Merge pull request #122 from neherlab/description-refactor

Description refactor

Author: ivan-aksamentov

docs/docs/pypangraph/tutorial4.md

@@ -92,10 +92,10 @@ For these cases, pypangraph provides a method to quickly survey all changes in c
 
 ![minimal synteny units](../assets/pp_t4_minimal_synteny_units.png)
 
-For this part of the tutorial we will analyze the `ecoli_graph.json.gz` graph, containing 10 _E. coli_ chromosomes. The minimal sinteny units for this graph can be extracted with the function:
+For this part of the tutorial we will analyze the `graph.json` file created [in the first tutorial](../tutorial/tutorial_1.md#building-the-pangraph), containing 10 _E. coli_ chromosomes. The minimal sinteny units for this graph can be extracted with the function:
 
 ```python
-graph = pp.Pangraph.from_json("ecoli_graph.json.gz")
+graph = pp.Pangraph.from_json("graph.json")
 
 # find MSUs
 threshold_len = 100  # minimal length of core blocks to consider
@@ -142,7 +142,7 @@ Similarly to what done for plasmids, we can visualize these units on Bandage. We
 pangraph export gfa \
     --no-duplicated \
     --minimum-depth 10 \
-    ecoli_graph.json.gz > ecoli.gfa
+    graph.json > ecoli.gfa
 ```
 
 And then we can export the dictionary of core-block colors with:

docs/docs/tutorial/tutorial_2.md

@@ -29,7 +29,8 @@ A path object has the following structure:
     "name": "NZ_CP010150",
     "nodes": [10429785587629589393, 10765941013351965021, 7771937209474314297, ...],
     "circular": true,
-    "tot_len": 4827779
+    "tot_len": 4827779,
+    "desc": null
 },
 ```
 
@@ -43,6 +44,7 @@ Here is a complete list containing a description of every entry in the path obje
 - `nodes` : the ordered list of node ids that make up the path.
 - `circular` : indicates whether the considered sequence is circular (e.g. plasmid) or not. This is controlled by the `--circular` flag of the [`build` command](../reference#pangraph-build).
 - `tot_len` : the total length of the path, in nucleotides.
+- `desc` : (optional) path description string, corresponding to the description field in the input fasta file. For example `>NZ_CP010150 Escherichia coli strain 1303 chromosome, complete genome` would be split in `name="NZ_CP010150"` and `desc="Escherichia coli strain 1303 chromosome, complete genome"`.
 
 
 ## Nodes

packages/pangraph/src/pangraph/pangraph_block.rs

@@ -167,8 +167,10 @@ impl PangraphBlock {
           )
           .unwrap();
 
-          let id = format!("{node_id} {meta}");
-          (id, None)
+          let id = node_id.to_string();
+          let descr = Some(meta);
+
+          (id, descr)
         }
         RecordNaming::Path => {
           let path_id = graph.nodes[node_id].path_id();

packages/pypangraph/pypangraph/class_graph.py

@@ -200,7 +200,12 @@ def core_genome_alignment(self, guide_strain=None):
         # convert to biopython alignment
         records = []
         for strain, seq in alignment.items():
-            record = SeqRecord.SeqRecord(Seq.Seq(seq), id=strain, description="")
+            desc = self.paths[strain].desc
+            if desc is None:
+                desc = ""
+            record = SeqRecord.SeqRecord(
+                Seq.Seq(seq), id=strain, name="", description=desc
+            )
             records.append(record)
         alignment = AlignIO.MultipleSeqAlignment(records)
 

packages/pypangraph/pypangraph/class_path.py

@@ -3,7 +3,8 @@
 
 class Path:
     """Pangraph path object. It has attributes:
-    - name (str): strain name
+    - name (str): strain name (fasta id pangraph in input file)
+    - descr (str): strain description (fasta description in pangraph input file)
     - circular (bool): whether the path object is circular
     - nodes (list): list of node ids in the path
     - nuc_len (int): total length of the path in base-pairs
@@ -15,6 +16,7 @@ def __init__(self, pan_path):
         self.circular = pan_path["circular"]
         self.nodes = pan_path["nodes"]
         self.nuc_len = pan_path["tot_len"]
+        self.desc = pan_path.get("desc", None)
 
     def __len__(self):
         """Returns the number of nodes in the path"""

packages/pypangraph/pypangraph/pangraph_schema.py

@@ -32,6 +32,7 @@
                 "tot_len": {"type": "integer", "format": "uint", "minimum": 0},
                 "circular": {"type": "boolean"},
                 "name": {"type": ["string", "null"]},
+                "desc": {"type": ["string", "null"]},
             },
             "required": ["id", "nodes", "tot_len", "circular"],
         },

packages/pypangraph/tests/data/ecoli_graph.json.gz

@@ -66,7 +66,8 @@
       ],
       "tot_len": 80596,
       "circular": true,
-      "name": "RCS48_p1"
+      "name": "RCS48_p1",
+      "desc": null
     },
     "1": {
       "id": 1,
@@ -135,7 +136,8 @@
       ],
       "tot_len": 80790,
       "circular": true,
-      "name": "RCS49_p1"
+      "name": "RCS49_p1",
+      "desc": null
     },
     "2": {
       "id": 2,
@@ -209,7 +211,8 @@
       ],
       "tot_len": 91307,
       "circular": true,
-      "name": "RCS64_p2"
+      "name": "RCS64_p2",
+      "desc": null
     },
     "3": {
       "id": 3,
@@ -279,7 +282,8 @@
       ],
       "tot_len": 87487,
       "circular": true,
-      "name": "RCS80_p1"
+      "name": "RCS80_p1",
+      "desc": null
     },
     "4": {
       "id": 4,
@@ -357,7 +361,8 @@
       ],
       "tot_len": 106000,
       "circular": true,
-      "name": "RCS100_p1"
+      "name": "RCS100_p1",
+      "desc": null
     },
     "5": {
       "id": 5,
@@ -443,7 +448,8 @@
       ],
       "tot_len": 108661,
       "circular": true,
-      "name": "RCS72_p1"
+      "name": "RCS72_p1",
+      "desc": null
     },
     "6": {
       "id": 6,
@@ -531,7 +537,8 @@
       ],
       "tot_len": 111333,
       "circular": true,
-      "name": "RCS34_p1"
+      "name": "RCS34_p1",
+      "desc": null
     },
     "7": {
       "id": 7,
@@ -617,7 +624,8 @@
       ],
       "tot_len": 108379,
       "circular": true,
-      "name": "RCS75_p1"
+      "name": "RCS75_p1",
+      "desc": null
     },
     "8": {
       "id": 8,
@@ -704,7 +712,8 @@
       ],
       "tot_len": 110066,
       "circular": true,
-      "name": "RCS76_p1"
+      "name": "RCS76_p1",
+      "desc": null
     },
     "9": {
       "id": 9,
@@ -772,7 +781,8 @@
       ],
       "tot_len": 93239,
       "circular": true,
-      "name": "RCS73_p1"
+      "name": "RCS73_p1",
+      "desc": null
     },
     "10": {
       "id": 10,
@@ -849,7 +859,8 @@
       ],
       "tot_len": 89006,
       "circular": true,
-      "name": "RCS29_p1"
+      "name": "RCS29_p1",
+      "desc": null
     },
     "11": {
       "id": 11,
@@ -925,7 +936,8 @@
       ],
       "tot_len": 88922,
       "circular": true,
-      "name": "RCS33_p1"
+      "name": "RCS33_p1",
+      "desc": null
     },
     "12": {
       "id": 12,
@@ -1004,7 +1016,8 @@
       ],
       "tot_len": 91634,
       "circular": true,
-      "name": "RCS71_p1"
+      "name": "RCS71_p1",
+      "desc": null
     },
     "13": {
       "id": 13,
@@ -1077,7 +1090,8 @@
       ],
       "tot_len": 94836,
       "circular": true,
-      "name": "RCS74_p1"
+      "name": "RCS74_p1",
+      "desc": null
     },
     "14": {
       "id": 14,
@@ -1160,7 +1174,8 @@
       ],
       "tot_len": 117655,
       "circular": true,
-      "name": "RCS58_p1"
+      "name": "RCS58_p1",
+      "desc": null
     }
   },
   "blocks": {