An ensemble approach to accurately detect somatic mutations using SomaticSeq.
Ontology highlight
ABSTRACT:
SUBMITTER: Fang LT
PROVIDER: S-EPMC4574535 | biostudies-literature | 2015 Sep
REPOSITORIES: biostudies-literature
Publications
An ensemble approach to accurately detect somatic mutations using SomaticSeq.
Fang Li Tai LT Afshar Pegah Tootoonchi PT Chhibber Aparna A Mohiyuddin Marghoob M Fan Yu Y Mu John C JC Gibeling Greg G Barr Sharon S Asadi Narges Bani NB Gerstein Mark B MB Koboldt Daniel C DC Wang Wenyi W Wong Wing H WH Lam Hugo Y K HY
Genome biology 20150917
SomaticSeq is an accurate somatic mutation detection pipeline implementing a stochastic boosting algorithm to produce highly accurate somatic mutation calls for both single nucleotide variants and small insertions and deletions. The workflow currently incorporates five state-of-the-art somatic mutation callers, and extracts over 70 individual genomic and sequencing features for each candidate site. A training set is provided to an adaptively boosted decision tree learner to create a classifier f ...[more]
Similar Datasets
Project description:Abstract The cost reduction in sequencing and the extensive genomic characterization of a wide variety of cancers are expanding tumor sequencing to a wide number of research groups and the clinical practice. Although specific pipelines have been generated for the identification of somatic mutations, their results usually differ considerably, and a common approach is to use several callers to achieve a more reliable set of mutations. This procedure is computationally expensive and time-consuming, and it suffers from the same limitations in sensitivity and specificity as other approaches. Expert revision of mutant calls is therefore required to verify calls that might be used for clinical diagnosis. This step could take advantage of machine learning techniques, as they provide a useful approach to incorporate expert-reviewed information for the identification of somatic mutations. Here we present RFcaller, a pipeline based on machine learning algorithms, for the detection of somatic mutations in tumor–normal paired samples that does not require large computing resources. RFcaller shows high accuracy for the detection of substitutions and insertions/deletions from whole genome or exome data. It allows the detection of mutations in driver genes missed by other approaches, and has been validated by comparison to deep and Sanger sequencing.
| S-EPMC10227442 | biostudies-literature
Project description:SummarySomatic Mutation calling method using a Random Forest (SMuRF) integrates predictions and auxiliary features from multiple somatic mutation callers using a supervised machine learning approach. SMuRF is trained on community-curated matched tumor and normal whole genome sequencing data. SMuRF predicts both SNVs and indels with high accuracy in genome or exome-level sequencing data. Furthermore, the method is robust across multiple tested cancer types and predicts low allele frequency variants with high accuracy. In contrast to existing ensemble-based somatic mutation calling approaches, SMuRF works out-of-the-box and is orders of magnitudes faster.Availability and implementationThe method is implemented in R and available at https://github.com/skandlab/SMuRF. SMuRF operates as an add-on to the community-developed bcbio-nextgen somatic variant calling pipeline.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC6735703 | biostudies-literature
Project description:Mutational signatures have emerged as powerful biomarkers in cancer patients, with prognostic and therapeutic implications. Wider clinical utility requires access to reproducible algorithms, which allow characterization of mutational signatures in a given tumor sample. Here, we show how mutational signature fitting can be applied to hematological cancer genomes to identify biologically and clinically important mutational processes, highlighting the importance of careful interpretation in light of biological knowledge. Our newly released R package mmsig comes with a dynamic error-suppression procedure that improves specificity in important clinical and biological settings. In particular, mmsig allows accurate detection of mutational signatures with low abundance, such as those introduced by APOBEC cytidine deaminases. This is particularly important in the most recent mutational signature reference (COSMIC v3.1) where each signature is more clearly defined. Our mutational signature fitting algorithm mmsig is a robust tool that can be implemented immediately in the clinic.
| S-EPMC8007623 | biostudies-literature
Project description:BackgroundRecently, a number of large-scale cancer genome sequencing projects have generated a large volume of somatic mutations; however, identifying the functional consequences and roles of somatic mutations in tumorigenesis remains a major challenge. Researchers have identified that protein pocket regions play critical roles in the interaction of proteins with small molecules, enzymes, and nucleic acid. As such, investigating the features of somatic mutations in protein pocket regions provides a promising approach to identifying new genotype-phenotype relationships in cancer.MethodsIn this study, we developed a protein pocket-based computational approach to uncover the functional consequences of somatic mutations in cancer. We mapped 1.2 million somatic mutations across 36 cancer types from the COSMIC database and The Cancer Genome Atlas (TCGA) onto the protein pocket regions of over 5,000 protein three-dimensional structures. We further integrated cancer cell line mutation profiles and drug pharmacological data from the Cancer Cell Line Encyclopedia (CCLE) onto protein pocket regions in order to identify putative biomarkers for anticancer drug responses.ResultsWe found that genes harboring protein pocket somatic mutations were significantly enriched in cancer driver genes. Furthermore, genes harboring pocket somatic mutations tended to be highly co-expressed in a co-expressed protein interaction network. Using a statistical framework, we identified four putative cancer genes (RWDD1, NCF1, PLEK, and VAV3), whose expression profiles were associated with overall poor survival rates in melanoma, lung, or colorectal cancer patients. Finally, genes harboring protein pocket mutations were more likely to be drug-sensitive or drug-resistant. In a case study, we illustrated that the BAX gene was associated with the sensitivity of three anticancer drugs (midostaurin, vinorelbine, and tipifarnib).ConclusionsThis study provides novel insights into the functional consequences of somatic mutations during tumorigenesis and for anticancer drug responses. The computational approach used might be beneficial to the study of somatic mutations in the era of cancer precision medicine.
| S-EPMC4213513 | biostudies-literature
Project description:Somatic mutations drive the growth of tumor cells and are pivotal biomarkers for many cancer treatments. Genetic association analysis using somatic mutations is an effective approach to study the functional impact of somatic mutations. However, standard regression methods are not appropriate for somatic mutation association studies because somatic mutation calls often have non-ignorable false positive rate and/or false negative rate. While large scale association analysis using somatic mutations becomes feasible recently-thanks for the improvement of sequencing techniques and the reduction of sequencing cost-there is an urgent need for a new statistical method designed for somatic mutation association analysis. We propose such a method with computationally efficient software implementation: Somatic mutation Association test with Measurement Errors (SAME). SAME accounts for somatic mutation calling uncertainty using a likelihood based approach. It can be used to assess the associations between continuous/dichotomous outcomes and individual mutations or gene-level mutations. Through simulation studies across a wide range of realistic scenarios, we show that SAME can significantly improve statistical power than the naive generalized linear model that ignores mutation calling uncertainty. Finally, using the data collected from The Cancer Genome Atlas (TCGA) project, we apply SAME to study the associations between somatic mutations and gene expression in 12 cancer types, as well as the associations between somatic mutations and colon cancer subtype defined by DNA methylation data. SAME recovered some interesting findings that were missed by the generalized linear model. In addition, we demonstrated that mutation-level and gene-level analyses are often more appropriate for oncogene and tumor-suppressor gene, respectively.
| S-EPMC6235399 | biostudies-literature
Project description:Mutation detecting is a routine work for sequencing data analysis and the trading of existing tools often involves the combinations of signals on a set of overlapped sequencing reads. However, the subclonal mutations, which are reported to contribute to tumor recurrence and metastasis, are sometimes eliminated by existing signals. When the clonal proportion decreases, signals often present ambiguous, while complicated interactions among signals break the IID assumption for most of the machine learning models. Although the mutation callers could lower the thresholds, false positives are significantly introduced. The main aim here was to detect the subclonal mutations with high specificity from the scenario of ambiguous sample purities or clonal proportions. We proposed a novel machine learning approach for filtering false positive calls to accurately detect mutations with wide spectrum subclonal proportion. We have carried out a series of experiments on both simulated and real datasets, and compared to several state-of-art approaches, including freebayes, MuTect2, Sentieon and SiNVICT. The results demonstrated that the proposed method adapts well to different diluted sequencing signals and can significantly reduce the false positive when detecting subclonal mutations. The codes have been uploaded at https://github.com/TrinaZ/TL-fpFilter for academic usage only.
| S-EPMC9723383 | biostudies-literature
Project description:BackgroundThe accurate screening of tumor genomic landscapes for somatic mutations using high-throughput sequencing involves a crucial step in precise clinical diagnosis and targeted therapy. However, the complex inherent features of cancer tissue, especially, tumor genetic intra-heterogeneity coupled with the problem of sequencing and alignment artifacts, makes somatic variant calling a challenging task. Current variant filtering strategies, such as rule-based filtering and consensus voting of different algorithms, have previously helped to increase specificity, although comes at the cost of sensitivity.MethodsIn light of this, we have developed the NeoMutate framework which incorporates 7 supervised machine learning (ML) algorithms to exploit the strengths of multiple variant callers, using a non-redundant set of biological and sequence features. We benchmarked NeoMutate by simulating more than 10,000 bona fide cancer-related mutations into three well-characterized Genome in a Bottle (GIAB) reference samples.ResultsA robust and exhaustive evaluation of NeoMutate's performance based on 5-fold cross validation experiments, in addition to 3 independent tests, demonstrated a substantially improved variant detection accuracy compared to any of its individual composite variant callers and consensus calling of multiple tools.ConclusionsWe show here that integrating multiple tools in an ensemble ML layer optimizes somatic variant detection rates, leading to a potentially improved variant selection framework for the diagnosis and treatment of cancer.
| S-EPMC6524241 | biostudies-literature
Project description:Somatic mutations are a large category of genetic variations, which play an essential role in tumorigenesis. Detection of somatic single nucleotide variants (SNVs) could facilitate downstream analysis of tumorigenesis. Many computational methods have been developed to detect SNVs, but most require normal matched samples to differentiate somatic SNVs from the normal state, which can be difficult to obtain. Therefore, developing new approaches for detecting somatic SNVs without matched samples are crucial. In this work, we detected somatic mutations from individual tumor samples based on a novel machine learning approach, svmSomatic, using next-generation sequencing (NGS) data. In addition, as somatic SNV detection can be impacted by multiple mutations, with germline mutations and co-occurrence of copy number variations (CNVs) common in organisms, we used the novel approach to distinguish somatic and germline mutations based on the NGS data from individual tumor samples. In summary, svmSomatic: (1) considers the influence of CNV co-occurrence in detecting somatic mutations; and (2) trains a support vector machine algorithm to distinguish between somatic and germline mutations, without requiring normal matched samples. We further tested and compared svmSomatic with other common methods. Results showed that svmSomatic performance, as measured by F1-score, was significantly better than that of others using both simulation and real NGS data.
| S-EPMC7995270 | biostudies-literature
Project description:Early and accurate diagnosis of stroke improves the probability of positive outcome. The objective of this study was to identify a pattern of gene expression in peripheral blood that could potentially be optimised to expedite the diagnosis of acute ischaemic stroke (AIS). A discovery cohort was recruited consisting of 39 AIS patients and 24 neurologically asymptomatic controls. Peripheral blood was sampled at emergency department admission, and genome-wide expression profiling was performed via microarray. A machine-learning technique known as genetic algorithm k-nearest neighbours (GA/kNN) was then used to identify a pattern of gene expression that could optimally discriminate between groups. This pattern of expression was then assessed via qRT-PCR in an independent validation cohort, where it was evaluated for its ability to discriminate between an additional 39 AIS patients and 30 neurologically asymptomatic controls, as well as 20 acute stroke mimics. GA/kNN identified 10 genes (ANTXR2, STK3, PDK4, CD163, MAL, GRAP, ID3, CTSZ, KIF1B and PLXDC2) whose coordinate pattern of expression was able to identify 98.4% of discovery cohort subjects correctly (97.4% sensitive, 100% specific). In the validation cohort, the expression levels of the same 10 genes were able to identify 95.6% of subjects correctly when comparing AIS patients to asymptomatic controls (92.3% sensitive, 100% specific), and 94.9% of subjects correctly when comparing AIS patients with stroke mimics (97.4% sensitive, 90.0% specific). The transcriptional pattern identified in this study shows strong diagnostic potential, and warrants further evaluation to determine its true clinical efficacy.
| S-EPMC5685316 | biostudies-literature
Project description:Determining the cancer type and molecular subtype has important clinical implications. The primary site is however unknown for some malignancies discovered in the metastatic stage. Moreover liquid biopsies may be used to screen for tumoral DNA, which upon detection needs to be assigned to a site-of-origin. Classifiers based on genomic features are a promising approach to prioritize the tumor anatomical site, type and subtype. We examined the predictive ability of causal (driver) somatic mutations in this task, comparing it against global patterns of non-selected (passenger) mutations, including features based on regional mutation density (RMD). In the task of distinguishing 18 cancer types, the driver mutations-mutated oncogenes or tumor suppressors, pathways and hotspots-classified 36% of the patients to the correct cancer type. In contrast, the features based on passenger mutations did so at 92% accuracy, with similar contribution from the RMD and the trinucleotide mutation spectra. The RMD and the spectra covered distinct sets of patients with predictions. In particular, introducing the RMD features into a combined classification model increased the fraction of diagnosed patients by 50 percentage points (at 20% FDR). Furthermore, RMD was able to discriminate molecular subtypes and/or anatomical site of six major cancers. The advantage of passenger mutations was upheld under high rates of false negative mutation calls and with exome sequencing, even though overall accuracy decreased. We suggest whole genome sequencing is valuable for classifying tumors because it captures global patterns emanating from mutational processes, which are informative of the underlying tumor biology.
| S-EPMC6483366 | biostudies-literature