From c7e92ce7527a5f312b69cc9c5f31ec2a3e6ba61d Mon Sep 17 00:00:00 2001
From: Jacob Hyrum Tye <142532933+jacob-tye@users.noreply.github.com>
Date: Thu, 10 Sep 2026 21:36:57 -0600
Subject: [PATCH 1/9] Add workflow to sync main branch into dev

---
 .github/workflows/sync-main-to-dev.yml | 59 ++++++++++++++++++++++++++
 1 file changed, 59 insertions(+)
 create mode 100644 .github/workflows/sync-main-to-dev.yml

diff --git a/.github/workflows/sync-main-to-dev.yml b/.github/workflows/sync-main-to-dev.yml
new file mode 100644
index 0000000..a96ea70
--- /dev/null
+++ b/.github/workflows/sync-main-to-dev.yml
@@ -0,0 +1,59 @@
+name: Sync main into dev
+
+on:
+  push:
+    branches:
+      - main
+
+permissions:
+  contents: read
+  pull-requests: write
+
+jobs:
+  sync-main-to-dev:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Check whether dev is behind main
+        id: check
+        run: |
+          git fetch origin main dev
+
+          if [ "$(git rev-list --count origin/dev..origin/main)" -gt 0 ]; then
+            echo "needs_sync=true" >> "$GITHUB_OUTPUT"
+          else
+            echo "needs_sync=false" >> "$GITHUB_OUTPUT"
+          fi
+
+      - name: Check for existing sync PR
+        if: steps.check.outputs.needs_sync == 'true'
+        id: pr
+        env:
+          GH_TOKEN: ${{ github.token }}
+        run: |
+          EXISTING_PR=$(gh pr list \
+            --base dev \
+            --head main \
+            --state open \
+            --json number \
+            --jq '.[0].number // empty')
+
+          echo "number=$EXISTING_PR" >> "$GITHUB_OUTPUT"
+
+      - name: Create sync PR
+        if: >
+          steps.check.outputs.needs_sync == 'true' &&
+          steps.pr.outputs.number == ''
+        env:
+          GH_TOKEN: ${{ github.token }}
+        run: |
+          gh pr create \
+            --base dev \
+            --head main \
+            --title "Sync main into dev" \
+            --body "Automatically created because main contains commits that are not yet in dev."

From 8f15aa6c664c11349fe321f2bee9558784bde29d Mon Sep 17 00:00:00 2001
From: Jacob Hyrum Tye <142532933+jacob-tye@users.noreply.github.com>
Date: Thu, 10 Sep 2026 21:43:15 -0600
Subject: [PATCH 2/9] Delete .github/workflows/sync-main-to-dev.yml

Do not have the right current permissions right now
---
 .github/workflows/sync-main-to-dev.yml | 59 --------------------------
 1 file changed, 59 deletions(-)
 delete mode 100644 .github/workflows/sync-main-to-dev.yml

diff --git a/.github/workflows/sync-main-to-dev.yml b/.github/workflows/sync-main-to-dev.yml
deleted file mode 100644
index a96ea70..0000000
--- a/.github/workflows/sync-main-to-dev.yml
+++ /dev/null
@@ -1,59 +0,0 @@
-name: Sync main into dev
-
-on:
-  push:
-    branches:
-      - main
-
-permissions:
-  contents: read
-  pull-requests: write
-
-jobs:
-  sync-main-to-dev:
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - name: Check whether dev is behind main
-        id: check
-        run: |
-          git fetch origin main dev
-
-          if [ "$(git rev-list --count origin/dev..origin/main)" -gt 0 ]; then
-            echo "needs_sync=true" >> "$GITHUB_OUTPUT"
-          else
-            echo "needs_sync=false" >> "$GITHUB_OUTPUT"
-          fi
-
-      - name: Check for existing sync PR
-        if: steps.check.outputs.needs_sync == 'true'
-        id: pr
-        env:
-          GH_TOKEN: ${{ github.token }}
-        run: |
-          EXISTING_PR=$(gh pr list \
-            --base dev \
-            --head main \
-            --state open \
-            --json number \
-            --jq '.[0].number // empty')
-
-          echo "number=$EXISTING_PR" >> "$GITHUB_OUTPUT"
-
-      - name: Create sync PR
-        if: >
-          steps.check.outputs.needs_sync == 'true' &&
-          steps.pr.outputs.number == ''
-        env:
-          GH_TOKEN: ${{ github.token }}
-        run: |
-          gh pr create \
-            --base dev \
-            --head main \
-            --title "Sync main into dev" \
-            --body "Automatically created because main contains commits that are not yet in dev."

From d0d0fbd928af6ed924ab4a8cbbb04d47d5b76917 Mon Sep 17 00:00:00 2001
From: Jacob Hyrum Tye <142532933+jacob-tye@users.noreply.github.com>
Date: Thu, 10 Sep 2026 22:18:32 -0600
Subject: [PATCH 3/9] Create CITATION.cff for MethylSeg

Add citation file for MethylSeg software with details.
---
 CITATION.cff | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)
 create mode 100644 CITATION.cff

diff --git a/CITATION.cff b/CITATION.cff
new file mode 100644
index 0000000..e86cd61
--- /dev/null
+++ b/CITATION.cff
@@ -0,0 +1,17 @@
+cff-version: 1.2.0
+message: "If you use MethylSeg, please cite this software."
+title: "MethylSeg"
+type: software
+abstract: >-
+  MethylSeg is a context-aware methylome segmentation method for identifying
+  partially methylated domains in whole-genome bisulfite sequencing and
+  methylation microarray data.
+authors:
+  - family-names: "Tye"
+    given-names: "Jacob"
+    orcid: "https://orcid.org/0009-0000-6883-9572"
+  - family-names: "Clement"
+    given-names: "Kendell"
+    orcid: "https://orcid.org/0000-0003-3808-0811"
+repository-code: "https://github.com/clementlab/MethylSeg"
+url: "https://github.com/clementlab/MethylSeg"

From 0343b38c59a7be0caebb44ce055dcd97e3b3eaab Mon Sep 17 00:00:00 2001
From: Jacob Tye <jacob.tye@utah.edu>
Date: Thu, 10 Sep 2026 22:59:01 -0600
Subject: [PATCH 4/9] updated readme

---
 CITATION.cff | 1 +
 README.md    | 9 +++++++--
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/CITATION.cff b/CITATION.cff
index e86cd61..0b77cd7 100644
--- a/CITATION.cff
+++ b/CITATION.cff
@@ -2,6 +2,7 @@ cff-version: 1.2.0
 message: "If you use MethylSeg, please cite this software."
 title: "MethylSeg"
 type: software
+version: "0.1.8"
 abstract: >-
   MethylSeg is a context-aware methylome segmentation method for identifying
   partially methylated domains in whole-genome bisulfite sequencing and
diff --git a/README.md b/README.md
index 38e3808..e4ed2d4 100644
--- a/README.md
+++ b/README.md
@@ -255,8 +255,13 @@ The BED files themselves are tab-delimited and do not contain a header.
 
 ## Citation
 
-A manuscript describing MethylSeg is in preparation. Citation information will
-be added when it becomes available.
+If you use MethylSeg, please cite the software using the
+[CITATION.cff](https://github.com/clementlab/MethylSeg/blob/main/CITATION.cff)
+metadata. On GitHub, select **Cite this repository** to copy the citation in APA
+or BibTeX format.
+
+A manuscript describing MethylSeg is in preparation. Its citation will be added
+when available.
 
 ## Planned support
 

From 047104129ec2ff35356aee2720baadd86270de11 Mon Sep 17 00:00:00 2001
From: Jacob Tye <jacob.tye@utah.edu>
Date: Fri, 18 Sep 2026 15:10:09 -0600
Subject: [PATCH 5/9] added pdf figure generation and parameter to set low
 coverage like values

---
 methylseg/helper_classes.py        |  5 +++++
 methylseg/methyl_state_assigner.py | 17 +++++++++++++++--
 methylseg/methylseg_pathway.py     |  2 ++
 3 files changed, 22 insertions(+), 2 deletions(-)

diff --git a/methylseg/helper_classes.py b/methylseg/helper_classes.py
index 8ed4b3f..480996e 100644
--- a/methylseg/helper_classes.py
+++ b/methylseg/helper_classes.py
@@ -174,6 +174,7 @@ def __init__(
         resolution="auto",
         min_coverage=10,
         remove_low_coverage_like_cpgs=False,
+        low_coverage_like_beta_values=None,
         chunk_size=1_000_000,
         retain_removed_rows=True,
     ):
@@ -195,6 +196,8 @@ def __init__(
             If ``True``, remove CpGs with beta values commonly produced by very
             low coverage counts, such as 0.0, 0.25, 0.33, 0.5, 0.66/0.67,
             0.75, and 1.0.
+        low_coverage_like_beta_values
+            A set of beta values that are indicative of low coverage.
         chunk_size
             Number of rows to read at a time when processing large files.
         retain_removed_rows
@@ -207,6 +210,8 @@ def __init__(
         self.resolution = resolution
         self.min_coverage = min_coverage
         self.remove_low_coverage_like_cpgs = remove_low_coverage_like_cpgs
+        if low_coverage_like_beta_values is not None:
+            self.LOW_COVERAGE_LIKE_BETA_VALUES = frozenset(low_coverage_like_beta_values)
         self.chunk_size = chunk_size
         self.retain_removed_rows = retain_removed_rows
 
diff --git a/methylseg/methyl_state_assigner.py b/methylseg/methyl_state_assigner.py
index 9c79387..cf2266a 100644
--- a/methylseg/methyl_state_assigner.py
+++ b/methylseg/methyl_state_assigner.py
@@ -1,6 +1,7 @@
 """Window-based emission feature engineering and KMeans state assignment."""
 
 from enum import Enum
+from pathlib import Path
 import textwrap
 import warnings
 
@@ -2556,11 +2557,18 @@ def plot_feature_distributions_by_kmeans_state(
         show_plots: bool = True,
         state_colors: dict | None = None,
         state_cutoffs: dict | None = None,
+        save_plots: bool | None = None,
+        save_pdf: bool = False,
     ):
         """Plot training-emission histograms stratified by KMeans state.
 
         ``state_cutoffs`` optionally controls the biological-state display
         labels; it does not change the KMeans assignments.
+
+        When ``save_plots`` is omitted, the legacy behavior is preserved:
+        plots are saved as PNG only when ``show_plots`` is false. Set
+        ``save_plots=True`` to save while displaying and ``save_pdf=True`` to
+        add same-stem PDF companions.
         """
         if not hasattr(self, "model"):
             raise ValueError("No trained model found. Please train a model first.")
@@ -2623,8 +2631,13 @@ def plot_feature_distributions_by_kmeans_state(
             ax.set_title(f"Distribution of {emission} by KMeans State")
             ax.legend()
             fig.tight_layout()
+            should_save = (not show_plots) if save_plots is None else save_plots
+            if should_save and self.out_dir is not None:
+                output_path = Path(self.out_dir) / f"feature_distribution_{emission}.png"
+                output_path.parent.mkdir(parents=True, exist_ok=True)
+                fig.savefig(output_path)
+                if save_pdf:
+                    fig.savefig(output_path.with_suffix(".pdf"))
             if show_plots:
                 plt.show()
-            elif self.out_dir is not None:
-                fig.savefig(f"{self.out_dir}/feature_distribution_{emission}.png")
             plt.close(fig)
diff --git a/methylseg/methylseg_pathway.py b/methylseg/methylseg_pathway.py
index 13b0e69..e96ac6a 100644
--- a/methylseg/methylseg_pathway.py
+++ b/methylseg/methylseg_pathway.py
@@ -83,6 +83,7 @@ def prepare_sample_info(
         resolution: str = "auto",
         min_coverage: int = 10,
         remove_low_coverage_like_cpgs: bool = False,
+        low_coverage_like_beta_values: set[float] | None = None,
     ) -> tuple[SampleInfo, pd.DataFrame]:
         """
         Prepare a methylation file into the package's canonical sample schema.
@@ -112,6 +113,7 @@ def prepare_sample_info(
             resolution=resolution,
             min_coverage=min_coverage,
             remove_low_coverage_like_cpgs=remove_low_coverage_like_cpgs,
+            low_coverage_like_beta_values=low_coverage_like_beta_values,
         ).prepare()
 
     @staticmethod

From 1258d61973b206bed9743333a05c072fcc9a7053 Mon Sep 17 00:00:00 2001
From: Jacob Tye <jacob.tye@utah.edu>
Date: Fri, 18 Sep 2026 16:11:04 -0600
Subject: [PATCH 6/9] added roadmap.md and updated links

---
 .gitignore   |  1 +
 README.md    |  7 +++----
 ROADMAP.md   | 17 +++++++++++++++++
 docs/conf.py | 12 ++++++++++--
 4 files changed, 31 insertions(+), 6 deletions(-)
 create mode 100644 ROADMAP.md

diff --git a/.gitignore b/.gitignore
index 66d843e..543b4b3 100644
--- a/.gitignore
+++ b/.gitignore
@@ -10,6 +10,7 @@ docs/_generated/
 docs/tutorials/generated/
 docs/readme.md
 docs/troubleshooting.md
+docs/roadmap.md
 docs/quickstart.png
 docs/_static/logo.png
 data/archive.tar.gz
diff --git a/README.md b/README.md
index e4ed2d4..6b1f44b 100644
--- a/README.md
+++ b/README.md
@@ -25,7 +25,8 @@ values were observed during testing:
 
 > [!NOTE]
 > Numba has known compatibility issues on ARM-based systems. See the
-> [Troubleshooting guide](TROUBLESHOOTING.md) for installation guidance.
+> [Troubleshooting guide](https://github.com/clementlab/MethylSeg/blob/main/TROUBLESHOOTING.md)
+> for installation guidance.
 
 ## Installation
 
@@ -44,8 +45,6 @@ or install the current version from GitHub:
 python -m pip install "git+https://github.com/clementlab/MethylSeg.git"
 ```
 
-
-
 ## Reference files
 
 ### Sample data
@@ -265,7 +264,7 @@ when available.
 
 ## Planned support
 
-- [ ] Add defaults for HM27 and EPIC microarray formats
+See [ROADMAP.md](https://github.com/clementlab/MethylSeg/blob/main/ROADMAP.md)
 
 ## Reporting issues
 
diff --git a/ROADMAP.md b/ROADMAP.md
new file mode 100644
index 0000000..5565633
--- /dev/null
+++ b/ROADMAP.md
@@ -0,0 +1,17 @@
+# MethylSeg Roadmap
+
+## 1.1.0
+
+- [ ] Develop and benchmark platform-specific defaults for HM27 and EPIC arrays
+- [ ] Add optional confidence scores for MethylSeg region calls
+
+## 1.2.0
+
+- [ ] Add a scalable multi-sample workflow
+  - Support efficient processing of multiple samples
+  - Generate cohort-level consensus regions and recurrence statistics
+
+## 2.0.0
+
+- [ ] Replace the external ctHMM implementation with an in-house model
+  - This will change the underlying model specification and may produce results that differ from MethylSeg 1.x.
diff --git a/docs/conf.py b/docs/conf.py
index a493d4c..10af16a 100644
--- a/docs/conf.py
+++ b/docs/conf.py
@@ -12,6 +12,7 @@
 GENERATED_TUTORIALS = DOCS_ROOT / "tutorials" / "generated"
 STAGED_README = DOCS_ROOT / "readme.md"
 STAGED_TROUBLESHOOTING = DOCS_ROOT / "troubleshooting.md"
+STAGED_ROADMAP = DOCS_ROOT / "roadmap.md"
 README_IMAGE = "quickstart.png"
 README_LOGO = "logo.png"
 REPOSITORY_URL = "https://github.com/clementlab/MethylSeg"
@@ -107,15 +108,21 @@ def _manual_rst_pages() -> list[str]:
         "tutorials",
         "api",
         "troubleshooting",
+        "roadmap",
     ]
 
 
 def _stage_readme() -> None:
-    """Copy the README while retargeting links that are relative to the repo."""
+    """Copy the README while retargeting repository links for Sphinx."""
     readme = (PACKAGE_ROOT / "README.md").read_text()
     readme = _convert_github_alerts(readme)
     readme = readme.replace(
-        "(TROUBLESHOOTING.md)", "(troubleshooting.md)"
+        f"({REPOSITORY_URL}/blob/main/TROUBLESHOOTING.md)",
+        "(troubleshooting.md)",
+    )
+    readme = readme.replace(
+        f"({REPOSITORY_URL}/blob/main/ROADMAP.md)",
+        "(roadmap.md)",
     )
     readme = readme.replace(
         "(examples/run_full_pipeline.ipynb)",
@@ -130,6 +137,7 @@ def _stage_readme() -> None:
     readme = readme.replace("(LICENSE.md)", f"({REPOSITORY_URL}/blob/main/LICENSE)")
     _write(STAGED_README, readme)
     _write(STAGED_TROUBLESHOOTING, (PACKAGE_ROOT / "TROUBLESHOOTING.md").read_text())
+    _write(STAGED_ROADMAP, (PACKAGE_ROOT / "ROADMAP.md").read_text())
     STATIC_ROOT.mkdir(parents=True, exist_ok=True)
     copy2(PACKAGE_ROOT / README_LOGO, STATIC_ROOT / README_LOGO)
     copy2(PACKAGE_ROOT / README_IMAGE, DOCS_ROOT / README_IMAGE)

From 06fa480df8797f4b9de9b27f669d89adf144b388 Mon Sep 17 00:00:00 2001
From: Jacob Hyrum Tye <142532933+jacob-tye@users.noreply.github.com>
Date: Tue, 22 Sep 2026 14:43:06 -0600
Subject: [PATCH 7/9] Add DOI badge to README

Added a DOI badge for citation in README.
---
 README.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/README.md b/README.md
index 6b1f44b..cc6da74 100644
--- a/README.md
+++ b/README.md
@@ -2,6 +2,8 @@
 
 ![logo](https://raw.githubusercontent.com/clementlab/MethylSeg/main/logo.png)
 
+[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.22904886.svg)](https://doi.org/10.5281/zenodo.22904886)
+
 MethylSeg is a Python toolkit for identifying methylation domains from
 whole-genome bisulfite sequencing (WGBS) and microarray methylation data. It
 supports data preparation, methylation-state model training, genome

From 92ef47a37254759a04a08c741b201a8017c5819a Mon Sep 17 00:00:00 2001
From: Jacob Hyrum Tye <142532933+jacob-tye@users.noreply.github.com>
Date: Tue, 22 Sep 2026 14:43:32 -0600
Subject: [PATCH 8/9] Change installation source to PyPI

Updated installation instructions to use PyPI instead of TestPyPI.
---
 README.md | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/README.md b/README.md
index cc6da74..e1d8ab2 100644
--- a/README.md
+++ b/README.md
@@ -32,13 +32,10 @@ values were observed during testing:
 
 ## Installation
 
-Install from TestPyPI
+Install from PyPI
 
 ```bash
-python -m pip install \
-  --index-url https://test.pypi.org/simple/ \
-  --extra-index-url https://pypi.org/simple/ \
-  methylseg
+python -m pip install methylseg
 ```
 
 or install the current version from GitHub:

From 6acf7b391817d2d10f764a2a9cb939b909b31157 Mon Sep 17 00:00:00 2001
From: Jacob Hyrum Tye <142532933+jacob-tye@users.noreply.github.com>
Date: Tue, 22 Sep 2026 14:46:17 -0600
Subject: [PATCH 9/9] Bump version from 0.1.8 to 1.0.0

---
 pyproject.toml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/pyproject.toml b/pyproject.toml
index 21c7658..d54ae81 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "methylseg"
-version = "0.1.8"
+version = "1.0.0"
 description = "Methylation segmentation utilities used in the TCGA methylation analysis repo."
 readme = "README.md"
 requires-python = ">=3.10"