Missing files for reproducing results

carpenter-singh-lab / 2022_Haghighi_NatureMethods

High-Dimensional Gene Expression and Morphology Profiles of Cells across 28,000 Genetic and Chemical Perturbations

BSD 3-Clause "New" or "Revised" License

46 stars 10 forks source link

Missing files for reproducing results #13

Open alonshpigler opened 1 year ago

alonshpigler commented 1 year ago

Hi,

Thanks for sharing this data along with the detailed analysis! I'm trying to reproduce the results from the paper, and found that there are some files are missing in order to do that. These files are loaded from the following workspace: "../JDR/".

For example, in the MoA prediction notebook:

rgcca_factors_ge=pd.read_csv("../JDR/results_CP_GE_cdrpbio/factors_rgcca_ge.txt",sep="\t").reset_index(drop=True).add_suffix('_ge')

Is there a possibility to add these to the repo?

In addition, the scripts for MoA clustering will also be beneficiary if shared.

Thanks!

shntnu commented 1 year ago

@alonshpigler thanks for your interest in our work and for pointing us to this missing component.

It appears that this folder was never committed to the repository, and we'd need to recreate it from scratch. I don't have an ETA on that right now.

We will loop back about the MOA clustering scripts.

MarziehHaghighi commented 1 year ago

MOA clustering scrips can indeed be found here and are not part of this repository. You will need to feed this the data provided in this benchmark into these scrips to generate the results in this paper!

shihanyu commented 1 year ago

yes， same problem miss JDR folder. when run rgcca_factors_cp=pd.read_csv("../JDR/results_CP_GE_lincs/factors_rgcca_cp.txt",sep="\t").reset_index(drop=True)