Merge branch 'dev'

byemaxx · Oct 3, 2024 · 01dfd0e · 01dfd0e
2 parents 239d751 + 0da348e
commit 01dfd0e
Show file tree

Hide file tree

Showing 20 changed files with 16,388 additions and 14,157 deletions.
diff --git a/Docs/ChangeLog.md b/Docs/ChangeLog.md
@@ -1,3 +1,14 @@
+# Version: 1.115.1
+## Date: 2024-10-03
+### Changes:
+- New: added multiprocessing option for LFQ.
+
+
+# Version: 1.115.0
+## Date: 2024-10-02
+### Changes:
+- New: added DriectLFQ algorithm option for quantification.
+
 # Version: 1.114.5
 ## Date: 2024-09-23
 ### Changes:

diff --git a/Docs/MetaX_Cookbook.assets/TaxaFunc_ready.png b/Docs/MetaX_Cookbook.assets/TaxaFunc_ready.png
diff --git a/Docs/MetaX_Cookbook.assets/set_multi_table.png b/Docs/MetaX_Cookbook.assets/set_multi_table.png
diff --git a/Docs/MetaX_Cookbook.md b/Docs/MetaX_Cookbook.md
@@ -275,6 +275,16 @@ Click **Create Proteins Intensity Table** to sum peptides to proteins if the Pro
 
 ### Data preprocessing
 
+- **Quantitative Method：**
+
+  - **<u>Sum</u>**: Sum the peptides intensity directly to Taxa, Functions or OTFs intensity.
+
+  - **<u>DirecteLFQ</u>**: Using DirecteLFQ to normalize the peptides and then estimate the intensity by using  *intensity traces*.
+
+
+
+- **Outlier handling:**
+
 There are several methods for detecting and handling outliers.
 
 - Two steps will be applied:

diff --git a/Docs/example.ipynb b/Docs/example.ipynb
@@ -91,14 +91,17 @@
     "Parameters:\n",
     "- `level (str)`: The taxonomic level to consider. Default is 's' (species).\n",
     "- `func_threshold (float)`: The threshold for function proportion. Default is 1.00.\n",
+    "- `outlier_params (dict)`: Parameters for outlier detection and handling. Default is {'outlier_detect_method': None, 'outlier_handle_method': None, 'outlier_detect_by_group': None, 'outlier_handle_by_group': None}.\n",
     "- `data_preprocess_params (dict)`: Parameters for data preprocessing. Default is {'normalize_method': None, 'transform_method': None,\n",
-    "                                    'batch_meta': None, 'outlier_detect_method': None, 'outlier_handle_method': None,\n",
-    "                                    'outlier_detect_by_group': None, 'outlier_handle_by_group': None, 'processing_order': None}.\n",
+    "                                    'batch_meta': None, 'outlier_detect_method': None, 'processing_order': None}.\n",
     "- `peptide_num_threshold (dict)`: Thresholds for peptide numbers in Function table, Taxa table, and Taxa-Function table.\n",
     "                                Default is {'taxa': 1, 'func': 1, 'taxa_func': 1}.\n",
     "- `sum_protein (bool)`: Whether to sum protein intensity. Default is False.\n",
     "- `sum_protein_params (dict)`: Parameters for summing protein intensity. Default is {'method': 'razor', 'by_sample': False,\n",
-    "                                'rank_method': 'unique_counts'}.\n"
+    "                                'rank_method': 'unique_counts', 'greedy_method': 'heap', 'peptide_num_threshold': 1}.\n",
+    "- `split_func (bool)`: Whether to split functions. Default is False.\n",
+    "- `split_func_params (dict)`: Parameters for splitting functions. Default is {'split_by': '|', 'share_intensity': Falsee}.\n",
+    "- `quant_method (str)`: The quantification method. Default is 'sum'. Options are 'sum', 'lfq'"
    ]
   },
   {
@@ -143,15 +146,20 @@
     "\n",
     "# sw.set_group('Person')\n",
     "# sw.set_group('Person')\n",
-    "sw.set_multi_tables(level='s', data_preprocess_params = {'normalize_method': None, 'transform_method': \"log10\",\n",
-    "                                                            'batch_meta': None, 'outlier_detect_method': None,\n",
-    "                                                            'outlier_handle_method': None,\n",
-    "                                                            'outlier_detect_by_group': None,\n",
-    "                                                            'outlier_handle_by_group': None,\n",
-    "                                                            'processing_order': None},\n",
-    "                    peptide_num_threshold = {'taxa': 3, 'func': 1, 'taxa_func': 1},\n",
-    "                    sum_protein=False)\n",
-    "# sw.set_multi_tables(level='s', sum_protein=True, sum_protein_params= { 'method': 'razor', 'by_sample': False, 'rank_method': 'unique'})"
+    "sw.set_multi_tables(level='s', \n",
+    "                    outlier_params = {'detect_method': 'zero-dominant', 'handle_method': 'original',\n",
+    "                        \"detection_by_group\" : 'Individual', \"handle_by_group\": None},\n",
+    "                    data_preprocess_params = {\n",
+    "                                            'normalize_method': None, \n",
+    "                                            'transform_method': \"log2\",\n",
+    "                                            'batch_meta': 'None', \n",
+    "                                            'processing_order': None},\n",
+    "                peptide_num_threshold = {'taxa': 2, 'func': 2, 'taxa_func': 2},\n",
+    "                keep_unknow_func=False, sum_protein=False, \n",
+    "                sum_protein_params = {'method': 'razor', 'by_sample': False, 'rank_method': 'unique_counts', 'greedy_method': 'heap', 'peptide_num_threshold': 3},\n",
+    "                split_func=True, split_func_params = {'split_by': '|', 'share_intensity': False},\n",
+    "                taxa_and_func_only_from_otf=False, quant_method='sum'\n",
+    "                )\n"
    ]
   },
   {