Somatic mutation detection and classification through probabilistic integration of clonal population information.
Ontology highlight
ABSTRACT:
SUBMITTER: Dorri F
PROVIDER: S-EPMC6355807 | biostudies-other | 2019
REPOSITORIES: biostudies-other
Publications
Somatic mutation detection and classification through probabilistic integration of clonal population information.
Dorri Fatemeh F Jewell Sean S Bouchard-Côté Alexandre A Shah Sohrab P SP
Communications biology 20190131
Somatic mutations are a primary contributor to malignancy in human cells. Accurate detection of mutations is needed to define the clonal composition of tumours whereby clones may have distinct phenotypic properties. Although analysis of mutations over multiple tumour samples from the same patient has the potential to enhance identification of clones, few analytic methods exploit the correlation structure across samples. We posited that incorporating clonal information into joint analysis over mu ...[more]
Similar Datasets
Project description:A cancer tumour consists of thousands of genetic mutations. Even after advancement in technology, the task of distinguishing genetic mutations, which act as driver for the growth of tumour with passengers (Neutral Genetic Mutations), is still being done manually. This is a time-consuming process where pathologists interpret every genetic mutation from the clinical evidence manually. These clinical shreds of evidence belong to a total of nine classes, but the criterion of classification is still unknown. The main aim of this research is to propose a multiclass classifier to classify the genetic mutations based on clinical evidence (i.e., the text description of these genetic mutations) using Natural Language Processing (NLP) techniques. The dataset for this research is taken from Kaggle and is provided by the Memorial Sloan Kettering Cancer Center (MSKCC). The world-class researchers and oncologists contribute the dataset. Three text transformation models, namely, CountVectorizer, TfidfVectorizer, and Word2Vec, are utilized for the conversion of text to a matrix of token counts. Three machine learning classification models, namely, Logistic Regression (LR), Random Forest (RF), and XGBoost (XGB), along with the Recurrent Neural Network (RNN) model of deep learning, are applied to the sparse matrix (keywords count representation) of text descriptions. The accuracy score of all the proposed classifiers is evaluated by using the confusion matrix. Finally, the empirical results show that the RNN model of deep learning has performed better than other proposed classifiers with the highest accuracy of 70%.
| S-EPMC8337154 | biostudies-literature
Project description:In patients with metastatic melanoma, the identification and validation of accurate prognostic biomarkers will assist rational treatment planning. Studies based on "-omics" technologies have focussed on a single high-throughput data type such as gene or microRNA transcripts. Occasionally, these features were evaluated in conjunction with limited clinico-pathologic data. With the increased availability of multiple data types, there is a pressing need to tease apart which of these sources contain the most valuable prognostic information. We evaluated and integrated several data types derived from the same tumor specimens in AJCC stage III melanoma patients - gene, protein, and microRNA expression as well as clinical, pathologic and mutation information - to determine their relative impact on prognosis. We used classification frameworks based on pre-validation and bootstrap multiple imputation classification to compare the prognostic power of each data source, both individually as well as integratively. We found that the prognostic utility of clinico-pathologic information was not out-performed by various "-omics" platforms. Rather, a combination of clinico-pathologic variables and mRNA expression data performed best. Furthermore, a patient-based classification analysis revealed that the prognostic accuracy of various data types was not the same for different patients, providing useful insights for ongoing developments in the individualized treatment of melanomas patients. SPECIAL NOTE: In this study, survival data were re-extracted from the MIA research database for all patients and brought up to date, revealing discrepancies affecting survival class in the case of four patients compared with the previous dataset (GSE53118: http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE53118). The current survival data are considered to be more accurate although the expression information has not changed. In addition, there were 5 samples (122, 144, 195, 264, and 358) for which gene expression information were not available at the time of analysis. However, the associated clinical information for these samples is provided since it was analysed elsewhere in the accompanying publication. Samples eligible for this study (n=84) were obtained from lymph node specimens (Melanoma Institute Australia (MIA) Biospecimen Bank) in which macroscopic tumor was observed, obtained from patients believed to be without distant metastases at the time of tumor banking based on clinical examination and computerised axial tomographic scanning of the brain, chest, abdomen and pelvis. Specimens were macro-dissected at time of banking and subsequently reviewed to meet minimum criteria for tumor cell content (>80%) and amount of necrosis (<30%). Linked clinical and pathologic data were obtained from the MIA research database. We previously analyzed the distribution of survival times in these samples and identified more favorable and less favorable groups as patients having time from surgery to death from melanoma greater than 4 years with no sign of relapse (n=25) or less than 1 year (n=22), respectively (Mann et al. 2013, PMID: 22931913). Since that publication, survival data have been re-extracted from the MIA research database for all patients and brought up to date, revealing discrepancies affecting survival class in the case of four patients compared with the previous dataset. The current survival data are considered to be more accurate. MRNA expression profiling and somatic mutation profiling, were performed as previously described in Mann et al. 2013 (PMID: 22931913).
2014-08-18 | E-GEOD-54467 | biostudies-arrayexpress
Project description:A major challenge for cancer pathologists is to determine whether a new tumor in a patient with cancer is a metastasis or an independent occurrence of the disease. In recent years numerous studies have evaluated pairs of tumor specimens to examine the similarity of the somatic characteristics of the tumors and to test for clonal relatedness. As the landscape of mutation testing has evolved a number of statistical methods for determining clonality have developed, notably for comparing losses of heterozygosity at candidate markers, and for comparing copy number profiles. Increasingly tumors are being evaluated for point mutations in panels of candidate genes using gene sequencing technologies. Comparison of the mutational profiles of pairs of tumors presents unusual methodological challenges: mutations at some loci are much more common than others; knowledge of the marginal mutation probabilities is scanty for most loci at which mutations might occur; the sample space of potential mutational profiles is vast. In this article we examine this problem and propose a test for clonal relatedness of a pair of tumors from a single patient. Using simulations, its properties are shown to be promising. The method is illustrated using several examples from the literature.
| S-EPMC4649945 | biostudies-literature
Project description:In patients with metastatic melanoma, the identification and validation of accurate prognostic biomarkers will assist rational treatment planning. Studies based on "-omics" technologies have focussed on a single high-throughput data type such as gene or microRNA transcripts. Occasionally, these features were evaluated in conjunction with limited clinico-pathologic data. With the increased availability of multiple data types, there is a pressing need to tease apart which of these sources contain the most valuable prognostic information. We evaluated and integrated several data types derived from the same tumor specimens in AJCC stage III melanoma patients - gene, protein, and microRNA expression as well as clinical, pathologic and mutation information - to determine their relative impact on prognosis. We used classification frameworks based on pre-validation and bootstrap multiple imputation classification to compare the prognostic power of each data source, both individually as well as integratively. We found that the prognostic utility of clinico-pathologic information was not out-performed by various "-omics" platforms. Rather, a combination of clinico-pathologic variables and mRNA expression data performed best. Furthermore, a patient-based classification analysis revealed that the prognostic accuracy of various data types was not the same for different patients, providing useful insights for ongoing developments in the individualized treatment of melanomas patients. SPECIAL NOTE: In this study, survival data were re-extracted from the MIA research database for all patients and brought up to date, revealing discrepancies affecting survival class in the case of four patients compared with the previous dataset (GSE53118: http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE53118). The current survival data are considered to be more accurate although the expression information has not changed. In addition, there were 5 samples (122, 144, 195, 264, and 358) for which gene expression information were not available at the time of analysis. However, the associated clinical information for these samples is provided since it was analysed elsewhere in the accompanying publication.
2014-08-18 | GSE54467 | GEO
Project description:Background TP53 is a very common tumor suppressor gene and has implicated in various cancers. A systematic immunological analysis of TP53 somatic mutation classification in multiple cancers is still lacking. Methods To assess the immunological value of TP53 somatic mutation classification in various cancers, we integrated a series of bioinformatics methods to analyze the role of TP53 gene across the public databases, such as UCSC Xena, Cancer Cell Line Encyclopedia (CCLE), Ensembl, and Genotype−Tissue Expression (GTEx). Results The results revealed that the TP53 expression level had significant difference in tumor tissues and normal tissues, and it had a high expression level in most malignant tumors. Moreover, the missense mutation is the most common type of TP53 mutation in most cancers. In addition, the Cox proportional hazards model analysis and Kaplan−Meier (KM) survival analysis demonstrated that the TP53 expression is a high-risk factor in brain lower-grade glioma (LGG), prostate adenocarcinoma (PRAD), and uterine carcinosarcoma (UCS), which is opposite in uterine corpus endometrial carcinoma (UCEC). Besides, compared to the TP53 nontruncating mutation classification samples, we found that TP53 truncating mutation samples had lower TP53 expression levels in certain types of cancer. Notably, TP53 was associated with the mismatch repair (MMR) gene in some cancers which contained truncating or nontruncating mutation. Based on the classification of truncating or nontruncating mutation, we also discovered that TP53 expression was positively or negatively correlated with the immune score, stromal score, and the levels of immune cell infiltration in different cancers. Conclusions Our research reveals an overarching landscape of immunological value on TP53 status in various malignant tumors. According to our results, we demonstrate that TP53 also plays an immunological role in various cancers.
| S-EPMC9940963 | biostudies-literature
Project description:In patients with metastatic melanoma, the identification and validation of accurate prognostic biomarkers will assist rational treatment planning. Studies based on "-omics" technologies have focussed on a single high-throughput data type such as gene or microRNA transcripts. Occasionally, these features were evaluated in conjunction with limited clinico-pathologic data. With the increased availability of multiple data types, there is a pressing need to tease apart which of these sources contain the most valuable prognostic information. We evaluated and integrated several data types derived from the same tumor specimens in AJCC stage III melanoma patients - gene, protein, and microRNA expression as well as clinical, pathologic and mutation information - to determine their relative impact on prognosis. We used classification frameworks based on pre-validation and bootstrap multiple imputation classification to compare the prognostic power of each data source, both individually as well as integratively. We found that the prognostic utility of clinico-pathologic information was not out-performed by various "-omics" platforms. Rather, a combination of clinico-pathologic variables and mRNA expression data performed best. Furthermore, a patient-based classification analysis revealed that the prognostic accuracy of various data types was not the same for different patients, providing useful insights for ongoing developments in the individualized treatment of melanomas patients. SPECIAL NOTE: In this study, survival data were re-extracted from the MIA research database for all patients and brought up to date, revealing discrepancies affecting survival class in the case of four patients compared with the previous dataset (GSE53118: http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE53118). The current survival data are considered to be more accurate although the expression information has not changed. In addition, there were 5 samples (122, 144, 195, 264, and 358) for which gene expression information were not available at the time of analysis. However, the associated clinical information for these samples is provided since it was analysed elsewhere in the accompanying publication. Samples eligible for this study (n=84) were obtained from lymph node specimens (Melanoma Institute Australia (MIA) Biospecimen Bank) in which macroscopic tumor was observed, obtained from patients believed to be without distant metastases at the time of tumor banking based on clinical examination and computerised axial tomographic scanning of the brain, chest, abdomen and pelvis. Specimens were macro-dissected at time of banking and subsequently reviewed to meet minimum criteria for tumor cell content (>80%) and amount of necrosis (<30%). Linked clinical and pathologic data were obtained from the MIA research database. We previously analyzed the distribution of survival times in these samples and identified more favorable and less favorable groups as patients having time from surgery to death from melanoma greater than 4 years with no sign of relapse (n=25) or less than 1 year (n=22), respectively (Mann et al. 2013, PMID: 22931913). Since that publication, survival data have been re-extracted from the MIA research database for all patients and brought up to date, revealing discrepancies affecting survival class in the case of four patients compared with the previous dataset. The current survival data are considered to be more accurate. MRNA expression profiling and somatic mutation profiling, were performed as previously described in Mann et al. 2013 (PMID: 22931913).
| S-ECPF-GEOD-54467 | biostudies-other
Project description:BACKGROUND:It is important to understand the motor deficits of children with Cerebral Palsy (CP). Our understanding of this motor disorder can be enriched by computational models of motor control. One crucial stage in generating movement involves combining uncertain information from different sources, and deficits in this process could contribute to reduced motor function in children with CP. Healthy adults can integrate previously-learned information (prior) with incoming sensory information (likelihood) in a close-to-optimal way when estimating object location, consistent with the use of Bayesian statistics. However, there are few studies investigating how children with CP perform sensorimotor integration. We compare sensorimotor estimation in children with CP and age-matched controls using a model-based analysis to understand the process. METHODS AND FINDINGS:We examined Bayesian sensorimotor integration in children with CP, aged between 5 and 12 years old, with Gross Motor Function Classification System (GMFCS) levels 1-3 and compared their estimation behavior with age-matched typically-developing (TD) children. We used a simple sensorimotor estimation task which requires participants to combine probabilistic information from different sources: a likelihood distribution (current sensory information) with a prior distribution (learned target information). In order to examine sensorimotor integration, we quantified how participants weighed statistical information from the two sources (prior and likelihood) and compared this to the statistical optimal weighting. We found that the weighing of statistical information in children with CP was as statistically efficient as that of TD children. CONCLUSIONS:We conclude that Bayesian sensorimotor integration is not impaired in children with CP and therefore, does not contribute to their motor deficits. Future research has the potential to enrich our understanding of motor disorders by investigating the stages of motor processing set out by computational models. Therapeutic interventions should exploit the ability of children with CP to use statistical information.
| S-EPMC5706703 | biostudies-literature
Project description:MotivationIdentification of small molecules in a biological sample remains a major bottleneck in molecular biology, despite a decade of rapid development of computational approaches for predicting molecular structures using mass spectrometry (MS) data. Recently, there has been increasing interest in utilizing other information sources, such as liquid chromatography (LC) retention time (RT), to improve identifications solely based on MS information, such as precursor mass-per-charge and tandem mass spectrometry (MS2).ResultsWe put forward a probabilistic modelling framework to integrate MS and RT data of multiple features in an LC-MS experiment. We model the MS measurements and all pairwise retention order information as a Markov random field and use efficient approximate inference for scoring and ranking potential molecular structures. Our experiments show improved identification accuracy by combining MS2 data and retention orders using our approach, thereby outperforming state-of-the-art methods. Furthermore, we demonstrate the benefit of our model when only a subset of LC-MS features has MS2 measurements available besides MS1.Availability and implementationSoftware and data are freely available at https://github.com/aalto-ics-kepaco/msms_rt_score_integration.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC8289373 | biostudies-literature
Project description:Analysing multiple cancer samples from an individual patient can provide insight into the way the disease evolves. Monitoring the expansion and contraction of distinct clones helps to reveal the mutations that initiate the disease and those that drive progression. Existing approaches for clonal tracking from sequencing data typically require the user to combine multiple tools that are not purpose-built for this task. Furthermore, most methods require a matched normal (non-tumour) sample, which limits the scope of application. We developed SuperFreq, a cancer exome sequencing analysis pipeline that integrates identification of somatic single nucleotide variants (SNVs) and copy number alterations (CNAs) and clonal tracking for both. SuperFreq does not require a matched normal and instead relies on unrelated controls. When analysing multiple samples from a single patient, SuperFreq cross checks variant calls to improve clonal tracking, which helps to separate somatic from germline variants, and to resolve overlapping CNA calls. To demonstrate our software we analysed 304 cancer-normal exome samples across 33 cancer types in The Cancer Genome Atlas (TCGA) and evaluated the quality of the SNV and CNA calls. We simulated clonal evolution through in silico mixing of cancer and normal samples in known proportion. We found that SuperFreq identified 93% of clones with a cellular fraction of at least 50% and mutations were assigned to the correct clone with high recall and precision. In addition, SuperFreq maintained a similar level of performance for most aspects of the analysis when run without a matched normal. SuperFreq is highly versatile and can be applied in many different experimental settings for the analysis of exomes and other capture libraries. We demonstrate an application of SuperFreq to leukaemia patients with diagnosis and relapse samples.
| S-EPMC7043783 | biostudies-literature
Project description:Accurate detection of somatic mutations is still a challenge in cancer analysis. Here we present NeuSomatic, the first convolutional neural network approach for somatic mutation detection, which significantly outperforms previous methods on different sequencing platforms, sequencing strategies, and tumor purities. NeuSomatic summarizes sequence alignments into small matrices and incorporates more than a hundred features to capture mutation signals effectively. It can be used universally as a stand-alone somatic mutation detection method or with an ensemble of existing methods to achieve the highest accuracy.
| S-EPMC6399298 | biostudies-literature