add plants; fix threshold (#4)

Author: ctb

chill_filter_web/__init__.py

@@ -136,7 +136,8 @@ def get_md5(path):
                 start = time.time()
                 status = branch.do_fastmultigather(
                     outpath,
-                    "prepare-db/animals-and-gtdb.rocksdb",
+#                    "prepare-db/animals-and-gtdb.rocksdb",
+                    "prepare-db/plants+animals+gtdb.rocksdb",
                     0,
                     KSIZE,
                     SCALED,
@@ -157,7 +158,7 @@ def get_md5(path):
 
             # load/process
             gather_df = pd.read_csv(csv_filename)
-            gather_df = gather_df[gather_df["f_unique_weighted"] >= 0.1]
+            gather_df = gather_df[gather_df["f_unique_weighted"] >= 0.001]
             if len(gather_df):
                 last_row = gather_df.tail(1).squeeze()
                 sum_weighted_found = last_row["sum_weighted_found"]

prepare-db/Snakefile

@@ -11,6 +11,7 @@ GENOMES = ['bosTau9',
 rule all:
     input:
         'animals-and-gtdb.rocksdb',
+        'plants+animals+gtdb.rocksdb',
 
 rule index_animals_and_gtdb:
     input:
@@ -32,6 +33,27 @@ rule animals_and_gtdb:
     """
 
 
+rule index_plants_animals_and_gtdb:
+    input:
+        "plants+animals+gtdb.mf.csv",
+    output:
+        protected(directory("plants+animals+gtdb.rocksdb")),
+    shell: """
+        sourmash scripts index {input} -o {output} -k 51
+    """
+
+rule plants_animals_and_gtdb:
+    input:
+        expand('outputs/{g}.k51.100k.sig.zip', g=GENOMES),
+        'outputs/all-gtdb-rs220.k51.100k.sig.zip',
+        'downloads/genbank-plants-merged-2024.07.sig.zip',
+    output:
+        'plants+animals+gtdb.mf.csv',
+    shell: """
+        sourmash sig collect -F csv {input} -o {output} --abspath
+    """
+
+
 rule downsample:
     input:
         "downloads/{g}.sig.zip",