example_mESC.py

#!/usr/bin/env python
# coding: utf-8

import sys

import pandas as pd
import numpy as np
import pickle as pkl
import sklearn as skl
import sklearn.preprocessing

import matplotlib as mpl

import matplotlib.pyplot as plt

import cyclum
from cyclum import writer


input_file_mask = 'data/mESC/mesc-tpm'
output_file_mask = './results/mESC_original/mesc-tpm'


# ## Read data
# Here we have label, so we load both. However, the label is not used until evaluation.

# In[5]:


def preprocess(input_file_mask):
    """
    Read in data and perform log transform (log2(x+1)), centering (mean = 1) and scaling (sd = 1).
    """
    tpm = writer.read_df_from_binary(input_file_mask).T
    sttpm = pd.DataFrame(data=skl.preprocessing.scale(np.log2(tpm.values + 1)), index=tpm.index, columns=tpm.columns)
    
    label = pd.read_csv(input_file_mask + '-label.txt', sep="\t", index_col=0).T
    return sttpm, label

sttpm, label = preprocess(input_file_mask)

model = cyclum.core.PreloadCyclum2(sttpm.values)

pseudotime, rotation = model.train()