Rawcopy: Improved copy number analysis with Affymetrix arrays

Mayrhofer, Markus; Viklund, Björn; Isaksson, Anders

doi:10.1038/srep36158

Cited by 59 publications

(54 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Raw SNP (Affymetrix 6) array data were analyzed using 'rawcopy' R library 35 . The copy number of individual genes were obtained from the segmentation file generated by 'rawcopy'.…”

Section: Copy Number Data Analysismentioning

confidence: 99%

Integrative omics data analysis uncovers biomarker genes and potential candidate drugs for G3 medulloblastoma

Guo

Cornick

et al. 2020

Preprint

View full text Add to dashboard Cite

Medulloblastoma (MB) is the most common malignant brain tumor in infants and children. Four molecular subtypes of MB are recognized: WNT, SHH, Group 3 (G3), and Group 4 (G4). Compared with WNT and SHH subtypes, G3 MBs exhibit significantly worse outcomes and higher metastatic rates, and there is no effective treatment yet. Moreover, G3 and G4 MBs are much more common in boys than girls, i.e., sex bias, which also plays important roles in cancer prognosis and drug response. However, the molecular mechanism of G3 remains unclear, and there are no well-identified biomarker genes associated with these phenotypes, i.e., worse survival rate, higher metastasis rate, and sex bias. In this exploratory study, we aim to identify potential biomarkers associated with the three phenotypes using integrative analysis of gene expression, methylation and copy number variation datasets. In the results, we identified a set of biomarker genes and linked them into a network signature. The network signature showed better performance in the separation of G3 MB patients into subtypes with a significant difference in terms of the three phenotypes. To identify potentially effective drugs for G3 MBs, a set of drugs with diverse targets were prioritized, which can potentially inhibit the network signature. These drugs or combinations thereof might be effective for G3 treatment.

show abstract

“…Raw SNP (Affymetrix 6) array data were analyzed using 'rawcopy' R library 35 . The copy number of individual genes were obtained from the segmentation file generated by 'rawcopy'.…”

Section: Copy Number Data Analysismentioning

confidence: 99%

Integrative omics data analysis uncovers biomarker genes and potential candidate drugs for G3 medulloblastoma

Guo

Cornick

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…For our initial tests we analyzed 12 samples of 5 neuroblastoma patients (material was either tumor, or disseminated tumor cells (DTCs)) on the Affymetrix CytoScan HD SNP array platform (Ambros et al, 2014). The resulting CEL files contain ∼ 2.8 Mio raw array intensity values which were converted into normalized log ratio (LRR) and B-allele frequency values (BAF) using Rawcopy, an open R package for processing Affymetrix microarray data (Mayrhofer et al, 2016). Rawcopy first calculates raw LRR and BAF values according to the following formulas where A and B are mean intensities of the respective SNPa probes (see (Mayrhofer et al, 2016) for details):…”

Section: Data Collection and Preprocessingmentioning

confidence: 99%

“…The encoded copy numbers at the probe positions were then evaluated against the manually curated truth-set. Rawcopy uses various built-in reference data precompiled from a large number (2875 samples, Supplementary Table 1 ( Mayrhofer et al, 2016)) of ethnically diverse samples, with variations also in technical quality to improve LRR and BAF normal-ization. Therefore, in the sense of training data, Rawcopy benefited from significantly more data compared to Deep SNP and the rest of the Deep Learning baselines that were only trained with 9 out of 12 available samples.…”

Section: Rawcopymentioning

confidence: 99%

“…Finally, by integrating attention-based localization layers, Deep SNP is capable of accurately pinpointing breakpoints without the need of using accurate labels for training and reduce the recall and increase breakpoint calling precision within the given genomic windows of 40,000 probes, compared to the general purpose state-of-the-art deep models. Though direct comparison is difficult, Deep SNP also compares well to biological tools such as Rawcopy (Mayrhofer et al, 2016) in predicting the presence of breakpoints.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep SNP: An End-to-end Deep Neural Network with Attention-based Localization for Break-point Detection in SNP Array Genomic data

Eghbal-zadeh

Fischer

Popitsch³

et al. 2018

Preprint

View full text Add to dashboard Cite

Diagnosis and risk stratification of cancer and many other diseases require the detection of genomic breakpoints as a prerequisite of calling copy number alterations (CNA). This, however, is still challenging and requires time-consuming manual curation. As deep-learning methods outperformed classical state-of-the-art algorithms in various domains and have also been successfully applied to life science problems including medicine and biology, we here propose Deep SNP, a novel Deep Neural Network to learn from genomic data. Specifically, we used a manually curated dataset from 12 genomic single nucleotide polymorphism array (SNPa) profiles as truth-set and aimed at predicting the presence or absence of genomic breakpoints, an indicator of structural chromosomal variations, in windows of 40,000 probes. We compare our results with wellknown neural network models as well as Rawcopy though this tool is designed to predict breakpoints and in addition genomic segments with high sensitivity. We show, that Deep SNP is capable of successfully predicting the presence or absence of a breakpoint in large genomic windows and outperforms state-of-the-art neural network models. Qualitative examples suggest that integration of a localization unit may enable breakpoint detection and prediction of genomic segments, even if the breakpoint coordinates were not provided for network training. These results warrant further evaluation of DeepSNP for breakpoint localization and subsequent calling of genomic segments.

show abstract

“…Breakpoint calling precision is increased within a given genomic window of probes compared with the general purpose state-of-the-art DNNs. Although direct comparison is difficult, DeepSNP also compares well with biological tools such as Rawcopy (Mayrhofer et al, 2016) in predicting the presence of breakpoints in this setting.…”

Section: Introductionmentioning

confidence: 99%

DeepSNP: An End-to-End Deep Neural Network with Attention-Based Localization for Breakpoint Detection in Single-Nucleotide Polymorphism Array Genomic Data

Eghbal-zadeh

Fischer

Popitsch³

et al. 2019

Journal of Computational Biology

View full text Add to dashboard Cite

Clinical decision-making in cancer and other diseases relies on timely and cost-effective genome-wide testing. Classical bioinformatic algorithms, such as Rawcopy, can support genomic analysis by calling genomic breakpoints and copy-number variations (CNVs), but often require manual data curation, which is error prone, time-consuming, and thus substantially increasing costs of genomic testing and hampering timely delivery of test results to the treating physician. We aimed to investigate whether deep learning algorithms can be used to learn from genome-wide single-nucleotide polymorphism array (SNPa) data and improve state-of-the-art algorithms. We developed, applied, and validated a novel deep neural network (DNN), DeepSNP. A manually curated data set of 50 SNPa analyses was used as truthset. We show that DeepSNP can learn from SNPa data and classify the presence or absence of genomic breakpoints within large genomic windows with high precision and recall. DeepSNP was compared with well-known neural network models as well as with Rawcopy. Moreover, the use of a localization unit indicates the ability to pinpoint genomic breakpoints despite their exact location not being provided while training. DeepSNP results demonstrate the potential of DNN architectures to learn from genomic SNPa data and encourage further adaptation for CNV detection in SNPa and other genomic data types.

show abstract

Rawcopy: Improved copy number analysis with Affymetrix arrays

Cited by 59 publications

References 21 publications

Integrative omics data analysis uncovers biomarker genes and potential candidate drugs for G3 medulloblastoma

Integrative omics data analysis uncovers biomarker genes and potential candidate drugs for G3 medulloblastoma

Deep SNP: An End-to-end Deep Neural Network with Attention-based Localization for Break-point Detection in SNP Array Genomic data

DeepSNP: An End-to-End Deep Neural Network with Attention-Based Localization for Breakpoint Detection in Single-Nucleotide Polymorphism Array Genomic Data

Contact Info

Product

Resources

About