TY - JOUR
T1 - Breast cancer subtype predictors revisited
T2 - From consensus to concordance?
AU - Sontrop, HMJ
AU - Reinders, MJT
AU - Moerland, Perry D.
PY - 2016
Y1 - 2016
N2 - Background: At the molecular level breast cancer comprises a heterogeneous set of subtypes associated with clear differences in gene expression and clinical outcomes. Single sample predictors (SSPs) are built via a two-stage approach consisting of clustering and subtype predictor construction based on the cluster labels of individual cases. SSPs have been criticized because their subtype assignments for the same samples were only moderately concordant
(Cohen’s κ<0.6).
Methods: We propose a semi-supervised approach where for five datasets, consensus sets were constructed consisting of those samples that were concordantly subtyped by a number of different predictors. Next, nine subtype
predictors - three SSPs, three subtype classification models (SCMs) and three novel rule-based predictors based on the St. Gallen surrogate intrinsic subtype definitions (STGs) - were constructed on the five consensus sets and their
associated consensus subtype labels. The predictors were validated on a compendium of over 4,000 uniformly preprocessed Affymetrix microarrays. Concordance between subtype predictors was assessed using Cohen’s kappa
statistic.
Results: In this standardized setup, subtype predictors of the same type (either SCM, SSP, or STG) but with a different gene list and/or consensus training set were associated with almost perfect levels of agreement (median κ>0.8).
Interestingly, for a given predictor type a change in consensus set led to higher concordance than a change to another gene list. The more challenging scenario where the predictor type, gene list and training set were all different
resulted in predictors with only substantial levels of concordance (median κ=0.74) on independent validation data.
Conclusions: Our results demonstrate that for a given subtype predictor type stringent standardization of the preprocessing stage, combined with carefully devised consensus training sets, leads to predictors that show almost
perfect levels of concordance. However, predictors of a different type are only substantially concordant, despite reaching almost perfect levels of concordance on training data.
AB - Background: At the molecular level breast cancer comprises a heterogeneous set of subtypes associated with clear differences in gene expression and clinical outcomes. Single sample predictors (SSPs) are built via a two-stage approach consisting of clustering and subtype predictor construction based on the cluster labels of individual cases. SSPs have been criticized because their subtype assignments for the same samples were only moderately concordant
(Cohen’s κ<0.6).
Methods: We propose a semi-supervised approach where for five datasets, consensus sets were constructed consisting of those samples that were concordantly subtyped by a number of different predictors. Next, nine subtype
predictors - three SSPs, three subtype classification models (SCMs) and three novel rule-based predictors based on the St. Gallen surrogate intrinsic subtype definitions (STGs) - were constructed on the five consensus sets and their
associated consensus subtype labels. The predictors were validated on a compendium of over 4,000 uniformly preprocessed Affymetrix microarrays. Concordance between subtype predictors was assessed using Cohen’s kappa
statistic.
Results: In this standardized setup, subtype predictors of the same type (either SCM, SSP, or STG) but with a different gene list and/or consensus training set were associated with almost perfect levels of agreement (median κ>0.8).
Interestingly, for a given predictor type a change in consensus set led to higher concordance than a change to another gene list. The more challenging scenario where the predictor type, gene list and training set were all different
resulted in predictors with only substantial levels of concordance (median κ=0.74) on independent validation data.
Conclusions: Our results demonstrate that for a given subtype predictor type stringent standardization of the preprocessing stage, combined with carefully devised consensus training sets, leads to predictors that show almost
perfect levels of concordance. However, predictors of a different type are only substantially concordant, despite reaching almost perfect levels of concordance on training data.
KW - Breast cancer
KW - Subtype
KW - Single sample predictor
KW - Concordance
KW - Gene expression
UR - http://resolver.tudelft.nl/uuid:e98e1d4c-8bec-4d8b-b8b8-bb43cc568327
U2 - 10.1186/s12920-016-0185-6
DO - 10.1186/s12920-016-0185-6
M3 - Article
SN - 1755-8794
SP - 1
EP - 14
JO - BMC Medical Genomics
JF - BMC Medical Genomics
ER -