SEARCH · PubMed Health

Results for “Simulation Training”

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 37 records · Page 2Linked to original sources

PubMed1977

[Mathematical model of transient long-term adaptation processes of the heart].

A mathematical model of the heart's long-term adaptation to changing load is described. The model is based on the long-term adaptation concept which assumes the phosphorylation potential changing in the heart muscle cells with the load to control the genetic apparatus activity and thus determine structural alterations ensuring adaptation. The computerized model reproduces the transient process in four major types of the heart's long-term adaptation, i.e. in a compensatory hypertrophy development and hypertrophy regression, as well as in the training and detraining states formation. The simulation results are in agreement with the available data and predict the phenomena that are not as yet substantiated by experiments.

Adaptation, Physiological↗

PubMed2025

insilicoSV: a flexible grammar-based framework for structural variant simulation and placement.

SUMMARY: Structural variants (SVs) are key drivers of genetic variation and disease in the genome. Their discovery remains challenging, however, in large part due to the scarcity of validated SV callsets and comprehensive benchmarks, which are essential for method development and evaluation. The growing number of data-driven learning-based approaches for SV discovery, in particular, requires large, diverse, and well-balanced training datasets to achieve reliable performance. To address this need, SV simulation has served as a key tool for assessing method performance and training SV models. However, existing SV simulators only support a fixed and limited set of SV classes and do not provide fine-grained control over the placement of SVs within specific contexts of the genome. Here we present insilicoSV, a versatile framework for SV simulation, which models SVs using a simple and flexible grammar, allowing users to easily define standard and custom arbitrary genome rearrangements, as well as encode genome placement constraints. This design allows insilicoSV to naturally support new and bespoke SV types, such as the complex rearrangements of cancer genomes. In addition to grammar-based modeling, insilicoSV provides built-in support for 26 predefined SV types, placement of user-provided SVs, small variant simulation, streamlined workflows for the simulation of genome evolution and genome mixtures, read simulation, alignment, and visualization. These features enable the creation of comprehensive genomic datasets for a variety of downstream applications, such as in-depth benchmarking of alignment and variant calling methods, as well as training of data-driven learning-based approaches for SV detection. AVAILABILITY AND IMPLEMENTATION: insilicoSV is available under the MIT license at https://github.com/PopicLab/insilicoSV and https://doi.org/10.5281/zenodo.17402009.

Software↗

PubMed2026

ARGformer: learning on ancestral recombination graphs with transformers.

MOTIVATION: Recent advances in inference of the ancestral recombination graph (ARG), which describes how segments of chromosomes trace back through recombination and shared lineages, have made it possible to reconstruct genome-wide genealogies for large cohorts, but it remains difficult to summarize and use this information for population genetic analyses. RESULTS: We present ARGformer, an encoder-only transformer that learns context-dependent embeddings with a self-supervised masked objective finetuned with contrastive learning for downstream retrieval tasks. We train ARGformer on genealogies from coalescent simulations and on genealogies inferred from ancient and present-day Homo sapiens genomes. Using only these learned embeddings, without access to genotype matrices, ARGformer captures patterns of global population structure and supports ancestry inference through clustering and nearest-neighbor retrieval. On genealogies that include archaic hominins, ARGformer can highlight Denisovan-derived segments in Oceanian genomes and reveals Oceanian-like ancestry in South American Indigenous populations. AVAILABILITY AND IMPLEMENTATION: ARGformer is available at https://github.com/AI-sandbox/ARGformer.

Humans↗

PubMed2025

Detecting Interspecific Positive Selection Using Convolutional Neural Networks.

Traditional statistical methods using maximum likelihood and Bayesian inference can detect positive selection from an interspecific phylogeny and a codon sequence alignment based on model assumptions, but they are prone to false positives due to alignment errors and can lack power. These problems are particularly pronounced when faced with high levels of indels and divergence. To address these issues, we trained and tested convolutional neural network models on simulated data and achieved higher accuracy in detecting selection across a specific range of phylogenetic scenarios and evolutionary modes. This advantage is particularly evident when performing inference on noisy data prone to misalignments. Our method shows some ability to account for these errors, where most statistical frameworks fail to do so in a tractable manner. We explore the generalizability of our convolutional neural network models to unseen evolutionary scenarios and identify future avenues to achieve broader utility. Once trained, our convolutional neural network model is faster at test time, making it a scalable alternative to traditional statistical methods for large-scale, multigene analyses. In addition to binary classification (inference of the presence or absence of positive selection during the evolution of the sequences), we use saliency maps to understand what the model learns and observe how this could be leveraged for sitewise inference of positive selection.

Neural Networks, Computer↗

PubMed1975

Adrenocortical activity and urinary cyclic AMP levels: effects of hypobaric hypoxia.

Six highly motivated and trained military test subjects were exposed to a simulated altitude of 4267 m (477 torr) for 48 hours, prededed and followed by sea level runs lasting 32 hours. During each scenario tests subjects were required to perform their respective military tasks on a continual basis with sporadic rest not exceeding several hours. Extremely high levels of plasma cortisol prior to the start of each session and persistently elevated concentrations of urinary 17-OH corticosteroids at sea level were consistently observed. (This observation probably explains the relatively minor changes in adrenocortical output noted during acute exposure to hypobaric hypoxia. Analogous results were obtained for urinary cyclic AMP, i.e. elevated baseline levels and minimal response to high altitude. The results indicate an attenuated response as well as an association between urinary measures of adrenocortical activity and cyclic AMP excretion.

17-Hydroxycorticosteroids↗

PubMed2026

Informing agent-based models with spatial data using convolutional autoencoders.

MOTIVATION: Spatial computational models such as agent-based models (ABMs) offer powerful in silico tools to study tumor dynamics, yet imaging data are still rarely used to inform these models directly. RESULTS: We present an ABM optimization framework that leverages convolutional encoders to compare spatial patterns between experimental imaging data and ABM-generated outputs within a shared latent space. This quantitative comparison was used to estimate ABM parameters across three datasets, ranging from synthetic data to 3D tumoroid-T cell co-culture microscopy and histopathology images from The Cancer Genome Atlas skin cutaneous melanoma samples. Estimated parameters were evaluated using data-derived features and experimental knowledge, including experimental conditions and gene expressions. Simulations using optimized parameters reproduced key spatial features of the training images, such as tumor boundary complexity and tumor-tumor neighborhood structure. Together, these results demonstrate a flexible framework for ABM parameter optimization using spatial data across modalities, enabling systematic investigation of how spatial architecture influences tumor progression and immune interactions. AVAILABILITY AND IMPLEMENTATION: Source code is available at https://github.com/SysBioOncology/ AutoencoderABM under the GPL-3.0 license, with corresponding data sets at https://zenodo.org/records/19022344.

Autoencoder↗

PubMed2026

How negative sampling shapes the performance of transcription factor binding site prediction models.

MOTIVATION: Transcription factors (TFs) are key players in gene regulation and development, where they activate and repress gene expression through DNA binding. Predicting transcription factor binding sites (TFBSs) has long been an active area of research, with many deep learning methods developed to tackle this problem. These models are often trained on TF ChIP-seq data, which is generally seen as only providing positive samples. The choice of datasets and negative sampling techniques is a critical yet often overlooked aspect of this work. RESULTS: In this study, we investigate the impact of different negative sampling techniques on TFBS prediction performance. We create high-quality test datasets based on ChIP-seq and ATAC-seq data, where true negatives can be identified as positions that are accessible but not bound by the TF in question. We then train models using various negative sampling techniques, including genomic sampling, shuffling, dinucleotide shuffling, neighborhood sampling, and cell line specific sampling, simulating cases where matching ATAC-seq data is not available. Our results show that, generally, metrics calculated on training datasets give inflated performance scores. Of the tested techniques, genomic sampling of negatives based on similarity to the positives performed by far the best, although still not reaching the performance of baseline models trained on high-quality datasets. Models trained on dinucleotide shuffled negatives performed poorly, despite being a common practice in the field. Our findings highlight the importance of carefully selecting negative sampling techniques for TFBS prediction, as they can significantly impact model performance and the interpretation of results. AVAILABILITY AND IMPLEMENTATION: The code used in this study is available at https://github.com/NatanTourne/TFBS-negatives (DOI: 10.5281/zenodo.18007567).

Binding Sites↗

PubMed2024

Distinguishing different psychiatric disorders using DDx-PRS.

Despite great progress on methods for case-control polygenic prediction (e.g. schizophrenia vs. control), there remains an unmet need for a method that genetically distinguishes clinically related disorders (e.g. schizophrenia (SCZ) vs. bipolar disorder (BIP) vs. depression (MDD) vs. control); such a method could have important clinical value, especially at disorder onset when differential diagnosis can be challenging. Here, we introduce a method, Differential Diagnosis-Polygenic Risk Score (DDx-PRS), that jointly estimates posterior probabilities of each possible diagnostic category (e.g. SCZ=50%, BIP=25%, MDD=15%, control=10%) by modeling variance/covariance structure across disorders, leveraging case-control polygenic risk scores (PRS) for each disorder (computed using existing methods) and prior clinical probabilities for each diagnostic category. DDx-PRS uses only summary-level training data and does not use tuning data, facilitating implementation in clinical settings. In simulations, DDx-PRS was well-calibrated (whereas a simpler approach that analyzes each disorder marginally was poorly calibrated), and effective in distinguishing each diagnostic category vs. the rest. We then applied DDx-PRS to Psychiatric Genomics Consortium SCZ/BIP/MDD/control data, including summary-level training data from 3 case-control GWAS ( N =41,917-173,140 cases; total N =1,048,683) and held-out test data from different cohorts with equal numbers of each diagnostic category (total N =11,460). DDx-PRS was well-calibrated and well-powered relative to these training sample sizes, attaining AUCs of 0.66 for SCZ vs. rest, 0.64 for BIP vs. rest, 0.59 for MDD vs. rest, and 0.68 for control vs. rest. DDx-PRS produced comparable results to methods that leverage tuning data, confirming that DDx-PRS is an effective method. True diagnosis probabilities in top deciles of predicted diagnosis probabilities were considerably larger than prior baseline probabilities, particularly in projections to larger training sample sizes, implying considerable potential for clinical utility under certain circumstances. In conclusion, DDx-PRS is an effective method for distinguishing clinically related disorders.

Journal Article↗

PubMed2026

Investigating cross-organism prediction of prokaryotic essential proteins using unsupervised language model and ensemble strategy.

Cross-organism prediction of essential proteins is a critical task for drug discovery and microbial engineering, yet the generalizability of existing machine learning models across diverse species remains a significant challenge. In this study, we propose DeepPEP, a large language model-based framework designed to reliably transfer essential protein annotations between distantly related organisms. Utilizing 66 curated prokaryotic datasets, we systematically evaluated DeepPEP's cross-organism performance under various conditions. Initial pairwise predictions revealed a correlation between performance and evolutionary distance; however, further investigation demonstrated that integrating training data from multiple organisms yields superior predictive power. In a benchmark scenario designed to simulate real-world applications, DeepPEP outperformed the state-of-the-art tool Geptop 2.0, showcasing a robust ability to identify species-specific essential proteins. Finally, a case study on novel genomes confirmed the model's practical effectiveness. Our results suggest that DeepPEP is a powerful strategy for prokaryotic essential protein prediction, and the rigorous evaluation framework established in this study provides a new benchmark for the field.

Large Language Models↗

PubMed2026

In silico screening of anti-atherosclerotic compounds from Morus alba leaves by machine learning and network pharmacology.

OBJECTIVE: This study integrates machine learning with network pharmacology, molecular docking, and molecular dynamics simulations to screen bioactive compounds from Mulberry leaves and elucidate their potential mechanisms against atherosclerosis (AS). METHODS: A training dataset of anti-AS active compounds was compiled and encoded as Morgan fingerprints. Three machine learning classifiers, specifically Random Forest (RF), Support Vector Machine (SVM), and Extreme Gradient Boosting (XG-Boost), were constructed and evaluated using multiple performance metrics. Potential active components from Mulberry leaves and AS-related targets were retrieved, followed by protein-protein interaction network construction and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis. Molecular docking was then performed to evaluate binding affinities between core targets and candidate compounds, and the most stable complex was subjected to molecular dynamics simulations using GROMACS (2025). RESULTS: The RF model achieved superior performance (accuracy= 0.8354, F1 = 0.8408, AUC = 0.9119) with 100% external validation accuracy. Thirteen anti-AS candidates were prioritized from mulberry leaves, four of which have been previously documented. Network pharmacology revealed AKT1 and IL6 as core targets, enriched in pathways such as endocrine resistance. Molecular docking and dynamics simulations confirmed strong binding between oxysanguinarine and AKT1, with the complex exhibiting high stability. CONCLUSION: The RF model provides a reliable computational tool for prioritizing anti-AS compounds from Mulberry leaves. The integrated analysis reveals that Mulberry leaves exert anti-atherosclerotic effects through multi-target (e.g., AKT1, IL6) and multi-pathway (e.g., PI3K-Akt) mechanisms, offering a framework for further experimental validation.

Morus↗

PubMed2025

PharaCon: a new framework for identifying bacteriophages via conditional representation learning.

MOTIVATION: Identifying bacteriophages (phages) within metagenomic sequences is essential for understanding microbial community dynamics. Transformer-based foundation models have been successfully employed to address various biological challenges. However, these models are typically pre-trained with self-supervised tasks that do not consider label variance in the pre-training data. This presents a challenge for phage identification as pre-training on mixed bacterial and phage data may lead to information bias due to the imbalance between bacterial and phage samples. RESULTS: To overcome this limitation, we proposed a novel conditional BERT framework that incorporates label classes as special tokens during pre-training. Specifically, our conditional BERT model attaches labels directly during tokenization, introducing label constraints into the model's input. Additionally, we introduced a new fine-tuning scheme that enables the conditional BERT to be effectively utilized for classification tasks. This framework allows the BERT model to acquire label-specific contextual representations from mixed sequence data during pre-training and applies the conditional BERT as a classifier during fine-tuning, and we named the fine-tuned model as PharaCon. We evaluated PharaCon against several existing methods on both simulated sequence datasets and real metagenomic contig datasets. The results demonstrate PharaCon's effectiveness and efficiency in phage identification, highlighting the advantages of incorporating label information during both pre-training and fine-tuning. AVAILABILITY AND IMPLEMENTATION: The source code and associated data can be accessed at https://github.com/Celestial-Bai/PharaCon.

Bacteriophages↗

PubMed2025

Leveraging local ancestry and cross-ancestry genetic architecture to improve genetic prediction of complex traits in admixed populations.

The broader application of polygenic risk score (PRS) is hindered by the limited transferability of PRS developed in Europeans to non-European populations. While many statistical methods have been developed to improve the performance of PRS in non-European populations, most of them focused on discrete genetic ancestry clusters and did not consider admixed individuals. Admixed individuals pose a unique challenge for PRS calculation due to the complexity of local ancestry and cross-ancestry effect sizes. Here, we present a statistical method called SDPR_admix for calculating PRS in admixed individuals. SDPR_admix characterizes the joint distribution of the effect sizes of a genetic variant with two ancestries to be both zero, ancestry enriched, or shared with correlation. SDPR_admix outperformed other methods in simulations and improved the prediction of real traits in European-African admixed individuals in UK Biobank when trained on the Population Architecture using Genomics and Epidemiology (PAGE) dataset (N = 13,000). Deployment of SDPR_admix on All of Us (N = 52,000) further increased the prediction accuracy by approximately 5-fold on average compared with training on PAGE. This enhancement was achieved with manageable computational time and cost, demonstrating the feasibility of training PRS models on large-scale All of Us data. We provided several examples demonstrating that both ancestral-enriched and shared effects, as included in the SDPR_admix prediction model, are helpful for improving polygenic prediction in admixed populations. We also applied SDPR_admix to construct PRS for admixed Americans with mixture of European and Amerindigenous ancestries and showed that SDPR_admix overall outperformed other methods.

Humans↗

PubMed2025

MRDagent: iterative and adaptive parameter optimization for stable ctDNA-based MRD detection in heterogeneous samples.

MOTIVATION: Minimal residual disease (MRD) as critical biomarker for cancer prognosis and management plays a crucial role in improving patient outcomes. However, detecting MRD via next-generation sequencing-based circulating tumor DNA variant calling remains unstable due to the extremely low variant allele frequency and significant inter- and intra-sample heterogeneity. Although parameter optimization can theoretically enhance the detection performance of variants, achieving stable MRD detection remains challenging due to three key factors: (i) the necessity for individualized parameter tuning across numerous heterogeneous genomic intervals within each sample, (ii) the tightly interdependent parameter requirements across different stages of variant detection workflows, and (iii) the limitations of current automated parameter optimization methods. RESULTS: In this study, we propose MRDagent, a novel variant detection tool designed specifically for MRD detection. MRDagent incorporates an iterative and self-adaptive optimization framework capable of handling unknown objectives, varying constraints, and highly coupled parameters across stages. A key innovation of MRDagent is the integration of a convolutional neural network-based meta-model, trained on historical data to enable rapid parameter prediction. This significantly enhances computational efficiency and generalization performance. Extensive evaluations on simulated and real-world datasets demonstrate MRDagent's superior and stable performance, providing an efficient, reliable solution for MRD detection in clinical and high-throughput research applications. AVAILABILITY AND IMPLEMENTATION: MRDagent is freely available at https://github.com/aAT0047/MRDagent.git. The corresponding dataset and software archive are available at Zenodo: https://doi.org/10.5281/zenodo.15458496.

Circulating Tumor DNA↗

PubMed2026

A module-based approach for post-omics, post-GWAS network-based gene classification.

MOTIVATION: Complex traits and diseases are highly polygenic and understanding the full set of genes involved is a central challenge in biomedicine. However, due to sample size limitations and noise (technical and biological), experimental approaches for disease-gene discovery such as transcriptomics and GWAS result in long, noisy, heterogeneous gene lists, which may be trimmed to a subset of likely relevant genes while leaving several false negatives. Computational gene classification approaches, especially those using genome-scale molecular interaction networks, are promising avenues for complementing such experimental findings by analytically expanding observed gene lists based on the functional relatedness between genes. We previously introduced the network-based gene classification approach, GenePlexus, which was rigorously benchmarked to show state-of-the-art performance, especially for predicting novel genes associated with biological processes and fine-grained phenotypes. Network-based gene classification performance,however, declines for diseases, especially when the inputs are omics and GWAS-based long gene lists. RESULTS: Here, we show that these disease gene lists span multiple biological processes spread across the molecular network, and we propose ModGenePlexus, a new network-based gene classification method that takes a two-stage approach. First, clustering and semi-supervised learning decomposes the input gene list into coherent, denoised network gene modules. Then, ModGenePlexus trains supervised (GenePlexus) classifiers for each module and aggregates predictions to return genome-wide rankings. We benchmarked ModGenePlexus across simulated data, transcriptomic signatures, and GWAS datasets (together spanning hundreds of diseases), showing improved recovery of known disease genes compared to GenePlexus. Beyond improved classification, the results of enrichment analysis of ModGenePlexus outputs are much more interpretable by virtue of revealing nuanced biological processes. Together, these results establish ModGenePlexus as a scalable, interpretable tool for gene classification of GWAS- and omics-derived gene lists across diverse biological contexts. AVAILABILITY AND IMPLEMENTATION: ModGenePlexus is freely available on GitHub at https://github.com/krishnanlab/ModGenePlexus, and the full source code and results supporting this study are available on Zenodo at https://zenodo.org/records/19857910.

Genome-Wide Association Study↗

PubMed2025

vcfsim: flexible simulation of all-sites VCFs with missing data.

BACKGROUND |: VCFs are the most widely used data format for encoding genetic variation. By design, standard VCFs do not include data from sites where all individuals are homozygous for the reference allele ("invariant sites") and thus do not differentiate these from sites where data are completely missing. However, missing data are a key feature of biological datasets across all domains of genomics, and many recent studies have shown that missing data can introduce a variety of statistical biases in the estimation of key population genetic parameters. A solution to this limitation is to include invariant sites in a standard VCF, creating an "all-sites VCF", exposing missing and invariant sites explicitly. One hurdle to the wider adoption of all-sites VCFs is a reliable parameterized simulation framework for generating biologically realistic all-sites VCFs. RESULTS |: Here, we introduce an open-source command line tool, vcfsim, that interfaces with the popular coalescent simulation platform msprime and provides convenience functions for simulating all-sites VCFs with variable levels of ploidy and missing data. We show that the post-processed VCFs generated using vcfsim align precisely with population genetic expectations (i.e. are statistically identical to raw msprime output), accurately introduce missing data, and permit the simulation of data with varying ploidy levels, including the simulation of intraindividual ploidy variation (e.g. heterogametic sex chromosomes) and population structures. CONCLUSIONS |: Our results vcfsim is a useful and easy-to-use tool for the benchmarking of new software tools, performing population genetic inference, training of machine learning models, and the exploration of the effects of missing data in genomics data sets.

Benchmarking↗

PubMed2026

Leading with Innovation: Maternal Health Transformation in New York City Health + Hospitals.

New York City's (NYC) maternal health crisis drew close attention in the late 2010s, driven by alarming data: Approximately 30 women died annually during childbirth in NYC, Black non-Hispanic women were 12 times more likely to die than white women, and more than 3,000 women experienced life-threatening birth complications each year. In response, NYC committed $12.8 million in July 2018 to reduce maternal mortality and eliminate racial disparities.NYC Health + Hospitals (H+H)-the nation's largest public health system, serving 1.1 million patients annually with roughly 15,000 births per year-became the primary vehicle for this initiative. With 80 percent of the system's deliveries covered by Medicaid and a patient population that is 51.2 percent Hispanic and 27.1 percent Black, H+H is uniquely positioned to lead the fight against maternal health inequity.Three flagship programs anchor H+H's response to the city's maternal mortality rate. The OB Simulation Program, launched in 2012 and expanded in 2018, was the first in the nation to use mannequins of color to train thousands of providers in obstetric emergencies. The Maternal Home Program, piloted at H+H's Kings County Hospital in 2019 and scaled system-wide by 2021, has served more than 10,341 patients, generating more than 33,000 referrals for social, behavioral health, and community resources. The Cardio-Obstetrics Program located at Kings County Hospital targets cardiovascular disease-the leading cause of maternal death among Black women-through screening, education, and community outreach. These programs are a health equity imperative, made more urgent by impending federal Medicaid cuts resulting from the H.R.1 One Big Beautiful Bill Act (passed on July 4, 2025).

Humans↗

PubMed1978

The relationship of post-stimulus time and interval histograms to the timing characteristics of spike trains.

PST (post-stimulus time) and interval histograms computed from recorded spike trains are related to an average timing characteristics of the spike train. The exact nature of this relationship varies with recording parameters, interfering signals, the histogram bin width, and the duration of the measurement interval. This work describes the conditions under which a PST histogram can serve as an unbiased estimate of the ensemble average of a spike train's intensity and an interval histogram can serve as an unbiased estimate of the probability density function of the interspike intervals. Simulation studies are used to confirm the validity of the theoretical results. As an example of an application, these results are used to analyze recordings of singleunit activity in the eight cranial nerve.

Action Potentials↗

PubMed2026

Implicit and explicit statistical learning in reading: Evidence from a randomized controlled-learning study and computational modeling.

A key challenge in reading acquisition is understanding how learners extract the complex probabilistic mappings between print, meaning, and sound. Statistical learning (SL) theory offers a mechanistic account of how such mappings are acquired, whether implicitly through exposure or explicitly through instruction. We conducted a randomized controlled-learning study in Chinese, a writing system characterized by multiple sub-lexical regularities linking orthography, semantics, and phonology. Ninety-five 2nd-3rd graders with or at risk for dyslexia were randomly assigned to one of three groups: an implicit-SL training group exposed to repeated lexical and sublexical orthography-semantics-phonology associations, an explicit-SL training group receiving the same input plus explicit instruction on the sublexical print-sound mapping, and a no-SL control group. Both SL groups outperformed controls on the characters they were trained on, as well as on untrained characters that required generalization. However, only the explicit group demonstrated abstraction of print-sound mapping to novel items. Neural network simulations further revealed distinct mechanisms supporting implicit and explicit SL, consistent with a dual-system account of reading acquisition. Together, these findings (1) clarify how implicit and explicit learning distinctly support the discovery of statistical structure in written language and (2) underscore the implicit-explicit dual learning mechanism underlying reading acquisition.

Humans↗