from FOXREG import ComparisonTree
import pandas as pd
import warnings
warnings.filterwarnings("ignore")

start_path = "/Users/mosesapostol/Desktop/work_folder/Jan14_presentation/replication study"
pbData = pd.read_csv("{}/PBMC_study/QA_QC_PBMC_rss_values_Feb3.csv".format(start_path))
df_pbmc_RAS = pd.read_csv("{}/PBMC_study/obj_AUC_metadata_PBMC_2_Feb22.csv".format(start_path))
labels3 = pbData.columns[1:-1].tolist()


PBMC_cell_Types = [
    "B",
    "CD14+ Mono",
    "NK",
    "CD8 T",
    "FCGR3A+ Mono",
    "DC",
    "Memory CD4 T"
    
]
comparisonPBMC = ComparisonTree("Naive CD4 T", df_pbmc_RAS, "cell_clusters", pbData, 
                                PBMC_cell_Types, "Unnamed: 0", "{}/PBMC_study/3.5_AUCellThresholds_Info_PVMC_QA_QC.tsv".format(start_path))
comparisonPBMC.construct_tree()

regulon_sig_PB = {}
for i in PBMC_cell_Types:
    p_vals = comparisonPBMC.plotRSS_NMF(i, drawQuadrants=True, include_pvals=True)
    regulon_sig_PB[i] = p_vals

comparisonPBMC.plot_3dEmbedding()

FCGR3A+ Mono -0.3754152823920266
CD14+ Mono -0.3023255813953488
DC -0.22480620155038758
NK 0.16500553709856036
B 0.46843853820598
CD8 T 0.49058693244739754
Memory CD4 T 0.769656699889258
FCGR3A+ Mono
CD14+ Mono
DC
NK
B
CD8 T

['B', 'CD14+ Mono', 'NK', 'CD8 T', 'FCGR3A+ Mono', 'DC', 'Memory CD4 T']
['SPIB', 'RFX5', 'IRF8', 'NFE2L2', 'IRF1', 'RELB', 'CEBPA', 'FOSL2', 'IRF7', 'NFE2', 'KLF4', 'SPI1', 'POLE3', 'STAT1', 'IRF2', 'TBL1XR1', 'MAX', 'ATF3', 'KLF11', 'ELF1', 'TRIM69', 'YY1', 'REL', 'KLF12', 'GTF2B', 'UTP18', 'KLF13', 'CTCF', 'THAP1', 'DBP', 'XBP1', 'TBX21', 'HOXB2', 'ATF1', 'ELK3', 'POLR2A', 'BCLAF1', 'ZNF143', 'ETS1', 'FLI1', 'KLF2', 'ELF2', 'ATF4']
{'FCGR3A+ Mono': '#b3b62f', 'CD14+ Mono': '#b6ff4d', 'DC': '#260be7', 'NK': '#23d2b0', 'B': '#de48b8', 'CD8 T': '#88d843'}