CRAVAT 4: Cancer-Related Analysis of Variants Toolkit

Masica, David L.; Douville, Christopher; Tokheim, Collin; Bhattacharya, Rohit; Kim, RyangGuk; Moad, Kyle; Ryan, Michaël; Karchin, Rachel

doi:10.1158/0008-5472.can-17-0338

Cited by 54 publications

(38 citation statements)

References 17 publications

(17 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Following the ranking of the predicted driver mutations, based on vectors of features, CHASM can predict how the mutation acts in tumorigenesis. The subsequently developed cancer-related analysis of variants toolkit (CRAVAT) is a suite of tools to interpret nonsynonymous mutations, including their mapping, annotation, impact, interpretation, and possible structural consequences [169]. Some software tools, such as Quaternary Protein Amino acid Clustering (QuartPAC) [170], identify statistically significant mutational clustering in 3D protein space, i.e., energy states, through combining available protein structures and mutational data in the COSMIC database.…”

Section: The Concept Of Driver Mutationsmentioning

confidence: 99%

Review: Precision medicine and driver mutations: Computational methods, functional assays and conformational principles for interpreting cancer drivers

et al. 2019

View full text Add to dashboard Cite

At the root of the so-called precision medicine or precision oncology, which is our focus here, is the hypothesis that cancer treatment would be considerably better if therapies were guided by a tumor’s genomic alterations. This hypothesis has sparked major initiatives focusing on whole-genome and/or exome sequencing, creation of large databases, and developing tools for their statistical analyses—all aspiring to identify actionable alterations, and thus molecular targets, in a patient. At the center of the massive amount of collected sequence data is their interpretations that largely rest on statistical analysis and phenotypic observations. Statistics is vital, because it guides identification of cancer-driving alterations. However, statistics of mutations do not identify a change in protein conformation; therefore, it may not define sufficiently accurate actionable mutations, neglecting those that are rare. Among the many thematic overviews of precision oncology, this review innovates by further comprehensively including precision pharmacology, and within this framework, articulating its protein structural landscape and consequences to cellular signaling pathways. It provides the underlying physicochemical basis, thereby also opening the door to a broader community.

show abstract

Section: The Concept Of Driver Mutationsmentioning

confidence: 99%

Review: Precision medicine and driver mutations: Computational methods, functional assays and conformational principles for interpreting cancer drivers

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Functional computational prediction methods include Sorted Intolerant From Tolerant (SIFT) (Sim et al, 2012), PolyPhen-2 (Adzhubei et al, 2010), Mutation Assessor (Reva et al, 2011), MutationTaster (Schwarz et al, 2010), CONsensus DELeteriousness score of missense mutations (Condel) (Gonzalez-Perez and Lopez-Bigas, 2011), Protein Variation Effect Analyzer (PROVEAN) (Choi et al, 2012), and Functional Analysis Through Hidden Markov Models (FATHMM) (Shihab et al, 2013). Cancer-specific High-throughput Annotation of Somatic Mutations (CHASM) (Carter et al, 2009; Douville et al, 2013; Masica et al, 2017), Cancer Driver Annotation (CanDrA) (Mao et al, 2013), and FATHMM (Shihab et al, 2013). Many new approaches have recently addressed a problem of locating driver mutations within the non-coding genome regions (Piraino and Furney, 2016).…”

Section: Introductionmentioning

confidence: 99%

Integration of Random Forest Classifiers and Deep Convolutional Neural Networks for Classification and Biomolecular Modeling of Cancer Driver Mutations

Agajanian

Odeyemi

Verkhivker

2019

Front. Mol. Biosci.

View full text Add to dashboard Cite

Development of machine learning solutions for prediction of functional and clinical significance of cancer driver genes and mutations are paramount in modern biomedical research and have gained a significant momentum in a recent decade. In this work, we integrate different machine learning approaches, including tree based methods, random forest and gradient boosted tree (GBT) classifiers along with deep convolutional neural networks (CNN) for prediction of cancer driver mutations in the genomic datasets. The feasibility of CNN in using raw nucleotide sequences for classification of cancer driver mutations was initially explored by employing label encoding, one hot encoding, and embedding to preprocess the DNA information. These classifiers were benchmarked against their tree-based alternatives in order to evaluate the performance on a relative scale. We then integrated DNA-based scores generated by CNN with various categories of conservational, evolutionary and functional features into a generalized random forest classifier. The results of this study have demonstrated that CNN can learn high level features from genomic information that are complementary to the ensemble-based predictors often employed for classification of cancer mutations. By combining deep learning-generated score with only two main ensemble-based functional features, we can achieve a superior performance of various machine learning classifiers. Our findings have also suggested that synergy of nucleotide-based deep learning scores and integrated metrics derived from protein sequence conservation scores can allow for robust classification of cancer driver mutations with a limited number of highly informative features. Machine learning predictions are leveraged in molecular simulations, protein stability, and network-based analysis of cancer mutations in the protein kinase genes to obtain insights about molecular signatures of driver mutations and enhance the interpretability of cancer-specific classification models.

show abstract

“…The ClinGen Pathogenicity Calculator (Patel et al 2017) offers a comprehensive ACMG classification interface, but only works with a single variant at a time, lacks automation, and cannot batch-process variants. On the other end of the spectrum, CRAVAT (Masica et al 2017) can batch-process collections of variants, but pathogenicity is ranked based on machine learning-based VEST and CHASM scores (Carter et al 2009(Carter et al , 2013; in contrast, PeCanPIE provides more granular annotations and discrete ACMG-recommended evidence tags, which allow analysts to see and weigh these individual contributions to overall variant pathogenicity.…”

Section: Discussionmentioning

confidence: 99%

Pediatric Cancer Variant Pathogenicity Information Exchange (PeCanPIE): a cloud-based platform for curating and classifying germline variants

et al. 2019

View full text Add to dashboard Cite

show abstract

CRAVAT 4: Cancer-Related Analysis of Variants Toolkit

Cited by 54 publications

References 17 publications

Review: Precision medicine and driver mutations: Computational methods, functional assays and conformational principles for interpreting cancer drivers

Review: Precision medicine and driver mutations: Computational methods, functional assays and conformational principles for interpreting cancer drivers

Integration of Random Forest Classifiers and Deep Convolutional Neural Networks for Classification and Biomolecular Modeling of Cancer Driver Mutations

Pediatric Cancer Variant Pathogenicity Information Exchange (PeCanPIE): a cloud-based platform for curating and classifying germline variants

Contact Info

Product

Resources

About