Merge branch 'development' into windowsfix

MannLabs · Jun 28, 2024 · 3b55654 · 3b55654
2 parents 9922319 + ca05c60
commit 3b55654
Show file tree

Hide file tree

Showing 2 changed files with 44 additions and 20 deletions.
diff --git a/alphabase/psm_reader/sage_reader.py b/alphabase/psm_reader/sage_reader.py
@@ -75,7 +75,7 @@ def lookup_modification(
 
     matched_mod = filtered_mod_df.sort_values(by="unimod_id").iloc[0]
 
-    return matched_mod["mod_name"]
+    return matched_mod["mod_name_stripped"]
 
 
 def capture_modifications(
@@ -122,7 +122,7 @@ def capture_modifications(
             mass_observed, previous_aa, mod_annotated_df, ppm_tolerance=ppm_tolerance
         )
         if mod is not None:
-            site_list.append(str(match_start - 1 - match_delta))
+            site_list.append(str(match_start - match_delta))
             mod_list.append(mod)
 
         else:

diff --git a/nbs_tests/psm_reader/sage_reader.ipynb b/nbs_tests/psm_reader/sage_reader.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -11,7 +11,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -22,7 +22,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -32,7 +32,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -42,7 +42,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -53,17 +53,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
     "#| hide\n",
-    "assert capture_modifications('Q[-17.026548]DQSANEKNK[+42.010567]LEM[+15.9949]NK[+42.010567]', annotated_mod_df) == ('0;9;12;14', 'Gln->pyro-Glu@Q^Any N-term;Acetyl@K;Oxidation@M;Acetyl@K')"
+    "modifications = capture_modifications('Q[-17.026548]DQSANEKNK[+42.010567]LEM[+15.9949]NK[+42.010567]', annotated_mod_df)\n",
+    "assert (\n",
+    "    modifications == ('1;10;13;15', 'Gln->pyro-Glu@Q^Any_N-term;Acetyl@K;Oxidation@M;Acetyl@K')\n",
+    "), modifications"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -73,7 +76,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
@@ -193,7 +196,7 @@
        "      <td>0.000106</td>\n",
        "      <td>False</td>\n",
        "      <td>7932</td>\n",
-       "      <td>1</td>\n",
+       "      <td>2</td>\n",
        "      <td>Carbamidomethyl@C</td>\n",
        "      <td>15</td>\n",
        "      <td>0.770401</td>\n",
@@ -227,7 +230,7 @@
        "      <td>0.000106</td>\n",
        "      <td>False</td>\n",
        "      <td>8375</td>\n",
-       "      <td>1</td>\n",
+       "      <td>2</td>\n",
        "      <td>Oxidation@M</td>\n",
        "      <td>15</td>\n",
        "      <td>0.804350</td>\n",
@@ -280,9 +283,9 @@
        "1  sp|P25815|S100P_HUMAN  0.000106  False      4250             \n",
        "2    sp|P06748|NPM_HUMAN  0.000106  False      9584             \n",
        "3   sp|O95602|RPA1_HUMAN  0.000106  False     10841             \n",
-       "4   sp|Q9HCK8|CHD8_HUMAN  0.000106  False      7932         1   \n",
+       "4   sp|Q9HCK8|CHD8_HUMAN  0.000106  False      7932         2   \n",
        "5    sp|Q86U86|PB1_HUMAN  0.000106  False     14771             \n",
-       "6   sp|Q86TC9|MYPN_HUMAN  0.000106  False      8375         1   \n",
+       "6   sp|Q86TC9|MYPN_HUMAN  0.000106  False      8375         2   \n",
        "7  sp|O14974|MYPT1_HUMAN  0.000106  False      1864             \n",
        "\n",
        "                mods  nAA   rt_norm  precursor_mz  \n",
@@ -296,7 +299,7 @@
        "7                      17  1.000000    821.387362  "
       ]
      },
-     "execution_count": null,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -321,15 +324,24 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [
     "#| hide\n",
     "assert np.all(psm_df['fdr'] <= 0.01)\n",
-    "assert psm_df['sequence'].iloc[4] == 'DCEDPEYKPLQGPPK'\n",
-    "assert psm_df['mod_sites'].iloc[4] == '1'\n",
-    "assert psm_df['mods'].iloc[4] == 'Carbamidomethyl@C'"
+    "assert (psm_df['mods'] != \"\").sum() == 2\n",
+    "assert (psm_df['mod_sites'] != \"\").sum() == 2\n",
+    "for seq, mods, mod_sites in psm_df[[\"sequence\",\"mods\",\"mod_sites\"]].values:\n",
+    "    if mods == \"\":\n",
+    "        assert mod_sites == \"\"\n",
+    "    else:\n",
+    "        mods = mods.split(\";\")\n",
+    "        mod_sites = mod_sites.split(\";\")\n",
+    "        for mod, site in zip(mods, mod_sites):\n",
+    "            if site == \"0\":\n",
+    "                continue\n",
+    "            assert seq[int(site)-1] == mod[-1]"
    ]
   }
  ],
@@ -338,6 +350,18 @@
    "display_name": "python3",
    "language": "python",
    "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.4"
   }
  },
  "nbformat": 4,