From a5157d0fd643960151d2494fa0a5e19ce0b6a44e Mon Sep 17 00:00:00 2001
From: Chris Bielow <chris.bielow@fu-berlin.de>
Date: Fri, 27 Sep 2024 17:06:34 +0200
Subject: [PATCH] Accession order fixes (#330)

* fix script: detect unsorted accessions; feature: report gap size

* re-establish ordered accessions

* Update version

* Update psi-ms.obo

---------

Co-authored-by: Joshua Klein <mobiusklein@gmail.com>
---
 psi-ms.obo                            | 34 +++++++++++++--------------
 scripts/find_next_available_number.py |  4 +++-
 2 files changed, 20 insertions(+), 18 deletions(-)

diff --git a/psi-ms.obo b/psi-ms.obo
index d52c811..4cb52a3 100644
--- a/psi-ms.obo
+++ b/psi-ms.obo
@@ -1,7 +1,7 @@
 format-version: 1.2
-data-version: 4.1.176
-date: 17:09:2024 15:26
-saved-by: Michael Hoopmann
+data-version: 4.1.177
+date: 27:09:2024 07:15
+saved-by: Chris Bielow
 auto-generated-by: OBO-Edit 2.3.1
 default-namespace: MS
 namespace-id-rule: * MS:$sequence(7,0,9999999)$
@@ -22522,6 +22522,20 @@ name: spectrum clustering software
 def: "Software designed to group multiple mass spectra by high similarity, generally with the goal of grouping replicate spectra derived from the same analyte." [PSI:MS]
 is_a: MS:1000531 ! software
 
+[Term]
+id: MS:1003407
+name: Scout
+def: "Identifying crosslinked peptides in complex protein mixtures" [PSI:MS]
+is_a: MS:1001456 ! analysis software
+
+[Term]
+id: MS:1003408
+name: Scout score
+def: "Scout identification search engine score" [PSI:MS]
+is_a: MS:1001143 ! PSM-level search engine specific statistic
+relationship: has_order MS:1003407 ! higher score better
+relationship: has_value_type xsd:double ! The allowed value-type for this CV term
+
 [Term]
 id: MS:1003409
 name: Stellar
@@ -24306,20 +24320,6 @@ synonym: "RT-MSMS-Q2" RELATED [PMID:24494671]
 synonym: "RT-MSMS-Q3" RELATED [PMID:24494671]
 synonym: "RT-MSMS-Q4" RELATED [PMID:24494671]
 
-[Term]
-id: MS:1003407
-name: Scout
-def: "Identifying crosslinked peptides in complex protein mixtures" [PSI:MS]
-is_a: MS:1001456 ! analysis software
-
-[Term]
-id: MS:1003408
-name: Scout score
-def: "Scout identification search engine score" [PSI:MS]
-is_a: MS:1001143 ! PSM-level search engine specific statistic
-relationship: has_order MS:1003407 ! higher score better
-relationship: has_value_type xsd:double ! The allowed value-type for this CV term
-
 [Term]
 id: PEFF:0000001
 name: PEFF CV term
diff --git a/scripts/find_next_available_number.py b/scripts/find_next_available_number.py
index 0efb069..6350c09 100644
--- a/scripts/find_next_available_number.py
+++ b/scripts/find_next_available_number.py
@@ -22,10 +22,12 @@ def collect_gaps(stream, min_value=1000300):
                     last_seen[cv] = acc
                     continue
                 diff = acc - last_in_cv
+                if diff < 1:
+                    sys.stderr.write(f"CV is not sorted! {cv}:{acc} found after {cv}:{last_in_cv}\n")
                 if diff > 1 and acc > min_value:
                     for i in range(1, diff):
                         gaps.append((cv, last_in_cv + i))
-                    sys.stderr.write(f"Found gap {gaps[-diff + 1]} to {gaps[-1]}\n")
+                    sys.stderr.write(f"Found gap of size {diff-1}: {gaps[-diff + 1]} to {gaps[-1]}\n")
                 last_seen[cv] = acc
         return gaps, last_seen
     except UnicodeDecodeError: