@article{TEXTUAL,
      recid = {10230},
      author = {Yang, Xinan and Regan, Kelly and Huang, Yong and Zhang,  Qingbei and Li, Jianrong and Seiwert, Tanguy Y. and Cohen,  Ezra E. W. and Xing, H. Rosie and Lussier, Yves A.},
      title = {Single Sample Expression-Anchored Mechanisms Predict  Survival in Head and Neck Cancer},
      journal = {PLOS Computational Biology},
      address = {2012-01-26},
      number = {TEXTUAL},
      abstract = {&lt;p&gt;Gene expression signatures that are predictive of  therapeutic response or prognosis are increasingly useful  in clinical care; however, mechanistic (and intuitive)  interpretation of expression arrays remains an unmet  challenge. Additionally, there is surprisingly little gene  overlap among distinct clinically validated expression  signatures. These “causality challenges” hinder the  adoption of signatures as compared to functionally  well-characterized single gene biomarkers. To increase the  utility of multi-gene signatures in survival studies, we  developed a novel approach to generate “personal mechanism  signatures” of molecular pathways and functions from gene  expression arrays. FAIME, the Functional Analysis of  Individual Microarray Expression, computes mechanism scores  using rank-weighted gene expression of an individual  sample. By comparing head and neck squamous cell carcinoma  (HNSCC) samples with non-tumor control tissues, the  precision and recall of deregulated FAIME-derived  mechanisms of pathways and molecular functions are  comparable to those produced by conventional cohort-wide  methods (e.g. GSEA). The overlap of “&lt;em&gt;Oncogenic FAIME  Features of HNSCC&lt;/em&gt;” (statistically significant and  differentially regulated FAIME-derived genesets  representing GO functions or KEGG pathways derived from  HNSCC tissue) among three distinct HNSCC datasets  (pathways:46%, &lt;em&gt;p&lt;/em&gt;&lt;0.001) is more significant than  the gene overlap (genes:4%). These &lt;em&gt;Oncogenic FAIME  Features of HNSCC&lt;/em&gt; can accurately discriminate tumors  from control tissues in two additional HNSCC datasets  (&lt;em&gt;n&lt;/em&gt; = 35 and 91, F-accuracy = 100% and 97%,  empirical &lt;em&gt;p&lt;/em&gt;&lt;0.001, area under the receiver  operating characteristic curves = 99% and 92%), and  stratify recurrence-free survival in patients from two  independent studies (&lt;em&gt;p&lt;/em&gt; = 0.0018 and  &lt;em&gt;p&lt;/em&gt; = 0.032, log-rank). Previous approaches  depending on group assignment of individual samples before  selecting features or learning a classifier are limited by  design to discrete-class prediction. In contrast, FAIME  calculates mechanism profiles for individual patients  without requiring group assignment in validation sets.  FAIME is more amenable for clinical deployment since it  translates the gene-level measurements of each given sample  into pathways and molecular function profiles that can be  applied to analyze continuous phenotypes in clinical  outcome studies (e.g. survival time, tumor volume).&lt;/p&gt;},
      url = {http://knowledge.uchicago.edu/record/10230},
}