From e952e8219103ac21b3ac8a6c5af2b469cdf9b4b5 Mon Sep 17 00:00:00 2001
From: Andrew Thrasher <adthrasher@gmail.com>
Date: Tue, 9 Dec 2025 09:36:56 -0600
Subject: [PATCH 01/24] feat: add additional probe filtering

---
 docker/minfi/Dockerfile                       |  3 +-
 scripts/methylation/filter.py                 | 16 +++++++++-
 scripts/methylation/list-sex-probes.R         | 15 +++++++++
 scripts/methylation/methylation-preprocess.R  | 15 +++++++++
 workflows/methylation/methylation-cohort.wdl  |  6 ++++
 .../methylation/methylation-preprocess.wdl    | 31 +++++++++++++++++++
 .../methylation/methylation-standard.wdl      |  3 ++
 7 files changed, 87 insertions(+), 2 deletions(-)
 create mode 100644 scripts/methylation/list-sex-probes.R

diff --git a/docker/minfi/Dockerfile b/docker/minfi/Dockerfile
index 8c979be56..a338a8859 100644
--- a/docker/minfi/Dockerfile
+++ b/docker/minfi/Dockerfile
@@ -8,4 +8,5 @@ RUN R --no-save <<SCRIPT
     BiocManager::install("IlluminaHumanMethylationEPICanno.ilm10b4.hg19")
 SCRIPT
 
-COPY --from=scripts --chmod=777 methylation/methylation-preprocess.R /scripts/methylation/methylation-preprocess.R
\ No newline at end of file
+COPY --from=scripts --chmod=777 methylation/methylation-preprocess.R /scripts/methylation/methylation-preprocess.R
+COPY --from=scripts --chmod=777 methylation/list-sex-probes.R /scripts/methylation/list-sex-probes.R
\ No newline at end of file
diff --git a/scripts/methylation/filter.py b/scripts/methylation/filter.py
index 96a9caf37..ef7a67a30 100644
--- a/scripts/methylation/filter.py
+++ b/scripts/methylation/filter.py
@@ -31,6 +31,7 @@ def get_args():
         help="Fraction of samples that must exceed the p-value threshold.",
     )
     parser.add_argument("--pval", type=str, help="P-values CSV file.")
+    parser.add_argument("--exclude", type=str, nargs='*', help="Files with probes to exclude.")
     parser.add_argument("beta", type=str, help="Beta values CSV file.")
     args = parser.parse_args()
 
@@ -40,6 +41,15 @@ def get_args():
 if __name__ == "__main__":
     args = get_args()
 
+    # Read probes to exclude
+    probes_to_exclude = []
+    if args.exclude is not None:
+        for exclude_file in args.exclude:
+            with open(exclude_file, "r") as ef:
+                for line in ef:
+                    probes_to_exclude.append(line.strip())
+        print("Number of probes to exclude:", len(probes_to_exclude))
+
     # Read p-values and find probes with high p-value in too many samples
     high_pval_probes = []
     if args.pval is not None:
@@ -66,6 +76,10 @@ def get_args():
             "high_pval_probes.csv", index=False, header=False
         )
 
+    # Combine with probes to exclude
+    exclude_probe_list = set(high_pval_probes).union(set(probes_to_exclude))
+    print("Total number of probes to exclude:", len(exclude_probe_list))
+
     # Read beta values and compute standard deviation
     data = []
 
@@ -78,7 +92,7 @@ def get_args():
 
             probe = line[0]
             sd = np.std([float(x) for x in line[1:]])
-            if probe not in high_pval_probes:
+            if probe not in exclude_probe_list:
                 data.append([probe, sd])
 
     sd_df = pd.DataFrame(data, columns=["probe", "sd"]).set_index("probe")
diff --git a/scripts/methylation/list-sex-probes.R b/scripts/methylation/list-sex-probes.R
new file mode 100644
index 000000000..3a5b11405
--- /dev/null
+++ b/scripts/methylation/list-sex-probes.R
@@ -0,0 +1,15 @@
+library(minfi)
+library(IlluminaHumanMethylationEPICmanifest)
+library(IlluminaHumanMethylationEPICanno.ilm10b4.hg19)
+
+
+ann <- getAnnotation(IlluminaHumanMethylationEPICanno.ilm10b4.hg19)
+good.probes <- rownames(ann)[ann$chr=="chrX" | ann$chr=="chrY"]
+
+write.table(
+  good.probes,
+  file = "sex_probes.txt",
+  quote = FALSE,
+  row.names = FALSE,
+  col.names = FALSE
+)
\ No newline at end of file
diff --git a/scripts/methylation/methylation-preprocess.R b/scripts/methylation/methylation-preprocess.R
index 236938332..da31beb7f 100644
--- a/scripts/methylation/methylation-preprocess.R
+++ b/scripts/methylation/methylation-preprocess.R
@@ -63,6 +63,13 @@ saveRDS(r_set, paste0(args$out_base, ".RSet.rds"))
 gr_set <- mapToGenome(r_set)
 saveRDS(gr_set, paste0(args$out_base, ".GRSet.rds"))
 
+# Get the list of sites with SNPs
+snps <- getSnpInfo(gr_set)
+gr_set_snps <- addSnpInfo(gr_set)
+# Remove probes with SNPs at CpG or single-base extension sites
+gr_set_snps <- dropLociWithSnps(gr_set_snps, snps=c("SBE","CpG"), maf=0)
+probes_without_snps <- featureNames(gr_set_snps)
+
 # Take the genomic mapped RatioSet and fill Beta values (non-normalized).
 # Get the NON-normalized beta values:
 beta <- getBeta(gr_set)
@@ -81,6 +88,14 @@ write.csv(sample_names, paste0(args$out_base, ".sampleNames.csv"))
 probe_names <- featureNames(gr_set)
 write.csv(probe_names, paste0(args$out_base, ".probeNames.csv"))
 
+# Write probes with SNPs
+probes_with_snps <- setdiff(probe_names, probes_without_snps)
+write.csv(probes_with_snps, paste0(args$out_base, ".probes_with_snps.csv"))
+write.csv(
+  probes_without_snps,
+  paste0(args$out_base, ".probes_without_snps.csv")
+)
+
 gr <- granges(gr_set)
 write.csv(gr, paste0(args$out_base, ".gr.csv"))
 
diff --git a/workflows/methylation/methylation-cohort.wdl b/workflows/methylation/methylation-cohort.wdl
index e1bf70be5..6d2a73c2f 100644
--- a/workflows/methylation/methylation-cohort.wdl
+++ b/workflows/methylation/methylation-cohort.wdl
@@ -17,6 +17,7 @@ workflow methylation_cohort {
 
     parameter_meta {
         unfiltered_normalized_beta: "Array of unfiltered normalized beta values for each sample"
+        sex_probe_list: "List of probes mapping to sex chromosomes to optionally filter"
         p_values: "Array of detection p-value files for each sample."
         skip_pvalue_check: "Skip filtering based on p-values, even if `p_values` is supplied."
         num_probes: "Number of probes to use when filtering to the top `num_probes` probes with the highest standard deviation."
@@ -24,6 +25,7 @@ workflow methylation_cohort {
 
     input {
         Array[File] unfiltered_normalized_beta
+        File? sex_probe_list
         Array[File] p_values = []
         Boolean skip_pvalue_check = false
         Int num_probes = 10000
@@ -120,6 +122,7 @@ workflow methylation_cohort {
         ),
         p_values = pval_file,
         num_probes,
+        additional_probes_to_exclude = select_all([sex_probe_list]),
     }
 
     call generate_umap { input:
@@ -212,6 +215,7 @@ task filter_probes {
     parameter_meta {
         beta_values: "Beta values for all samples"
         p_values: "P-values for all samples"
+        additional_probes_to_exclude: "Additional probes to exclude from the analysis"
         prefix: "Prefix for the output files. The extensions `.beta.csv` and `.probes.csv` will be appended."
         pval_threshold: "P-value cutoff to determine poor quality probes"
         pval_sample_fraction: "Fraction of samples that must exceed p-value threshold to exclude probe"
@@ -221,6 +225,7 @@ task filter_probes {
     input {
         File beta_values
         File? p_values
+        Array[File] additional_probes_to_exclude = []
         String prefix = "filtered"
         Float pval_threshold = 0.01
         Float pval_sample_fraction = 0.5
@@ -237,6 +242,7 @@ task filter_probes {
             --pval-threshold ~{pval_threshold} \
             --pval-sample-fraction ~{pval_sample_fraction} \
             ~{"--pval '" + p_values + "'"} \
+            ~{sep(" ", prefix("--exclude ", quote(additional_probes_to_exclude)))} \
             "~{beta_values}"
     >>>
 
diff --git a/workflows/methylation/methylation-preprocess.wdl b/workflows/methylation/methylation-preprocess.wdl
index 95132cfc8..f5ab788d3 100644
--- a/workflows/methylation/methylation-preprocess.wdl
+++ b/workflows/methylation/methylation-preprocess.wdl
@@ -68,3 +68,34 @@ task process_raw_idats {
         maxRetries: 1
     }
 }
+
+task list_sex_probes {
+    meta {
+        description: "List probes that map to the sex chromosomes"
+        outputs: {
+            probe_list: "List of probe names that map to the sex chromosomes"
+        }
+    }
+
+    parameter_meta {}
+
+    input {}
+
+    command <<<
+        set -euo pipefail
+
+        Rscript /scripts/methylation/list-sex-probes.R
+    >>>
+
+    output {
+        File probe_list = "sex_probes.txt"
+    }
+
+    runtime {
+        container: "ghcr.io/stjudecloud/minfi:1.48.0-7"
+        memory: "8 GB"
+        cpu: 1
+        disks: "2 GB"
+        maxRetries: 1
+    }
+}
diff --git a/workflows/methylation/methylation-standard.wdl b/workflows/methylation/methylation-standard.wdl
index 618d41efb..02d47febd 100644
--- a/workflows/methylation/methylation-standard.wdl
+++ b/workflows/methylation/methylation-standard.wdl
@@ -36,10 +36,13 @@ workflow methylation {
         }
     }
 
+    call preprocess.list_sex_probes {}
+
     call cohort.methylation_cohort { input:
         unfiltered_normalized_beta =
             process_raw_idats.beta_swan_norm_unfiltered_genomic,
         p_values = process_raw_idats.probe_pvalues,
+        sex_probe_list = list_sex_probes.probe_list,
     }
 
     output {

From 65b22a929907ff78f691a3037804260c4f19f7bb Mon Sep 17 00:00:00 2001
From: Andrew Thrasher <adthrasher@gmail.com>
Date: Tue, 9 Dec 2025 09:38:29 -0600
Subject: [PATCH 02/24] chore: add snps output

---
 workflows/methylation/methylation-preprocess.wdl | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/workflows/methylation/methylation-preprocess.wdl b/workflows/methylation/methylation-preprocess.wdl
index f5ab788d3..08d15bb89 100644
--- a/workflows/methylation/methylation-preprocess.wdl
+++ b/workflows/methylation/methylation-preprocess.wdl
@@ -58,6 +58,8 @@ task process_raw_idats {
         File m_values = out_base + ".m_values.csv"
         File probe_names = out_base + ".probeNames.csv"
         File probe_pvalues = out_base + ".detectionP.csv"
+        File probes_with_snps = out_base + ".probes_with_snps.csv"
+        File probes_without_snps = out_base + ".probes_without_snps.csv"
     }
 
     runtime {

From 2dbf660a39063be56f8f5507e909ce4ba83e9063 Mon Sep 17 00:00:00 2001
From: Andrew Thrasher <adthrasher@gmail.com>
Date: Tue, 9 Dec 2025 09:51:18 -0600
Subject: [PATCH 03/24] chore: bump minfi docker image

---
 docker/minfi/package.json                        | 2 +-
 workflows/methylation/methylation-preprocess.wdl | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/docker/minfi/package.json b/docker/minfi/package.json
index 6ff678bc3..1d4a8c985 100644
--- a/docker/minfi/package.json
+++ b/docker/minfi/package.json
@@ -1,5 +1,5 @@
 {
     "name": "minfi",
     "version": "1.48.0",
-    "revision": "7"
+    "revision": "8"
 }
diff --git a/workflows/methylation/methylation-preprocess.wdl b/workflows/methylation/methylation-preprocess.wdl
index 08d15bb89..29722c75c 100644
--- a/workflows/methylation/methylation-preprocess.wdl
+++ b/workflows/methylation/methylation-preprocess.wdl
@@ -63,7 +63,7 @@ task process_raw_idats {
     }
 
     runtime {
-        container: "ghcr.io/stjudecloud/minfi:1.48.0-7"
+        container: "ghcr.io/stjudecloud/minfi:1.48.0-8"
         memory: "8 GB"
         cpu: 1
         disks: "~{disk_size_gb} GB"
@@ -94,7 +94,7 @@ task list_sex_probes {
     }
 
     runtime {
-        container: "ghcr.io/stjudecloud/minfi:1.48.0-7"
+        container: "ghcr.io/stjudecloud/minfi:1.48.0-8"
         memory: "8 GB"
         cpu: 1
         disks: "2 GB"

From 624f56fd14b96707d23369f70b874c5ca8669095 Mon Sep 17 00:00:00 2001
From: Andrew Thrasher <adthrasher@gmail.com>
Date: Tue, 9 Dec 2025 10:19:12 -0600
Subject: [PATCH 04/24] chore: update file format

---
 scripts/methylation/filter.py                    |  4 +++-
 scripts/methylation/methylation-preprocess.R     | 13 ++++++++++---
 workflows/methylation/methylation-preprocess.wdl |  6 ++++--
 3 files changed, 17 insertions(+), 6 deletions(-)

diff --git a/scripts/methylation/filter.py b/scripts/methylation/filter.py
index ef7a67a30..048c49fd9 100644
--- a/scripts/methylation/filter.py
+++ b/scripts/methylation/filter.py
@@ -31,7 +31,9 @@ def get_args():
         help="Fraction of samples that must exceed the p-value threshold.",
     )
     parser.add_argument("--pval", type=str, help="P-values CSV file.")
-    parser.add_argument("--exclude", type=str, nargs='*', help="Files with probes to exclude.")
+    parser.add_argument(
+        "--exclude", type=str, nargs='*', help="Files with probes to exclude."
+    )
     parser.add_argument("beta", type=str, help="Beta values CSV file.")
     args = parser.parse_args()
 
diff --git a/scripts/methylation/methylation-preprocess.R b/scripts/methylation/methylation-preprocess.R
index da31beb7f..f5e1680c6 100644
--- a/scripts/methylation/methylation-preprocess.R
+++ b/scripts/methylation/methylation-preprocess.R
@@ -90,10 +90,17 @@ write.csv(probe_names, paste0(args$out_base, ".probeNames.csv"))
 
 # Write probes with SNPs
 probes_with_snps <- setdiff(probe_names, probes_without_snps)
-write.csv(probes_with_snps, paste0(args$out_base, ".probes_with_snps.csv"))
-write.csv(
+write.table(
+  probes_with_snps,
+  paste0(args$out_base, ".probes_with_snps.tab"),
+  row.names = FALSE,
+  col.names = FALSE,
+)
+write.table(
   probes_without_snps,
-  paste0(args$out_base, ".probes_without_snps.csv")
+  paste0(args$out_base, ".probes_without_snps.tab"),
+  row.names = FALSE,
+  col.names = FALSE,
 )
 
 gr <- granges(gr_set)
diff --git a/workflows/methylation/methylation-preprocess.wdl b/workflows/methylation/methylation-preprocess.wdl
index 29722c75c..79e36d9de 100644
--- a/workflows/methylation/methylation-preprocess.wdl
+++ b/workflows/methylation/methylation-preprocess.wdl
@@ -12,6 +12,8 @@ task process_raw_idats {
             m_values: "M values",
             probe_names: "Probe names found on the array",
             probe_pvalues: "Matrix (in CSV format) containing detection p-values for every (common) probe on the array as rows.",
+            probes_with_snps: "List of probes that contain SNPs",
+            probes_without_snps: "List of probes that do not contain SNPs",
         }
     }
 
@@ -58,8 +60,8 @@ task process_raw_idats {
         File m_values = out_base + ".m_values.csv"
         File probe_names = out_base + ".probeNames.csv"
         File probe_pvalues = out_base + ".detectionP.csv"
-        File probes_with_snps = out_base + ".probes_with_snps.csv"
-        File probes_without_snps = out_base + ".probes_without_snps.csv"
+        File probes_with_snps = out_base + ".probes_with_snps.tab"
+        File probes_without_snps = out_base + ".probes_without_snps.tab"
     }
 
     runtime {

From 1418d8e545236038c2ec28f6356e1e126e9f023c Mon Sep 17 00:00:00 2001
From: Andrew Thrasher <adthrasher@gmail.com>
Date: Tue, 9 Dec 2025 16:21:09 -0600
Subject: [PATCH 05/24] chore: remove quotes from tabular output

---
 scripts/methylation/methylation-preprocess.R | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/scripts/methylation/methylation-preprocess.R b/scripts/methylation/methylation-preprocess.R
index f5e1680c6..b936d58ef 100644
--- a/scripts/methylation/methylation-preprocess.R
+++ b/scripts/methylation/methylation-preprocess.R
@@ -95,12 +95,14 @@ write.table(
   paste0(args$out_base, ".probes_with_snps.tab"),
   row.names = FALSE,
   col.names = FALSE,
+  quote = FALSE,
 )
 write.table(
   probes_without_snps,
   paste0(args$out_base, ".probes_without_snps.tab"),
   row.names = FALSE,
   col.names = FALSE,
+  quote = FALSE,
 )
 
 gr <- granges(gr_set)

From c34478b2613dbcaa78095bb84e904754f8f3a6d3 Mon Sep 17 00:00:00 2001
From: Andrew Thrasher <adthrasher@gmail.com>
Date: Tue, 9 Dec 2025 16:28:42 -0600
Subject: [PATCH 06/24] chore: ruff format

---
 scripts/methylation/filter.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/methylation/filter.py b/scripts/methylation/filter.py
index 048c49fd9..0a7457480 100644
--- a/scripts/methylation/filter.py
+++ b/scripts/methylation/filter.py
@@ -32,7 +32,7 @@ def get_args():
     )
     parser.add_argument("--pval", type=str, help="P-values CSV file.")
     parser.add_argument(
-        "--exclude", type=str, nargs='*', help="Files with probes to exclude."
+        "--exclude", type=str, nargs="*", help="Files with probes to exclude."
     )
     parser.add_argument("beta", type=str, help="Beta values CSV file.")
     args = parser.parse_args()

From 712b11d5b6d6e3a9eae638206c7c703f31010dd7 Mon Sep 17 00:00:00 2001
From: Andrew Thrasher <adthrasher@gmail.com>
Date: Tue, 9 Dec 2025 16:30:24 -0600
Subject: [PATCH 07/24] chore: lint

---
 scripts/methylation/list-sex-probes.R        | 6 +++---
 scripts/methylation/methylation-preprocess.R | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/scripts/methylation/list-sex-probes.R b/scripts/methylation/list-sex-probes.R
index 3a5b11405..8d3ca8d83 100644
--- a/scripts/methylation/list-sex-probes.R
+++ b/scripts/methylation/list-sex-probes.R
@@ -4,12 +4,12 @@ library(IlluminaHumanMethylationEPICanno.ilm10b4.hg19)
 
 
 ann <- getAnnotation(IlluminaHumanMethylationEPICanno.ilm10b4.hg19)
-good.probes <- rownames(ann)[ann$chr=="chrX" | ann$chr=="chrY"]
+good_probes <- rownames(ann)[ann$chr == "chrX" | ann$chr == "chrY"]
 
 write.table(
-  good.probes,
+  good_probes,
   file = "sex_probes.txt",
   quote = FALSE,
   row.names = FALSE,
   col.names = FALSE
-)
\ No newline at end of file
+)
diff --git a/scripts/methylation/methylation-preprocess.R b/scripts/methylation/methylation-preprocess.R
index b936d58ef..e432cc3b7 100644
--- a/scripts/methylation/methylation-preprocess.R
+++ b/scripts/methylation/methylation-preprocess.R
@@ -67,7 +67,7 @@ saveRDS(gr_set, paste0(args$out_base, ".GRSet.rds"))
 snps <- getSnpInfo(gr_set)
 gr_set_snps <- addSnpInfo(gr_set)
 # Remove probes with SNPs at CpG or single-base extension sites
-gr_set_snps <- dropLociWithSnps(gr_set_snps, snps=c("SBE","CpG"), maf=0)
+gr_set_snps <- dropLociWithSnps(gr_set_snps, snps = c("SBE", "CpG"), maf = 0)
 probes_without_snps <- featureNames(gr_set_snps)
 
 # Take the genomic mapped RatioSet and fill Beta values (non-normalized).

From 3042a9d7930ab44b651add38b8ae265d3975cc03 Mon Sep 17 00:00:00 2001
From: Andrew Thrasher <adthrasher@gmail.com>
Date: Tue, 9 Dec 2025 16:32:04 -0600
Subject: [PATCH 08/24] chore: bump pandas

---
 docker/pandas/package.json                   | 2 +-
 workflows/methylation/methylation-cohort.wdl | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/docker/pandas/package.json b/docker/pandas/package.json
index 99bbe68cf..f61a87646 100644
--- a/docker/pandas/package.json
+++ b/docker/pandas/package.json
@@ -1,5 +1,5 @@
 {
     "name": "pandas",
     "version": "2.2.1",
-    "revision": "6"
+    "revision": "7"
 }
diff --git a/workflows/methylation/methylation-cohort.wdl b/workflows/methylation/methylation-cohort.wdl
index 6d2a73c2f..774537495 100644
--- a/workflows/methylation/methylation-cohort.wdl
+++ b/workflows/methylation/methylation-cohort.wdl
@@ -194,7 +194,7 @@ task combine_data {
     }
 
     runtime {
-        container: "ghcr.io/stjudecloud/pandas:2.2.1-6"
+        container: "ghcr.io/stjudecloud/pandas:2.2.1-7"
         memory: "~{memory_gb} GB"
         cpu: 1
         disks: "~{disk_size_gb} GB"
@@ -252,7 +252,7 @@ task filter_probes {
     }
 
     runtime {
-        container: "ghcr.io/stjudecloud/pandas:2.2.1-6"
+        container: "ghcr.io/stjudecloud/pandas:2.2.1-7"
         memory: "8 GB"
         cpu: 1
         disks: "~{disk_size_gb} GB"

From 2ed6ed7541fbc0fbea8e84d4f655faf40a9e04e7 Mon Sep 17 00:00:00 2001
From: Andrew Thrasher <adthrasher@gmail.com>
Date: Tue, 9 Dec 2025 21:26:23 -0600
Subject: [PATCH 09/24] chore: combine snp probe lists

---
 workflows/methylation/methylation-cohort.wdl  |  4 +-
 .../methylation/methylation-standard.wdl      | 44 +++++++++++++++++++
 2 files changed, 46 insertions(+), 2 deletions(-)

diff --git a/workflows/methylation/methylation-cohort.wdl b/workflows/methylation/methylation-cohort.wdl
index 774537495..49013b5b0 100644
--- a/workflows/methylation/methylation-cohort.wdl
+++ b/workflows/methylation/methylation-cohort.wdl
@@ -194,7 +194,7 @@ task combine_data {
     }
 
     runtime {
-        container: "ghcr.io/stjudecloud/pandas:2.2.1-7"
+        container: "ghcr.io/stjudecloud/pandas:branch-methylation_filtering-2.2.1-7"
         memory: "~{memory_gb} GB"
         cpu: 1
         disks: "~{disk_size_gb} GB"
@@ -252,7 +252,7 @@ task filter_probes {
     }
 
     runtime {
-        container: "ghcr.io/stjudecloud/pandas:2.2.1-7"
+        container: "ghcr.io/stjudecloud/pandas:branch-methylation_filtering-2.2.1-7"
         memory: "8 GB"
         cpu: 1
         disks: "~{disk_size_gb} GB"
diff --git a/workflows/methylation/methylation-standard.wdl b/workflows/methylation/methylation-standard.wdl
index 02d47febd..26a324c45 100644
--- a/workflows/methylation/methylation-standard.wdl
+++ b/workflows/methylation/methylation-standard.wdl
@@ -45,6 +45,11 @@ workflow methylation {
         sex_probe_list = list_sex_probes.probe_list,
     }
 
+    call concat_and_uniq { input:
+        input_files = process_raw_idats.probes_with_snps,
+        output_file_name = "probes_with_snps.txt"
+    }
+
     output {
         Array[File] beta_swan_norm_unfiltered_genomic =
             process_raw_idats.beta_swan_norm_unfiltered_genomic
@@ -54,5 +59,44 @@ workflow methylation {
         File umap_embedding = methylation_cohort.umap_embedding
         File umap_plot = methylation_cohort.umap_plot
         File? probe_pvalues = methylation_cohort.probe_pvalues
+        File probes_with_snps = concat_and_uniq.output_file
+    }
+}
+
+task concat_and_uniq {
+    meta {
+        description: "Concatenate multiple files and retain unique lines"
+        outputs: {
+            output_file: "File containing unique lines from all input files"
+        }
+    }
+
+    parameter_meta {
+        input_files: "Array of input files to concatenate"
+        output_file_name: "Name of the output file"
     }
+
+    input {
+        Array[File] input_files
+        String output_file_name = "unique_lines.txt"
+    }
+
+    command <<<
+        set -euo pipefail
+
+        cat ~{sep(" ", quote(input_files))} | sort | uniq > "~{output_file_name}"
+    >>>
+
+    output {
+        File output_file = "~{output_file_name}"
+    }
+
+    runtime {
+        container: "ghcr.io/stjudecloud/pandas:branch-methylation_filtering-2.2.1-7"
+        memory: "2 GB"
+        cpu: 1
+        disks: "4 GB"
+        maxRetries: 1
+    }
+
 }

From ae1c8e9ce8379b859712156d31aaa2e7d4e8587f Mon Sep 17 00:00:00 2001
From: Andrew Thrasher <adthrasher@gmail.com>
Date: Tue, 9 Dec 2025 21:29:37 -0600
Subject: [PATCH 10/24] chore: lint

---
 workflows/methylation/methylation-standard.wdl | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/workflows/methylation/methylation-standard.wdl b/workflows/methylation/methylation-standard.wdl
index 26a324c45..dcc565371 100644
--- a/workflows/methylation/methylation-standard.wdl
+++ b/workflows/methylation/methylation-standard.wdl
@@ -16,6 +16,7 @@ workflow methylation {
             umap_embedding: "UMAP embedding for all samples",
             umap_plot: "UMAP plot for all samples",
             probe_pvalues: "Matrix (in CSV format) containing detection p-values for every (common) probe on the array as rows and all of the input samples as columns.",
+            probes_with_snps: "List of probes that are affected by SNPs",
         }
         allowNestedInputs: true
     }
@@ -46,8 +47,8 @@ workflow methylation {
     }
 
     call concat_and_uniq { input:
-        input_files = process_raw_idats.probes_with_snps,
-        output_file_name = "probes_with_snps.txt"
+        files_to_combine = process_raw_idats.probes_with_snps,
+        output_file_name = "probes_with_snps.txt",
     }
 
     output {
@@ -59,7 +60,7 @@ workflow methylation {
         File umap_embedding = methylation_cohort.umap_embedding
         File umap_plot = methylation_cohort.umap_plot
         File? probe_pvalues = methylation_cohort.probe_pvalues
-        File probes_with_snps = concat_and_uniq.output_file
+        File probes_with_snps = concat_and_uniq.combined_file
     }
 }
 
@@ -67,28 +68,28 @@ task concat_and_uniq {
     meta {
         description: "Concatenate multiple files and retain unique lines"
         outputs: {
-            output_file: "File containing unique lines from all input files"
+            combined_file: "File containing unique lines from all input files"
         }
     }
 
     parameter_meta {
-        input_files: "Array of input files to concatenate"
+        files_to_combine: "Array of input files to concatenate"
         output_file_name: "Name of the output file"
     }
 
     input {
-        Array[File] input_files
+        Array[File] files_to_combine
         String output_file_name = "unique_lines.txt"
     }
 
     command <<<
         set -euo pipefail
 
-        cat ~{sep(" ", quote(input_files))} | sort | uniq > "~{output_file_name}"
+        sort ~{sep(" ", quote(files_to_combine))} | uniq > "~{output_file_name}"
     >>>
 
     output {
-        File output_file = "~{output_file_name}"
+        File combined_file = "~{output_file_name}"
     }
 
     runtime {
@@ -98,5 +99,4 @@ task concat_and_uniq {
         disks: "4 GB"
         maxRetries: 1
     }
-
 }

From fe6511bf55a7ea7d32d4f8181352d6af00706503 Mon Sep 17 00:00:00 2001
From: Andrew Thrasher <adthrasher@gmail.com>
Date: Wed, 10 Dec 2025 15:30:05 -0600
Subject: [PATCH 11/24] chore: cleanup linked files

---
 workflows/methylation/methylation-preprocess.wdl | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/workflows/methylation/methylation-preprocess.wdl b/workflows/methylation/methylation-preprocess.wdl
index 79e36d9de..e37ae8d1b 100644
--- a/workflows/methylation/methylation-preprocess.wdl
+++ b/workflows/methylation/methylation-preprocess.wdl
@@ -47,6 +47,8 @@ task process_raw_idats {
             --idat_base "~{idat_base}" \
             --out_base "~{out_base}" \
             --seed ~{seed}
+
+        rm ./*.idat
     >>>
 
     output {

From 6ad8b26ff6ffc1f38e2eea21289b7140110c72ec Mon Sep 17 00:00:00 2001
From: Andrew Thrasher <adthrasher@gmail.com>
Date: Wed, 10 Dec 2025 15:30:48 -0600
Subject: [PATCH 12/24] chore: iterative merge of snp probe lists

---
 .../methylation/methylation-standard.wdl      | 46 +++++++++++++++++--
 1 file changed, 42 insertions(+), 4 deletions(-)

diff --git a/workflows/methylation/methylation-standard.wdl b/workflows/methylation/methylation-standard.wdl
index dcc565371..a4ef34480 100644
--- a/workflows/methylation/methylation-standard.wdl
+++ b/workflows/methylation/methylation-standard.wdl
@@ -46,9 +46,44 @@ workflow methylation {
         sex_probe_list = list_sex_probes.probe_list,
     }
 
-    call concat_and_uniq { input:
-        files_to_combine = process_raw_idats.probes_with_snps,
-        output_file_name = "probes_with_snps.txt",
+    Array[File] probe_files = process_raw_idats.probes_with_snps
+    Int probelist_length = length(probe_files)
+    Int max_length = 100
+
+    if (probelist_length > max_length){
+        scatter (merge_num in range((probelist_length / max_length) + 1)){
+            # Get the sublist of probe files
+            scatter (probe_num in range(max_length)){
+                Int num = (
+                    if merge_num > 0
+                    then probe_num + (merge_num * max_length)
+                    else probe_num
+                )
+                if (num < probelist_length){
+                    File probe_list = probe_files[num]
+                }
+            }
+        }
+        scatter (iter_index in range(length(probe_list))){
+            call concat_and_uniq { input:
+                files_to_combine = select_all(probe_list[iter_index]),
+                output_file_name = "probes_with_snps_part_~{iter_index}.txt",
+            }
+        }
+
+        call concat_and_uniq as final_cat { input:
+            files_to_combine = flatten([
+                concat_and_uniq.combined_file
+            ]),
+            output_file_name = "probes_with_snps.txt",
+        }
+    }
+
+    if (probelist_length <= max_length){
+        call concat_and_uniq as simple_merge { input:
+            files_to_combine = probe_files,
+            output_file_name = "probes_with_snps.csv",
+        }
     }
 
     output {
@@ -60,7 +95,10 @@ workflow methylation {
         File umap_embedding = methylation_cohort.umap_embedding
         File umap_plot = methylation_cohort.umap_plot
         File? probe_pvalues = methylation_cohort.probe_pvalues
-        File probes_with_snps = concat_and_uniq.combined_file
+        File probes_with_snps = select_first([
+            final_cat.combined_file,
+            simple_merge.combined_file,
+        ])
     }
 }
 

From da8c77390b7faf43525dc2c047daee4bb433c029 Mon Sep 17 00:00:00 2001
From: Andrew Thrasher <adthrasher@gmail.com>
Date: Wed, 10 Dec 2025 18:53:03 -0600
Subject: [PATCH 13/24] chore: fix argument

---
 scripts/methylation/filter.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/methylation/filter.py b/scripts/methylation/filter.py
index 0a7457480..de3aaf396 100644
--- a/scripts/methylation/filter.py
+++ b/scripts/methylation/filter.py
@@ -32,7 +32,7 @@ def get_args():
     )
     parser.add_argument("--pval", type=str, help="P-values CSV file.")
     parser.add_argument(
-        "--exclude", type=str, nargs="*", help="Files with probes to exclude."
+        "--exclude", type=str, action="append", help="Files with probes to exclude."
     )
     parser.add_argument("beta", type=str, help="Beta values CSV file.")
     args = parser.parse_args()

From 70ef3781aedcbae6fa53f025b561852077b941e5 Mon Sep 17 00:00:00 2001
From: Andrew Thrasher <adthrasher@gmail.com>
Date: Thu, 11 Dec 2025 08:40:55 -0600
Subject: [PATCH 14/24] chore: add probes on sex chromosomes to output

---
 workflows/methylation/methylation-standard.wdl | 1 +
 1 file changed, 1 insertion(+)

diff --git a/workflows/methylation/methylation-standard.wdl b/workflows/methylation/methylation-standard.wdl
index a4ef34480..b3526b34e 100644
--- a/workflows/methylation/methylation-standard.wdl
+++ b/workflows/methylation/methylation-standard.wdl
@@ -99,6 +99,7 @@ workflow methylation {
             final_cat.combined_file,
             simple_merge.combined_file,
         ])
+        File st = list_sex_probes.probe_list
     }
 }
 

From 57b1e3a170a7da966476e6f52ca307f921f42783 Mon Sep 17 00:00:00 2001
From: Andrew Thrasher <adthrasher@gmail.com>
Date: Mon, 15 Dec 2025 12:20:35 -0500
Subject: [PATCH 15/24] chore: add high p-val probe list

---
 workflows/methylation/methylation-cohort.wdl   | 2 ++
 workflows/methylation/methylation-standard.wdl | 1 +
 2 files changed, 3 insertions(+)

diff --git a/workflows/methylation/methylation-cohort.wdl b/workflows/methylation/methylation-cohort.wdl
index 49013b5b0..94b29b901 100644
--- a/workflows/methylation/methylation-cohort.wdl
+++ b/workflows/methylation/methylation-cohort.wdl
@@ -145,6 +145,7 @@ workflow methylation_cohort {
         File umap_embedding = generate_umap.umap
         File umap_plot = plot_umap.umap_plot
         File? probe_pvalues = pval_file
+        File high_pval_probes = filter_probes.high_pval_probes
     }
 }
 
@@ -249,6 +250,7 @@ task filter_probes {
     output {
         File filtered_beta_values = "~{prefix}.beta.csv"
         File filtered_probes = "~{prefix}.probes.csv"
+        File high_pval_probes = "high_pval_probes.csv"
     }
 
     runtime {
diff --git a/workflows/methylation/methylation-standard.wdl b/workflows/methylation/methylation-standard.wdl
index b3526b34e..aff88f3ce 100644
--- a/workflows/methylation/methylation-standard.wdl
+++ b/workflows/methylation/methylation-standard.wdl
@@ -100,6 +100,7 @@ workflow methylation {
             simple_merge.combined_file,
         ])
         File st = list_sex_probes.probe_list
+        File high_pval_probes = methylation_cohort.high_pval_probes
     }
 }
 

From d464f497e3afb454502b0516e22c2b2cd61bd8dd Mon Sep 17 00:00:00 2001
From: Andrew Thrasher <adthrasher@gmail.com>
Date: Mon, 15 Dec 2025 12:26:05 -0500
Subject: [PATCH 16/24] chore: print non-genomic probe list

---
 scripts/methylation/methylation-preprocess.R | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/scripts/methylation/methylation-preprocess.R b/scripts/methylation/methylation-preprocess.R
index e432cc3b7..4766ac1a2 100644
--- a/scripts/methylation/methylation-preprocess.R
+++ b/scripts/methylation/methylation-preprocess.R
@@ -63,6 +63,8 @@ saveRDS(r_set, paste0(args$out_base, ".RSet.rds"))
 gr_set <- mapToGenome(r_set)
 saveRDS(gr_set, paste0(args$out_base, ".GRSet.rds"))
 
+non_genomic_probes <- setdiff(featureNames(r_set), featureNames(gr_set))
+
 # Get the list of sites with SNPs
 snps <- getSnpInfo(gr_set)
 gr_set_snps <- addSnpInfo(gr_set)
@@ -105,6 +107,15 @@ write.table(
   quote = FALSE,
 )
 
+# Write non-genomic probe list
+write.table(
+  non_genomic_probes,
+  paste0(args$out_base, ".non_genomic_probes.tab"),
+  row.names = FALSE,
+  col.names = FALSE,
+  quote = FALSE,
+)
+
 gr <- granges(gr_set)
 write.csv(gr, paste0(args$out_base, ".gr.csv"))
 

From 9070d4373fe7739013ef6a70b80b29166418f117 Mon Sep 17 00:00:00 2001
From: Andrew Thrasher <adthrasher@gmail.com>
Date: Mon, 15 Dec 2025 12:27:31 -0500
Subject: [PATCH 17/24] chore: add non-genomic probe list to task output

---
 workflows/methylation/methylation-preprocess.wdl | 1 +
 1 file changed, 1 insertion(+)

diff --git a/workflows/methylation/methylation-preprocess.wdl b/workflows/methylation/methylation-preprocess.wdl
index e37ae8d1b..1f76e4a84 100644
--- a/workflows/methylation/methylation-preprocess.wdl
+++ b/workflows/methylation/methylation-preprocess.wdl
@@ -64,6 +64,7 @@ task process_raw_idats {
         File probe_pvalues = out_base + ".detectionP.csv"
         File probes_with_snps = out_base + ".probes_with_snps.tab"
         File probes_without_snps = out_base + ".probes_without_snps.tab"
+        File non_genomic_probes = out_base + ".non_genomic_probes.tab"
     }
 
     runtime {

From 6d107fcf7d4921c7de1613829f4a23150e4e2dec Mon Sep 17 00:00:00 2001
From: Andrew Thrasher <adthrasher@gmail.com>
Date: Tue, 16 Dec 2025 10:29:35 -0500
Subject: [PATCH 18/24] chore: rename output

---
 workflows/methylation/methylation-standard.wdl | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/workflows/methylation/methylation-standard.wdl b/workflows/methylation/methylation-standard.wdl
index aff88f3ce..5c2f3c84a 100644
--- a/workflows/methylation/methylation-standard.wdl
+++ b/workflows/methylation/methylation-standard.wdl
@@ -99,7 +99,7 @@ workflow methylation {
             final_cat.combined_file,
             simple_merge.combined_file,
         ])
-        File st = list_sex_probes.probe_list
+        File sex_probe_list = list_sex_probes.probe_list
         File high_pval_probes = methylation_cohort.high_pval_probes
     }
 }

From 112a7c56fd0b77eba0b6d722d3da3a18dabdce58 Mon Sep 17 00:00:00 2001
From: Andrew Thrasher <adthrasher@gmail.com>
Date: Tue, 16 Dec 2025 10:38:10 -0500
Subject: [PATCH 19/24] chore: cleanup output docs and add merging of
 non-genomic probe lists

---
 workflows/methylation/methylation-cohort.wdl  |  2 +
 .../methylation/methylation-preprocess.wdl    |  1 +
 .../methylation/methylation-standard.wdl      | 46 +++++++++++++++++++
 3 files changed, 49 insertions(+)

diff --git a/workflows/methylation/methylation-cohort.wdl b/workflows/methylation/methylation-cohort.wdl
index 94b29b901..852e44fbb 100644
--- a/workflows/methylation/methylation-cohort.wdl
+++ b/workflows/methylation/methylation-cohort.wdl
@@ -11,6 +11,7 @@ workflow methylation_cohort {
             umap_embedding: "UMAP embedding for all samples",
             umap_plot: "UMAP plot for all samples",
             probe_pvalues: "Matrix (in CSV format) containing detection p-values for every (common) probe on the array as rows and all of the input samples as columns.",
+            high_pval_probes: "List of probes that were filtered out due to high p-values",
         }
         allowNestedInputs: true
     }
@@ -210,6 +211,7 @@ task filter_probes {
         outputs: {
             filtered_beta_values: "Filtered beta values for all samples",
             filtered_probes: "Probes that were retained after filtering.",
+            high_pval_probes: "Probes that were filtered out due to high p-values",
         }
     }
 
diff --git a/workflows/methylation/methylation-preprocess.wdl b/workflows/methylation/methylation-preprocess.wdl
index 1f76e4a84..cc53ca97c 100644
--- a/workflows/methylation/methylation-preprocess.wdl
+++ b/workflows/methylation/methylation-preprocess.wdl
@@ -14,6 +14,7 @@ task process_raw_idats {
             probe_pvalues: "Matrix (in CSV format) containing detection p-values for every (common) probe on the array as rows.",
             probes_with_snps: "List of probes that contain SNPs",
             probes_without_snps: "List of probes that do not contain SNPs",
+            non_genomic_probes: "List of probes that do not map to the genome",
         }
     }
 
diff --git a/workflows/methylation/methylation-standard.wdl b/workflows/methylation/methylation-standard.wdl
index 5c2f3c84a..02625de8f 100644
--- a/workflows/methylation/methylation-standard.wdl
+++ b/workflows/methylation/methylation-standard.wdl
@@ -17,6 +17,9 @@ workflow methylation {
             umap_plot: "UMAP plot for all samples",
             probe_pvalues: "Matrix (in CSV format) containing detection p-values for every (common) probe on the array as rows and all of the input samples as columns.",
             probes_with_snps: "List of probes that are affected by SNPs",
+            sex_probe_list: "List of probes that map to sex chromosomes",
+            high_pval_probes: "List of probes that were filtered out due to high p-values",
+            non_genomic_probes: "List of probes that do not map to the genome",
         }
         allowNestedInputs: true
     }
@@ -86,6 +89,45 @@ workflow methylation {
         }
     }
 
+    Array[File] non_genomic_probe_list = process_raw_idats.non_genomic_probes
+    Int non_genomic_probelist_length = length(non_genomic_probe_list)
+
+    if (non_genomic_probelist_length > max_length){
+        scatter (merge_num in range((non_genomic_probelist_length / max_length) + 1)){
+            # Get the sublist of probe files
+            scatter (probe_num in range(max_length)){
+                Int num_ng = (
+                    if merge_num > 0
+                    then probe_num + (merge_num * max_length)
+                    else probe_num
+                )
+                if (num_ng < non_genomic_probelist_length){
+                    File probe_list_non_genomic = non_genomic_probe_list[num_ng]
+                }
+            }
+        }
+        scatter (iter_index in range(length(probe_list_non_genomic))){
+            call concat_and_uniq as non_genomic_concat { input:
+                files_to_combine = select_all(probe_list_non_genomic[iter_index]),
+                output_file_name = "non_genomic_probes_part_~{iter_index}.txt",
+            }
+        }
+
+        call concat_and_uniq as final_cat_non_genomic { input:
+            files_to_combine = flatten([
+                non_genomic_concat.combined_file
+            ]),
+            output_file_name = "non_genomic_probes.txt",
+        }
+    }
+
+    if (non_genomic_probelist_length <= max_length){
+        call concat_and_uniq as simple_merge_non_genomic { input:
+            files_to_combine = non_genomic_probe_list,
+            output_file_name = "non_genomic_probes.csv",
+        }
+    }
+
     output {
         Array[File] beta_swan_norm_unfiltered_genomic =
             process_raw_idats.beta_swan_norm_unfiltered_genomic
@@ -101,6 +143,10 @@ workflow methylation {
         ])
         File sex_probe_list = list_sex_probes.probe_list
         File high_pval_probes = methylation_cohort.high_pval_probes
+        File non_genomic_probes = select_first([
+            final_cat_non_genomic.combined_file,
+            simple_merge_non_genomic.combined_file,
+        ])
     }
 }
 

From 44e9584216888fab362bca7162cf20a26ba895c2 Mon Sep 17 00:00:00 2001
From: Andrew Thrasher <adthrasher@gmail.com>
Date: Tue, 16 Dec 2025 10:49:24 -0500
Subject: [PATCH 20/24] chore: make output optional

---
 workflows/methylation/methylation-cohort.wdl   | 2 +-
 workflows/methylation/methylation-standard.wdl | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/workflows/methylation/methylation-cohort.wdl b/workflows/methylation/methylation-cohort.wdl
index 852e44fbb..bf2fbc92b 100644
--- a/workflows/methylation/methylation-cohort.wdl
+++ b/workflows/methylation/methylation-cohort.wdl
@@ -146,7 +146,7 @@ workflow methylation_cohort {
         File umap_embedding = generate_umap.umap
         File umap_plot = plot_umap.umap_plot
         File? probe_pvalues = pval_file
-        File high_pval_probes = filter_probes.high_pval_probes
+        File? high_pval_probes = filter_probes.high_pval_probes
     }
 }
 
diff --git a/workflows/methylation/methylation-standard.wdl b/workflows/methylation/methylation-standard.wdl
index 02625de8f..460c35f93 100644
--- a/workflows/methylation/methylation-standard.wdl
+++ b/workflows/methylation/methylation-standard.wdl
@@ -142,7 +142,7 @@ workflow methylation {
             simple_merge.combined_file,
         ])
         File sex_probe_list = list_sex_probes.probe_list
-        File high_pval_probes = methylation_cohort.high_pval_probes
+        File? high_pval_probes = methylation_cohort.high_pval_probes
         File non_genomic_probes = select_first([
             final_cat_non_genomic.combined_file,
             simple_merge_non_genomic.combined_file,

From cdddb5b9d7eefba83bda2a2729a4fb32e1ebf962 Mon Sep 17 00:00:00 2001
From: Andrew Thrasher <adthrasher@gmail.com>
Date: Tue, 16 Dec 2025 12:35:45 -0500
Subject: [PATCH 21/24] chore: make output optional

---
 workflows/methylation/methylation-cohort.wdl | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/workflows/methylation/methylation-cohort.wdl b/workflows/methylation/methylation-cohort.wdl
index bf2fbc92b..568dcf0d8 100644
--- a/workflows/methylation/methylation-cohort.wdl
+++ b/workflows/methylation/methylation-cohort.wdl
@@ -252,7 +252,7 @@ task filter_probes {
     output {
         File filtered_beta_values = "~{prefix}.beta.csv"
         File filtered_probes = "~{prefix}.probes.csv"
-        File high_pval_probes = "high_pval_probes.csv"
+        File? high_pval_probes = "high_pval_probes.csv"
     }
 
     runtime {

From 15934761ab177326ebb9071c2ee37db53a1dcaf1 Mon Sep 17 00:00:00 2001
From: Andrew Thrasher <adthrasher@gmail.com>
Date: Tue, 16 Dec 2025 16:00:11 -0500
Subject: [PATCH 22/24] chore: remove branch containers

---
 workflows/methylation/methylation-cohort.wdl   | 4 ++--
 workflows/methylation/methylation-standard.wdl | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/workflows/methylation/methylation-cohort.wdl b/workflows/methylation/methylation-cohort.wdl
index 568dcf0d8..7c6d0fd4f 100644
--- a/workflows/methylation/methylation-cohort.wdl
+++ b/workflows/methylation/methylation-cohort.wdl
@@ -196,7 +196,7 @@ task combine_data {
     }
 
     runtime {
-        container: "ghcr.io/stjudecloud/pandas:branch-methylation_filtering-2.2.1-7"
+        container: "ghcr.io/stjudecloud/pandas:2.2.1-7"
         memory: "~{memory_gb} GB"
         cpu: 1
         disks: "~{disk_size_gb} GB"
@@ -256,7 +256,7 @@ task filter_probes {
     }
 
     runtime {
-        container: "ghcr.io/stjudecloud/pandas:branch-methylation_filtering-2.2.1-7"
+        container: "ghcr.io/stjudecloud/pandas:2.2.1-7"
         memory: "8 GB"
         cpu: 1
         disks: "~{disk_size_gb} GB"
diff --git a/workflows/methylation/methylation-standard.wdl b/workflows/methylation/methylation-standard.wdl
index 460c35f93..ebb783996 100644
--- a/workflows/methylation/methylation-standard.wdl
+++ b/workflows/methylation/methylation-standard.wdl
@@ -179,7 +179,7 @@ task concat_and_uniq {
     }
 
     runtime {
-        container: "ghcr.io/stjudecloud/pandas:branch-methylation_filtering-2.2.1-7"
+        container: "ghcr.io/stjudecloud/pandas:2.2.1-7"
         memory: "2 GB"
         cpu: 1
         disks: "4 GB"

From 9d7604f632779d68d0af8e0884d66da5ea34cff3 Mon Sep 17 00:00:00 2001
From: Andrew Thrasher <adthrasher@gmail.com>
Date: Tue, 16 Dec 2025 16:15:10 -0500
Subject: [PATCH 23/24] chore: update CHANGELOG

---
 scripts/CHANGELOG.md               | 11 +++++++++++
 workflows/methylation/CHANGELOG.md | 11 ++++++++++-
 2 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/scripts/CHANGELOG.md b/scripts/CHANGELOG.md
index ffd29b6fa..e05b6743e 100644
--- a/scripts/CHANGELOG.md
+++ b/scripts/CHANGELOG.md
@@ -8,6 +8,17 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/).
 
 Any change to the `scripts/` directory should be accompanied by version increases in the `docker/` directory! If you are editing this file, please ensure these changes propagate!
 
+## 2025 December
+
+### Added
+
+- Added `list-sex-probes.R` to dump the list of probes that align to the sex chromosomes [#283](https://github.com/stjudecloud/workflows/pull/283)
+
+### Changed
+
+- `filter.py` now accepts an optional set of files listing probes to exclude [#283](https://github.com/stjudecloud/workflows/pull/283)
+- `methylation-preprocess.R` now outputs non-genomic probes, SNP affected probes, and non-SNP affected probes [#283](https://github.com/stjudecloud/workflows/pull/283)
+
 ## 2025 September
 
 ### Added
diff --git a/workflows/methylation/CHANGELOG.md b/workflows/methylation/CHANGELOG.md
index 8a0182c82..1ccf44cee 100644
--- a/workflows/methylation/CHANGELOG.md
+++ b/workflows/methylation/CHANGELOG.md
@@ -3,7 +3,16 @@
 All notable changes to this project will be documented in this file.
  
 The format is based on [Keep a Changelog](http://keepachangelog.com/).
- 
+
+## 2025 December
+
+### Added
+
+- Now outputs list of probes that map to sex chromosomes [#283](https://github.com/stjudecloud/workflows/pull/283)
+- Pipeline writes out the list of filtered probes [#283](https://github.com/stjudecloud/workflows/pull/283)
+- Pipeline writes out list of probes that are affected by SNPs [#283](https://github.com/stjudecloud/workflows/pull/283)
+- Pipeline writes out list of probes that were filtered for not mapping to genomic coordinates [#283](https://github.com/stjudecloud/workflows/pull/283)
+
 ## 2025 September
 
 ### Added

From c0d93880a75320a94ba4ff06c980d87921559ee8 Mon Sep 17 00:00:00 2001
From: Andrew Thrasher <adthrasher@gmail.com>
Date: Mon, 5 Jan 2026 14:12:38 -0500
Subject: [PATCH 24/24] chore: Apply suggestions from code review

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Ari Frantz <ari.frantz@stjude.org>
---
 scripts/methylation/list-sex-probes.R          | 4 ++--
 workflows/methylation/methylation-standard.wdl | 6 +++---
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/scripts/methylation/list-sex-probes.R b/scripts/methylation/list-sex-probes.R
index 8d3ca8d83..8937d575c 100644
--- a/scripts/methylation/list-sex-probes.R
+++ b/scripts/methylation/list-sex-probes.R
@@ -4,10 +4,10 @@ library(IlluminaHumanMethylationEPICanno.ilm10b4.hg19)
 
 
 ann <- getAnnotation(IlluminaHumanMethylationEPICanno.ilm10b4.hg19)
-good_probes <- rownames(ann)[ann$chr == "chrX" | ann$chr == "chrY"]
+sex_probes <- rownames(ann)[ann$chr == "chrX" | ann$chr == "chrY"]
 
 write.table(
-  good_probes,
+  sex_probes,
   file = "sex_probes.txt",
   quote = FALSE,
   row.names = FALSE,
diff --git a/workflows/methylation/methylation-standard.wdl b/workflows/methylation/methylation-standard.wdl
index ebb783996..f8670fa72 100644
--- a/workflows/methylation/methylation-standard.wdl
+++ b/workflows/methylation/methylation-standard.wdl
@@ -85,7 +85,7 @@ workflow methylation {
     if (probelist_length <= max_length){
         call concat_and_uniq as simple_merge { input:
             files_to_combine = probe_files,
-            output_file_name = "probes_with_snps.csv",
+            output_file_name = "probes_with_snps.tab",
         }
     }
 
@@ -124,7 +124,7 @@ workflow methylation {
     if (non_genomic_probelist_length <= max_length){
         call concat_and_uniq as simple_merge_non_genomic { input:
             files_to_combine = non_genomic_probe_list,
-            output_file_name = "non_genomic_probes.csv",
+            output_file_name = "non_genomic_probes.tab",
         }
     }
 
@@ -171,7 +171,7 @@ task concat_and_uniq {
     command <<<
         set -euo pipefail
 
-        sort ~{sep(" ", quote(files_to_combine))} | uniq > "~{output_file_name}"
+        sort -u ~{sep(" ", quote(files_to_combine))} > "~{output_file_name}"
     >>>
 
     output {