Predicting cancer type from tumour DNA signatures

Soh, Kee Pang; Szczurek, Ewa; Sakoparnig, Thomas; Beerenwinkel, Niko

doi:10.1186/s13073-017-0493-2

Cited by 53 publications

(39 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our study, we were able to obtain reasonable accuracy performances using the germline matrix only as an input. This suggests that germline variation may be more important than previously reported based on prior methods (15). More specifically, we found that breast cancer and colorectal cancer have the best performance using only germline information, suggesting that these two cancers probably confers higher heritability compared to others.…”

Section: Discussionsupporting

confidence: 44%

“…To help improve cancer diagnosis and targeted therapies, cancer type classification methods are continually being upgraded. Traditionally, the majority of classification methods based on DNA sequencing data has relied on studying single point somatic mutations with various regression models (15,39,40). Mutations involving insertions and deletions as well as germline mutations have been largely ignored due to the high dimensionality problem.…”

Section: Discussionmentioning

confidence: 99%

“…More recently, cancer classification methods have utilized mutational profiles. Somatic mutations were employed to distinguish 28 cancer types resulting in an overall accuracy of 49.4% suggesting somatic point mutations alone as individual variables may not be sufficient to classify cancer types (15) . In particular, insertions and deletions as well as germline variation have also been found to be associated with cancer (16,17).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep learning for cancer type classification

Zeng¹,

Mao

et al. 2019

Preprint

View full text Add to dashboard Cite

Genetic information is becoming more readily available and is increasingly being used to predict patient cancer types as well as their subtypes. Most classification methods thus far utilize somatic mutations as independent features for classification and are limited by study power. To address these limitations, we propose DeepCues, a deep learning model that utilizes convolutional neural networks to derive features from DNA sequencing data for disease classification and relevant gene discovery. Using whole-exome sequencing, germline variants and somatic mutations, including insertions and deletions, are interactively amalgamated as features. In this study, we applied DeepCues to a dataset from TCGA to classify seven different types of major cancers and obtained an overall accuracy of 77.6%. We compared DeepCues to conventional methods and demonstrated a significant overall improvement (p=8.8E-25). Using DeepCues, we found that the top 20 genes associated with breast cancer have a 40% overlap with the top 20 breast cancer genes in the COSMIC database. These data support DeepCues as a novel method to improve the representational resolution of both germline variants and somatic mutations interactively and their power in predicting cancer types, as well the genes involved in each cancer.

show abstract

Section: Discussionsupporting

confidence: 44%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning for cancer type classification

Zeng¹,

Mao

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…Previous work in the area of DNA-based tumour type identification has used targeted gene panel 40 and whole exome [41][42][43] sequencing strategies. The targeted gene-based approach described in Tothill 40 is able to discriminate a handful of tumour types that have distinctive driver gene profiles, and can identify known therapeutic response biomarkers, but does not have broader applicability to the problem of tumour typing.…”

Section: Discussionmentioning

confidence: 99%

A deep learning system can accurately classify primary and metastatic cancers based on patterns of passenger mutations

Jiao

Atwal

Polak

et al. 2017

Preprint

View full text Add to dashboard Cite

In cancer, the primary tumour's organ of origin and histopathology are the strongest determinants of its clinical behaviour, but in 3% of the time a cancer patient presents with metastatic tumour and no obvious primary. Challenges also arise when distinguishing a metastatic recurrence of a previously treated cancer from the emergence of a new one. Here we train a deep learning classifier to predict cancer type based on patterns of somatic passenger mutations detected in whole genome sequencing (WGS) of 2606 tumours representing 24 common cancer types. Our classifier achieves an accuracy of 91% on held-out tumor samples and 82% and 85% respectively on independent primary and metastatic samples, roughly double the accuracy of trained pathologists when presented with a metastatic tumour without knowledge of the primary. Surprisingly, adding information on driver mutations reduced classifier accuracy. Our results have immediate clinical applicability, underscoring how patterns of somatic passenger mutations encode the state of the cell of origin, and can inform future strategies to detect the source of cell-free circulating tumour DNA.

show abstract

“…The majority of studies involving DNA mutations have used mutations as individual variables. Soh et al [20] used somatic mutations derived from 100 representative genes to distinguish cancer types and the results concluded that using somatic point mutations alone as individual variables was not sufficient to classify cancer types. Despite the fact that mutations in many genes have been identified in cancer, it is not yet understood how these genes cumulatively interact in the development and progression of cancer.…”

Section: Related Workmentioning

confidence: 99%

Cancer classification and pathway discovery using non-negative matrix factorization

Zeng

Mao

et al. 2019

Journal of Biomedical Informatics

View full text Add to dashboard Cite

Extracting genetic information from a full range of sequencing data is important for understanding diseases. We propose a novel method to effectively explore the landscape of genetic mutations and aggregate them to predict cancer type. We used multinomial logistic regression, nonsmooth non-negative matrix factorization (nsNMF), and support vector machine (SVM) to utilize the full range of sequencing data, aiming at better aggregating genetic mutations and improving their power in predicting cancer types. Specifically, we introduced a classifier to distinguish cancer types using somatic mutations obtained from whole-exome sequencing data. Mutations were identified from multiple cancers and scored using SIFT, PP2, and CADD, and grouped at the individual gene level. The nsNMF was then applied to reduce dimensionality and to obtain coefficient and basis matrices. A feature matrix was derived from the obtained matrices to train a classifier for cancer type classification with the SVM model. We have demonstrated that the classifier was able to distinguish the cancer types with reasonable accuracy. In five-fold crossvalidations using mutation counts as features, the average prediction accuracy was 77.1% (SEM=0.1%), significantly outperforming baselines and outperforming models using mutation scores as features. Using the factor matrices derived from the nsNMF, we identified multiple genes and pathways that are significantly associated with each cancer type. This study presents a generic and complete pipeline to study the associations between somatic mutations and cancers. The discovered genes and pathways associated with each cancer type can lead to biological insights. The proposed method can be adapted to other studies for disease classification and pathway discovery.

show abstract

Predicting cancer type from tumour DNA signatures

Cited by 53 publications

References 61 publications

Deep learning for cancer type classification

Deep learning for cancer type classification

A deep learning system can accurately classify primary and metastatic cancers based on patterns of passenger mutations

Cancer classification and pathway discovery using non-negative matrix factorization

Contact Info

Product

Resources

About