Estimate mash Prior Covariances and Mixture Weights

Build the mash prior covariance list U and mixture weights w from a {strong[, random, null]} SumStats collection. Split out of mashPipeline so the covariance-estimation chain lives in one place. The default builds every non-udr covariance component (canonical + pca + flash + flashNonneg) and refines them with mashr extreme deconvolution (cov_ed).

Usage

mashPriorCovariances(
  sumStatsList,
  alpha,
  vhat = NULL,
  components = c("canonical", "pca", "flash", "flashNonneg"),
  engine = c("covEd", "covUdr", "none"),
  nPcs = NULL,
  priorCovariances = NULL,
  priorComponents = NULL,
  inputScale = c("auto", "beta", "z"),
  mashDataArgs = MashDataOptions(),
  mashArgs = MashOptions(),
  setSeed = 999
)

Arguments

sumStatsList: Named list (or S4Vectors::SimpleList) with at least "strong" (the discovery set the covariances are learned on).
alpha: mash alpha.
vhat: Residual correlation matrix (V); typically from mashResidualCorrelation. NULL -> identity.
components: Data-driven covariance components, any of "canonical", "pca", "flash" (default cov_flash), "flashNonneg" (cov_flash(factors = "nonneg")). Built in that fixed order. May instead be a MashComponentParam record, which names the components and carries each one's options.
engine: Covariance-refinement engine, either a name or the matching constructor carrying that engine's settings. "covEd" (default; CovEdOptions – mashr's exported cov_ed() extreme deconvolution, whose default algorithm = "bovy" IS the Bovy et al. 2011 method, weights from a final mash()); "covUdr" (CovUdrOptions – udr ED / TED updates, returning weights directly – OPT-IN, known numerical issues, so not the default; UdFitOptions(unconstrained.update = "ted") additionally needs i.i.d. (z-scale) data); "none" to skip refinement.
nPcs: PCs seeded into cov_pca. Default ncol(Bhat) - 1.
priorCovariances: Optional caller-supplied prior U: a non-empty named list of nCond x nCond matrices, or a mashPriorCovariances result, which is unwrapped to its U. When supplied, the covariance chain is bypassed and only the mixture-weight fit runs.
priorComponents: Optional caller-supplied raw covariance components (a non-empty named list, e.g. the concatenated mashCovarianceComponents outputs, or a mashPriorCovariances result, which is unwrapped to its U). When supplied, these are refined by engine instead of being rebuilt internally – the mixture-prior pipeline where separate steps built the components. components / nPcs are then ignored. Distinct from priorCovariances, which bypasses the engine entirely.
inputScale: SumStats -> matrix conversion scale.
mashDataArgs: Extra arguments for mashr::mash_set_data(), built with MashDataOptions – for example zero_Bhat_Shat_reset or zero_Shat_reset. Bhat, Shat, alpha and V are supplied by pecotmr and are refused by the constructor.
mashArgs: Extra arguments for mashr::mash(), built with MashOptions – for example nullweight, optmethod or verbose. data, Ulist, outputlevel and seed are owned by pecotmr and are refused by the constructor.
setSeed: Integer seed, or NULL to leave the ambient RNG untouched.

Value

list(U, w, loglik): the covariance list, the mashr::get_estimated_pi() mixture weights, and the fit log-likelihood (NULL for the cov_ed engine).

Examples

data(qtlSumStatsMulticontextExample)
ss <- qtlSumStatsMulticontextExample
sumStatsList <- list(strong = ss, random = ss)
mashPriorCovariances(sumStatsList, alpha = 0)
#> Adding factor 1 to flash object...
#> Adding factor 2 to flash object...
#> Adding factor 3 to flash object...
#> Factor doesn't significantly increase objective and won't be added.
#> Wrapping up...
#> Done.
#> Backfitting 2 factors (tolerance: 8.94e-06)...
#>   Difference between iterations is within 1.0e+00...
#>   Difference between iterations is within 1.0e-01...
#>   Difference between iterations is within 1.0e-02...
#>   Difference between iterations is within 1.0e-03...
#>   Difference between iterations is within 1.0e-04...
#> Wrapping up...
#> Done.
#> Adding factor 1 to flash object...
#> Adding factor 2 to flash object...
#> Adding factor 3 to flash object...
#> Factor doesn't significantly increase objective and won't be added.
#> Wrapping up...
#> Done.
#> Backfitting 2 factors (tolerance: 8.94e-06)...
#>   Difference between iterations is within 1.0e+00...
#>   Difference between iterations is within 1.0e-01...
#>   Difference between iterations is within 1.0e-02...
#>   Difference between iterations is within 1.0e-03...
#> Wrapping up...
#> Done.
#>  - Computing 200 x 273 likelihood matrix.
#>  - Likelihood calculations took 0.02 seconds.
#>  - Fitting model with 273 mixture components.
#>  - Model fitting took 0.41 seconds.
#> $U
#> $U$ED_PCA_1
#>             brain     blood     muscle
#> brain  0.15289673 0.1351045 0.09075052
#> blood  0.13510450 0.2928071 0.14918350
#> muscle 0.09075052 0.1491835 0.17091815
#> 
#> $U$ED_PCA_2
#>                brain         blood        muscle
#> brain   7.071112e-02  3.869435e-06 -6.163860e-06
#> blood   3.869435e-06  7.074430e-02 -5.356393e-05
#> muscle -6.163860e-06 -5.356393e-05  7.079600e-02
#> 
#> $U$ED_tPCA
#>              brain       blood      muscle
#> brain  0.072756163 0.003235763 0.002527583
#> blood  0.003235763 0.075853371 0.003947439
#> muscle 0.002527583 0.003947439 0.073942083
#> 
#> $U$ED_tFLASH_default
#>              brain       blood      muscle
#> brain  0.071877036 0.001950940 0.002284472
#> blood  0.001950940 0.073990396 0.003889138
#> muscle 0.002284472 0.003889138 0.075466277
#> 
#> $U$ED_FLASH_default_1
#>            brain     blood    muscle
#> brain  0.1684507 0.1420732 0.1028400
#> blood  0.1420732 0.2772258 0.1494864
#> muscle 0.1028400 0.1494864 0.1789167
#> 
#> $U$ED_FLASH_default_2
#>                brain         blood        muscle
#> brain   7.072856e-02  1.459131e-05 -2.837483e-05
#> blood   1.459131e-05  7.072258e-02 -2.314856e-05
#> muscle -2.837483e-05 -2.314856e-05  7.075569e-02
#> 
#> $U$ED_tFLASH_nonneg
#>              brain       blood      muscle
#> brain  0.072149086 0.002133816 0.002382316
#> blood  0.002133816 0.073876114 0.003535475
#> muscle 0.002382316 0.003535475 0.074867554
#> 
#> $U$ED_FLASH_nonneg_1
#>             brain     blood     muscle
#> brain  0.16797922 0.1438778 0.09877292
#> blood  0.14387777 0.2835319 0.14610302
#> muscle 0.09877292 0.1461030 0.17101125
#> 
#> $U$ED_FLASH_nonneg_2
#>               brain        blood       muscle
#> brain  7.071068e-02 2.264767e-09 2.813069e-07
#> blood  2.264767e-09 7.071070e-02 2.422564e-06
#> muscle 2.813069e-07 2.422564e-06 7.101158e-02
#> 
#> $U$identity
#>      [,1] [,2] [,3]
#> [1,]    1    0    0
#> [2,]    0    1    0
#> [3,]    0    0    1
#> 
#> $U$brain
#>      [,1] [,2] [,3]
#> [1,]    1    0    0
#> [2,]    0    0    0
#> [3,]    0    0    0
#> 
#> $U$blood
#>      [,1] [,2] [,3]
#> [1,]    0    0    0
#> [2,]    0    1    0
#> [3,]    0    0    0
#> 
#> $U$muscle
#>      [,1] [,2] [,3]
#> [1,]    0    0    0
#> [2,]    0    0    0
#> [3,]    0    0    1
#> 
#> $U$equal_effects
#>      [,1] [,2] [,3]
#> [1,]    1    1    1
#> [2,]    1    1    1
#> [3,]    1    1    1
#> 
#> $U$simple_het_1
#>      [,1] [,2] [,3]
#> [1,] 1.00 0.25 0.25
#> [2,] 0.25 1.00 0.25
#> [3,] 0.25 0.25 1.00
#> 
#> $U$simple_het_2
#>      [,1] [,2] [,3]
#> [1,]  1.0  0.5  0.5
#> [2,]  0.5  1.0  0.5
#> [3,]  0.5  0.5  1.0
#> 
#> $U$simple_het_3
#>      [,1] [,2] [,3]
#> [1,] 1.00 0.75 0.75
#> [2,] 0.75 1.00 0.75
#> [3,] 0.75 0.75 1.00
#> 
#> 
#> $w
#>               null           ED_PCA_1           ED_PCA_2            ED_tPCA 
#>         0.67084039         0.00000000         0.00000000         0.00000000 
#>  ED_tFLASH_default ED_FLASH_default_1 ED_FLASH_default_2   ED_tFLASH_nonneg 
#>         0.00000000         0.00000000         0.00000000         0.00000000 
#>  ED_FLASH_nonneg_1  ED_FLASH_nonneg_2           identity              brain 
#>         0.00000000         0.00000000         0.00000000         0.00000000 
#>              blood             muscle      equal_effects       simple_het_1 
#>         0.00000000         0.01470376         0.31445585         0.00000000 
#>       simple_het_2       simple_het_3 
#>         0.00000000         0.00000000 
#> 
#> $loglik
#> NULL
#>

Usage

Arguments

Value

See also

Examples