From f4e84c15a7484ca44715873cde138f4160bc5e88 Mon Sep 17 00:00:00 2001
From: Tony Wu <wu.anthon@northeastern.edu>
Date: Fri, 24 Oct 2025 16:17:22 -0400
Subject: [PATCH 01/17] initial trial of only filtering down to known
 phosphosites

---
 R/getSubnetworkFromIndra.R | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/R/getSubnetworkFromIndra.R b/R/getSubnetworkFromIndra.R
index ab3e232..f27b672 100644
--- a/R/getSubnetworkFromIndra.R
+++ b/R/getSubnetworkFromIndra.R
@@ -66,6 +66,9 @@ getSubnetworkFromIndra <- function(input,
     edges <- .constructEdgesDataFrame(res, input, protein_level_data)
     edges <- .filterEdgesDataFrame(edges, paper_count_cutoff, correlation_cutoff)
     nodes <- .constructNodesDataFrame(input, edges)
+    ptm_overlap <- calculatePTMOverlapAggregated(edges, nodes)
+    edges <- edges[ptm_overlap[paste(edges$source, edges$target, edges$interaction, sep = "-")] != "", ]
+    nodes <- nodes[nodes$id %in% c(edges$source, edges$target), ]
     warning(
         "NOTICE: This function includes third-party software components
         that are licensed under the BSD 2-Clause License. Please ensure to

From b5936625ab8eb1532f3e772310ed09728ceb87f2 Mon Sep 17 00:00:00 2001
From: Tony Wu <wu.anthon@northeastern.edu>
Date: Fri, 7 Nov 2025 11:07:04 -0500
Subject: [PATCH 02/17] adjust curation filtering

---
 R/getSubnetworkFromIndra.R | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/R/getSubnetworkFromIndra.R b/R/getSubnetworkFromIndra.R
index f27b672..cf5eb3d 100644
--- a/R/getSubnetworkFromIndra.R
+++ b/R/getSubnetworkFromIndra.R
@@ -69,6 +69,16 @@ getSubnetworkFromIndra <- function(input,
     ptm_overlap <- calculatePTMOverlapAggregated(edges, nodes)
     edges <- edges[ptm_overlap[paste(edges$source, edges$target, edges$interaction, sep = "-")] != "", ]
     nodes <- nodes[nodes$id %in% c(edges$source, edges$target), ]
+    if (filter_by_curation) {
+        for (i in seq(1, nrow(edges))) {
+            stmt_hash <- edges$statement_hash[i]
+            incorrect_count <- .get_incorrect_curation_count(stmt_hash, api_key)
+            edges$evidence_count[i] <- edges$evidence_count[i] - incorrect_count
+            Sys.sleep(0.1)
+        }
+        edges <- edges[edges$evidence_count >= evidence_count_cutoff, ]
+        nodes <- nodes[nodes$id %in% c(edges$source, edges$target), ]
+    }
     warning(
         "NOTICE: This function includes third-party software components
         that are licensed under the BSD 2-Clause License. Please ensure to

From a641336343077b063b34ba7abc37ee329bdb4333 Mon Sep 17 00:00:00 2001
From: Tony Wu <wu.anthon@northeastern.edu>
Date: Fri, 7 Nov 2025 11:07:26 -0500
Subject: [PATCH 03/17] make curation filtering more efficient

---
 R/utils_getSubnetworkFromIndra.R | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/R/utils_getSubnetworkFromIndra.R b/R/utils_getSubnetworkFromIndra.R
index 3f3a674..87d7430 100644
--- a/R/utils_getSubnetworkFromIndra.R
+++ b/R/utils_getSubnetworkFromIndra.R
@@ -123,16 +123,16 @@
             res
         )
     }
-    if (filter_by_curation) {
-        for (i in seq_along(res)) {
-            stmt_json <- fromJSON(res[[i]]$data$stmt_json)
-            stmt_hash <- stmt_json$matches_hash
-            incorrect_count <- .get_incorrect_curation_count(stmt_hash, api_key)
-            res[[i]]$data$evidence_count <- res[[i]]$data$evidence_count - incorrect_count
-            # Todo: Also subtract source_counts accordingly if requested
-            Sys.sleep(0.1)
-        }
-    }
+    # if (filter_by_curation) {
+    #     for (i in seq_along(res)) {
+    #         stmt_json <- fromJSON(res[[i]]$data$stmt_json)
+    #         stmt_hash <- stmt_json$matches_hash
+    #         incorrect_count <- .get_incorrect_curation_count(stmt_hash, api_key)
+    #         res[[i]]$data$evidence_count <- res[[i]]$data$evidence_count - incorrect_count
+    #         # Todo: Also subtract source_counts accordingly if requested
+    #         Sys.sleep(0.1)
+    #     }
+    # }
     res = Filter(
         function(statement) statement$data$evidence_count >= evidence_count_cutoff, 
         res

From 71feccc66e0faf4a3cf7d6d1b4b453d3199b99f1 Mon Sep 17 00:00:00 2001
From: Tony Wu <wu.anthon@northeastern.edu>
Date: Fri, 7 Nov 2025 12:01:28 -0500
Subject: [PATCH 04/17] fix statement hash problem

---
 R/getSubnetworkFromIndra.R | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/R/getSubnetworkFromIndra.R b/R/getSubnetworkFromIndra.R
index cf5eb3d..07af1fd 100644
--- a/R/getSubnetworkFromIndra.R
+++ b/R/getSubnetworkFromIndra.R
@@ -71,7 +71,7 @@ getSubnetworkFromIndra <- function(input,
     nodes <- nodes[nodes$id %in% c(edges$source, edges$target), ]
     if (filter_by_curation) {
         for (i in seq(1, nrow(edges))) {
-            stmt_hash <- edges$statement_hash[i]
+            stmt_hash <- edges$stmt_hash[i]
             incorrect_count <- .get_incorrect_curation_count(stmt_hash, api_key)
             edges$evidence_count[i] <- edges$evidence_count[i] - incorrect_count
             Sys.sleep(0.1)

From 5269fdc2299caa5e6a274591de0d429c503cbcbe Mon Sep 17 00:00:00 2001
From: Tony Wu <wu.anthon@northeastern.edu>
Date: Fri, 7 Nov 2025 12:12:05 -0500
Subject: [PATCH 05/17] fix curation bug

---
 R/getSubnetworkFromIndra.R | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/R/getSubnetworkFromIndra.R b/R/getSubnetworkFromIndra.R
index 07af1fd..3d2b738 100644
--- a/R/getSubnetworkFromIndra.R
+++ b/R/getSubnetworkFromIndra.R
@@ -76,7 +76,7 @@ getSubnetworkFromIndra <- function(input,
             edges$evidence_count[i] <- edges$evidence_count[i] - incorrect_count
             Sys.sleep(0.1)
         }
-        edges <- edges[edges$evidence_count >= evidence_count_cutoff, ]
+        edges <- edges[edges$evidenceCount >= evidence_count_cutoff, ]
         nodes <- nodes[nodes$id %in% c(edges$source, edges$target), ]
     }
     warning(

From 357e48becb828119b2e05d3c95d13dd1eb6cc766 Mon Sep 17 00:00:00 2001
From: Tony Wu <wu.anthon@northeastern.edu>
Date: Fri, 7 Nov 2025 12:18:42 -0500
Subject: [PATCH 06/17] get correct column for evidenceCount

---
 R/getSubnetworkFromIndra.R | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/R/getSubnetworkFromIndra.R b/R/getSubnetworkFromIndra.R
index 3d2b738..f56c59e 100644
--- a/R/getSubnetworkFromIndra.R
+++ b/R/getSubnetworkFromIndra.R
@@ -70,12 +70,12 @@ getSubnetworkFromIndra <- function(input,
     edges <- edges[ptm_overlap[paste(edges$source, edges$target, edges$interaction, sep = "-")] != "", ]
     nodes <- nodes[nodes$id %in% c(edges$source, edges$target), ]
     if (filter_by_curation) {
-        for (i in seq(1, nrow(edges))) {
-            stmt_hash <- edges$stmt_hash[i]
-            incorrect_count <- .get_incorrect_curation_count(stmt_hash, api_key)
-            edges$evidence_count[i] <- edges$evidence_count[i] - incorrect_count
+        incorrect_counts <- numeric(nrow(edges))
+        for (i in seq_len(nrow(edges))) {
+            incorrect_counts[i] <- .get_incorrect_curation_count(edges$stmt_hash[i], api_key)
             Sys.sleep(0.1)
         }
+        edges$evidenceCount <- edges$evidenceCount - incorrect_counts
         edges <- edges[edges$evidenceCount >= evidence_count_cutoff, ]
         nodes <- nodes[nodes$id %in% c(edges$source, edges$target), ]
     }

From f0743870a583798238af4b2097808ae827416cf6 Mon Sep 17 00:00:00 2001
From: Tony Wu <wu.anthon@northeastern.edu>
Date: Fri, 7 Nov 2025 12:29:51 -0500
Subject: [PATCH 07/17] get rid of na site temporarily

---
 R/getSubnetworkFromIndra.R | 1 +
 1 file changed, 1 insertion(+)

diff --git a/R/getSubnetworkFromIndra.R b/R/getSubnetworkFromIndra.R
index f56c59e..7ae374a 100644
--- a/R/getSubnetworkFromIndra.R
+++ b/R/getSubnetworkFromIndra.R
@@ -68,6 +68,7 @@ getSubnetworkFromIndra <- function(input,
     nodes <- .constructNodesDataFrame(input, edges)
     ptm_overlap <- calculatePTMOverlapAggregated(edges, nodes)
     edges <- edges[ptm_overlap[paste(edges$source, edges$target, edges$interaction, sep = "-")] != "", ]
+    edges <- edges[!is.na(edges$site),]
     nodes <- nodes[nodes$id %in% c(edges$source, edges$target), ]
     if (filter_by_curation) {
         incorrect_counts <- numeric(nrow(edges))

From d13da36b4308f94e5b57655444cd1c1e28b5ec85 Mon Sep 17 00:00:00 2001
From: Tony Wu <wu.anthon@northeastern.edu>
Date: Fri, 7 Nov 2025 14:58:05 -0500
Subject: [PATCH 08/17] fix bug with ptm adjustment

---
 R/getSubnetworkFromIndra.R | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/R/getSubnetworkFromIndra.R b/R/getSubnetworkFromIndra.R
index 7ae374a..27497dd 100644
--- a/R/getSubnetworkFromIndra.R
+++ b/R/getSubnetworkFromIndra.R
@@ -66,10 +66,12 @@ getSubnetworkFromIndra <- function(input,
     edges <- .constructEdgesDataFrame(res, input, protein_level_data)
     edges <- .filterEdgesDataFrame(edges, paper_count_cutoff, correlation_cutoff)
     nodes <- .constructNodesDataFrame(input, edges)
-    ptm_overlap <- calculatePTMOverlapAggregated(edges, nodes)
-    edges <- edges[ptm_overlap[paste(edges$source, edges$target, edges$interaction, sep = "-")] != "", ]
-    edges <- edges[!is.na(edges$site),]
-    nodes <- nodes[nodes$id %in% c(edges$source, edges$target), ]
+    if (nrow(edges[!is.na(edges$site), ]) > 0) {
+        ptm_overlap <- calculatePTMOverlapAggregated(edges, nodes)
+        edges <- edges[ptm_overlap[paste(edges$source, edges$target, edges$interaction, sep = "-")] != "", ]
+        edges <- edges[!is.na(edges$site),]
+        nodes <- nodes[nodes$id %in% c(edges$source, edges$target), ]
+    }
     if (filter_by_curation) {
         incorrect_counts <- numeric(nrow(edges))
         for (i in seq_len(nrow(edges))) {

From 8cf6fbf0e5ef2011633c5b71e14905d645b68aa8 Mon Sep 17 00:00:00 2001
From: Tony Wu <wu.anthon@northeastern.edu>
Date: Fri, 7 Nov 2025 15:23:48 -0500
Subject: [PATCH 09/17] fix ptm execution problem

---
 R/getSubnetworkFromIndra.R | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/R/getSubnetworkFromIndra.R b/R/getSubnetworkFromIndra.R
index 27497dd..1db77cd 100644
--- a/R/getSubnetworkFromIndra.R
+++ b/R/getSubnetworkFromIndra.R
@@ -66,7 +66,7 @@ getSubnetworkFromIndra <- function(input,
     edges <- .constructEdgesDataFrame(res, input, protein_level_data)
     edges <- .filterEdgesDataFrame(edges, paper_count_cutoff, correlation_cutoff)
     nodes <- .constructNodesDataFrame(input, edges)
-    if (nrow(edges[!is.na(edges$site), ]) > 0) {
+    if (nrow(nodes[!is.na(nodes$Site), ]) > 0) {
         ptm_overlap <- calculatePTMOverlapAggregated(edges, nodes)
         edges <- edges[ptm_overlap[paste(edges$source, edges$target, edges$interaction, sep = "-")] != "", ]
         edges <- edges[!is.na(edges$site),]

From 7ece0b8fcf827ee910b49b38a43ae9e7c20c1906 Mon Sep 17 00:00:00 2001
From: Tony Wu <wu.anthon@northeastern.edu>
Date: Tue, 24 Feb 2026 15:38:12 -0500
Subject: [PATCH 10/17] adjust filtering by curation as a separate subfunction

---
 R/getSubnetworkFromIndra.R       | 11 +----------
 R/utils_getSubnetworkFromIndra.R | 29 +++++++++++++++--------------
 2 files changed, 16 insertions(+), 24 deletions(-)

diff --git a/R/getSubnetworkFromIndra.R b/R/getSubnetworkFromIndra.R
index 1db77cd..9bf27e7 100644
--- a/R/getSubnetworkFromIndra.R
+++ b/R/getSubnetworkFromIndra.R
@@ -72,16 +72,7 @@ getSubnetworkFromIndra <- function(input,
         edges <- edges[!is.na(edges$site),]
         nodes <- nodes[nodes$id %in% c(edges$source, edges$target), ]
     }
-    if (filter_by_curation) {
-        incorrect_counts <- numeric(nrow(edges))
-        for (i in seq_len(nrow(edges))) {
-            incorrect_counts[i] <- .get_incorrect_curation_count(edges$stmt_hash[i], api_key)
-            Sys.sleep(0.1)
-        }
-        edges$evidenceCount <- edges$evidenceCount - incorrect_counts
-        edges <- edges[edges$evidenceCount >= evidence_count_cutoff, ]
-        nodes <- nodes[nodes$id %in% c(edges$source, edges$target), ]
-    }
+    subnetwork = .filterByCuration(nodes, edges, filter_by_curation)
     warning(
         "NOTICE: This function includes third-party software components
         that are licensed under the BSD 2-Clause License. Please ensure to
diff --git a/R/utils_getSubnetworkFromIndra.R b/R/utils_getSubnetworkFromIndra.R
index 87d7430..57d885f 100644
--- a/R/utils_getSubnetworkFromIndra.R
+++ b/R/utils_getSubnetworkFromIndra.R
@@ -99,15 +99,12 @@
 #' @param interaction_types interaction types to filter by
 #' @param evidence_count_cutoff number of evidence to filter on for each paper
 #' @param sources_filter list of sources to filter by. Default is NULL, i.e. no filter
-#' @param filter_by_curation logical, whether to filter out statements that
-#' have been curated as incorrect in INDRA.  Default is FALSE.
-#' @param api_key string of INDRA API key for accessing curated statements.
 #' @return filtered list of INDRA statements
 #' @importFrom jsonlite fromJSON
 #' @keywords internal
 #' @noRd
 .filterIndraResponse <- function(res, interaction_types, evidence_count_cutoff, 
-                                 sources_filter = NULL, filter_by_curation = FALSE, api_key = "") {
+                                 sources_filter = NULL) {
     if (!is.null(interaction_types)) {
         res = Filter(
             function(statement) statement$data$stmt_type %in% interaction_types, 
@@ -123,16 +120,6 @@
             res
         )
     }
-    # if (filter_by_curation) {
-    #     for (i in seq_along(res)) {
-    #         stmt_json <- fromJSON(res[[i]]$data$stmt_json)
-    #         stmt_hash <- stmt_json$matches_hash
-    #         incorrect_count <- .get_incorrect_curation_count(stmt_hash, api_key)
-    #         res[[i]]$data$evidence_count <- res[[i]]$data$evidence_count - incorrect_count
-    #         # Todo: Also subtract source_counts accordingly if requested
-    #         Sys.sleep(0.1)
-    #     }
-    # }
     res = Filter(
         function(statement) statement$data$evidence_count >= evidence_count_cutoff, 
         res
@@ -373,6 +360,20 @@
     return(edges)
 }
 
+.filterByCuration = function(nodes, edges, filter_by_curation) {
+    if (filter_by_curation) {
+        incorrect_counts <- numeric(nrow(edges))
+        for (i in seq_len(nrow(edges))) {
+            incorrect_counts[i] <- .get_incorrect_curation_count(edges$stmt_hash[i], api_key)
+            Sys.sleep(0.1)
+        }
+        edges$evidenceCount <- edges$evidenceCount - incorrect_counts
+        edges <- edges[edges$evidenceCount >= evidence_count_cutoff, ]
+        nodes <- nodes[nodes$id %in% c(edges$source, edges$target), ]
+    }
+    return(list(nodes = nodes, edges = edges))
+}
+
 #' Construct correlation matrix from MSstats
 #' @param protein_level_data output of dataProcess
 #' @importFrom tidyr pivot_wider

From 76cd92a9c055c9a30491667992a736169b525c38 Mon Sep 17 00:00:00 2001
From: Tony Wu <wu.anthon@northeastern.edu>
Date: Tue, 24 Feb 2026 15:39:09 -0500
Subject: [PATCH 11/17] fix curation code

---
 R/utils_getSubnetworkFromIndra.R | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/R/utils_getSubnetworkFromIndra.R b/R/utils_getSubnetworkFromIndra.R
index 57d885f..4b14fd0 100644
--- a/R/utils_getSubnetworkFromIndra.R
+++ b/R/utils_getSubnetworkFromIndra.R
@@ -68,9 +68,9 @@
 
 #' @importFrom httr GET status_code content
 #' @importFrom jsonlite fromJSON
-.get_incorrect_curation_count <- function(stmt_hash, api_key) {
+.get_incorrect_curation_count <- function(stmt_hash) {
     stmt_hash_char <- as.character(stmt_hash)
-    url <- paste0("https://db.indra.bio/curation/list/", stmt_hash_char, "?api_key=", api_key)
+    url <- paste0("https://db.indra.bio/curation/list/", stmt_hash_char)
 
     tryCatch({
         response <- GET(url)
@@ -364,7 +364,7 @@
     if (filter_by_curation) {
         incorrect_counts <- numeric(nrow(edges))
         for (i in seq_len(nrow(edges))) {
-            incorrect_counts[i] <- .get_incorrect_curation_count(edges$stmt_hash[i], api_key)
+            incorrect_counts[i] <- .get_incorrect_curation_count(edges$stmt_hash[i])
             Sys.sleep(0.1)
         }
         edges$evidenceCount <- edges$evidenceCount - incorrect_counts

From 405802c11dbd4b7b77a8972927a629a604398e55 Mon Sep 17 00:00:00 2001
From: Tony Wu <wu.anthon@northeastern.edu>
Date: Tue, 24 Feb 2026 15:40:47 -0500
Subject: [PATCH 12/17] update docs

---
 R/getSubnetworkFromIndra.R     | 4 +---
 man/exportNetworkToHTML.Rd     | 1 +
 man/generateCytoscapeConfig.Rd | 3 ++-
 man/getSubnetworkFromIndra.Rd  | 5 +----
 man/previewNetworkInBrowser.Rd | 8 +++++++-
 5 files changed, 12 insertions(+), 9 deletions(-)

diff --git a/R/getSubnetworkFromIndra.R b/R/getSubnetworkFromIndra.R
index 9bf27e7..faf4c52 100644
--- a/R/getSubnetworkFromIndra.R
+++ b/R/getSubnetworkFromIndra.R
@@ -32,7 +32,6 @@
 #' as "namespace:identifier", e.g. "HGNC:1234" or "CHEBI:4911".
 #' @param filter_by_curation logical, whether to filter out statements that
 #' have been curated as incorrect in INDRA.  Default is FALSE.
-#' @param api_key string of INDRA API key for accessing curated statements.
 #'
 #' @return list of 2 data.frames, nodes and edges
 #'
@@ -57,8 +56,7 @@ getSubnetworkFromIndra <- function(input,
                                    sources_filter = NULL,
                                    logfc_cutoff = NULL,
                                    force_include_other = NULL, 
-                                   filter_by_curation = FALSE, 
-                                   api_key = "") {
+                                   filter_by_curation = FALSE) {
     input <- .filterGetSubnetworkFromIndraInput(input, pvalueCutoff, logfc_cutoff, force_include_other)
     .validateGetSubnetworkFromIndraInput(input, protein_level_data, sources_filter, force_include_other)
     res <- .callIndraCogexApi(input$HgncId, force_include_other)
diff --git a/man/exportNetworkToHTML.Rd b/man/exportNetworkToHTML.Rd
index 2e9910a..d5f9a7d 100644
--- a/man/exportNetworkToHTML.Rd
+++ b/man/exportNetworkToHTML.Rd
@@ -9,6 +9,7 @@ exportNetworkToHTML(
   edges,
   filename = "network_visualization.html",
   displayLabelType = "id",
+  nodeFontSize = 12,
   ...
 )
 }
diff --git a/man/generateCytoscapeConfig.Rd b/man/generateCytoscapeConfig.Rd
index 07c70b8..fc6c562 100644
--- a/man/generateCytoscapeConfig.Rd
+++ b/man/generateCytoscapeConfig.Rd
@@ -10,7 +10,8 @@ generateCytoscapeConfig(
   display_label_type = "id",
   container_id = "network-cy",
   event_handlers = NULL,
-  layout_options = NULL
+  layout_options = NULL,
+  node_font_size = 12
 )
 }
 \arguments{
diff --git a/man/getSubnetworkFromIndra.Rd b/man/getSubnetworkFromIndra.Rd
index 94d27f9..8722e39 100644
--- a/man/getSubnetworkFromIndra.Rd
+++ b/man/getSubnetworkFromIndra.Rd
@@ -15,8 +15,7 @@ getSubnetworkFromIndra(
   sources_filter = NULL,
   logfc_cutoff = NULL,
   force_include_other = NULL,
-  filter_by_curation = FALSE,
-  api_key = ""
+  filter_by_curation = FALSE
 )
 }
 \arguments{
@@ -59,8 +58,6 @@ as "namespace:identifier", e.g. "HGNC:1234" or "CHEBI:4911".}
 
 \item{filter_by_curation}{logical, whether to filter out statements that
 have been curated as incorrect in INDRA.  Default is FALSE.}
-
-\item{api_key}{string of INDRA API key for accessing curated statements.}
 }
 \value{
 list of 2 data.frames, nodes and edges
diff --git a/man/previewNetworkInBrowser.Rd b/man/previewNetworkInBrowser.Rd
index 6dde024..d0ac40e 100644
--- a/man/previewNetworkInBrowser.Rd
+++ b/man/previewNetworkInBrowser.Rd
@@ -4,7 +4,13 @@
 \alias{previewNetworkInBrowser}
 \title{Preview network in browser}
 \usage{
-previewNetworkInBrowser(nodes, edges, displayLabelType = "id", ...)
+previewNetworkInBrowser(
+  nodes,
+  edges,
+  displayLabelType = "id",
+  nodeFontSize = 12,
+  ...
+)
 }
 \arguments{
 \item{nodes}{Data frame with node information}

From fcebec1206267ad1590e83f234260aad08294261 Mon Sep 17 00:00:00 2001
From: Tony Wu <wu.anthon@northeastern.edu>
Date: Tue, 24 Feb 2026 15:45:17 -0500
Subject: [PATCH 13/17] enable option to filter by ptm site

---
 R/getSubnetworkFromIndra.R       | 17 ++++++++---------
 R/utils_getSubnetworkFromIndra.R | 10 ++++++++++
 man/getSubnetworkFromIndra.Rd    |  7 ++++++-
 3 files changed, 24 insertions(+), 10 deletions(-)

diff --git a/R/getSubnetworkFromIndra.R b/R/getSubnetworkFromIndra.R
index faf4c52..027d426 100644
--- a/R/getSubnetworkFromIndra.R
+++ b/R/getSubnetworkFromIndra.R
@@ -32,6 +32,9 @@
 #' as "namespace:identifier", e.g. "HGNC:1234" or "CHEBI:4911".
 #' @param filter_by_curation logical, whether to filter out statements that
 #' have been curated as incorrect in INDRA.  Default is FALSE.
+#' @param filter_by_ptm_site logical, whether to filter edges based on whether the 
+#' site information from INDRA matches with the PTM site in the input.  Default is FALSE.  
+#' Only applicable for differential PTM abundance results.
 #'
 #' @return list of 2 data.frames, nodes and edges
 #'
@@ -56,7 +59,8 @@ getSubnetworkFromIndra <- function(input,
                                    sources_filter = NULL,
                                    logfc_cutoff = NULL,
                                    force_include_other = NULL, 
-                                   filter_by_curation = FALSE) {
+                                   filter_by_curation = FALSE,
+                                   filter_by_ptm_site = FALSE) {
     input <- .filterGetSubnetworkFromIndraInput(input, pvalueCutoff, logfc_cutoff, force_include_other)
     .validateGetSubnetworkFromIndraInput(input, protein_level_data, sources_filter, force_include_other)
     res <- .callIndraCogexApi(input$HgncId, force_include_other)
@@ -64,13 +68,8 @@ getSubnetworkFromIndra <- function(input,
     edges <- .constructEdgesDataFrame(res, input, protein_level_data)
     edges <- .filterEdgesDataFrame(edges, paper_count_cutoff, correlation_cutoff)
     nodes <- .constructNodesDataFrame(input, edges)
-    if (nrow(nodes[!is.na(nodes$Site), ]) > 0) {
-        ptm_overlap <- calculatePTMOverlapAggregated(edges, nodes)
-        edges <- edges[ptm_overlap[paste(edges$source, edges$target, edges$interaction, sep = "-")] != "", ]
-        edges <- edges[!is.na(edges$site),]
-        nodes <- nodes[nodes$id %in% c(edges$source, edges$target), ]
-    }
-    subnetwork = .filterByCuration(nodes, edges, filter_by_curation)
+    subnetwork = .filterByPtmSite(nodes, edges, filter_by_ptm_site)
+    subnetwork = .filterByCuration(subnetwork$nodes, subnetwork$edges, filter_by_curation)
     warning(
         "NOTICE: This function includes third-party software components
         that are licensed under the BSD 2-Clause License. Please ensure to
@@ -78,5 +77,5 @@ getSubnetworkFromIndra <- function(input,
         package or utilizing the results based on this package.
         See the LICENSE file for more details."
     )
-    return(list(nodes = nodes, edges = edges))
+    return(subnetwork)
 }
diff --git a/R/utils_getSubnetworkFromIndra.R b/R/utils_getSubnetworkFromIndra.R
index 4b14fd0..b398ebf 100644
--- a/R/utils_getSubnetworkFromIndra.R
+++ b/R/utils_getSubnetworkFromIndra.R
@@ -374,6 +374,16 @@
     return(list(nodes = nodes, edges = edges))
 }
 
+.filterByPtmSite = function(nodes, edges, filter_by_ptm_site) {
+    if (filter_by_ptm_site && nrow(nodes[!is.na(nodes$Site), ]) > 0) {
+        ptm_overlap <- calculatePTMOverlapAggregated(edges, nodes)
+        edges <- edges[ptm_overlap[paste(edges$source, edges$target, edges$interaction, sep = "-")] != "", ]
+        edges <- edges[!is.na(edges$site),]
+        nodes <- nodes[nodes$id %in% c(edges$source, edges$target), ]
+    }
+    return(list(nodes = nodes, edges = edges))
+}
+
 #' Construct correlation matrix from MSstats
 #' @param protein_level_data output of dataProcess
 #' @importFrom tidyr pivot_wider
diff --git a/man/getSubnetworkFromIndra.Rd b/man/getSubnetworkFromIndra.Rd
index 8722e39..a670d6e 100644
--- a/man/getSubnetworkFromIndra.Rd
+++ b/man/getSubnetworkFromIndra.Rd
@@ -15,7 +15,8 @@ getSubnetworkFromIndra(
   sources_filter = NULL,
   logfc_cutoff = NULL,
   force_include_other = NULL,
-  filter_by_curation = FALSE
+  filter_by_curation = FALSE,
+  filter_by_ptm_site = FALSE
 )
 }
 \arguments{
@@ -58,6 +59,10 @@ as "namespace:identifier", e.g. "HGNC:1234" or "CHEBI:4911".}
 
 \item{filter_by_curation}{logical, whether to filter out statements that
 have been curated as incorrect in INDRA.  Default is FALSE.}
+
+\item{filter_by_ptm_site}{logical, whether to filter edges based on whether the 
+site information from INDRA matches with the PTM site in the input.  Default is FALSE.  
+Only applicable for differential PTM abundance results.}
 }
 \value{
 list of 2 data.frames, nodes and edges

From d3fcc1012e7a1e7f7aa31826295f187dae506275 Mon Sep 17 00:00:00 2001
From: Tony Wu <wu.anthon@northeastern.edu>
Date: Tue, 24 Feb 2026 15:50:17 -0500
Subject: [PATCH 14/17] fix code

---
 R/getSubnetworkFromIndra.R | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/R/getSubnetworkFromIndra.R b/R/getSubnetworkFromIndra.R
index 027d426..536efab 100644
--- a/R/getSubnetworkFromIndra.R
+++ b/R/getSubnetworkFromIndra.R
@@ -64,7 +64,7 @@ getSubnetworkFromIndra <- function(input,
     input <- .filterGetSubnetworkFromIndraInput(input, pvalueCutoff, logfc_cutoff, force_include_other)
     .validateGetSubnetworkFromIndraInput(input, protein_level_data, sources_filter, force_include_other)
     res <- .callIndraCogexApi(input$HgncId, force_include_other)
-    res <- .filterIndraResponse(res, statement_types, evidence_count_cutoff, sources_filter, filter_by_curation, api_key)
+    res <- .filterIndraResponse(res, statement_types, evidence_count_cutoff, sources_filter)
     edges <- .constructEdgesDataFrame(res, input, protein_level_data)
     edges <- .filterEdgesDataFrame(edges, paper_count_cutoff, correlation_cutoff)
     nodes <- .constructNodesDataFrame(input, edges)

From c7ea894cea6ae692c511d88e4c137057c8e23427 Mon Sep 17 00:00:00 2001
From: Tony Wu <wu.anthon@northeastern.edu>
Date: Tue, 24 Feb 2026 17:31:05 -0500
Subject: [PATCH 15/17] coderabbit comments

---
 R/getSubnetworkFromIndra.R       | 2 +-
 R/utils_getSubnetworkFromIndra.R | 5 +++--
 R/visualizeNetworksWithHTML.R    | 2 ++
 man/exportNetworkToHTML.Rd       | 2 ++
 4 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/R/getSubnetworkFromIndra.R b/R/getSubnetworkFromIndra.R
index 536efab..09f1f30 100644
--- a/R/getSubnetworkFromIndra.R
+++ b/R/getSubnetworkFromIndra.R
@@ -69,7 +69,7 @@ getSubnetworkFromIndra <- function(input,
     edges <- .filterEdgesDataFrame(edges, paper_count_cutoff, correlation_cutoff)
     nodes <- .constructNodesDataFrame(input, edges)
     subnetwork = .filterByPtmSite(nodes, edges, filter_by_ptm_site)
-    subnetwork = .filterByCuration(subnetwork$nodes, subnetwork$edges, filter_by_curation)
+    subnetwork = .filterByCuration(subnetwork$nodes, subnetwork$edges, evidence_count_cutoff, filter_by_curation)
     warning(
         "NOTICE: This function includes third-party software components
         that are licensed under the BSD 2-Clause License. Please ensure to
diff --git a/R/utils_getSubnetworkFromIndra.R b/R/utils_getSubnetworkFromIndra.R
index b398ebf..6fb27a0 100644
--- a/R/utils_getSubnetworkFromIndra.R
+++ b/R/utils_getSubnetworkFromIndra.R
@@ -360,7 +360,7 @@
     return(edges)
 }
 
-.filterByCuration = function(nodes, edges, filter_by_curation) {
+.filterByCuration = function(nodes, edges, evidence_count_cutoff, filter_by_curation) {
     if (filter_by_curation) {
         incorrect_counts <- numeric(nrow(edges))
         for (i in seq_len(nrow(edges))) {
@@ -377,7 +377,8 @@
 .filterByPtmSite = function(nodes, edges, filter_by_ptm_site) {
     if (filter_by_ptm_site && nrow(nodes[!is.na(nodes$Site), ]) > 0) {
         ptm_overlap <- calculatePTMOverlapAggregated(edges, nodes)
-        edges <- edges[ptm_overlap[paste(edges$source, edges$target, edges$interaction, sep = "-")] != "", ]
+        keep <- ptm_overlap[paste(edges$source, edges$target, edges$interaction, sep = "-")]
+        edges <- edges[!is.na(keep) & keep != "", ]
         edges <- edges[!is.na(edges$site),]
         nodes <- nodes[nodes$id %in% c(edges$source, edges$target), ]
     }
diff --git a/R/visualizeNetworksWithHTML.R b/R/visualizeNetworksWithHTML.R
index 1c13cfa..8fdd79a 100644
--- a/R/visualizeNetworksWithHTML.R
+++ b/R/visualizeNetworksWithHTML.R
@@ -78,6 +78,7 @@ getRelationshipProperties <- function() {
 #' @param edges Data frame with edge information including 'target' and 'site' columns
 #' @param nodes Data frame with node information including 'id' and 'Site' columns
 #' @return Vector of overlap descriptions for each unique edge (after consolidation)
+#' @keywords internal
 #' @noRd
 calculatePTMOverlapAggregated <- function(edges, nodes) {
     if (nrow(edges) == 0) return(character(0))
@@ -1141,6 +1142,7 @@ createEdgeClickHandler <- function() {
 #' @param edges Data frame with edge information  
 #' @param filename Output HTML filename
 #' @param displayLabelType Type of label to display ("id" or "hgncName")
+#' @param nodeFontSize Font size for node labels (default: 12)
 #' @param ... Additional arguments passed to exportCytoscapeToHTML()
 #' @export
 #' @return Invisibly returns the file path of the created HTML file
diff --git a/man/exportNetworkToHTML.Rd b/man/exportNetworkToHTML.Rd
index d5f9a7d..ca8f679 100644
--- a/man/exportNetworkToHTML.Rd
+++ b/man/exportNetworkToHTML.Rd
@@ -22,6 +22,8 @@ exportNetworkToHTML(
 
 \item{displayLabelType}{Type of label to display ("id" or "hgncName")}
 
+\item{nodeFontSize}{Font size for node labels (default: 12)}
+
 \item{...}{Additional arguments passed to exportCytoscapeToHTML()}
 }
 \value{

From ccb661c7a13d5359221e5e557020e56ca98a19b2 Mon Sep 17 00:00:00 2001
From: Tony Wu <wu.anthon@northeastern.edu>
Date: Tue, 24 Feb 2026 17:39:12 -0500
Subject: [PATCH 16/17] change interaction types to statement types

---
 R/utils_getSubnetworkFromIndra.R | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/R/utils_getSubnetworkFromIndra.R b/R/utils_getSubnetworkFromIndra.R
index 6fb27a0..303512d 100644
--- a/R/utils_getSubnetworkFromIndra.R
+++ b/R/utils_getSubnetworkFromIndra.R
@@ -96,18 +96,18 @@
 
 #' Call INDRA Cogex API and return response
 #' @param res response from INDRA
-#' @param interaction_types interaction types to filter by
+#' @param statement_types interaction types to filter by
 #' @param evidence_count_cutoff number of evidence to filter on for each paper
 #' @param sources_filter list of sources to filter by. Default is NULL, i.e. no filter
 #' @return filtered list of INDRA statements
 #' @importFrom jsonlite fromJSON
 #' @keywords internal
 #' @noRd
-.filterIndraResponse <- function(res, interaction_types, evidence_count_cutoff, 
+.filterIndraResponse <- function(res, statement_types, evidence_count_cutoff, 
                                  sources_filter = NULL) {
-    if (!is.null(interaction_types)) {
+    if (!is.null(statement_types)) {
         res = Filter(
-            function(statement) statement$data$stmt_type %in% interaction_types, 
+            function(statement) statement$data$stmt_type %in% statement_types, 
             res)
     }
     if (!is.null(sources_filter)) {

From 7c4e728609ca5ead4d92b52bdf3a5432056a1d7a Mon Sep 17 00:00:00 2001
From: Tony Wu <wu.anthon@northeastern.edu>
Date: Tue, 24 Feb 2026 17:40:34 -0500
Subject: [PATCH 17/17] add a dot to indicate internal function

---
 R/utils_getSubnetworkFromIndra.R | 2 +-
 R/visualizeNetworksWithHTML.R    | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/R/utils_getSubnetworkFromIndra.R b/R/utils_getSubnetworkFromIndra.R
index 303512d..a5a717c 100644
--- a/R/utils_getSubnetworkFromIndra.R
+++ b/R/utils_getSubnetworkFromIndra.R
@@ -376,7 +376,7 @@
 
 .filterByPtmSite = function(nodes, edges, filter_by_ptm_site) {
     if (filter_by_ptm_site && nrow(nodes[!is.na(nodes$Site), ]) > 0) {
-        ptm_overlap <- calculatePTMOverlapAggregated(edges, nodes)
+        ptm_overlap <- .calculatePTMOverlapAggregated(edges, nodes)
         keep <- ptm_overlap[paste(edges$source, edges$target, edges$interaction, sep = "-")]
         edges <- edges[!is.na(keep) & keep != "", ]
         edges <- edges[!is.na(edges$site),]
diff --git a/R/visualizeNetworksWithHTML.R b/R/visualizeNetworksWithHTML.R
index 8fdd79a..db8b64c 100644
--- a/R/visualizeNetworksWithHTML.R
+++ b/R/visualizeNetworksWithHTML.R
@@ -80,7 +80,7 @@ getRelationshipProperties <- function() {
 #' @return Vector of overlap descriptions for each unique edge (after consolidation)
 #' @keywords internal
 #' @noRd
-calculatePTMOverlapAggregated <- function(edges, nodes) {
+.calculatePTMOverlapAggregated <- function(edges, nodes) {
     if (nrow(edges) == 0) return(character(0))
     
     # Group edges by source-target-interaction to match consolidation logic
@@ -154,7 +154,7 @@ consolidateEdges <- function(edges, nodes = NULL) {
     
     # Calculate aggregated PTM overlap information if nodes are provided
     ptm_overlap_map <- if (!is.null(nodes)) {
-        calculatePTMOverlapAggregated(edges, nodes)
+        .calculatePTMOverlapAggregated(edges, nodes)
     } else {
         NULL
     }