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

# # T cell annotations
# 
# In this notebook, we upload cell type annotations assigned by our domain experts. These annotations were generated using markers and by interactive investigation of our .h5ad files.
# 
# As these are derived from our .h5ad files, we'll connect them to the HISE analysis chain by chaching those files and using `hisepy.upload.upload_files()`.

# In[1]:


import hisepy
from datetime import date


# For T cells, this was done in multiple steps. First, we clustered all T cells, then we used these original clusters to identify several T cell subsets for iterative clustering.
# 
# Here, we'll combine these steps to build the link in our reproducibility chain.

# In[2]:


in_files = [
    '70651e60-282b-4ed0-96f6-414547297232',  # Naive CD4 T cell .h5ad
    '1ad9302d-6fd5-49b0-be4c-8a08492c7cb7',  # MAIT CD8 T cell .h5ad
    '6c1dff43-ddc5-437b-8e3d-dd5a32553b16',  # CM CD8 T cell .h5ad
    'b671c53a-2698-41c1-a886-9ab939306716',  # EM CD8 T cell .h5ad
    '35b11bcf-7a45-4714-b470-9f7627d6fbbd',  # Treg cell .h5ad
    '5ae29893-5a77-4081-86d1-523713a237e6',  # Naive CD8 T cell .h5ad
    '90a71622-5713-47f7-82e8-18e164ca9454',  # Proliferating T cell .h5ad
    'e5ec7efd-a210-4b98-9f45-f95ab5e6cc83',  # gdT cell .h5ad
    'd33ef147-59db-4fb6-950c-1dd8af242d4f',  # ISG-high T cell .h5ad
    'a04b6a89-81ff-43ca-b0f8-0b1939f407f1'   # Other T cell .h5ad
]
hise_res = hisepy.reader.cache_files(in_files)


# In[8]:


out_files = [
    'annotations/pbmc_ref_t-cd4-naive_annotations_2024-03-05.csv',
    'annotations/pbmc_ref_t-mait_annotations_2024-03-05.csv',
    'annotations/pbmc_ref_t-cd8-cm_annotations_2024-03-05.csv',
    'annotations/pbmc_ref_t-cd8-em_annotations_2024-03-05.csv',
    'annotations/pbmc_ref_treg_annotations_2024-03-05.csv',
    'annotations/pbmc_ref_t-cd8-naive_annotations_2024-03-05.csv',
    'annotations/pbmc_ref_t-proliferating_annotations_2024-03-05.csv',
    'annotations/pbmc_ref_t-gd_annotations_2024-03-05.csv',
    'annotations/pbmc_ref_t-isg-high_annotations_2024-03-05.csv',
    'annotations/pbmc_ref_t-other_annotations_2024-03-05.csv'
]


# In[9]:


study_space_uuid = '64097865-486d-43b3-8f94-74994e0a72e0'
title = 'T annotations {d}'.format(d = date.today())


# In[10]:


hisepy.upload.upload_files(
    files = out_files,
    study_space_id = study_space_uuid,
    title = title,
    input_file_ids = in_files
)


# In[11]:


import session_info
session_info.show()


# In[ ]: