get_ipython().run_cell_magic(
'R',
'-i metadata_filename -i project_id -i base_dir -i local_dir -i num_runs',
'\nsource(paste0(base_dir, \'/generic_expression_patterns_modules/DE_analysis.R\'))\n\n# Files created: "<local_dir>/DE_stats/DE_stats_simulated_data_SRP012656_<n>.txt"\nfor (i in 0:(num_runs-1)){\n simulated_data_filename <- paste(local_dir, \n "pseudo_experiment/selected_simulated_data_",\n project_id,\n "_", \n i,\n ".txt",\n sep = "")\n \n get_DE_stats_limma(metadata_filename,\n project_id, \n simulated_data_filename,\n "simulated",\n local_dir,\n i)\n}'
)
# ### Rank genes
# In[14]:
analysis_type = "DE"
template_DE_stats, simulated_DE_summary_stats = ranking.process_and_rank_genes_pathways(
template_DE_stats_filename,
local_dir,
num_runs,
project_id,
analysis_type,
col_to_rank_genes,
logFC_name,
pvalue_name,
)
# ### Gene summary table
# In[15]:
summary_gene_ranks = ranking.generate_summary_table(
template_DE_stats_filename, template_DE_stats, simulated_DE_summary_stats,
col_to_rank_genes, local_dir, 'gene', params)
summary_gene_ranks.head()
# In[13]:
analysis_type = "GSA"
template_GSEA_stats_filename = os.path.join(
local_dir,
"GSA_stats",
f"{enrichment_method}_stats_template_data_{project_id}_real.txt"
)
template_GSEA_stats, simulated_GSEA_summary_stats = ranking.process_and_rank_genes_pathways(
template_GSEA_stats_filename,
local_dir,
num_runs,
project_id,
analysis_type,
col_to_rank_pathways,
enrichment_method
)
# ## Pathway summary table
# In[14]:
# Create intermediate file: "<local_dir>/gene_summary_table_<col_to_rank_pathways>.tsv"
summary_pathway_ranks = ranking.generate_summary_table(
template_GSEA_stats_filename,
template_GSEA_stats,
