Function for primary code to perform co-expression analysis, with or without data transformation,
using mixture models. The output of `coseq_run`

is an S3 object of class `coseq`

.

1 2 3 |

`y` |
( |

`K` |
Number of clusters (a single value or a vector of values) |

`conds` |
Vector of length |

`norm` |
The type of estimator to be used to normalize for differences in
library size: (“ |

`model` |
Type of mixture model to use (“ |

`transformation` |
Transformation type to be used: “ |

`subset` |
Optional vector providing the indices of a subset of
genes that should be used for the co-expression analysis (i.e., row indices
of the data matrix |

`meanFilterCutoff` |
Value used to filter low mean normalized counts if desired (by default, set to a value of 50) |

`modelChoice` |
Criterion used to select the best model. For Gaussian mixture models,
“ |

`parallel` |
If |

`BPPARAM` |
Optional parameter object passed internally to |

`...` |
Additional optional parameters. |

An S3 object of class `coseq`

containing the following:

`results ` |
Object of class |

`model ` |
Model used, either |

`transformation ` |
Transformation used on the data |

`tcounts ` |
Transformed data using to estimate model |

`y_profiles ` |
Normalized profiles for use in plotting |

`norm ` |
Normalization factors used in the analysis |

Andrea Rau

1 2 3 4 5 6 7 8 9 10 | ```
## Simulate toy data, n = 300 observations
set.seed(12345)
countmat <- matrix(runif(300*4, min=0, max=500), nrow=300, ncol=4)
countmat <- countmat[which(rowSums(countmat) > 0),]
conds <- rep(c("A","B","C","D"), each=2)
## Run the Normal mixture model for K = 2,3,4
## The following are equivalent:
run <- coseq_run(y=countmat, K=2:4, iter=5, transformation="arcsin")
run <- coseq(y=countmat, K=2:4, iter=5, transformation="arcsin")
``` |

Questions? Problems? Suggestions? Tweet to @rdrrHQ or email at ian@mutexlabs.com.

All documentation is copyright its authors; we didn't write any of that.