From 58769b587671bd8024782abe414394a8c2438ebb Mon Sep 17 00:00:00 2001
From: ArthurDeclercq <Arthur.Declercq@UGent.be>
Date: Mon, 30 Oct 2023 17:08:20 +0100
Subject: [PATCH 1/3] minor modification fixes and logging

---
 ms2rescore/parse_psms.py | 20 ++++++++++++++++++--
 1 file changed, 18 insertions(+), 2 deletions(-)

diff --git a/ms2rescore/parse_psms.py b/ms2rescore/parse_psms.py
index e116c32f..ce0c968d 100644
--- a/ms2rescore/parse_psms.py
+++ b/ms2rescore/parse_psms.py
@@ -41,13 +41,29 @@ def parse_psms(config: Dict, psm_list: Union[PSMList, None]) -> PSMList:
         )
 
     logger.debug("Parsing modifications...")
+    modifications_found = set(
+        [
+            re.search(r"\[([^\[\]]*)\]", x.proforma).group(1)
+            for x in psm_list["peptidoform"]
+            if "[" in x.proforma
+        ]
+    )
+    logger.debug(f"Found modifications: {modifications_found}")
+    non_mapped_modifications = modifications_found - set(config["modification_mapping"].keys())
+    if non_mapped_modifications:
+        logger.warning(
+            f"Non-mapped modifications found: {non_mapped_modifications}\nThis can be ignored if Unimod modification label"
+        )
     psm_list.rename_modifications(config["modification_mapping"])
     psm_list.add_fixed_modifications(config["fixed_modifications"])
     psm_list.apply_fixed_modifications()
 
-    logger.debug("Applying `psm_id_pattern`...")
     if config["psm_id_pattern"]:
         pattern = re.compile(config["psm_id_pattern"])
+        logger.debug(f"Applying `psm_id_pattern`...")
+        logger.debug(
+            f"Parsing `{psm_list['spectrum_id'][0]}` to `{_match_psm_ids(psm_list['spectrum_id'][0], pattern)}`"
+        )
         new_ids = [_match_psm_ids(old_id, pattern) for old_id in psm_list["spectrum_id"]]
         psm_list["spectrum_id"] = new_ids
 
@@ -125,6 +141,6 @@ def _match_psm_ids(old_id, regex_pattern):
         return match[1]
     except (TypeError, IndexError):
         raise MS2RescoreConfigurationError(
-            "`psm_id_pattern` could not be matched to all PSM spectrum IDs."
+            f"`psm_id_pattern` could not be extracted from PSM spectrum IDs (i.e. {old_id})."
             " Ensure that the regex contains a capturing group?"
         )

From 30661c063e2a228d4b9a1655a6c9454db92ac54b Mon Sep 17 00:00:00 2001
From: ArthurDeclercq <Arthur.Declercq@UGent.be>
Date: Mon, 30 Oct 2023 17:08:28 +0100
Subject: [PATCH 2/3] dockerfile addition

---
 Dockerfile | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/Dockerfile b/Dockerfile
index 2fde54a8..f3fe2778 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -10,7 +10,10 @@ ADD README.md /ms2rescore/README.md
 ADD MANIFEST.in /ms2rescore/MANIFEST.in
 ADD ms2rescore /ms2rescore/ms2rescore
 
-RUN apt-get update && apt-get install python3-pip procps -y \
+RUN apt-get update
+RUN apt-get install -y libglib2.0-0 libsm6 libxrender1 libxext6
+
+RUN apt-get install python3-pip procps -y \
     && rm -rf /var/lib/apt/lists/* \
     && pip3 install ms2rescore/
 

From 8dda81f438ab2dac6502a0362b5cd459336298f7 Mon Sep 17 00:00:00 2001
From: RalfG <ralfg@hotmail.be>
Date: Mon, 30 Oct 2023 18:15:44 -0400
Subject: [PATCH 3/3] Merge dockerfile commands

---
 Dockerfile | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/Dockerfile b/Dockerfile
index f3fe2778..59fc4000 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -10,10 +10,8 @@ ADD README.md /ms2rescore/README.md
 ADD MANIFEST.in /ms2rescore/MANIFEST.in
 ADD ms2rescore /ms2rescore/ms2rescore
 
-RUN apt-get update
-RUN apt-get install -y libglib2.0-0 libsm6 libxrender1 libxext6
-
-RUN apt-get install python3-pip procps -y \
+RUN apt-get update \
+    && apt-get install -y python3-pip procps libglib2.0-0 libsm6 libxrender1 libxext6 \
     && rm -rf /var/lib/apt/lists/* \
     && pip3 install ms2rescore/