Dataset Information

Characteristics and Validation Techniques for PCA-Based Gene-Expression Signatures.

ABSTRACT: Background. Many gene-expression signatures exist for describing the biological state of profiled tumors. Principal Component Analysis (PCA) can be used to summarize a gene signature into a single score. Our hypothesis is that gene signatures can be validated when applied to new datasets, using inherent properties of PCA. Results. This validation is based on four key concepts. Coherence: elements of a gene signature should be correlated beyond chance. UNIQUENESS:the general direction of the data being examined can drive most of the observed signal. Robustness: if a gene signature is designed to measure a single biological effect, then this signal should be sufficiently strong and distinct compared to other signals within the signature. Transferability: the derived PCA gene signature score should describe the same biology in the target dataset as it does in the training dataset. Conclusions. The proposed validation procedure ensures that PCA-based gene signatures perform as expected when applied to datasets other than those that the signatures were trained upon. Complex signatures, describing multiple independent biological components, are also easily identified.

SUBMITTER: Berglund AE

PROVIDER: S-EPMC5317117 | biostudies-literature | 2017

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Characteristics and Validation Techniques for PCA-Based Gene-Expression Signatures.

Berglund Anders E AE Welsh Eric A EA Eschrich Steven A SA

International journal of genomics 20170206

<i>Background</i>. Many gene-expression signatures exist for describing the biological state of profiled tumors. Principal Component Analysis (PCA) can be used to summarize a gene signature into a single score. Our hypothesis is that gene signatures can be validated when applied to new datasets, using inherent properties of PCA. <i>Results</i>. This validation is based on four key concepts. Coherence: elements of a gene signature should be correlated beyond chance.<h4>Uniqueness</h4>the general ...[more]

PMID: 28265563

Similar Datasets

Project description:Glioblastoma (GBM) heterogeneity in the genomic and phenotypic properties has potentiated personalized approach against specific therapeutic targets of each GBM patient. The Cancer Genome Atlas (TCGA) Research Network has been established the comprehensive genomic abnormalities of GBM, which sub-classified GBMs into 4 different molecular subtypes. The molecular subtypes could be utilized to develop personalized treatment strategy for each subtype. We applied a classifying method, NTP (Nearest Template Prediction) method to determine molecular subtype of each GBM patient and corresponding orthotopic xenograft animal model. The models were derived from GBM cells dissociated from patient's surgical sample. Specific drug candidates for each subtype were selected using an integrated pharmacological network database (PharmDB), which link drugs with subtype specific genes. Treatment effects of the drug candidates were determined by in vitro limiting dilution assay using patient-derived GBM cells primarily cultured from orthotopic xenograft tumors. The consistent identification of molecular subtype by the NTP method was validated using TCGA database. When subtypes were determined by the NTP method, orthotopic xenograft animal models faithfully maintained the molecular subtypes of parental tumors. Subtype specific drugs not only showed significant inhibition effects on the in vitro clonogenicity of patient-derived GBM cells but also synergistically reversed temozolomide resistance of MGMT-unmethylated patient-derived GBM cells. However, inhibitory effects on the clonogenicity were not totally subtype-specific. Personalized treatment approach based on genetic characteristics of each GBM could make better treatment outcomes of GBMs, although more sophisticated classifying techniques and subtype specific drugs need to be further elucidated. Gene expression profiling experiments were conducted for 25 patient-derived xenograft glioblastoma samples using Affymetrix Human Gene 1.0 ST arrays according to manufacturer's protocol.

Project description:BACKGROUND: Classical approaches to predicting patient clinical outcome via gene expression information are primarily based on differential expression of unrelated genes (single-gene approaches) or genes related by, for example, biologic pathway or function (gene-sets). Recently, network-based approaches utilising interaction information between genes have emerged. An open problem is whether such approaches add value to the more traditional methods of signature modelling. We explored this question via comparison of the most widely employed single-gene, gene-set, and network-based methods, using gene expression microarray data from two different cancers: melanoma and ovarian. We considered two kinds of network approaches. The first of these identifies informative genes using gene expression and network connectivity information combined, the latter drawn from prior knowledge of protein-protein interactions. The second approach focuses on identification of informative sub-networks (small networks of interacting proteins, again from prior knowledge networks). For all methods we performed 100 rounds of 5-fold cross-validation under 3 different classifiers. For network-based approaches, we considered two different protein-protein interaction networks. We quantified resulting patterns of misclassification and discussed the relative value of each relative to ongoing development of prognostic biomarkers. RESULTS: We found that single-gene, gene-set and network methods yielded similar error rates in melanoma and ovarian cancer data. Crucially, however, our novel and detailed patient-level analyses revealed that the different methods were correctly classifying alternate subsets of patients in each cohort. We also found that the network-based NetRank feature selection method was the most stable. CONCLUSIONS: Next-generation methods of gene expression signature modelling harness data from external networks and are foreshadowed as a standard mode of analysis. But what do they add to traditional approaches? Our findings indicate there is value in the way in which different subspaces of the patient sample are captured differently among the various methods, highlighting the possibility of 'combination' classifiers capable of identifying which patients will be more accurately classified by one particular method over another. We have seen this clearly for the first time because of our in-depth analysis at the level of individual patients.

Dataset Information

Characteristics and Validation Techniques for PCA-Based Gene-Expression Signatures.

Publications

Characteristics and Validation Techniques for PCA-Based Gene-Expression Signatures.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets