PyEvoMotion 0.1.1__py3-none-any.whl → 0.1.2__py3-none-any.whl

share/figUSA_run_args.json

@@ -5,6 +5,7 @@
     "delta_t": "7D",
     "show": false,
     "export_plots": true,
+    "confidence_level": 0.95,
     "length_filter": 0,
     "kind": "total",
     "filter": null,

share/figUSA_stats.tsv

@@ -1,34 +1,34 @@
-date	mean number of mutations	var number of mutations	size
-2020-12-17	34.666666666666664	5.066666666666665	6
-2020-12-24	33.976190476190474	3.7311265969802596	42
-2020-12-31	34.19230769230769	2.546953046953047	78
-2021-01-07	35.15238095238095	5.4188644688644745	105
-2021-01-14	36.39887640449438	4.094236018536149	178
-2021-01-21	37.67487684729064	4.557137979807834	203
-2021-01-28	38.28421052631579	4.2745737583395	285
-2021-02-04	38.86852589641434	4.146645418326694	251
-2021-02-11	39.538699690402474	4.584677807049599	323
-2021-02-18	40.1993769470405	5.741374610591899	321
-2021-02-25	40.53168044077135	5.183385842351184	363
-2021-03-04	40.43465045592705	7.520868856104973	329
-2021-03-11	41.03508771929825	6.573545300200646	342
-2021-03-18	41.24050632911393	7.756730707447153	395
-2021-03-25	41.31578947368421	6.91238966982674	323
-2021-04-01	41.463611859838274	6.357456108399504	371
-2021-04-08	41.80653266331658	8.771040340240246	398
-2021-04-15	42.03133903133903	8.596157916157916	351
-2021-04-22	42.390243902439025	7.597295864262986	369
-2021-04-29	42.429752066115704	7.4004383361490325	363
-2021-05-06	42.70674486803519	7.531395549422115	341
-2021-05-13	42.96060606060606	9.405738233397797	330
-2021-05-20	43.21902017291066	11.183105395545644	347
-2021-05-27	43.90149253731343	11.154937885423184	335
-2021-06-03	43.76347305389221	11.958902015788244	334
-2021-06-10	44.061624649859944	11.277090611525502	357
-2021-06-17	44.22287390029326	11.103122304640328	341
-2021-06-24	44.62145110410095	9.539791558519338	317
-2021-07-01	44.512121212121215	11.460338951828312	330
-2021-07-08	44.526490066225165	8.841488636113615	302
-2021-07-15	44.91830065359477	9.275270545376623	306
-2021-07-22	44.656462585034014	9.31161338255439	294
-2021-07-29	45.55797101449275	9.13895059769385	138
+date	mean number of mutations	var number of mutations	size	dt_idx
+2020-12-17	34.666666666666664	5.066666666666665	6	0.0
+2020-12-24	33.976190476190474	3.7311265969802596	42	1.0
+2020-12-31	34.19230769230769	2.546953046953047	78	2.0
+2021-01-07	35.15238095238095	5.4188644688644745	105	3.0
+2021-01-14	36.39887640449438	4.094236018536149	178	4.0
+2021-01-21	37.67487684729064	4.557137979807834	203	5.0
+2021-01-28	38.28421052631579	4.2745737583395	285	6.0
+2021-02-04	38.86852589641434	4.146645418326694	251	7.0
+2021-02-11	39.538699690402474	4.584677807049599	323	8.0
+2021-02-18	40.1993769470405	5.741374610591899	321	9.0
+2021-02-25	40.53168044077135	5.183385842351184	363	10.0
+2021-03-04	40.43465045592705	7.520868856104973	329	11.0
+2021-03-11	41.03508771929825	6.573545300200646	342	12.0
+2021-03-18	41.24050632911393	7.756730707447153	395	13.0
+2021-03-25	41.31578947368421	6.91238966982674	323	14.0
+2021-04-01	41.463611859838274	6.357456108399504	371	15.0
+2021-04-08	41.80653266331658	8.771040340240246	398	16.0
+2021-04-15	42.03133903133903	8.596157916157916	351	17.0
+2021-04-22	42.390243902439025	7.597295864262986	369	18.0
+2021-04-29	42.429752066115704	7.4004383361490325	363	19.0
+2021-05-06	42.70674486803519	7.531395549422115	341	20.0
+2021-05-13	42.96060606060606	9.405738233397797	330	21.0
+2021-05-20	43.21902017291066	11.183105395545644	347	22.0
+2021-05-27	43.90149253731343	11.154937885423184	335	23.0
+2021-06-03	43.76347305389221	11.958902015788244	334	24.0
+2021-06-10	44.061624649859944	11.277090611525502	357	25.0
+2021-06-17	44.22287390029326	11.103122304640328	341	26.0
+2021-06-24	44.62145110410095	9.539791558519338	317	27.0
+2021-07-01	44.512121212121215	11.460338951828312	330	28.0
+2021-07-08	44.526490066225165	8.841488636113615	302	29.0
+2021-07-15	44.91830065359477	9.275270545376623	306	30.0
+2021-07-22	44.656462585034014	9.31161338255439	294	31.0
+2021-07-29	45.55797101449275	9.13895059769385	138	32.0

share/generate_sequences_from_test5_data.py

@@ -0,0 +1,107 @@
+#´:°•.°+.*•´.*:˚.°*.˚•´.°:°•.°•.*•´.*:˚.°*.˚•´.°:°•.°+.*•´.*:#
+#                           IMPORTS                          #
+#.•°:°.´+˚.*°.˚:*.´•*.+°.•°:´*.´•*.•°.•°:°.´:•˚°.*°.˚:*.´+°.•#
+
+import os
+import numpy as np
+import pandas as pd
+
+from Bio import SeqIO
+from Bio.SeqRecord import SeqRecord
+
+#´:°•.°+.*•´.*:˚.°*.˚•´.°:°•.°•.*•´.*:˚.°*.˚•´.°:°•.°+.*•´.*:#
+#                          CONSTANTS                         #
+#.•°:°.´+˚.*°.˚:*.´•*.+°.•°:´*.´•*.•°.•°:°.´:•˚°.*°.˚:*.´+°.•#
+
+WUHAN_REF_PATH = "tests/data/test3/test3UK.fasta"
+DATE_MAP = dict(zip(
+    range(41),
+    pd.date_range(start="2020-01-01", periods=41, freq="7D")
+))
+NUCLEOTIDES = {"A", "C", "G", "T"}
+TEST5_BASE_PATH = "tests/data/test5"
+
+#´:°•.°+.*•´.*:˚.°*.˚•´.°:°•.°•.*•´.*:˚.°*.˚•´.°:°•.°+.*•´.*:#
+#                          FUNCTIONS                         #
+#.•°:°.´+˚.*°.˚:*.´•*.+°.•°:´*.´•*.•°.•°:°.´:•˚°.*°.˚:*.´+°.•#
+
+def load_synthdata(path: str) -> pd.DataFrame:
+    """Loads the synthdata from the given path.
+    """
+
+    df = pd.read_csv(path, sep="\t", index_col=0)
+    df.columns = [f"seq{k}" for k in range(len(df.columns))]
+
+    return df
+
+def get_wuhan_ref() -> SeqRecord:
+    """Returns the Wuhan reference sequence.
+    """
+    # We know the Wuhan sequence is the first one in the file
+    with open(WUHAN_REF_PATH, "r") as f:
+        for record in SeqIO.parse(f, "fasta"):
+            return record
+
+def create_synthetic_sequence(mut_num: int, wuhan_ref: SeqRecord) -> str:
+    """Creates a synthetic sequence from the Wuhan reference sequence.
+    """
+    _seq = list(wuhan_ref.seq)
+    mut_positions = np.random.choice(range(len(_seq)), mut_num, replace=False)
+    nucleotides = [
+        np.random.choice(list(NUCLEOTIDES - {_seq[i]}))
+        for i in mut_positions
+    ]
+    for pos, nuc in zip(mut_positions, nucleotides):
+        _seq[pos] = nuc
+    return "".join(_seq)
+
+
+def create_synthetic_sequences(output_path: str, synthdata: pd.DataFrame, wuhan_ref: SeqRecord) -> None:
+    """Creates the synthetic dataset from the synthdata reference and the Wuhan reference sequence.
+    """
+    with open(f"{output_path}.fasta", "w") as f, open(f"{output_path}.tsv", "w") as g:
+        f.write(f">{wuhan_ref.id}\n{wuhan_ref.seq}\n")
+        g.write(f"id\tdate\n{wuhan_ref.id}\t2019-12-29\n")
+        for row_idx, row in synthdata.iterrows():
+            for col_name, col in row.items():
+                # Fetch the row number, the column name and the entry in the synthdata
+                f.write(f">{col_name}_{row_idx}\n{create_synthetic_sequence(col, wuhan_ref)}\n")
+                g.write(f"{col_name}_{row_idx}\t{DATE_MAP[row_idx].strftime('%Y-%m-%d')}\n")
+
+def process_test5_files():
+    """Process all .txt files in test5 subdirectories and generate corresponding .fasta and .tsv files.
+    """
+    WUHAN_REF = get_wuhan_ref()
+
+    for subdir in os.listdir(TEST5_BASE_PATH):
+        txt_files = [
+            file
+            for file in os.listdir(f"{TEST5_BASE_PATH}/{subdir}")
+            if file.endswith(".txt")
+        ]
+
+        for txt_file in txt_files:
+        
+            name = txt_file.strip(".txt")
+            create_synthetic_sequences(
+                f"{TEST5_BASE_PATH}/{subdir}/{name}",
+                load_synthdata(
+                    f"{TEST5_BASE_PATH}/{subdir}/{txt_file}"
+                ),
+                WUHAN_REF
+            )
+        
+
+#´:°•.°+.*•´.*:˚.°*.˚•´.°:°•.°•.*•´.*:˚.°*.˚•´.°:°•.°+.*•´.*:#
+#                           MAIN                             #
+#.•°:°.´+˚.*°.˚:*.´•*.+°.•°:´*.´•*.•°.•°:°.´:•˚°.*°.˚:*.´+°.•#
+
+def main():
+    """Main function to process all test5 files.
+    """
+    print("Processing all .txt files in test5 subdirectories...")
+    process_test5_files()
+    print("All synthetic datasets created successfully.")
+
+if __name__ == "__main__":
+    main()