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/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/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/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/scripts/methylation/filter.py b/scripts/methylation/filter.py
index 96a9caf37..de3aaf396 100644
--- a/scripts/methylation/filter.py
+++ b/scripts/methylation/filter.py
@@ -31,6 +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, action="append", help="Files with probes to exclude."
+    )
     parser.add_argument("beta", type=str, help="Beta values CSV file.")
     args = parser.parse_args()
 
@@ -40,6 +43,15 @@ 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 +78,10 @@ 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 +94,7 @@ 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..8937d575c
--- /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)
+sex_probes <- rownames(ann)[ann$chr == "chrX" | ann$chr == "chrY"]
+
+write.table(
+  sex_probes,
+  file = "sex_probes.txt",
+  quote = FALSE,
+  row.names = FALSE,
+  col.names = FALSE
+)
diff --git a/scripts/methylation/methylation-preprocess.R b/scripts/methylation/methylation-preprocess.R
index 236938332..4766ac1a2 100644
--- a/scripts/methylation/methylation-preprocess.R
+++ b/scripts/methylation/methylation-preprocess.R
@@ -63,6 +63,15 @@ 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)
+# 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 +90,32 @@ 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.table(
+  probes_with_snps,
+  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,
+)
+
+# 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"))
 
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
diff --git a/workflows/methylation/methylation-cohort.wdl b/workflows/methylation/methylation-cohort.wdl
index e1bf70be5..7c6d0fd4f 100644
--- a/workflows/methylation/methylation-cohort.wdl
+++ b/workflows/methylation/methylation-cohort.wdl
@@ -11,12 +11,14 @@ 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
     }
 
     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 +26,7 @@ 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 +123,7 @@ workflow methylation_cohort {
         ),
         p_values = pval_file,
         num_probes,
+        additional_probes_to_exclude = select_all([sex_probe_list]),
     }
 
     call generate_umap { input:
@@ -142,6 +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
     }
 }
 
@@ -191,7 +196,7 @@ 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"
@@ -206,12 +211,14 @@ 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",
         }
     }
 
     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 +228,7 @@ 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
@@ -237,16 +245,18 @@ 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}"
     >>>
 
     output {
         File filtered_beta_values = "~{prefix}.beta.csv"
         File filtered_probes = "~{prefix}.probes.csv"
+        File? high_pval_probes = "high_pval_probes.csv"
     }
 
     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"
diff --git a/workflows/methylation/methylation-preprocess.wdl b/workflows/methylation/methylation-preprocess.wdl
index 95132cfc8..cc53ca97c 100644
--- a/workflows/methylation/methylation-preprocess.wdl
+++ b/workflows/methylation/methylation-preprocess.wdl
@@ -12,6 +12,9 @@ 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",
+            non_genomic_probes: "List of probes that do not map to the genome",
         }
     }
 
@@ -45,6 +48,8 @@ task process_raw_idats {
             --idat_base "~{idat_base}" \
             --out_base "~{out_base}" \
             --seed ~{seed}
+
+        rm ./*.idat
     >>>
 
     output {
@@ -58,13 +63,47 @@ 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.tab"
+        File probes_without_snps = out_base + ".probes_without_snps.tab"
+        File non_genomic_probes = out_base + ".non_genomic_probes.tab"
     }
 
     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"
         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:1.48.0-8"
+        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..f8670fa72 100644
--- a/workflows/methylation/methylation-standard.wdl
+++ b/workflows/methylation/methylation-standard.wdl
@@ -16,6 +16,10 @@ 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",
+            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
     }
@@ -36,10 +40,92 @@ 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,
+    }
+
+    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.tab",
+        }
+    }
+
+    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.tab",
+        }
     }
 
     output {
@@ -51,5 +137,52 @@ 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 = select_first([
+            final_cat.combined_file,
+            simple_merge.combined_file,
+        ])
+        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,
+        ])
+    }
+}
+
+task concat_and_uniq {
+    meta {
+        description: "Concatenate multiple files and retain unique lines"
+        outputs: {
+            combined_file: "File containing unique lines from all input files"
+        }
+    }
+
+    parameter_meta {
+        files_to_combine: "Array of input files to concatenate"
+        output_file_name: "Name of the output file"
+    }
+
+    input {
+        Array[File] files_to_combine
+        String output_file_name = "unique_lines.txt"
+    }
+
+    command <<<
+        set -euo pipefail
+
+        sort -u ~{sep(" ", quote(files_to_combine))} > "~{output_file_name}"
+    >>>
+
+    output {
+        File combined_file = "~{output_file_name}"
+    }
+
+    runtime {
+        container: "ghcr.io/stjudecloud/pandas:2.2.1-7"
+        memory: "2 GB"
+        cpu: 1
+        disks: "4 GB"
+        maxRetries: 1
     }
 }