From 26b9f961d75788a3a8cd8da6325e420e31737005 Mon Sep 17 00:00:00 2001
From: Michelle Wang <tomichellewang@gmail.com>
Date: Thu, 5 Nov 2026 00:59:55 -0500
Subject: [PATCH 1/3] prepend sub- prefix if it's not there

---
 src/brainflex/core/get_data.py |  6 ++++++
 tests/core/test_get_data.py    | 15 +++++++++++++++
 2 files changed, 21 insertions(+)

diff --git a/src/brainflex/core/get_data.py b/src/brainflex/core/get_data.py
index 5f44f45..66b923f 100644
--- a/src/brainflex/core/get_data.py
+++ b/src/brainflex/core/get_data.py
@@ -181,6 +181,8 @@ def _get_freesurfer(
 def _write_pheno(layout: DatasetLayout, session_ids: dict[str, str]) -> None:
     """Copy participants.tsv to the tabular directory, with a session ID column.
 
+    Participant IDs without the ``sub-`` prefix have it prepended.
+
     Participants without BIDS imaging data get an empty session ID. Warns if
     participant IDs and BIDS subjects do not fully match, and raises ValueError
     if none match.
@@ -196,6 +198,10 @@ def _write_pheno(layout: DatasetLayout, session_ids: dict[str, str]) -> None:
         fieldnames = reader.fieldnames
         rows = list(reader)
 
+    for row in rows:
+        if not row[COL_PARTICIPANT_ID].startswith(BIDS_SUBJECT_PREFIX):
+            row[COL_PARTICIPANT_ID] = BIDS_SUBJECT_PREFIX + row[COL_PARTICIPANT_ID]
+
     fieldnames = [COL_PARTICIPANT_ID, COL_SESSION_ID] + [
         col for col in fieldnames if col not in (COL_PARTICIPANT_ID, COL_SESSION_ID)
     ]
diff --git a/tests/core/test_get_data.py b/tests/core/test_get_data.py
index 341b8ea..b39b9fd 100644
--- a/tests/core/test_get_data.py
+++ b/tests/core/test_get_data.py
@@ -188,6 +188,21 @@ def test_no_matching_participants(
         with pytest.raises(ValueError, match="No participant IDs"):
             get_data(root, DATASET_ID)
 
+    def test_participants_without_prefix(
+        self, mock_s3: dict[tuple[str, str], bytes], root: Path
+    ):
+        mock_s3[(OPENNEURO_BUCKET, f"{DATASET_ID}/participants.tsv")] = (
+            b"participant_id\tage\n01\t20\n02\t30\nsub-03\t40\n"
+        )
+        dpath_study = get_data(root, DATASET_ID)
+        pheno = (dpath_study / "tabular" / "pheno.tsv").read_text()
+        assert pheno == (
+            "participant_id\tsession_id\tage\n"
+            "sub-01\tses-unnamed\t20\n"
+            "sub-02\tses-unnamed\t30\n"
+            "sub-03\t\t40\n"
+        )
+
     def test_no_participants_json(
         self, mock_s3: dict[tuple[str, str], bytes], root: Path
     ):

From 45fc62a7a51b6cb84ba8602da349e44cefebd0af Mon Sep 17 00:00:00 2001
From: Michelle Wang <tomichellewang@gmail.com>
Date: Thu, 5 Nov 2026 01:04:45 -0500
Subject: [PATCH 2/3] emit warning if sub- needed to be added

---
 src/brainflex/core/get_data.py | 10 ++++++++--
 tests/core/test_get_data.py    | 11 +++++++++--
 2 files changed, 17 insertions(+), 4 deletions(-)

diff --git a/src/brainflex/core/get_data.py b/src/brainflex/core/get_data.py
index 66b923f..42cf27e 100644
--- a/src/brainflex/core/get_data.py
+++ b/src/brainflex/core/get_data.py
@@ -199,8 +199,14 @@ def _write_pheno(layout: DatasetLayout, session_ids: dict[str, str]) -> None:
         rows = list(reader)
 
     for row in rows:
-        if not row[COL_PARTICIPANT_ID].startswith(BIDS_SUBJECT_PREFIX):
-            row[COL_PARTICIPANT_ID] = BIDS_SUBJECT_PREFIX + row[COL_PARTICIPANT_ID]
+        participant_id = row[COL_PARTICIPANT_ID]
+        if not participant_id.startswith(BIDS_SUBJECT_PREFIX):
+            row[COL_PARTICIPANT_ID] = BIDS_SUBJECT_PREFIX + participant_id
+            warnings.warn(
+                f"Prepended {BIDS_SUBJECT_PREFIX!r} to participant ID"
+                f" {participant_id!r} in {PARTICIPANTS_FILENAME}",
+                stacklevel=3,
+            )
 
     fieldnames = [COL_PARTICIPANT_ID, COL_SESSION_ID] + [
         col for col in fieldnames if col not in (COL_PARTICIPANT_ID, COL_SESSION_ID)
diff --git a/tests/core/test_get_data.py b/tests/core/test_get_data.py
index b39b9fd..07c1b38 100644
--- a/tests/core/test_get_data.py
+++ b/tests/core/test_get_data.py
@@ -183,7 +183,7 @@ def test_no_matching_participants(
         self, mock_s3: dict[tuple[str, str], bytes], root: Path
     ):
         mock_s3[(OPENNEURO_BUCKET, f"{DATASET_ID}/participants.tsv")] = (
-            b"participant_id\tage\nSZ_0113\t25\n"
+            b"participant_id\tage\nsub-SZ0113\t25\n"
         )
         with pytest.raises(ValueError, match="No participant IDs"):
             get_data(root, DATASET_ID)
@@ -194,7 +194,14 @@ def test_participants_without_prefix(
         mock_s3[(OPENNEURO_BUCKET, f"{DATASET_ID}/participants.tsv")] = (
             b"participant_id\tage\n01\t20\n02\t30\nsub-03\t40\n"
         )
-        dpath_study = get_data(root, DATASET_ID)
+        with pytest.warns(UserWarning) as record_warnings:
+            dpath_study = get_data(root, DATASET_ID)
+        assert [
+            str(w.message) for w in record_warnings if "Prepended" in str(w.message)
+        ] == [
+            "Prepended 'sub-' to participant ID '01' in participants.tsv",
+            "Prepended 'sub-' to participant ID '02' in participants.tsv",
+        ]
         pheno = (dpath_study / "tabular" / "pheno.tsv").read_text()
         assert pheno == (
             "participant_id\tsession_id\tage\n"

From 08b2448b78e75c46c4add16f84dd490fa298c019 Mon Sep 17 00:00:00 2001
From: Michelle Wang <tomichellewang@gmail.com>
Date: Thu, 5 Nov 2026 09:56:31 -0500
Subject: [PATCH 3/3] fix failing test

---
 tests/core/test_get_data.py | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tests/core/test_get_data.py b/tests/core/test_get_data.py
index 181714b..f367d41 100644
--- a/tests/core/test_get_data.py
+++ b/tests/core/test_get_data.py
@@ -228,7 +228,6 @@ def test_participants_without_prefix(
             "participant_id\tsession_id\tage\n"
             "sub-01\tses-unnamed\t20\n"
             "sub-02\tses-unnamed\t30\n"
-            "sub-03\t\t40\n"
         )
 
     def test_no_participants_json(