Add some end-to-end tests in CI and example Viridian data subset

Closes #208

fixup

Author: jeromekelleher

.github/workflows/ci.yml

@@ -16,8 +16,8 @@ jobs:
   #       with:
   #         python-version: '3.11'
   #     - uses: pre-commit/[email protected]
-  test:
-    name: Test
+  unit:
+    name: Unit tests
     runs-on: ubuntu-latest
 
     steps:
@@ -43,8 +43,51 @@ jobs:
       #     # https://github.com/coverallsapp/github-action
       #     fail-on-error: false
 
+  end_to_end:
+    name: End to end tests
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install '.[dev,analysis]'
+
+      - name: Create basedir and copy data
+        run: |
+          mkdir -p testrun
+          cp -R tests/data testrun/data
+          gunzip testrun/data/alignments.fasta.gz
+
+      - name: Import alignments
+        run: |
+          python3 -m sc2ts import-alignments testrun/alignments.db \
+            testrun/data/alignments.fasta
+          python3 -m sc2ts info-alignments testrun/alignments.db
+
+      - name: Import metadata
+        run: |
+          python3 -m sc2ts import-metadata testrun/data/metadata.tsv testrun/metadata.db
+          python3 -m sc2ts info-metadata testrun/metadata.db
+
+      - name: Run inference
+        run: |
+          python3 -m sc2ts daily-extend -v testrun/alignments.db testrun/metadata.db \
+            testrun/ --min-group-size=2
+
+      - name: Validate
+        run: |
+          python3 -m sc2ts validate -v testrun/alignments.db testrun/2020-02-13.ts
+
+      - name: MatchDB
+        run: |
+          python3 -m sc2ts info-matches testrun/match.db
+
   packaging:
-    name: Packaging
+    name: Packaging tests
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4

make_test_data.py

@@ -0,0 +1,48 @@
+# Script to make the test subset data.
+import contextlib
+import sys
+
+import pandas as pd
+
+import sc2ts
+
+
+def write_fasta(strain, alignment, out):
+    s = bytes(alignment.astype("S1").data).decode()
+    print(f">{strain}", file=out)
+    print(s[1:], file=out)
+
+
+def main(alignment_store, metadata_db, output_prefix):
+    dates = metadata_db.get_days()
+    alignment_path = output_prefix + "/alignments.fasta"
+    metadata_path = output_prefix + "/metadata.tsv"
+    metadata = []
+    with open(alignment_path, "w") as alignment_file:
+        strains = []
+        for date in dates[:20]:
+            records = list(metadata_db.get(date))
+            for record in records[:5]:
+                strain = record["strain"]
+                alignment = alignment_store[strain]
+                write_fasta(strain, alignment, alignment_file)
+                metadata.append(record)
+
+    # Add a record for a missing sequence.
+    record = dict(record)
+    record["strain"] = "ERR_MISSING"
+    metadata.append(record)
+
+    df = pd.DataFrame(metadata)
+    df.to_csv(metadata_path, sep="\t", index=False)
+
+
+if __name__ == "__main__":
+    if len(sys.argv) != 4:
+        raise ValueError(
+            "Usage: python3 make_test_data.py [alignment_db] [metadata_db] [prefix]"
+        )
+    with contextlib.ExitStack() as exit_stack:
+        alignment_store = exit_stack.enter_context(sc2ts.AlignmentStore(sys.argv[1]))
+        metadata_db = exit_stack.enter_context(sc2ts.MetadataDb(sys.argv[2]))
+        main(alignment_store, metadata_db, sys.argv[3])

sc2ts/cli.py

@@ -18,6 +18,7 @@
 import tsinfer
 import click
 import daiquiri
+import pandas as pd
 
 import sc2ts
 from . import core
@@ -177,11 +178,7 @@ def add_provenance(ts, output_file):
     tables = ts.dump_tables()
     tables.provenances.add_row(json.dumps(provenance))
     tables.dump(output_file)
-
-
-def dump_samples(samples, output_file):
-    with open(output_file, "wb") as f:
-        pickle.dump(samples, file=f)
+    logger.info(f"Wrote {output_file}")
 
 
 @click.command()
@@ -199,12 +196,13 @@ def dump_samples(samples, output_file):
     ),
 )
 @click.option("--num-mismatches", default=None, type=float, help="num-mismatches")
-@click.option("--max-hmm-cost", default=None, type=float, help="max-hmm-cost")
+@click.option("--max-hmm-cost", default=5, type=float, help="max-hmm-cost")
 @click.option(
     "--min-group-size",
-    default=None,
+    default=10,
     type=int,
     help="Minimum size of groups of reconsidered samples",
+    show_default=True
 )
 @click.option(
     "--num-past-days",
@@ -327,14 +325,53 @@ def validate(alignment_db, ts_file, verbose):
     """
     setup_logging(verbose)
 
-    if ts_file.endswith(".tsz"):
-        ts = tszip.decompress(ts_file)
-    else:
-        ts = tskit.load(ts_file)
+    ts = tszip.load(ts_file)
     with sc2ts.AlignmentStore(alignment_db) as alignment_store:
         inference.validate(ts, alignment_store, show_progress=True)
 
 
+@click.command()
+@click.argument("ts_file")
+@click.option("-v", "--verbose", count=True)
+def export_alignments(ts_file, verbose):
+    """
+    Export alignments from the specified tskit file to FASTA
+    """
+    setup_logging(verbose)
+    ts = tszip.load(ts_file)
+    for u, alignment in zip(ts.samples(), ts.alignments(left=1)):
+        strain = ts.node(u).metadata["strain"]
+        if strain == core.REFERENCE_STRAIN:
+            continue
+        print(f">{strain}")
+        print(alignment)
+
+
+@click.command()
+@click.argument("ts_file")
+@click.option("-v", "--verbose", count=True)
+def export_metadata(ts_file, verbose):
+    """
+    Export metadata from the specified tskit file to TSV
+    """
+    setup_logging(verbose)
+    ts = tszip.load(ts_file)
+    data = []
+    for u in ts.samples():
+        md = ts.node(u).metadata
+        if md["strain"] == core.REFERENCE_STRAIN:
+            continue
+        try:
+            # FIXME this try/except is needed because of some samples not having full
+            # metadata. Can drop when fixed.
+            del md["sc2ts"]
+        except KeyError:
+            pass
+        data.append(md)
+    df = pd.DataFrame(data)
+    df.to_csv(sys.stdout, sep="\t", index=False)
+
+
 def examine_recombinant(work):
     base_ts = tszip.decompress(work.ts_path)
     with sc2ts.AlignmentStore(work.alignment_db) as a:
@@ -437,6 +474,8 @@ def cli():
 cli.add_command(info_alignments)
 cli.add_command(info_metadata)
 cli.add_command(info_matches)
+cli.add_command(export_alignments)
+cli.add_command(export_metadata)
 
 cli.add_command(daily_extend)
 cli.add_command(validate)

sc2ts/inference.py

@@ -830,28 +830,6 @@ def add_matching_results(
     return ts  # , excluded_samples, added_samples
 
 
-def fetch_samples_from_pickle_file(date, num_past_days=None, in_dir=None):
-    if in_dir is None:
-        return []
-    if num_past_days is None:
-        num_past_days = 0
-    file_suffix = ".excluded_samples.pickle"
-    samples = []
-    for i in range(num_past_days, 0, -1):
-        past_date = date - datetime.timedelta(days=i)
-        pickle_file = in_dir + "/"
-        pickle_file += past_date.strftime("%Y-%m-%d") + file_suffix
-        if os.path.exists(pickle_file):
-            samples += parse_pickle_file(pickle_file)
-    return samples
-
-
-def parse_pickle_file(pickle_file):
-    """Return a list of Sample objects."""
-    with open(pickle_file, "rb") as f:
-        samples = pickle.load(f)
-    return samples
-
 
 def solve_num_mismatches(ts, k):
     """

sc2ts/metadata.py

@@ -8,22 +8,6 @@
 logger = logging.getLogger(__name__)
 
 
-def metadata_to_db(csv_path, db_path):
-
-    df = pd.read_csv(
-        csv_path,
-        sep="\t",
-        parse_dates=["date", "date_submitted"],
-    )
-    db_path = pathlib.Path(db_path)
-    if db_path.exists():
-        db_path.unlink()
-    with sqlite3.connect(db_path) as conn:
-        df.to_sql("samples", conn, index=False)
-        conn.execute("CREATE INDEX [ix_samples_strain] on 'samples' ([strain]);")
-        conn.execute("CREATE INDEX [ix_samples_date] on 'samples' ([date]);")
-
-
 def dict_factory(cursor, row):
     col_names = [col[0] for col in cursor.description]
     return {key: value for key, value in zip(col_names, row)}
@@ -75,7 +59,9 @@ def get(self, date):
             for row in self.conn.execute(sql, [date]):
                 yield row
 
-    def get_days(self, date):
+    def get_days(self, date=None):
+        if date is None:
+            date = "2000-01-01"
         sql = "SELECT DISTINCT(date) FROM samples WHERE date>? ORDER BY date;"
         with self.conn:
             dates = []

tests/data/alignments.fasta.gz

@@ -0,0 +1,57 @@
+Study	Sample	Experiment	strain	Platform	Country	Region	Collection_date	date_submitted	date	Date_tree_order	Viridian_result	Genbank_accession	Genbank_other_runs	In_Viridian_tree	In_intersection	Artic_primer_version	Viridian_amplicon_scheme	Viridian_N	Genbank_N	Viridian_pangolin	Viridian_scorpio	Genbank_pangolin	Genbank_scorpio	Genbank_tree_name	Viridian_cons_len	Viridian_cons_het
+PRJNA625669	SAMN19315526	SRX10971427	SRR14631544	ION_TORRENT	India	Vadodara, Gujarat	2020-01-01	2021-05-25	2020-01-01	Date	PASS	.	.	T	F	.	COVID-AMPLISEQ-V1	3	.	B.1.36.29	.	.	.	.	29832	0
+PRJNA631042	SAMN14891491	SRX8325850	SRR11772659	ILLUMINA	USA	none	2020-01-19	2020-05-13	2020-01-19	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	0	.	A	.	.	.	.	29836	0
+PRJNA613958	SAMN14422702	SRX7976447	SRR11397727	OXFORD_NANOPORE	Australia	Melbourne, Victoria	2020-01-24	2020-03-25	2020-01-24	Date	PASS	MT450919.1	SRR11397730	T	F	.	COVID-ARTIC-V3	572	.	B	.	.	.	.	29836	0
+PRJNA613958	SAMN14422702	SRX7976444	SRR11397730	ILLUMINA	Australia	Melbourne, Victoria	2020-01-24	2020-03-25	2020-01-24	Date	PASS	MT450919.1	SRR11397727	T	F	.	COVID-ARTIC-V3	545	.	B	.	.	.	.	29804	0
+PRJNA613958	SAMN14422703	SRX7976448	SRR11397726	OXFORD_NANOPORE	Australia	Melbourne, Victoria	2020-01-25	2020-03-25	2020-01-25	Date	PASS	MT450920.1	SRR11397729	T	F	.	COVID-ARTIC-V3	284	.	B	.	.	.	.	29835	0
+PRJNA613958	SAMN14422703	SRX7976445	SRR11397729	ILLUMINA	Australia	Melbourne, Victoria	2020-01-25	2020-03-25	2020-01-25	Date	PASS	MT450920.1	SRR11397726	T	F	.	COVID-ARTIC-V3	557	.	B	.	.	.	.	29812	0
+PRJNA627662	SAMN14678591	SRX8163980	SRR11597198	ILLUMINA	China	Shanghai	2020-01-25	2020-05-14	2020-01-25	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	257	.	A	.	.	.	.	29836	0
+PRJNA627662	SAMN14678596	SRX8164035	SRR11597143	ILLUMINA	China	Shanghai	2020-01-28	2020-05-14	2020-01-28	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	257	.	B	.	.	.	.	29836	0
+PRJNA627662	SAMN14678595	SRX8164024	SRR11597154	ILLUMINA	China	Shanghai	2020-01-28	2020-05-14	2020-01-28	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	498	.	B	.	.	.	.	29836	1
+PRJNA692078	SAMN17313446	SRX12029627	SRR15736313	ILLUMINA	United Kingdom	none	2020-06-16	2021-09-09	2020-01-29	Date	PASS	OK041130.1	.	T	T	.	COVID-ARTIC-V3	0	0	A.5	.	A	.	SRR15736313.genbank.OK041130.1	29836	3
+PRJNA627662	SAMN14678598	SRX8164057	SRR11597121	ILLUMINA	China	Shanghai	2020-01-29	2020-05-14	2020-01-29	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	257	.	A	.	.	.	.	29836	0
+PRJNA627662	SAMN14678597	SRX8164046	SRR11597132	ILLUMINA	China	Shanghai	2020-01-29	2020-05-14	2020-01-29	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	0	.	A	.	.	.	.	29836	0
+PRJNA627662	SAMN14678599	SRX8163958	SRR11597220	ILLUMINA	China	Shanghai	2020-01-29	2020-05-14	2020-01-29	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	510	.	B	.	.	.	.	29836	0
+PRJNA613958	SAMN15459283	SRX8677806	SRR12162232	ILLUMINA	Australia	South Australia	2020-01-30	2020-07-08	2020-01-30	Date	PASS	MT745749.1	.	T	T	.	COVID-ARTIC-V3	306	0	B	.	B.1	.	SRR12162232.genbank.MT745749.1	29814	0
+PRJNA613958	SAMN15459282	SRX8677805	SRR12162233	ILLUMINA	Australia	South Australia	2020-01-30	2020-07-08	2020-01-30	Date	PASS	MT745748.1	.	T	T	.	COVID-ARTIC-V3	0	0	B.1	.	B.1	.	SRR12162233.genbank.MT745748.1	29810	0
+PRJNA613958	SAMN15459281	SRX8677804	SRR12162234	ILLUMINA	Australia	South Australia	2020-01-30	2020-07-08	2020-01-30	Date	PASS	MT745747.1	.	T	T	.	COVID-ARTIC-V3	0	0	B.1	.	B.1	.	SRR12162234.genbank.MT745747.1	29813	0
+PRJNA613958	SAMN15459280	SRX8677803	SRR12162235	ILLUMINA	Australia	South Australia	2020-01-30	2020-07-08	2020-01-30	Date	PASS	MT745746.1	.	T	T	.	COVID-ARTIC-V3	353	0	B	.	B.1	.	SRR12162235.genbank.MT745746.1	29810	0
+PRJNA627662	SAMN14678628	SRX8164001	SRR11597177	ILLUMINA	China	Shanghai	2020-01-30	2020-05-14	2020-01-30	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	487	.	A	.	.	.	.	29836	2
+PRJNA613958	SAMN14546631	SRX8070647	SRR11494548	ILLUMINA	Australia	Victoria	2020-01-31	2020-04-14	2020-01-31	Date	PASS	MT450930.1	.	T	T	.	COVID-ARTIC-V3	523	302	A	.	A	.	SRR11494548.genbank.MT450930.1	29812	0
+PRJNA636446	SAMN15077499	SRX8450360	SRR11903408	ILLUMINA	Canada	Toronto	2020-02	2020-06-02	2020-02-01	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	502	.	B.4	.	.	.	.	29814	0
+PRJNA627662	SAMN14678661	SRX8164038	SRR11597140	ILLUMINA	China	Shanghai	2020-02-01	2020-05-14	2020-02-01	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	321	.	A	.	.	.	.	29836	2
+PRJNA627662	SAMN14678658	SRX8164034	SRR11597144	ILLUMINA	China	Shanghai	2020-02-01	2020-05-14	2020-02-01	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	336	.	B	.	.	.	.	29836	0
+PRJNA627662	SAMN14678651	SRX8164027	SRR11597151	ILLUMINA	China	Shanghai	2020-02-01	2020-05-14	2020-02-01	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	230	.	A	.	.	.	.	29836	0
+PRJNA627662	SAMN14678649	SRX8164025	SRR11597153	ILLUMINA	China	Shanghai	2020-02-01	2020-05-14	2020-02-01	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	64	.	B	.	.	.	.	29836	1
+PRJNA627662	SAMN14678685	SRX8164064	SRR11597114	ILLUMINA	China	Shanghai	2020-02-02	2020-05-14	2020-02-02	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	280	.	B	.	.	.	.	29836	1
+PRJNA627662	SAMN14678684	SRX8164063	SRR11597115	ILLUMINA	China	Shanghai	2020-02-02	2020-05-14	2020-02-02	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	258	.	B	.	.	.	.	29832	2
+PRJNA627662	SAMN14678639	SRX8164014	SRR11597164	ILLUMINA	China	Shanghai	2020-02-01	2020-05-14	2020-02-02	End	PASS	.	.	T	F	.	COVID-ARTIC-V3	0	.	B	.	.	.	.	29835	1
+PRJNA627662	SAMN14678616	SRX8163988	SRR11597190	ILLUMINA	China	Shanghai	2020-02-05	2020-05-14	2020-02-02	End	PASS	.	.	T	F	.	COVID-ARTIC-V3	0	.	B	.	.	.	.	29833	2
+PRJNA627662	SAMN14678611	SRX8163983	SRR11597195	ILLUMINA	China	Shanghai	2020-02-04	2020-05-14	2020-02-02	End	PASS	.	.	T	F	.	COVID-ARTIC-V3	320	.	A	.	.	.	.	29836	0
+PRJEB37886	SAMEA6957880	ERX4198061	ERR4239266	ILLUMINA	United Kingdom	none	2020-02-03	2020-06-15	2020-02-03	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	551	.	B.1	.	.	.	.	29802	1
+PRJNA627662	SAMN14678615	SRX8163987	SRR11597191	ILLUMINA	China	Shanghai	2020-02-01	2020-05-14	2020-02-03	End	PASS	.	.	T	F	.	COVID-ARTIC-V3	0	.	A	.	.	.	.	29836	1
+PRJNA627662	SAMN14678665	SRX8164042	SRR11597136	ILLUMINA	China	Shanghai	2020-02-04	2020-05-14	2020-02-04	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	651	.	B	.	.	.	.	29836	1
+PRJNA627662	SAMN14678632	SRX8164006	SRR11597172	ILLUMINA	China	Shanghai	2020-02-04	2020-05-14	2020-02-04	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	550	.	B	.	.	.	.	29836	0
+PRJNA627662	SAMN14678630	SRX8164004	SRR11597174	ILLUMINA	China	Shanghai	2020-02-04	2020-05-14	2020-02-04	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	306	.	B	.	.	.	.	29833	1
+PRJNA627662	SAMN14678629	SRX8164003	SRR11597175	ILLUMINA	China	Shanghai	2020-02-04	2020-05-14	2020-02-04	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	281	.	B	.	.	.	.	29836	1
+PRJNA627662	SAMN14678618	SRX8163990	SRR11597188	ILLUMINA	China	Shanghai	2020-02-04	2020-05-14	2020-02-04	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	257	.	B	.	.	.	.	29836	0
+PRJNA627662	SAMN14678647	SRX8164022	SRR11597156	ILLUMINA	China	Shanghai	2020-02-05	2020-05-14	2020-02-05	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	343	.	A	.	.	.	.	29836	0
+PRJNA627662	SAMN14678636	SRX8164010	SRR11597168	ILLUMINA	China	Shanghai	2020-02-06	2020-05-14	2020-02-06	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	590	.	B	.	.	.	.	29836	0
+PRJNA627662	SAMN14678627	SRX8164000	SRR11597178	ILLUMINA	China	Shanghai	2020-02-06	2020-05-14	2020-02-06	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	505	.	B	.	.	.	.	29836	0
+PRJNA627662	SAMN14678610	SRX8163982	SRR11597196	ILLUMINA	China	Shanghai	2020-02-06	2020-05-14	2020-02-06	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	257	.	B.1	.	.	.	.	29836	0
+PRJNA627662	SAMN14678656	SRX8164032	SRR11597146	ILLUMINA	China	Shanghai	2020-02-07	2020-05-14	2020-02-07	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	0	.	A	.	.	.	.	29836	0
+PRJNA627662	SAMN14678652	SRX8164028	SRR11597150	ILLUMINA	China	Shanghai	2020-02-07	2020-05-14	2020-02-07	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	257	.	B.4	.	.	.	.	29836	0
+PRJNA613958	SAMN14422707	SRX7976456	SRR11397718	ILLUMINA	Australia	Melbourne, Victoria	2020-02-08	2020-03-25	2020-02-08	Date	PASS	MT450924.1	SRR11397722	T	F	.	COVID-ARTIC-V3	292	.	A	.	.	.	.	29802	0
+PRJNA613958	SAMN14422707	SRX7976452	SRR11397722	OXFORD_NANOPORE	Australia	Melbourne, Victoria	2020-02-08	2020-03-25	2020-02-08	Date	PASS	MT450924.1	SRR11397718	T	F	.	COVID-ARTIC-V3	283	.	A	.	.	.	.	29835	0
+PRJNA627662	SAMN14678662	SRX8164039	SRR11597139	ILLUMINA	China	Shanghai	2020-02-08	2020-05-14	2020-02-08	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	320	.	B.4	.	.	.	.	29836	0
+PRJNA627662	SAMN14678640	SRX8164015	SRR11597163	ILLUMINA	China	Shanghai	2020-02-08	2020-05-14	2020-02-08	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	320	.	B	.	.	.	.	29836	0
+PRJEB37886	SAMEA6916645	ERX4167203	ERR4206180	ILLUMINA	United Kingdom	none	2020-02-09	2020-06-07	2020-02-09	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	558	.	B.40	.	.	.	.	29796	1
+PRJNA627662	SAMN14678692	SRX8163962	SRR11597216	ILLUMINA	China	Shanghai	2020-02-09	2020-05-14	2020-02-09	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	0	.	B	.	.	.	.	29836	0
+PRJEB37886	SAMEA7504820	ERX4650148	ERR4780335	ILLUMINA	United Kingdom	none	2020-02-10	2020-11-02	2020-02-10	Date	PASS	.	.	T	F	3	COVID-ARTIC-V3	496	.	B.1.177	.	.	.	.	29836	0
+PRJNA627662	SAMN14678683	SRX8164062	SRR11597116	ILLUMINA	China	Shanghai	2020-02-10	2020-05-14	2020-02-10	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	612	.	B	.	.	.	.	29838	3
+PRJNA627662	SAMN14678700	SRX8163971	SRR11597207	ILLUMINA	China	Shanghai	2020-02-11	2020-05-14	2020-02-11	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	0	.	B	.	.	.	.	29836	1
+PRJNA627662	SAMN14678690	SRX8163960	SRR11597218	ILLUMINA	China	Shanghai	2020-02-11	2020-05-14	2020-02-11	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	0	.	A	.	.	.	.	29833	1
+PRJEB37886	SAMEA6916128	ERX4165491	ERR4204459	ILLUMINA	United Kingdom	none	2020-02-13	2020-06-06	2020-02-13	Date	PASS	OX627332.1	ERR4204503	T	F	.	COVID-ARTIC-V3	32	.	B.33	.	.	.	.	29807	0
+PRJEB37886	SAMEA6917193	ERX4166598	ERR4205570	ILLUMINA	United Kingdom	none	2020-02-13	2020-06-07	2020-02-13	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	573	.	B.40	.	.	.	.	29802	2
+PRJEB37886	SAMEA6917193	ERX4167623	ERR4206593	ILLUMINA	United Kingdom	none	2020-02-13	2020-06-07	2020-02-13	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	622	.	B.40	.	.	.	.	29805	0
+PRJEB37886	SAMEA6917193	ERX4167623	ERR_MISSING	ILLUMINA	United Kingdom	none	2020-02-13	2020-06-07	2020-02-13	Date	PASS	.	.	T	F	.	COVID-ARTIC-V3	622	.	B.40	.	.	.	.	29805	0