omicverse icon indicating copy to clipboard operation
omicverse copied to clipboard

self.bulk_seq_group in _bulk2single.py is defined but not use

Open hitwbt opened this issue 1 year ago • 0 comments

    def bulk_preprocess_lazy(self,)->None:
        """
        Preprocess the bulk data

        Arguments:
            group: The group of the bulk data. Default is None. It need to set to calculate the mean of each group.
        """

        print("......drop duplicates index in bulk data")
        self.bulk_data=data_drop_duplicates_index(self.bulk_data)
        print("......deseq2 normalize the bulk data")
        self.bulk_data=deseq2_normalize(self.bulk_data)
        print("......log10 the bulk data")
        self.bulk_data=np.log10(self.bulk_data+1)
        print("......calculate the mean of each group")
        if self.bulk_group is None:
            self.bulk_seq_group=self.bulk_data
            return None
        else:
            data_dg_v=self.bulk_data[self.bulk_group].mean(axis=1)
            data_dg=pd.DataFrame(index=data_dg_v.index)
            data_dg['group']=data_dg_v
            self.bulk_seq_group=data_dg
        return None

Thank you for developing the omicverse package. I have a little question in the process of learning single-cell interpolation. That is, in the bulk_preprocess_lazy() function of _bulk2single.py, You calculated the average bulk expression of self.bulk_seq_group based on self.bulk_group, but I didn't see how it worked in the follow-up work. Is the bulk expression necessary in the single-cell interpolation process?

hitwbt avatar Sep 29 '24 09:09 hitwbt