Skip to content

update column names in dyad_feature.parquet #55

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
AbhirupaGhosh merged 1 commit into from
Sep 21, 2026
Merged

update column names in dyad_feature.parquet #55

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
38 changes: 19 additions & 19 deletions R/feature_to_head.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,13 +43,13 @@
#' protein|gene --> struct:STRUCTURE
#' }
#'
#' The type prefix on each target keeps feature namespaces separate, so a
#' The type prefix on each feature keeps feature namespaces separate, so a
#' generic feature name cannot collide across scales downstream.
#'
#' The output edge list contains two columns:
#' \describe{
#' \item{source}{Protein-gene dyad identifier.}
#' \item{target}{Feature node identifier prefixed by feature type.}
#' \item{dyad}{Protein-gene dyad identifier.}
#' \item{feature}{Feature node identifier prefixed by feature type.}
#' }
#'
#' @return Invisibly returns the path to the generated
Expand Down Expand Up @@ -273,7 +273,7 @@ buildDyadFeatureMap <- function(
# =========================

# Collapse each protein/gene pair into a single "protein|gene" dyad id; this
# is the source node for every edge in the output network.
# is the dyad node for every edge in the output network.
DBI::dbExecute(
con,
"
Expand Down Expand Up @@ -452,20 +452,20 @@ buildDyadFeatureMap <- function(
# Build network edge queries
# =========================

# Each entry is a SELECT returning (source, target) rows that are UNIONed into
# Each entry is a SELECT returning (dyad, feature) rows that are UNIONed into
# the final edge list. In the joined queries below `pgd` aliases the
# `protein_gene_dyad` view, so `pgd.dyad` is the "protein|gene" dyad id.
edge_queries <- c(
"
SELECT DISTINCT
dyad AS source,
CONCAT('protein:', protein) AS target
dyad AS dyad,
CONCAT('protein:', protein) AS feature
FROM protein_gene_dyad
",
"
SELECT DISTINCT
dyad AS source,
CONCAT('gene:', gene) AS target
dyad AS dyad,
CONCAT('gene:', gene) AS feature
FROM protein_gene_dyad
"
)
Expand All @@ -480,8 +480,8 @@ buildDyadFeatureMap <- function(
edge_queries,
"
SELECT DISTINCT
pgd.dyad AS source,
CONCAT('struct:', sg.struct) AS target
pgd.dyad AS dyad,
CONCAT('struct:', sg.struct) AS feature
FROM protein_gene_dyad pgd
JOIN v_struct_genes sg
ON pgd.gene = sg.gene
Expand All @@ -499,8 +499,8 @@ buildDyadFeatureMap <- function(
edge_queries,
"
SELECT DISTINCT
pgd.dyad AS source,
CONCAT('pfam:', pf.feature) AS target
pgd.dyad AS dyad,
CONCAT('pfam:', pf.feature) AS feature
FROM protein_gene_dyad pgd
JOIN v_pfam pf
ON pgd.protein = pf.protein
Expand All @@ -518,8 +518,8 @@ buildDyadFeatureMap <- function(
edge_queries,
"
SELECT DISTINCT
pgd.dyad AS source,
CONCAT('cog:', cf.feature) AS target
pgd.dyad AS dyad,
CONCAT('cog:', cf.feature) AS feature
FROM protein_gene_dyad pgd
JOIN v_cog cf
ON pgd.protein = cf.protein
Expand All @@ -537,8 +537,8 @@ buildDyadFeatureMap <- function(
edge_queries,
"
SELECT DISTINCT
pgd.dyad AS source,
CONCAT('amr:', af.feature) AS target
pgd.dyad AS dyad,
CONCAT('amr:', af.feature) AS feature
FROM protein_gene_dyad pgd
JOIN v_amrfinder af
ON pgd.protein = af.protein
Expand All @@ -556,8 +556,8 @@ buildDyadFeatureMap <- function(
edge_queries,
"
SELECT DISTINCT
pgd.dyad AS source,
CONCAT('defense:', df.feature) AS target
pgd.dyad AS dyad,
CONCAT('defense:', df.feature) AS feature
FROM protein_gene_dyad pgd
JOIN v_defensecas df
ON pgd.protein = df.protein
Expand Down