SEARCH · Search PubMed

Results for “machine learning prediction 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.

SourceResearch connectionFrom yearThrough year

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

At least 361 records · Page 20Linked to original sources

PubMed2005

Development of CYP3A4 inhibition models: comparisons of machine-learning techniques and molecular descriptors.

Computational models of cytochrome P450 3A4 inhibition were developed based on high-throughput screening data for 4470 proprietary compounds. Multiple models differentiating inhibitors (IC(50) <3 microM) and noninhibitors were generated using various machine-learning algorithms (recursive partitioning [RP], Bayesian classifier, logistic regression, k-nearest-neighbor, and support vector machine [SVM]) with structural fingerprints and topological indices. Nineteen models were evaluated by internal 10-fold cross-validation and also by an independent test set. Three most predictive models, Barnard Chemical Information (BCI)-fingerprint/SVM, MDL-keyset/SVM, and topological indices/RP, correctly classified 249, 248, and 236 compounds of 291 noninhibitors and 135, 137, and 147 compounds of 179 inhibitors in the validation set. Their overall accuracies were 82%, 82%, and 81%, respectively. Investigating applicability of the BCI/SVM model found a strong correlation between the predictive performance and the structural similarity to the training set. Using Tanimoto similarity index as a confidence measurement for the predictions, the limitation of the extrapolation was 0.7 in the case of the BCI/SVM model. Taking consensus of the 3 best models yielded a further improvement in predictive capability, kappa = 0.65 and accuracy = 83%. The consensus model could also be tuned to minimize either false positives or false negatives depending on the emphasis of the screening.

Artificial Intelligence↗

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↗

PubMed2005

PCP: a program for supervised classification of gene expression profiles.

UNLABELLED: PCP (Pattern Classification Program) is an open-source machine learning program for supervised classification of patterns (vectors of measurements). The principal use of PCP in bioinformatics is design and evaluation of classifiers for use in clinical diagnostic tests based on measurements of gene expression. PCP implements leading pattern classification and gene selection algorithms and incorporates cross-validation estimation of classifier performance. Importantly, the implementation integrates gene selection and class prediction stages, which is vital for computing reliable performance estimates in small-sample scenarios. Additionally, the program includes automated and efficient model selection (optimization of parameters) for support vector machine (SVM) classifier. The distribution includes Linux and Windows/Cygwin binaries. The program can easily be ported to other platforms. AVAILABILITY: Free download at http://pcp.sourceforge.net

Algorithms↗

PubMed2002

Predictive non-linear modeling of complex data by artificial neural networks.

An artificial neural network (ANN) is an artificial intelligence tool that identifies arbitrary nonlinear multiparametric discriminant functions directly from experimental data. The use of ANNs has gained increasing popularity for applications where a mechanistic description of the dependency between dependent and independent variables is either unknown or very complex. This machine learning technique can be roughly described as a universal algebraic function that will distinguish signal from noise directly from experimental data. The application of ANNs to complex relationships makes them highly attractive for the study of biological systems. Recent applications include the analysis of expression profiles and genomic and proteomic sequences.

Biochemical Phenomena↗

PubMed2025

Development and validation of a machine learning prognostic model based on an epigenomic signature in patients with pancreatic ductal adenocarcinoma.

BACKGROUND: In Pancreatic Ductal Adenocarcinoma (PDAC), current prognostic scores are unable to fully capture the biological heterogeneity of the disease. While some approaches investigating the role of multi-omics in PDAC are emerging, the analysis of methylation data is under exploited. MATERIALS AND METHODS: We analyzed CpG sites from two publicly available datasets, the TCGA-PAAD used as discovery set and the CPTAC-PDA as external test set. Single mutations and co-mutation of KRAS and TP53 genes were identified as targets, and differentially methylated CpG sites (DMC) were detected accordingly. We trained and validated Random Forest (RF) models to predict each target. Area Under the Receiver Operating Characteristic curve (AUROC) and Area Under the Precision-Recall curve (AUPRC) were used as performance metrics. Then, we performed consensus clustering from the DMCs to identify novel patients' profiles. Finally, we trained and validated a combination of eXtreme Gradient Boosting (XGB) and tree models to select an epigenomic prognostic determinant. RESULTS: From 598 DMCs extracted, an RF model predicted KRAS and TP53 co-mutation on the external test set with AUROC of 0.77 and AUPRC of 0.87. The consensus clustering allowed us to identify 4 clusters (C1, C2, C3, and C4) of patients. The C4 cluster captured a subgroup of patients with favorable Overall Survival (OS) with respect to others. The XGB model perfectly predicted C4 vs other clusters on the discovery set. In both cohorts, patients were stratified into two risk groups according to methylation levels of cg16854533, individuated as the most important CpG site. CONCLUSION: We analyzed methylation data to develop a classifier for the TP53 and KRAS mutational status. Four prognostic clusters were pointed out and a prognostic model using a CpG site was validated in an independent cohort. Our results evidence that the proposed use of methylation data facilitates risk stratification for PDAC.

Humans↗

PubMed2006

Machine learning techniques for in silico modeling of drug metabolism.

The computational assessment of drug metabolism has gained considerable interest in pharmaceutical research. Amongst others, machine learning techniques have been employed to model relationships between the chemical structure of a compound and its metabolic fate. Examples for these techniques, which were originally developed in fields far from drug discovery, are artificial neural networks or support vector machines. This paper summarizes the application of various machine learning techniques to predict the interaction between organic molecules and metabolic enzymes. More complex endpoints such as metabolic stability or in vivo clearance will also be addressed. It is shown that the prediction of metabolic endpoints with machine learning techniques has made considerable progress over the past few years. Depending on the procedure used, either classification or quantitative prediction is possible for even large and diverse compound sets. Together with the expanding experimental data basis, these in silico methods have become valuable tools in the drug discovery and development process.

Artificial Intelligence↗

PubMed2004

Interaction profile-based protein classification of death domain.

BACKGROUND: The increasing number of protein sequences and 3D structure obtained from genomic initiatives is leading many of us to focus on proteomics, and to dedicate our experimental and computational efforts on the creation and analysis of information derived from 3D structure. In particular, the high-throughput generation of protein-protein interaction data from a few organisms makes such an approach very important towards understanding the molecular recognition that make-up the entire protein-protein interaction network. Since the generation of sequences, and experimental protein-protein interactions increases faster than the 3D structure determination of protein complexes, there is tremendous interest in developing in silico methods that generate such structure for prediction and classification purposes. In this study we focused on classifying protein family members based on their protein-protein interaction distinctiveness. Structure-based classification of protein-protein interfaces has been described initially by Ponstingl et al. 1 and more recently by Valdar et al. 2 and Mintseris et al. 3, from complex structures that have been solved experimentally. However, little has been done on protein classification based on the prediction of protein-protein complexes obtained from homology modeling and docking simulation. RESULTS: We have developed an in silico classification system entitled HODOCO (Homology modeling, Docking and Classification Oracle), in which protein Residue Potential Interaction Profiles (RPIPS) are used to summarize protein-protein interaction characteristics. This system applied to a dataset of 64 proteins of the death domain superfamily was used to classify each member into its proper subfamily. Two classification methods were attempted, heuristic and support vector machine learning. Both methods were tested with a 5-fold cross-validation. The heuristic approach yielded a 61% average accuracy, while the machine learning approach yielded an 89% average accuracy. CONCLUSION: We have confirmed the reliability and potential value of classifying proteins via their predicted interactions. Our results are in the same range of accuracy as other studies that classify protein-protein interactions from 3D complex structure obtained experimentally. While our classification scheme does not take directly into account sequence information our results are in agreement with functional and sequence based classification of death domain family members.

Humans↗

PubMed2005

Machine learning can improve prediction of severity in acute pancreatitis using admission values of APACHE II score and C-reactive protein.

BACKGROUND: Acute pancreatitis (AP) has a variable course. Accurate early prediction of severity is essential to direct clinical care. Current assessment tools are inaccurate, and unable to adapt to new parameters. None of the current systems uses C-reactive protein (CRP). Modern machine-learning tools can address these issues. METHODS: 370 patients admitted with AP in a 5-year period were retrospectively assessed; after exclusions, 265 patients were studied. First recorded values for physical examination and blood tests, aetiology, severity and complications were recorded. A kernel logistic regression model was used to remove redundant features, and identify the relationships between relevant features and outcome. Bootstrapping was used to make the best use of data and obtain confidence estimates on the parameters of the model. RESULTS: A model containing 8 variables (age, CRP, respiratory rate, pO2 on air, arterial pH, serum creatinine, white cell count and GCS) predicted a severe attack with an area under the receiver-operating characteristic curve (AUC) of 0.82 (SD 0.01). The optimum cut-off value for predicting severity gave sensitivity and specificity of 0.87 and 0.71 respectively. The predictions were significantly better (p = 0.0036) than admission APACHE II scores in the same patients (AUC 0.74) and better than historical admission APACHE II data (AUC 0.68-0.75). CONCLUSIONS: This system for the first time combines admission values of selected components of APACHE II and CRP for prediction of severe AP. The score is simple to use, and is more accurate than admission APACHE II alone. It is adaptable and would allow incorporation of new predictive factors.

APACHE↗

PubMed2026

Multi-level Transcriptomic and Machine-learning Analyses Identify MZT1 as a Proliferation-associated Prognostic Marker in Lung Adenocarcinoma.

BACKGROUND/AIM: Lung adenocarcinoma (LUAD) exhibits substantial molecular heterogeneity and variable clinical outcomes, highlighting the need for biomarkers that reflect core tumor biological processes. Centrosome-associated proteins regulate mitotic fidelity and genome stability, yet their roles in LUAD remain incompletely defined. In this study, we systematically characterized mitotic spindle organizing protein 1 (MOZART1; MZT1) and related family members in LUAD. MATERIALS AND METHODS: We performed integrated analyses combining bulk transcriptomic datasets, survival modeling, gene set enrichment, immune deconvolution, machine-learning based prognostic modeling, and single-cell RNA sequencing. Expression patterns and clinical associations of MZT family genes were evaluated across pan-cancer and LUAD cohorts. RESULTS: MZT family genes were consistently upregulated in tumor tissues, with MZT1 showing the most robust expression pattern. Elevated MZT1 expression was significantly associated with reduced overall survival. Functional analyses revealed coordinated activation of proliferative and genome maintenance pathways, including G2/M checkpoint regulation, E2F and MYC signaling, and DNA repair. A multivariable analysis indicated that the prognostic association of MZT1 was reduced after adjusting for canonical proliferation markers, suggesting partial overlap with established proliferation signals. The LASSO-based Cox model demonstrated stable time-dependent predictive performance at 1-, 3-, and 5-year survival. Immune analyses indicated associations between MZT1 expression and tumor microenvironmental features. Single-cell analysis showed that MZT1 expression was predominantly enriched in malignant epithelial cells and associated with proliferative cellular states. Protein-level validation supported concordance with transcriptomic findings. CONCLUSION: MZT1 is a proliferation-associated marker that integrates clinical risk, transcriptional programs, cellular heterogeneity, and predictive modeling in LUAD, providing a potential framework for biomarker development and risk stratification.

Humans↗

PubMed2006

Modular DAG-RNN architectures for assembling coarse protein structures.

We develop and test machine learning methods for the prediction of coarse 3D protein structures, where a protein is represented by a set of rigid rods associated with its secondary structure elements (alpha-helices and beta-strands). First, we employ cascades of recursive neural networks derived from graphical models to predict the relative placements of segments. These are represented as discretized distance and angle maps, and the discretization levels are statistically inferred from a large and curated dataset. Coarse 3D folds of proteins are then assembled starting from topological information predicted in the first stage. Reconstruction is carried out by minimizing a cost function taking the form of a purely geometrical potential. We show that the proposed architecture outperforms simpler alternatives and can accurately predict binary and multiclass coarse maps. The reconstruction procedure proves to be fast and often leads to topologically correct coarse structures that could be exploited as a starting point for various protein modeling strategies. The fully integrated rod-shaped protein builder (predictor of contact maps + reconstruction algorithm) can be accessed at http://distill.ucd.ie/.

Algorithms↗

PubMed2003

Learning to control a brain-machine interface for reaching and grasping by primates.

Reaching and grasping in primates depend on the coordination of neural activity in large frontoparietal ensembles. Here we demonstrate that primates can learn to reach and grasp virtual objects by controlling a robot arm through a closed-loop brain-machine interface (BMIc) that uses multiple mathematical models to extract several motor parameters (i.e., hand position, velocity, gripping force, and the EMGs of multiple arm muscles) from the electrical activity of frontoparietal neuronal ensembles. As single neurons typically contribute to the encoding of several motor parameters, we observed that high BMIc accuracy required recording from large neuronal ensembles. Continuous BMIc operation by monkeys led to significant improvements in both model predictions and behavioral performance. Using visual feedback, monkeys succeeded in producing robot reach-and-grasp movements even when their arms did not move. Learning to operate the BMIc was paralleled by functional reorganization in multiple cortical areas, suggesting that the dynamic properties of the BMIc were incorporated into motor and sensory cortical representations.

Animals↗

PubMed2025

FOSB is a key factor in the genetic link between inflammatory bowel disease and acute myocardial infarction: multiple bioinformatics analyses and validation.

BACKGROUND: Inflammatory Bowel Disease (IBD), which includes Crohn's disease and ulcerative colitis, is associated with an increased risk of Acute Myocardial Infarction (AMI). The genetic mechanisms underlying this link are not well understood. METHODS: We downloaded IBD and AMI-related microarray datasets from the NCBI Gene Expression Omnibus (GEO) database. Differentially expressed genes (DEGs) were identified and analyzed using enrichment analysis and Weighted Gene Co-expression Network Analysis (WGCNA). Machine learning techniques, including LASSO, random forest, and Boruta, were employed to screen for hub genes. These genes were validated through qRT-PCR and Western blotting. Single-cell sequencing was used to confirm findings. Additionally, potential therapeutic targets were identified using the Connectivity Map (CMap) database. RESULTS: Five key hub genes-THBD, FOSB, ADGPR3, IL1R2, and PLAUR-were identified as significantly involved in both IBD and AMI pathogenesis. A diagnostic model for AMI constructed using these hub genes demonstrated high predictive accuracy. Single-cell sequencing analysis and several potential drugs targeting these hub genes were identified, offering new therapeutic avenues. CONCLUSION: This study highlights the crucial role of FOSB and other hub genes in the comorbidity of IBD and AMI. The findings provide novel insights for early diagnosis and potential therapeutic strategies, emphasizing the importance of further investigation into these genetic links.

Humans↗

PubMed2025

Landscape of essential growth and fluconazole-resistance genes in the human fungal pathogen Cryptococcus neoformans.

Fungi can cause devastating invasive infections, typically in immunocompromised patients. Treatment is complicated both by the evolutionary similarity between humans and fungi and by the frequent emergence of drug resistance. Studies in fungal pathogens have long been slowed by a lack of high-throughput tools and community resources that are common in model organisms. Here we demonstrate a high-throughput transposon mutagenesis and sequencing (TN-seq) system in Cryptococcus neoformans that enables genome-wide determination of gene essentiality. We employed a random forest machine learning approach to classify the C. neoformans genome as essential or nonessential, predicting 1,465 essential genes, including 302 that lack human orthologs. These genes are ideal targets for new antifungal drug development. TN-seq also enables genome-wide measurement of the fitness contribution of genes to phenotypes of interest. As proof of principle, we demonstrate the genome-wide contribution of genes to growth in fluconazole, a clinically used antifungal. We show a novel role for the well-studied RIM101 pathway in fluconazole susceptibility. We also show that insertions of transposons into the 5' upstream region can drive sensitization of essential genes, enabling screenlike assays of both essential and nonessential components of the genome. Using this approach, we demonstrate a role for mitochondrial function in fluconazole sensitivity, such that tuning down many essential mitochondrial genes via 5' insertions can drive resistance to fluconazole. Our assay system will be valuable in future studies of C. neoformans, particularly in examining the consequences of genotypic diversity.

Cryptococcus neoformans↗

PubMed2026

A Multi-omics Regulated Cell Death Framework Defines Immune Phenotypes and Guides Precision Therapy in Colorectal Cancer.

Colorectal cancer (CRC) is molecularly and immunologically heterogeneous, contributing to variable treatment response. Because regulated cell death (RCD) intersects with tumor metabolism, immune regulation, and therapeutic susceptibility, we built an RCD-centered framework for CRC stratification. Multi-cohort transcriptomic data were used to infer RCD subtypes with non-negative matrix factorization (NMF) and non-negative least squares (NNLS). Genomic, bulk RNA-seq, single-cell RNA-seq, and spatial transcriptomic datasets were integrated to characterize subtype-associated biology. Machine-learning models were developed for immunotherapy response and survival-risk estimation. Candidate compounds were screened by GDSC2-based drug-sensitivity modeling and molecular docking, and FSTL3 was functionally assessed in vitro. The framework separated CRC samples into two RCD-related phenotypes resembling immune-hot and immune-cold states. RCD1 showed immune activation and higher mutational burden, whereas RCD2 showed immune-suppressed features, intratumoral heterogeneity, and aggressive biology. RCD-associated signatures showed potential for predicting immunotherapy response and survival risk. Dasatinib was prioritized for immune-cold, high-risk tumors, with preliminary evidence supporting its activity in CRC cells, while functional assays suggested a role for FSTL3 in growth, invasion, epithelial-mesenchymal transition, and apoptosis regulation. These findings suggest that RCD-based multi-omics analysis may refine CRC stratification and help generate therapeutic hypotheses.

Colorectal cancer↗

PubMed2005

Protein sequence-based risk classification for human papillomaviruses.

Human papillomaviruses (HPVs) are small DNA tumor viruses which infect epithelial tissues and induce hyperproliferative lesions. Infection by high-risk genital HPVs is associated with the development of anogenital cancers. Classification of risk types is important in understanding the mechanisms in infection and in developing novel instruments for medical examination such as DNA microarrays. The sequence-based classification methods are useful in classifying risk types by considering residues in conserved positions. In this paper, we present a machine learning approach to the classification of HPV risk types by using the protein sequences. Our approach is based on the hidden Markov model and the kernel method. The former searches informative subsequence positions and the latter computes efficiently to classify protein sequences. In the experiments, the classifier predicted four unknown HPV types exactly. An additional result shows that the kernel-based classifiers learned with more informative subsequences outperform the classifiers learned with the whole sequence or random subsequences.

Amino Acid Sequence↗

PubMed2026

ORBIT: Oncogenic Representation Learning via Bi-Prototype Contrastive Learning in Hyperbolic Space for cancer driver gene identification.

Accurate identification of cancer driver genes is crucial for precision oncology but remains challenging due to the complexity of integrating heterogeneous data and modeling dynamic biological systems. To address these limitations, we propose ORBIT (Oncogenic Representation Learning via Bi-Prototype Contrastive Learning in Hyperbolic Space). Our framework synergistically fuses multi-omics profiles with functional network data using a context-adaptive graph reweighting mechanism to capture cancer-specific dynamics. The model employs a bi-prototype contrastive learning strategy within hyperbolic space, which aligns gene representations around distinct driver and non-driver semantic anchors while preserving the intrinsic hierarchy of biological networks. Comprehensive evaluations demonstrate that ORBIT achieves highly competitive stability in pan-cancer analysis while consistently outperforming state-of-the-art methods in cancer-specific predictions. Furthermore, functional enrichment analysis confirms that the model effectively segregates core cancer pathways, and drug sensitivity profiling validates the clinical relevance of the identified drivers. By integrating hyperbolic geometry with context-adaptive learning, ORBIT offers a robust and interpretable paradigm for precision medicine. The source codes and datasets are publicly accessible at https://github.com/spcho-dev/ORBIT.

Humans↗

PubMed2026

Development and validation of a serum peptidomic signature for early detection of asymptomatic ovarian cancer: A multi-center prospective study.

Early detection of asymptomatic ovarian cancer (asym-OC) remains a critical challenge, the failure of which underlies its high mortality. Performing serum peptidomic profiling of 843 participants in the cohort SOCFCP, we distill 1,081 initial features into a 7-marker panel for asym-OC detection via a biology-informed machine-learning (ML)-based feature selection strategy. Three markers significantly revert toward non-OC levels after surgery. Integrating the panel with age, CA125, and HE4, we develop and externally validate (n = 159) a LightGBM model, ProMS+. For early-stage OC detection, ProMS+ shows a specificity of 92.6% at 95.0% sensitivity, outperforming CA125 (44.7%), HE4 (11.2%), and Risk of Ovarian Malignancy Algorithm (ROMA) (24.0%), with an area under the curve (AUC) of 0.993. In a simulated high-risk population (n = 100,000; OC prevalence = 1%), ProMS+ yields a high AUC (0.983) and a higher positive predictive value than CA125, HE4, and Age + CA125 + HE4 combined model (0.201 vs. 0.027, 0.090, and 0.064). ProMS+ offers a promising, non-invasive, and interpretable approach for the early detection of asym-OC.

Humans↗

PubMed2003

Predicting gene function in Saccharomyces cerevisiae.

MOTIVATION: S.cerevisiae is one of the most important model organisms, and has has been the focus of over a century of study. In spite of these efforts, 40% of its open reading frames (ORFs) remain classified as having unknown function (MIPS: Munich Information Center for Protein Sequences). We wished to make predictions for the function of these ORFs using data mining, as we have previously successfully done for the genomes of M.tuberculosis and E.coli. Applying this approach to the larger and eukaryotic S.cerevisiae genome involves modifying the machine learning and data mining algorithms, as this is a larger organism with more data available, and a more challenging functional classification. RESULTS: Novel extensions to the machine learning and data mining algorithms have been devised in order to deal with the challenges. Accurate rules have been learned and predictions have been made for many of the ORFs whose function is currently unknown. The rules are informative, agree with known biology and allow for scientific discovery. AVAILABILITY: All predictions are freely available from http://www.genepredictions.org, all datasets used in this study are freely available from http://www.aber.ac.uk/compsci/Research/bio/dss/yeastdataand software for relational data mining is available from http://www.aber.ac.uk/compsci/Research/bio/dss/polyfarm.

Chromosome Mapping↗