Cancer Type Classification in Liquid Biopsies Based on Sparse Mutational Profiles Enabled through Data Augmentation and Integration.
Ontology highlight
ABSTRACT:
SUBMITTER: Danyi A
PROVIDER: S-EPMC8780455 | biostudies-literature | 2021 Dec
REPOSITORIES: biostudies-literature
Publications
Cancer Type Classification in Liquid Biopsies Based on Sparse Mutational Profiles Enabled through Data Augmentation and Integration.
Danyi Alexandra A Jager Myrthe M de Ridder Jeroen J
Life (Basel, Switzerland) 20211221 1
Identifying the cell of origin of cancer is important to guide treatment decisions. Machine learning approaches have been proposed to classify the cell of origin based on somatic mutation profiles from solid biopsies. However, solid biopsies can cause complications and certain tumors are not accessible. Liquid biopsies are promising alternatives but their somatic mutation profile is sparse and current machine learning models fail to perform in this setting. We propose an improved method to deal ...[more]
Similar Datasets
Project description:Genomic selection (GS) is revolutionizing plant breeding. However, its practical implementation is still challenging, since there are many factors that affect its accuracy. For this reason, this research explores data augmentation with the goal of improving its accuracy. Deep neural networks with data augmentation (DA) generate synthetic data from the original training set to increase the training set and to improve the prediction performance of any statistical or machine learning algorithm. There is much empirical evidence of their success in many computer vision applications. Due to this, DA was explored in the context of GS using 14 real datasets. We found empirical evidence that DA is a powerful tool to improve the prediction accuracy, since we improved the prediction accuracy of the top lines in the 14 datasets under study. On average, across datasets and traits, the gain in prediction performance of the DA approach regarding the Conventional method in the top 20% of lines in the testing set was 108.4% in terms of the NRMSE and 107.4% in terms of the MAAPE, but a worse performance was observed on the whole testing set. We encourage more empirical evaluations to support our findings.
| S-EPMC10969940 | biostudies-literature
Project description:Although the intraoperative molecular diagnosis of the approximately 100 known brain tumor entities described to date has been a goal of neuropathology for the past decade, achieving this within a clinically relevant timeframe of under 1 h after biopsy collection remains elusive. Advances in third-generation sequencing have brought this goal closer, but established machine learning techniques rely on computationally intensive methods, making them impractical for live diagnostic workflows in clinical applications. Here we present MethyLYZR, a naive Bayesian framework enabling fully tractable, live classification of cancer epigenomes. For evaluation, we used nanopore sequencing to classify over 200 brain tumor samples, including 10 sequenced in a clinical setting next to the operating room, achieving highly accurate results within 15 min of sequencing. MethyLYZR can be run in parallel with an ongoing nanopore experiment with negligible computational overhead. Therefore, the only limiting factors for even faster time to results are DNA extraction time and the nanopore sequencer's maximum parallel throughput. Although more evidence from prospective studies is needed, our study suggests the potential applicability of MethyLYZR for live molecular classification of nervous system malignancies using nanopore sequencing not only for the neurosurgical intraoperative use case but also for other oncologic indications and the classification of tumors from cell-free DNA in liquid biopsies.
| S-EPMC11922770 | biostudies-literature
Project description:The emergence of high-throughput genomic datasets from different sources and platforms (e.g., gene expression, single nucleotide polymorphisms (SNP), and copy number variation (CNV)) has greatly enhanced our understandings of the interplay of these genomic factors as well as their influences on the complex diseases. It is challenging to explore the relationship between these different types of genomic data sets. In this paper, we focus on a multivariate statistical method, canonical correlation analysis (CCA) method for this problem. Conventional CCA method does not work effectively if the number of data samples is significantly less than that of biomarkers, which is a typical case for genomic data (e.g., SNPs). Sparse CCA (sCCA) methods were introduced to overcome such difficulty, mostly using penalizations with l-1 norm (CCA-l1) or the combination of l-1and l-2 norm (CCA-elastic net). However, they overlook the structural or group effect within genomic data in the analysis, which often exist and are important (e.g., SNPs spanning a gene interact and work together as a group).We propose a new group sparse CCA method (CCA-sparse group) along with an effective numerical algorithm to study the mutual relationship between two different types of genomic data (i.e., SNP and gene expression). We then extend the model to a more general formulation that can include the existing sCCA models. We apply the model to feature/variable selection from two data sets and compare our group sparse CCA method with existing sCCA methods on both simulation and two real datasets (human gliomas data and NCI60 data). We use a graphical representation of the samples with a pair of canonical variates to demonstrate the discriminating characteristic of the selected features. Pathway analysis is further performed for biological interpretation of those features.The CCA-sparse group method incorporates group effects of features into the correlation analysis while performs individual feature selection simultaneously. It outperforms the two sCCA methods (CCA-l1 and CCA-group) by identifying the correlated features with more true positives while controlling total discordance at a lower level on the simulated data, even if the group effect does not exist or there are irrelevant features grouped with true correlated features. Compared with our proposed CCA-group sparse models, CCA-l1 tends to select less true correlated features while CCA-group inclines to select more redundant features.
| S-EPMC3751310 | biostudies-literature
Project description:BackgroundResolving the differential diagnosis between brain metastases (BM), glioblastomas (GBM), and central nervous system lymphomas (CNSL) is an important dilemma for the clinical management of the main three intra-axial brain tumor types. Currently, treatment decisions require invasive diagnostic surgical biopsies that carry risks and morbidity. This study aimed to utilize methylomes from cerebrospinal fluid (CSF), a biofluid proximal to brain tumors, for reliable non-invasive classification that addresses limitations associated with low target abundance in existing approaches.MethodsBinomial GLMnet classifiers of tumor type were built, in fifty iterations of 80% discovery sets, using CSF methylomes obtained from 57 BM, GBM, CNSL, and non-neoplastic control patients. Publicly-available tissue methylation profiles (N = 197) on these entities and normal brain parenchyma were used for validation and model optimization.ResultsModels reliably distinguished between BM (area under receiver operating characteristic curve [AUROC] = 0.93, 95% confidence interval [CI]: 0.71-1.0), GBM (AUROC = 0.83, 95% CI: 0.63-1.0), and CNSL (AUROC = 0.91, 95% CI: 0.66-1.0) in independent 20% validation sets. For validation, CSF-based methylome signatures reliably distinguished between tumor types within external tissue samples and tumors from non-neoplastic controls in CSF and tissue. CSF methylome signals were observed to align closely with tissue signatures for each entity. An additional set of optimized CSF-based models, built using tumor-specific features present in tissue data, showed enhanced classification accuracy.ConclusionsCSF methylomes are reliable for liquid biopsy-based classification of the major three malignant brain tumor types. We discuss how liquid biopsies may impact brain cancer management in the future by avoiding surgical risks, classifying unbiopsiable tumors, and guiding surgical planning when resection is indicated.
| S-EPMC10398815 | biostudies-literature
Project description:Partial least squares (PLS) is a well known dimension reduction method which has been recently adapted for high dimensional classification problems in genome biology. We develop sparse versions of the recently proposed two PLS-based classification methods using sparse partial least squares (SPLS). These sparse versions aim to achieve variable selection and dimension reduction simultaneously. We consider both binary and multicategory classification. We provide analytical and simulation-based insights about the variable selection properties of these approaches and benchmark them on well known publicly available datasets that involve tumor classification with high dimensional gene expression data. We show that incorporation of SPLS into a generalized linear model (GLM) framework provides higher sensitivity in variable selection for multicategory classification with unbalanced sample sizes between classes. As the sample size increases, the two-stage approach provides comparable sensitivity with better specificity in variable selection. In binary classification and multicategory classification with balanced sample sizes, the two-stage approach provides comparable variable selection and prediction accuracy as the GLM version and is computationally more efficient.
| S-EPMC2861314 | biostudies-literature
Project description:Early detection of lung cancer is crucial for patient survival and treatment. Recent advancements in next-generation sequencing (NGS) analysis enable cell-free DNA (cfDNA) liquid biopsy to detect changes, like chromosomal rearrangements, somatic mutations, and copy number variations (CNVs), in cancer. Machine learning (ML) analysis using cancer markers is a highly promising tool for identifying patterns and anomalies in cancers, making the development of ML-based analysis methods essential. We collected blood samples from 92 lung cancer patients and 80 healthy individuals to analyze the distinction between them. The detection of lung cancer markers Cyfra21 and carcinoembryonic antigen (CEA) in blood revealed significant differences between patients and controls. We performed machine learning analysis to obtain AUC values via Adaptive Boosting (AdaBoost), Multi-Layer Perceptron (MLP), and Logistic Regression (LR) using cancer markers, cfDNA concentrations, and CNV screening. Furthermore, combining the analysis of all multi-omics data for ML showed higher AUC values compared with analyzing each element separately, suggesting the potential for a highly accurate diagnosis of cancer. Overall, our results from ML analysis using multi-omics data obtained from blood demonstrate a remarkable ability of the model to distinguish between lung cancer and healthy individuals, highlighting the potential for a diagnostic model against lung cancer.
| S-EPMC10526503 | biostudies-literature
Project description:We aimed to identify common mCRC profiles associated with a discordant mutational status of RAS between the standard of care (SoC) tumour tissue tests and ctDNA tests to understand ctDNA detection and improve treatment responses. This was a multicentre, retrospective and prospective study. A total of 366 Spanish mCRC patients were independently recruited. BEAMing ddPCR technology was employed to detect ctDNA RAS mutations, and logistic regression analyses were performed to investigate clinicopathological factors associated with discordance. The highest concordance ratios were observed in profiles with multiple metastatic sites when the liver was present (89.7%; 95% CI 84.8-93.2), profiles with synchronous disease without primary tumour resection (90.2%; 95% CI 83.6-94.3) and profiles with mCRC originating in the left colon (91.3%; 95% CI 85.0-95.0). Metachronous disease originating in the right colon (OR = 6.1; 95% CI 1.7-26.5; p-value = 0.006) or rectum (OR = 5.0; 95% CI 1.5-17.8; p-value = 0.009) showed the highest probability of discrepancies. Primary tumour resection and a higher frequency of single metastases in the peritoneum or lungs in these patients were associated with reduced plasmatic mutation allele fractions (MAFs) and an increased probability of showing false-negative genotypes. Additional testing of patients with mCRC originating in the right colon or rectum with a single non-mutated ctDNA test is advised before the choice of therapy.
| S-EPMC10377339 | biostudies-literature
Project description:Over recent decades, machine learning, an integral subfield of artificial intelligence, has revolutionized diverse sectors, enabling data-driven decisions with minimal human intervention. In particular, the field of educational assessment emerges as a promising area for machine learning applications, where students can be classified and diagnosed using their performance data. The objectives of Diagnostic Classification Models (DCMs), which provide a suite of methods for diagnosing students' cognitive states in relation to the mastery of necessary cognitive attributes for solving problems in a test, can be effectively addressed through machine learning techniques. However, the challenge lies in the latent nature of cognitive status, which makes it difficult to obtain labels for the training dataset. Consequently, the application of machine learning methods to DCMs often assumes smaller training sets with labels derived either from theoretical considerations or human experts. In this study, the authors propose a supervised diagnostic classification model with data augmentation (SDCM-DA). This method is designed to utilize the augmented data using a data generation model constructed by leveraging the probability of correct responses for each attribute mastery pattern derived from the expert-labeled dataset. To explore the benefits of data augmentation, a simulation study is carried out, contrasting it with classification methods that rely solely on the expert-labeled dataset for training. The findings reveal that utilizing data augmentation with the estimated probabilities of correct responses substantially enhances classification accuracy. This holds true even when the augmentation originates from a small labeled sample with occasional labeling errors, and when the tests contain lower-quality items that may inaccurately measure students' true cognitive status. Moreover, the study demonstrates that leveraging augmented data for learning can enable the successful classification of students, thereby eliminating the necessity for specifying an underlying response model.
| S-EPMC10769086 | biostudies-literature
Project description:BackgroundHigh throughput data are complex and methods that reveal structure underlying the data are most useful. Principal component analysis, frequently implemented as a singular value decomposition, is a popular technique in this respect. Nowadays often the challenge is to reveal structure in several sources of information (e.g., transcriptomics, proteomics) that are available for the same biological entities under study. Simultaneous component methods are most promising in this respect. However, the interpretation of the principal and simultaneous components is often daunting because contributions of each of the biomolecules (transcripts, proteins) have to be taken into account.ResultsWe propose a sparse simultaneous component method that makes many of the parameters redundant by shrinking them to zero. It includes principal component analysis, sparse principal component analysis, and ordinary simultaneous component analysis as special cases. Several penalties can be tuned that account in different ways for the block structure present in the integrated data. This yields known sparse approaches as the lasso, the ridge penalty, the elastic net, the group lasso, sparse group lasso, and elitist lasso. In addition, the algorithmic results can be easily transposed to the context of regression. Metabolomics data obtained with two measurement platforms for the same set of Escherichia coli samples are used to illustrate the proposed methodology and the properties of different penalties with respect to sparseness across and within data blocks.ConclusionSparse simultaneous component analysis is a useful method for data integration: First, simultaneous analyses of multiple blocks offer advantages over sequential and separate analyses and second, interpretation of the results is highly facilitated by their sparseness. The approach offered is flexible and allows to take the block structure in different ways into account. As such, structures can be found that are exclusively tied to one data platform (group lasso approach) as well as structures that involve all data platforms (Elitist lasso approach).AvailabilityThe additional file contains a MATLAB implementation of the sparse simultaneous component method.
| S-EPMC3283562 | biostudies-literature
Project description:Multivariate pattern recognition methods are increasingly being used to identify multiregional brain activity patterns that collectively discriminate one cognitive condition or experimental group from another, using fMRI data. The performance of these methods is often limited because the number of regions considered in the analysis of fMRI data is large compared to the number of observations (trials or participants). Existing methods that aim to tackle this dimensionality problem are less than optimal because they either over-fit the data or are computationally intractable. Here, we describe a novel method based on logistic regression using a combination of L1 and L2 norm regularization that more accurately estimates discriminative brain regions across multiple conditions or groups. The L1 norm, computed using a fast estimation procedure, ensures a fast, sparse and generalizable solution; the L2 norm ensures that correlated brain regions are included in the resulting solution, a critical aspect of fMRI data analysis often overlooked by existing methods. We first evaluate the performance of our method on simulated data and then examine its effectiveness in discriminating between well-matched music and speech stimuli. We also compared our procedures with other methods which use either L1-norm regularization alone or support vector machine-based feature elimination. On simulated data, our methods performed significantly better than existing methods across a wide range of contrast-to-noise ratios and feature prevalence rates. On experimental fMRI data, our methods were more effective in selectively isolating a distributed fronto-temporal network that distinguished between brain regions known to be involved in speech and music processing. These findings suggest that our method is not only computationally efficient, but it also achieves the twin objectives of identifying relevant discriminative brain regions and accurately classifying fMRI data.
| S-EPMC2856747 | biostudies-literature