Bioconductor / Contributions

Contribute Packages to Bioconductor
134 stars 33 forks source link

IMPACC #2655

Closed luqingan closed 2 years ago

luqingan commented 2 years ago

Update the following URL to point to the GitHub repository of the package you wish to submit to Bioconductor

Confirm the following by editing each check box to '[x]'

I am familiar with the essential aspects of Bioconductor software management, including:

For questions/help about the submission process, including questions about the output of the automatic reports generated by the SPB (Single Package Builder), please use the #package-submission channel of our Community Slack. Follow the link on the home page of the Bioconductor website to sign up.

bioc-issue-bot commented 2 years ago

Hi @luqingan

Thanks for submitting your package. We are taking a quick look at it and you will hear back from us soon.

The DESCRIPTION file for this package is:

Package: IMPACC
Type: Package
Title: Fast and Interpretable Consensus Clustering via Minipatch Learning
Version: 0.99.0
Authors@R: person("Luqin", "Gan", email = "glq.gan@gmail.com",role = c("aut", "cre"))
Description: This package provides powerful methodologies for consensus clustering using minipatch learning with random or adaptive schemes. The methods provide interpretability in terms of feature importance and are particularly applicable to sparse, high-dimensional data sets common in bioinformatics. 
License: Artistic-2.0
Encoding: UTF-8
LazyData: false
Imports: mvtnorm, matrixStats, stats, cluster,SNFtool,knitr,nnet
LazyDataCompression:xz
Depends: R(>= 4.1.0)
VignetteBuilder: knitr
biocViews: SingleCell, Software, Clustering, RNASeq, DifferentialExpression,KEGG, Regression, FeatureExtraction
vjcitn commented 2 years ago

The vignette has long list of optimization trace. Should suppress. You should use SummarizedExperiment or other integrative containers in Bioconductor. Please revise. Do not use a list like

library(IMPACC)
data(yan)
yan$raw[1:3, 1:3]
##        GSM896803 GSM896804 GSM896805
## A1BG           8         6         2
## A1BGAS        24        18         4
## A1CF        1306      1072       828
yan$sc_cnt[1:3, 1:3]
##        GSM896803 GSM896804 GSM896805
## A1BG    3.169925  2.807355  1.584963
## A1BGAS  4.643856  4.247928  2.321928
## A1CF   10.352043 10.067434  9.695228
head(yan$sc_label)
## [1] "Oocyte " "Oocyte " "Oocyte " "Zygote " "Zygote " "Zygote "

Notice the trailing blanks in the cell type strings. Intended? Accidental?

Does the vignette reader need to see

impacc_multinomial = IMPACC(d=yan$sc_cnt,K = K,reps = 1,feature_evaluation = 'multinomial', verbose=FALSE)
## Burn-in stage
## # weights:  3 (2 variable)
## initial  value 15.249238 
## final  value 12.759554 
## converged
## # weights:  3 (2 variable)
## initial  value 15.249238 
## iter  10 value 10.231735
## iter  10 value 10.231735
## iter  10 value 10.231735
## final  value 10.231735 
## converged
## # weights:  3 (2 variable)
## initial  value 15.249238 
## final  value 12.092815 
## converged
## # weights:  3 (2 variable)
## initial  value 15.249238 
## final  value 10.908304 
## converged
## # weights:  3 (2 variable)
## initial  value 15.249238 
## final  value 9.906160 
## converged
## # weights:  3 (2 variable)
## initial  value 15.249238 
## iter  10 value 0.035134
## iter  20 value 0.005524
## iter  30 value 0.001722
## iter  40 value 0.000603
## iter  50 value 0.000226
## final  value 0.000098 
## converged
## # weights:  3 (2 variable)
## initial  value 15.249238 
## final  value 11.907750 
## converged
## # weights:  3 (2 variable)
## initial  value 15.249238 
## iter  10 value 4.080592
## final  value 4.078276 
## converged
## # weights:  3 (2 variable)
## initial  value 15.249238 
## iter  10 value 3.546823
## iter  20 value 3.460980
## iter  30 value 3.458233
## final  value 3.458233 
## converged
## # weights:  3 (2 variable)
## initial  value 15.249238 
## iter  10 value 1.243145
## iter  20 value 0.727943
## iter  30 value 0.586823
## iter  40 value 0.462228
## iter  50 value 0.368125
## iter  60 value 0.306748
## iter  70 value 0.264036
## iter  80 value 0.232274
## iter  90 value 0.207367
## iter 100 value 0.187116
## final  value 0.187116 
## stopped after 100 iterations
## # weights:  3 (2 variable)
## initial  value 15.249238 
## final  value 12.837630 
## converged
## # weights:  3 (2 variable)
## initial  value 15.249238 
## iter  10 value 10.021199
## iter  20 value 10.010808
## iter  30 value 10.009744
## iter  40 value 10.009324
## iter  50 value 10.009074
## iter  60 value 10.008905
## iter  70 value 10.008784
## iter  80 value 10.008693
## iter  90 value 10.008622

Please look carefully at guidelines for submission.

vjcitn commented 2 years ago

Will you be addressing these comments? For now I will close the issue; reopen when you have a response.