## ----include = FALSE----------------------------------------------------------
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  eval = FALSE
)

## ----setup--------------------------------------------------------------------
# library(unitcm)

## ----search-basic-------------------------------------------------------------
# # Free-text search across all fields
# hits <- search_target2np(search = "quercetin")
# hits
# 
# # Exact-match by gene symbol
# tp53 <- search_target2np(
#   search = "TP53",
#   search_field = "gene_symbol",
#   search_mode = "exact"
# )
# tp53
# attr(tp53, "total")

## ----search-filters-----------------------------------------------------------
# # Combine filters
# results <- search_target2np(
#   search = "curcumin",
#   search_field = "compound_name",
#   source_db = "BindingDB",
#   target_organism = "Homo sapiens",
#   activity_type = "IC50"
# )
# results

## ----filter-options-----------------------------------------------------------
# # What filter values exist?
# opts <- fetch_target2np_filters()
# opts$source_db
# opts$target_organism
# opts$activity_type
# 
# # Global database statistics
# stats <- fetch_target2np_stats()
# stats$total_records
# stats$source_db_distribution

## ----detail-------------------------------------------------------------------
# detail <- get_target2np(1)
# detail$compound_name
# detail$gene_symbol
# detail$activity_value
# detail$activity_units
# detail$pmid

## ----batch--------------------------------------------------------------------
# batch <- batch_target2np(c("TP53", "BRCA1", "EGFR", "VEGFA"))
# batch
# attr(batch, "queries_matched")
# attr(batch, "queries_not_found")
# 
# # UniProt-based batch
# batch_up <- batch_target2np(
#   c("P04637", "P38398"),
#   id_type = "uniprot_id"
# )

## ----drugclip-----------------------------------------------------------------
# # High-confidence predictions for quercetin
# dc_high <- search_target2np_drugclip(
#   search = "quercetin",
#   search_field = "compound_name",
#   confidence = "high"
# )
# dc_high
# 
# # Score-based filtering
# dc <- search_target2np_drugclip(
#   search = "EGFR",
#   search_field = "gene_symbol",
#   min_score = 0.7
# )
# dc

## ----sea----------------------------------------------------------------------
# # High-confidence SEA predictions
# sea_high <- search_target2np_sea(
#   search = "quercetin",
#   search_field = "compound_name",
#   confidence = "high"
# )
# sea_high
# 
# # Filter by adjusted p-value
# sea <- search_target2np_sea(
#   search = "TP53",
#   search_field = "gene_symbol",
#   max_pvalue = 0.01
# )
# sea

## ----multi-source-------------------------------------------------------------
# summary <- target2np_multi_source_summary(
#   search = "TP53",
#   search_field = "gene_symbol"
# )
# 
# # How many results per source?
# summary$source_counts
# 
# # Target overlap across data sources
# summary$target_overlap
# 
# # Confidence-level distribution for each source
# summary$confidence_distribution
# 
# # Compound-target pairs found in >= 2 sources
# summary$cross_validated
# 
# # Natural-language interpretation
# cat(summary$suggestion_text)

## ----aggregated---------------------------------------------------------------
# # Pairs seen in >= 3 databases
# agg <- aggregated_target2np(
#   search = "quercetin",
#   min_sources = 3
# )
# agg
# 
# # Include DrugCLIP/SEA prediction counts as additional sources
# agg_pred <- aggregated_target2np(
#   search = "quercetin",
#   min_sources = 2,
#   include_predictions = TRUE
# )
# agg_pred

## ----workflow-----------------------------------------------------------------
# # 1. Check experimental evidence
# exp <- search_target2np(
#   search = "quercetin",
#   search_field = "compound_name",
#   search_mode = "fuzzy",
#   all_pages = TRUE
# )
# nrow(exp)
# 
# # 2. Get multi-source summary in one call
# ms <- target2np_multi_source_summary(
#   search = "quercetin",
#   search_field = "compound_name",
#   search_mode = "fuzzy"
# )
# ms$source_counts
# ms$cross_validated
# 
# # 3. Batch-check the top cross-validated targets
# top_genes <- unique(vapply(
#   ms$cross_validated, `[[`, character(1), "gene_symbol"
# ))
# if (length(top_genes) > 0) {
#   batch_detail <- batch_target2np(top_genes)
#   batch_detail
# }