bfrmParam-class: Class '"bfrmParam"'

In Sage-Bionetworks/bfrm: Bayesian Factor Regression Modelling (bfrm)

Objects from the Class

Objects can be created by calls of the form new("bfrmParam", ...).

Slots

nobservations:

Object of class "numeric" ~~ total number of samples (observations) in data – SET AUTOMATICALLY BY bfrm or evolve FUNCTION CALL

nvariables:

Object of class "numeric" ~~ total number of varialbes (features) in data – SET AUTOMATICALLY BY bfrm or evolve FUNCTION CALL

nbinaryresponses:

Object of class "numeric" ~~ total number of binary response variables – SET AUTOMATICALLY BY bfrm or evolve FUNCTION CALL

ncategoricalresponses:

Object of class "numeric" ~~ total number of categorical response variables – SET AUTOMATICALLY BY bfrm or evolve FUNCTION CALL

nsurvivalresponses:

Object of class "numeric" ~~ total number of survival response variables – SET AUTOMATICALLY BY bfrm or evolve FUNCTION CALL

ncontinuousresponses:

Object of class "numeric" ~~ total number of continuous response variables – SET AUTOMATICALLY BY bfrm or evolve FUNCTION CALL

ndesignvariables:

Object of class "numeric" ~~ number of design covariates, including the intercept – SET AUTOMATICALLY BY bfrm or evolve FUNCTION CALL – default value is 1 if no design variables are passed

ncontrolvariables:

Object of class "numeric" ~~ total number of control, or "assay-artifact", covariates – SET AUTOMATICALLY BY bfrm or evolve FUNCTION CALL – default value is 0 if no control varialbes are passed

nlatentfactors:

Object of class "numeric" ~~ either (1) the number of latent factors in the model for static bfrm model; or (2) the starting number of latent factors in the model for evolutionary bfrm (evolve) model – SET AUTOMATICALLY BY bfrm or evolve FUNCTION CALL

datafile:

Object of class "character" ~~ name of the datafile passed to the bfrm binary – SET AUTOMATICALLY BY bfrm or evolve FUNCTION CALL

hfile:

Object of class "character" ~~ name of the file that contains the design and control variables passed to the bfrm binary – SET AUTOMATICALLY BY bfrm or evolve FUNCTION CALL

responsemaskfile:

Object of class "character" ~~ name of the file that indicates response masking passed to the bfrm binary – SET AUTOMATICALLY BY bfrm or evolve FUNCTION CALL

xmaskfile:

Object of class "character" ~~ name of the file that indicates masked variables in the data matrix passed to the bfrm binary – SET AUTOMATICALLY BY bfrm or evolve FUNCTION CALL

shapeofb:

Object of class "numeric" ~~ This parameter defines the constraints placed on the factor loading matrix B. Takes either 0 (no constraint) or 2 (upper triangular of B set to zero) as its value – default value is 2

nongaussianfactors:

Object of class "numeric" ~~ indicator as to whether a gaussian model (0) or Dirichlet Process (1) model is used for latent factors – default value is 1

priorpsia:

Object of class "numeric" ~~ hyper-parameter values for the inverse-Gamma(a,b) prior for elements of Psi, the vector of residual varialbes for all X varianbles – default value is 2 which is set for Affy gene expression data using rma log2

priorpsib:

Object of class "numeric" ~~ hyper-parameter values for the inverse-Gamma(a,b) prior for elements of Psi, the vector of residual varialbes for all X varianbles – default value is 0.005 which is set for Affy gene expression data using rma log2

priorsurvivalpsia:

Object of class "numeric" ~~ hyper-parameter values for the inverse-gamma(a,b) prior for residual variances of an included survival response variable; right censored survival data are modelled as log-normal, linear regressions – default value is 2

priorsurvivalpsib:

Object of class "numeric" ~~ hyper-parameter values for the inverse-gamma(a,b) prior for residual variances of an included survival response variable; right censored survival data are modelled as log-normal, linear regressions – default value is 0.5

priorrhomean:

Object of class "numeric" ~~ hyper-parameter values for the Beta(PriorRhoMean* PriorRhoN, (1-PriorRhoMean)*PriorRhoN) prior for the sparsity base rate parameters - the elements of the vector Rho – defaults value is 0.001

priorrhon:

Object of class "numeric" ~~ hyper-parameter values for the Beta(PriorRhoMean* PriorRhoN, (1-PriorRhoMean)*PriorRhoN) prior for the sparsity base rate parameters - the elements of the vector Rho – defaults value is 200

priorpimean:

Object of class "numeric" ~~ hyper-parameter values for the Beta(PriorPiMean* PriorPiN, (1-PriorPiMean)*PriorPiN) prior for the hierachical components of the prior on non-zero inclusion probabilities – default value is 0.9

priorpin:

Object of class "numeric" ~~ hyper-parameter values for the Beta(PriorPiMean* PriorPiN, (1-PriorPiMean)*PriorPiN) prior for the hierachical components of the prior on non-zero inclusion probabilities – default value is 10

priortaudesigna:

Object of class "numeric" ~~ hyper-parameter values for the inverse-Gamma(a,b) prior for the variances Tau of the design/control factor effects – default value is 5

priortaudesignb:

Object of class "numeric" ~~ hyper-parameter values for the inverse-Gamma(a,b) prior for the variances Tau of the design/control factor effects – default value is 1

priortauresponsebinarya:

Object of class "numeric" ~~ hyper-parameter values for the inverse-Gamma(a,b) prior for the variances Tau of the binary response factors – default value is 5

priortauresponsebinaryb:

Object of class "numeric" ~~ hyper-parameter values for the inverse-Gamma(a,b) prior for the variances Tau of the binary response factors – default value is 1

priortauresponsecategoricala:

Object of class "numeric" ~~ hyper-parameter values for the inverse-Gamma(a,b) prior for the variances Tau of the categorical response factors – default value is 5

priortauresponsecategoricalb:

Object of class "numeric" ~~ hyper-parameter values for the inverse-Gamma(a,b) prior for the variances Tau of the categorical response factors – default value is 1

priortauresponsesurvivala:

Object of class "numeric" ~~ hyper-parameter values for the inverse-Gamma(a,b) prior for the variances Tau in the of the survival response factors – default value is 5

priortauresponsesurvivalb:

Object of class "numeric" ~~ hyper-parameter values for the inverse-Gamma(a,b) prior for the variances Tau in the of the survival response factors – default value is 1

priortauresponsecontinuousa:

Object of class "numeric" ~~ hyper-parameter values for the inverse-Gamma(a,b) prior for the variances Tau of the continuous response factors – default value is 5

priortauresponsecontinuousb:

Object of class "numeric" ~~ hyper-parameter values for the inverse-Gamma(a,b) prior for the variances Tau of the continuous response factors – default value is 1

priortaulatenta:

Object of class "numeric" ~~ hyper-parameter values for the inverse-Gamma(a,b) prior of the variances Tau for the latent factors – default value is 5

priortaulatentb:

Object of class "numeric" ~~ hyper-parameter values for the inverse-Gamma(a,b) prior of the variances Tau for the latent factors – default value is 1

priorinterceptmean:

Object of class "numeric" ~~ prior mean for the intercept (baseline level) of X variables – default value is 8 based on prototype of Affy gene expression data

priorinterceptvar:

Object of class "numeric" ~~ prior variance for the intercept (baseline level) of X variables – default value is 100 based on prototype of Affy gene expression data

priorcontinuousmean:

Object of class "numeric" ~~ prior mean for the intercept (baseline) of any continuous response variables – default value is 0

priorcontinuousvar:

Object of class "numeric" ~~ prior variance for the intercept (baseline) of any continuous response variables – default value is 1

priorsurvivalmean:

Object of class "numeric" ~~ prior mean for the intercept (baseline) of any survival response variables – default value is 2

priorsurvivalvar:

Object of class "numeric" ~~ prior mean for the intercept (baseline) of any survival response variables – default value is 10

evol:

Object of class "numeric" ~~ indicator for evolutionary mode – SET AUTOMATICALLY BY bfrm (0) or evolve (1) FUNCTION CALL

evolvarin:

Object of class "numeric" ~~ number of variables used to initialize the evolutionary analysis – SET AUTOMATICALLY BY evolve FUNCTION CALL

evolvarinfile:

Object of class "character" ~~ indices of the variables included in the initializing set – SET AUTOMATICALLY BY evolve FUNCTION CALL – default value is 1 (first variable in X matrix)

evolincludevariablethreshold:

Object of class "numeric" ~~ threshold for bringing a new variables into the model – default value is 0.75

evolincludefactorthreshold:

Object of class "numeric" ~~ threshold for adding a new latent factor into the model – default value is 0.75

evolminiumvariablesinfactor:

Object of class "numeric" ~~ minimum number of variables (genes) showing significant association with a factor in order for the factor to be included in the model – default value is 5

evolmaximumfactors:

Object of class "numeric" ~~ maximum number of latent factors that the final model can have – default value is 5

evolmaximumvariables:

Object of class "numeric" ~~ maximum number of variables the final model can have – default value is 100

evolmaximumvariablesperiteration:

Object of class "numeric" ~~ maximum number of variables that can be added to the model at each iteration – default value is 5

evolmaximumvariablesperfactor:

Object of class "numeric" ~~ maximum number of variables that can be weighted on any one factor – default value is 15

inclusionmethod:

Object of class "numeric" ~~ default value is 1

burnin:

Object of class "numeric" ~~ number of burn-in iterations in the MCMC – default value is 2000

nmcsamples:

Object of class "numeric" ~~ number of MCMC iterations – default value is 5000

printiteration:

Object of class "numeric" ~~ number defining how often MCMC iterations are printed to screen – default value is 100

prioralphaa:

Object of class "numeric" ~~ prior parameters for the Gamma prior for Alpha – default value is 1

prioralphab:

Object of class "numeric" ~~ prior parameters for the Gamma prior for Alpha – default value is 1

See Also

model classes

bfrmModel, evolveModel

methods

bfrm, projection

model results

bfrmResult

Examples

showClass("bfrmParam")

Sage-Bionetworks/bfrm documentation built on May 9, 2019, 12:11 p.m.