A machine learning approach for accurate and real-time DNA sequence identification.
Ontology highlight
ABSTRACT: Background
The all-electronic Single Molecule Break Junction (SMBJ) method is an emerging alternative to traditional polymerase chain reaction (PCR) techniques for genetic sequencing and identification. Existing work indicates that the current spectra recorded from SMBJ experimentations contain unique signatures to identify known sequences from a dataset. However, the spectra are typically extremely noisy due to the stochastic and complex interactions between the substrate, sample, environment, and the measuring system, necessitating hundreds or thousands of experimentations to obtain reliable and accurate results.Results
This article presents a DNA sequence identification system based on the current spectra of ten short strand sequences, including a pair that differs by a single mismatch. By employing a gradient boosted tree classifier model trained on conductance histograms, we demonstrate that extremely high accuracy, ranging from approximately 96 % for molecules differing by a single mismatch to 99.5 % otherwise, is possible. Further, such accuracy metrics are achievable in near real-time with just twenty or thirty SMBJ measurements instead of hundreds or thousands. We also demonstrate that a tandem classifier architecture, where the first stage is a multiclass classifier and the second stage is a binary classifier, can be employed to boost the single mismatched pair's identification accuracy to 99.5 %.Conclusions
A monolithic classifier, or more generally, a multistage classifier with model specific parameters that depend on experimental current spectra can be used to successfully identify DNA strands.
SUBMITTER: Wang Y
PROVIDER: S-EPMC8268518 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundChangeful seasonal influenza activity in subtropical areas such as Taiwan causes problems in epidemic preparedness. The Taiwan Centers for Disease Control has maintained real-time national influenza surveillance systems since 2004. Except for timely monitoring, epidemic forecasting using the national influenza surveillance data can provide pivotal information for public health response.ObjectiveWe aimed to develop predictive models using machine learning to provide real-time influenza-like illness forecasts.MethodsUsing surveillance data of influenza-like illness visits from emergency departments (from the Real-Time Outbreak and Disease Surveillance System), outpatient departments (from the National Health Insurance database), and the records of patients with severe influenza with complications (from the National Notifiable Disease Surveillance System), we developed 4 machine learning models (autoregressive integrated moving average, random forest, support vector regression, and extreme gradient boosting) to produce weekly influenza-like illness predictions for a given week and 3 subsequent weeks. We established a framework of the machine learning models and used an ensemble approach called stacking to integrate these predictions. We trained the models using historical data from 2008-2014. We evaluated their predictive ability during 2015-2017 for each of the 4-week time periods using Pearson correlation, mean absolute percentage error (MAPE), and hit rate of trend prediction. A dashboard website was built to visualize the forecasts, and the results of real-world implementation of this forecasting framework in 2018 were evaluated using the same metrics.ResultsAll models could accurately predict the timing and magnitudes of the seasonal peaks in the then-current week (nowcast) (ρ=0.802-0.965; MAPE: 5.2%-9.2%; hit rate: 0.577-0.756), 1-week (ρ=0.803-0.918; MAPE: 8.3%-11.8%; hit rate: 0.643-0.747), 2-week (ρ=0.783-0.867; MAPE: 10.1%-15.3%; hit rate: 0.669-0.734), and 3-week forecasts (ρ=0.676-0.801; MAPE: 12.0%-18.9%; hit rate: 0.643-0.786), especially the ensemble model. In real-world implementation in 2018, the forecasting performance was still accurate in nowcasts (ρ=0.875-0.969; MAPE: 5.3%-8.0%; hit rate: 0.582-0.782) and remained satisfactory in 3-week forecasts (ρ=0.721-0.908; MAPE: 7.6%-13.5%; hit rate: 0.596-0.904).ConclusionsThis machine learning and ensemble approach can make accurate, real-time influenza-like illness forecasts for a 4-week period, and thus, facilitate decision making.
| S-EPMC7439145 | biostudies-literature
Project description:The wide-ranging adoption of quantum technologies requires practical, high-performance advances in our ability to maintain quantum coherence while facing the challenge of state collapse under measurement. Here we use techniques from control theory and machine learning to predict the future evolution of a qubit's state; we deploy this information to suppress stochastic, semiclassical decoherence, even when access to measurements is limited. First, we implement a time-division multiplexed approach, interleaving measurement periods with periods of unsupervised but stabilised operation during which qubits are available, for example, in quantum information experiments. Second, we employ predictive feedback during sequential but time delayed measurements to reduce the Dick effect as encountered in passive frequency standards. Both experiments demonstrate significant improvements in qubit-phase stability over 'traditional' measurement-based feedback approaches by exploiting time domain correlations in the noise processes. This technique requires no additional hardware and is applicable to all two-level quantum systems where projective measurements are possible.
| S-EPMC5241809 | biostudies-other
Project description:Mass spectrometry-based proteomics technologies are the prime methods for the high-throughput identification of proteins expressed in complex biological samples. Nevertheless, mass spectrometry’s technical limitations still hinder its ability to identify low abundance proteins in complex samples. Characterizing such proteins is essential to provide a comprehensive understanding of the biological processes taking place in a sample. Still today, a large part of the mass spectrometry-based proteomics performed use a data-dependent approach that favors the acquisition of mass spectra and detection of proteins of higher abundance. Combined to the fact that the computational identification of proteins from mass spectrometry data is typically performed after mass spectrometry data acquisition, large numbers of mass spectra are redundantly collected from the same abundant proteins and little to no mass spectra are acquired for proteins of lower abundance. To address this problem, we propose a novel supervised learning algorithm that identifies proteins in real-time as mass spectrometry data is acquired and prevents the further data acquisition related to confidently identified proteins to improve the identification sensitivity of low abundance proteins. We show in real-time simulations of a previously performed mass spectrometry analysis of a HEK293 cell lysates that our approach can identify 92.1% of the proteins using 66.2% of the MS2 spectra acquired in the experiment. We also demonstrate that our approach is fast enough for real-time mass spectrometry analysis, is flexible and that it outperforms previously proposed methods. Our method efficient usage of mass spectrometry resources will provide a more comprehensive characterization of proteomes in complex samples.
2020-10-27 | PXD017673 | Pride
Project description:Since the onset of the COVID-19 pandemic, increasing cases with variable outcomes continue globally because of variants and despite vaccines and therapies. There is a need to identify at-risk individuals early that would benefit from timely medical interventions. DNA methylation provides an opportunity to identify an epigenetic signature of individuals at increased risk. We utilized machine learning to identify DNA methylation signatures of COVID-19 disease from data available through NCBI Gene Expression Omnibus. A training cohort of 460 individuals (164 COVID-19-infected and 296 non-infected) and an external validation dataset of 128 individuals (102 COVID-19-infected and 26 non-COVID-associated pneumonia) were reanalyzed. Data was processed using ChAMP and beta values were logit transformed. The JADBio AutoML platform was leveraged to identify a methylation signature associated with severe COVID-19 disease. We identified a random forest classification model from 4 unique methylation sites with the power to discern individuals with severe COVID-19 disease. The average area under the curve of receiver operator characteristic (AUC-ROC) of the model was 0.933 and the average area under the precision-recall curve (AUC-PRC) was 0.965. When applied to our external validation, this model produced an AUC-ROC of 0.898 and an AUC-PRC of 0.864. These results further our understanding of the utility of DNA methylation in COVID-19 disease pathology and serve as a platform to inform future COVID-19 related studies.
| S-EPMC9580434 | biostudies-literature
Project description:BackgroundPredicting the function of an unknown protein is an essential goal in bioinformatics. Sequence similarity-based approaches are widely used for function prediction; however, they are often inadequate in the absence of similar sequences or when the sequence similarity among known protein sequences is statistically weak. This study aimed to develop an accurate prediction method for identifying protein function, irrespective of sequence and structural similarities.ResultsA highly accurate prediction method capable of identifying protein function, based solely on protein sequence properties, is described. This method analyses and identifies specific features of the protein sequence that are highly correlated with certain protein functions and determines the combination of protein sequence features that best characterises protein function. Thirty-three features that represent subtle differences in local regions and full regions of the protein sequences were introduced. On the basis of 484 features extracted solely from the protein sequence, models were built to predict the functions of 11 different proteins from a broad range of cellular components, molecular functions, and biological processes. The accuracy of protein function prediction using random forests with feature selection ranged from 94.23% to 100%. The local sequence information was found to have a broad range of applicability in predicting protein function.ConclusionWe present an accurate prediction method using a machine-learning approach based solely on protein sequence properties. The primary contribution of this paper is to propose new PNPRD features representing global and/or local differences in sequences, based on positively and/or negatively charged residues, to assist in predicting protein function. In addition, we identified a compact and useful feature subset for predicting the function of various proteins. Our results indicate that sequence-based classifiers can provide good results among a broad range of proteins, that the proposed features are useful in predicting several functions, and that the combination of our and traditional features may support the creation of a discriminative feature set for specific protein functions.
| S-EPMC2731080 | biostudies-literature
Project description:Candida parapsilosis is the Candida species isolated the second most frequently from blood cultures in South America and some European countries, such as Spain. Since 2005, this species has been considered a complex of 3 closely related species: C. parapsilosis, Candida metapsilosis, and Candida orthopsilosis. Here, we describe a real-time TaqMan-MGB PCR assay, using mitochondrial DNA (mtDNA) as the target, which readily distinguishes these 3 species. We first used comparative genomics to locate syntenic regions between these 3 mitochondrial genomes and then selected NADH5 as the target for the real-time PCR assay. Probes were designed to include a combination of different single-nucleotide polymorphisms that are able to differentiate each species within the C. parapsilosis complex. This new methodology was first tested using mtDNA and then genomic DNA from 4 reference and 5 clinical strains. For assay validation, a total of 96 clinical isolates and 4 American Type Culture Collection (ATCC) isolates previously identified by internal transcribed spacer (ITS) ribosomal DNA (rDNA) sequencing were tested. Real-time PCR using genomic DNA was able to differentiate the 3 species with 100% accuracy. No amplification was observed when DNA from other species was used as the template. We observed 100% congruence with ITS rDNA sequencing identification, including for 30 strains used in blind testing. This novel method allows a quick and accurate intracomplex identification of C. parapsilosis and saves time compared with sequencing, which so far has been considered the "gold standard" for Candida yeast identification. In addition, this assay provides a useful tool for epidemiological and clinical studies of these emergent species.
| S-EPMC3405582 | biostudies-literature
Project description:BackgroundOdorant binding proteins (OBPs) are believed to shuttle odorants from the environment to the underlying odorant receptors, for which they could potentially serve as odorant presenters. Although several sequence based search methods have been exploited for protein family prediction, less effort has been devoted to the prediction of OBPs from sequence data and this area is more challenging due to poor sequence identity between these proteins.ResultsIn this paper, we propose a new algorithm that uses Regularized Least Squares Classifier (RLSC) in conjunction with multiple physicochemical properties of amino acids to predict odorant-binding proteins. The algorithm was applied to the dataset derived from Pfam and GenDiS database and we obtained overall prediction accuracy of 97.7% (94.5% and 98.4% for positive and negative classes respectively).ConclusionOur study suggests that RLSC is potentially useful for predicting the odorant binding proteins from sequence-derived properties irrespective of sequence similarity. Our method predicts 92.8% of 56 odorant binding proteins non-homologous to any protein in the swissprot database and 97.1% of the 414 independent dataset proteins, suggesting the usefulness of RLSC method for facilitating the prediction of odorant binding proteins from sequence information.
| S-EPMC2216042 | biostudies-literature
Project description:BACKGROUND AND PURPOSE:MR imaging-based modeling of tumor cell density can substantially improve targeted treatment of glioblastoma. Unfortunately, interpatient variability limits the predictive ability of many modeling approaches. We present a transfer learning method that generates individualized patient models, grounded in the wealth of population data, while also detecting and adjusting for interpatient variabilities based on each patient's own histologic data. MATERIALS AND METHODS:We recruited patients with primary glioblastoma undergoing image-guided biopsies and preoperative imaging, including contrast-enhanced MR imaging, dynamic susceptibility contrast MR imaging, and diffusion tensor imaging. We calculated relative cerebral blood volume from DSC-MR imaging and mean diffusivity and fractional anisotropy from DTI. Following image coregistration, we assessed tumor cell density for each biopsy and identified corresponding localized MR imaging measurements. We then explored a range of univariate and multivariate predictive models of tumor cell density based on MR imaging measurements in a generalized one-model-fits-all approach. We then implemented both univariate and multivariate individualized transfer learning predictive models, which harness the available population-level data but allow individual variability in their predictions. Finally, we compared Pearson correlation coefficients and mean absolute error between the individualized transfer learning and generalized one-model-fits-all models. RESULTS:Tumor cell density significantly correlated with relative CBV (r = 0.33, P < .001), and T1-weighted postcontrast (r = 0.36, P < .001) on univariate analysis after correcting for multiple comparisons. With single-variable modeling (using relative CBV), transfer learning increased predictive performance (r = 0.53, mean absolute error = 15.19%) compared with one-model-fits-all (r = 0.27, mean absolute error = 17.79%). With multivariate modeling, transfer learning further improved performance (r = 0.88, mean absolute error = 5.66%) compared with one-model-fits-all (r = 0.39, mean absolute error = 16.55%). CONCLUSIONS:Transfer learning significantly improves predictive modeling performance for quantifying tumor cell density in glioblastoma.
| S-EPMC6474354 | biostudies-other
Project description:Quantifying sequence-specific protein-ligand interactions is critical for understanding and exploiting numerous cellular processes, including gene expression regulation and signal transduction. Given their importance, next-generation sequencing (NGS) based assays that characterize such recognition with high-throughput are increasingly being used to profile a range of protein classes and interactions. However, these methods do not measure the biophysical parameters that have long been used to uncover the quantitative rules underlying sequence recognition. We developed a highly flexible machine learning framework, called ProBound, to quantify sequence recognition in terms of biophysical parameters based on NGS data. ProBound quantifies transcription factor (TF) behavior with models that accurately predict binding affinity over a range exceeding that of previous resources, captures the impact of DNA modifications and conformational flexibility of multi-TF complexes, and infers specificity directly from \textit{in vivo} data such as ChIP-seq without peak calling. When coupled with a new assay called Kd-seq, it quantifies the absolute affinity of protein-ligand interactions. Its applicability extends beyond thermodynamic equilibrium binding, to the kinetics of kinase-substrate interactions. Altogether, ProBound provides a versatile algorithmic framework for understanding sequence recognition in a wide variety of biological contexts.
2021-06-02 | GSE175942 | GEO
Project description:CRISPR-Cas genes are extraordinarily diverse and evolve rapidly when compared to other prokaryotic genes. With the rapid increase in newly sequenced archaeal and bacterial genomes, manual identification of CRISPR-Cas systems is no longer viable. Thus, an automated approach is required for advancing our understanding of the evolution and diversity of these systems and for finding new candidates for genome engineering in eukaryotic models. We introduce CRISPRcasIdentifier, a new machine learning-based tool that combines regression and classification models for the prediction of potentially missing proteins in instances of CRISPR-Cas systems and the prediction of their respective subtypes. In contrast to other available tools, CRISPRcasIdentifier can both detect cas genes and extract potential association rules that reveal functional modules for CRISPR-Cas systems. In our experimental benchmark on the most recently published and comprehensive CRISPR-Cas system dataset, CRISPRcasIdentifier was compared with recent and state-of-the-art tools. According to the experimental results, CRISPRcasIdentifier presented the best Cas protein identification and subtype classification performance. Overall, our tool greatly extends the classification of CRISPR cassettes and, for the first time, predicts missing Cas proteins and association rules between Cas proteins. Additionally, we investigated the properties of CRISPR subtypes. The proposed tool relies not only on the knowledge of manual CRISPR annotation but also on models trained using machine learning.
| S-EPMC7298778 | biostudies-literature