidomics data.

A mechanism-guided framework for prioritizing membrane-interaction antimicrobial peptide candidates from proteomics-derived peptide mixtures is presented. The framework integrates conservative machine-learning-based antimicrobial peptide (AMP) screening with a literature-derived membrane-interaction plausibility (MAP) assessment and a data-driven membrane-interaction ranking function (AIPx), followed by structural visualization for interpretability. MAP encodes physicochemical characteristics commonly associated with peptide-membrane interaction and provides a graded plausibility assessment. Building upon this physicochemically interpretable framework, AIPx ranks peptides using feature weights calibrated from experimentally characterized anti-Vibrio peptides, where minimum inhibitory concentration (MIC) values are used as a coarse-grained ranking reference rather than a direct prediction target. In a peptidomics-based peptide fractionation study targeting Vibrio spp., AIPx exhibited a consistent relationship with experimentally observed antibacterial activity. Distributional analysis revealed that peptide fractions exhibiting high anti-Vibrio activity are characterized by enrichment of high-ranking peptides rather than by AMP abundance alone. By structuring AMP identification and prioritization as sequential stages, the MAP + AIPx framework enables interpretable and experimentally actionable candidate selection by reducing biologically implausible candidates. The framework facilitates species-oriented prioritization of AMP candidates, addressing a key challenge in antimicrobial peptide discovery where activity may depend on target-specific membrane characteristics. Moreover, the approach is extensible through species-specific calibration and supports interpretable, mechanism-informed prioritization in antimicrobial peptide discovery.

Proteomics↗

PubMed2006

Predicting carcinoid heart disease with the noisy-threshold classifier.

OBJECTIVE: To predict the development of carcinoid heart disease (CHD), which is a life-threatening complication of certain neuroendocrine tumors. To this end, a novel type of Bayesian classifier, known as the noisy-threshold classifier, is applied. MATERIALS AND METHODS: Fifty-four cases of patients that suffered from a low-grade midgut carcinoid tumor, of which 22 patients developed CHD, were obtained from the Netherlands Cancer Institute (NKI). Eleven attributes that are known at admission have been used to classify whether the patient develops CHD. Classification accuracy and area under the receiver operating characteristics (ROC) curve of the noisy-threshold classifier are compared with those of the naive-Bayes classifier, logistic regression, the decision-tree learning algorithm C4.5, and a decision rule, as formulated by an expert physician. RESULTS: The noisy-threshold classifier showed the best classification accuracy of 72% correctly classified cases, although differences were significant only for logistic regression and C4.5. An area under the ROC curve of 0.66 was attained for the noisy-threshold classifier, and equaled that of the physician's decision-rule. CONCLUSIONS: The noisy-threshold classifier performed favorably to other state-of-the-art classification algorithms, and equally well as a decision-rule that was formulated by the physician. Furthermore, the semantics of the noisy-threshold classifier make it a useful machine learning technique in domains where multiple causes influence a common effect.

Algorithms↗

PubMed2004

Supervised machine learning techniques for the classification of metabolic disorders in newborns.

MOTIVATION: During the Bavarian newborn screening programme all newborns have been tested for about 20 inherited metabolic disorders. Owing to the amount and complexity of the generated experimental data, machine learning techniques provide a promising approach to investigate novel patterns in high-dimensional metabolic data which form the source for constructing classification rules with high discriminatory power. RESULTS: Six machine learning techniques have been investigated for their classification accuracy focusing on two metabolic disorders, phenylketo nuria (PKU) and medium-chain acyl-CoA dehydrogenase deficiency (MCADD). Logistic regression analysis led to superior classification rules (sensitivity >96.8%, specificity >99.98%) compared to all investigated algorithms. Including novel constellations of metabolites into the models, the positive predictive value could be strongly increased (PKU 71.9% versus 16.2%, MCADD 88.4% versus 54.6% compared to the established diagnostic markers). Our results clearly prove that the mined data confirm the known and indicate some novel metabolic patterns which may contribute to a better understanding of newborn metabolism.

Algorithms↗

PubMed2024

Biomarkers related to m6A and succinic acid metabolism in papillary thyroid carcinoma.

BACKGROUND: Studies have shown that m6A modification is related to the occurrence and development of papillary thyroid carcinoma (PTC). The disorder of succinic acid metabolism is associated with the occurrence and development of various tumors. However, there are few studies based on m6A and succinate metabolism-related genes (SMRGs) in PTC. METHODS: The TCGA-Thyroid carcinoma (THCA), GSE33630, 1159 SMRGs, and 23 m6A regulatory factors were collected from the online databases. Subsequently, the differentially expressed genes (DEGs) were selected between PTC (Tumor) and Normal samples. The overlapping genes among the DEGs, m6A, and SMRGs were applied to screen the biomarkers. Using the 3 machine-learning algorithms, the biomarkers were determined based on the overlapping genes. Next, the biomarkers were evaluated by the ROC curve and expression analysis in TCGA-THCA and GSE33630. Then, the overall survival (OS) differences were compared between the high-and low-expression biomarkers. Finally, immune infiltration analysis, molecular regulatory network, and drug prediction were performed based on the biomarkers. RESULTS: In TCGA-THCA, there were 2800 DEGs between and Normal samples, and then 7 overlapping genes were obtained. Importantly, ADK, TNFRSF10B, CYP7B1, FGFR2, and CPQ were determined as biomarkers with excellent diagnostic efficiency (AUC > 0.7). In PTC samples, ADK and TNFRSF10B were high-expressed while CYP7B1, FGFR2, and CPQ were low-expressed. Especially, the high-expression groups of ADK had a better prognosis, while the high-expression groups of CYP7B1, FGFR2, and CPQ had a worse prognosis. Afterward, immune infiltration analysis found that 16 immune cells had infiltration differences between the Tumor and Normal samples. Finally, transcription factor SP1 could regulate CYP7B1 and TNFRSF10B. Moreover, Navitoclax was a potential drug for PTC patients. CONCLUSION: Overall, we described 5 biomarkers associated with adverse prognosis of PTC, including ADK, TNFRSF10B, CYP7B1, FGFR2, and CPQ. All these biomarkers were involved in succinate metabolism and m6A modification of RNA. This set of biomarkers should be explored further for their diagnostic value in PTC. Investigations into the mechanistic role of alteration of succinate metabolism and m6A modification of RNA pathways in the pathophysiology of PTC are warranted.

Humans↗