added citation, updated sample sheet handling

q2_surpi/_formats_and_types.py

@@ -1,3 +1,4 @@
+import io
 import pandas
 from qiime2.plugin import SemanticType, ValidationError
 import qiime2.plugin.model as model
@@ -7,7 +8,9 @@
 GENUS_KEY = "genus"
 FAMILY_KEY = "family"
 TAG_KEY = "tag"
-SAMPLE_NAME_KEY = 'sample'
+SAMPLE_NAME_KEY = 'Sample_Name'
+INDEX_1_KEY = "index"
+INDEX_2_KEY = "index2"
 BARCODE_KEY = 'barcode'
 
 
@@ -39,26 +42,56 @@ def _validate_(self, level):
             raise ValidationError("Expected at least one row, but got none")
 
 
-# TODO: this is speculative code and may need to be adjusted; I don't
-#  know yet what the sample info looks like
 class SurpiSampleSheetFormat(model.TextFileFormat):
-    """Represents a tab-delimited sample sheet file used by SURPI+."""
+    """Represents a csv-delimited sample sheet file used by SURPI+."""
 
     def _validate_(self, level):
-        # Validate that the file is a tsv and that it has the expected columns
-        # for those that are fixed. Note that we don't validate the values in
-        # the columns, as we don't know what they should be.
-        with self.path.open("r") as f:
-            df = pandas.read_csv(f, header=0, sep='\t')
-
-        if ((SAMPLE_NAME_KEY not in df.columns) or
-                (BARCODE_KEY not in df.columns)):
-            raise ValidationError(
-                f"Expected '{SAMPLE_NAME_KEY}' and '{BARCODE_KEY}' columns, "
-                f"but got {df.columns}")
-
-        if len(df) == 0:
-            raise ValidationError("Expected at least one row, but got none")
+        _ = surpi_count_fp_to_df(self.path)
+
+
+def surpi_count_fp_to_df(fp: str) -> pandas.DataFrame:
+    # open the file and count each line until we find one that starts with
+    # [Data]
+
+    data_table_lines = []
+    is_data = False
+    with open(fp, "r") as f:
+        for line in f:
+            if line.startswith("[Data]"):
+                is_data = True
+                continue
+            # endif line.startswith("[Data]")
+
+            if is_data and not line.startswith(','):
+                data_table_lines.append(line)
+            # endif is_data and not line.startswith(',')
+        # endfor line in f
+    # endwith self.path.open("r") as f
+
+    if len(data_table_lines) == 0:
+        raise ValidationError(
+            "Expected section starting with '[Data]', but didn't find one")
+
+    # create a streamio object from the list of lines
+    data_table_stream = io.StringIO("\n".join(data_table_lines))
+
+    # Validate that the file is a tsv and that it has the expected columns
+    # for those that are fixed. Note that we don't validate the values in
+    # the columns, as we don't know what they should be.
+    df = pandas.read_csv(data_table_stream, header=0, sep=',')
+
+    if ((SAMPLE_NAME_KEY not in df.columns) or
+            (INDEX_1_KEY not in df.columns) or
+            (INDEX_2_KEY not in df.columns)):
+        raise ValidationError(
+            f"Expected at least '{SAMPLE_NAME_KEY}', '{INDEX_1_KEY}', and "
+            f"'{INDEX_2_KEY}' columns, but got {df.columns}")
+
+    if len(df) == 0:
+        raise ValidationError("Expected at least one row, but got none")
+
+    df[BARCODE_KEY] = df[INDEX_1_KEY] + "+" + df[INDEX_2_KEY]
+    return df
 
 
 SurpiCountTableDirectoryFormat = model.SingleFileDirectoryFormat(

q2_surpi/citations.bib

@@ -0,0 +1,11 @@
+@ARTICLE{Miller2019,
+  title={Laboratory validation of a clinical metagenomic sequencing assay for pathogen detection in cerebrospinal fluid},
+  author={Miller, Steve and Naccache, Samia N and Samayoa, Erik and Messacar, Kevin and Arevalo, Shaun and Federman, Scot and Stryke, Doug and Pham, Elizabeth and Fung, Becky and Bolosky, William J and Ingebrigtsen, Danielle and Lorizio, Walter and Paff, Sandra M and Leake, John A and Pesano, Rick and DeBiasi, Roberta and Dominguez, Samuel and Chiu, Charles Y},
+  journal={Genome Res.},
+  publisher={Cold Spring Harbor Laboratory},
+  volume={29},
+  number={5},
+  pages={831--842},
+  month={may},
+  year={2019}
+}

q2_surpi/plugin_setup.py

@@ -5,7 +5,8 @@
 import q2_surpi
 from q2_surpi._formats_and_types import (
     SurpiCountTable, SurpiCountTableFormat, SurpiCountTableDirectoryFormat,
-    SurpiSampleSheet, SurpiSampleSheetFormat, SurpiSampleSheetDirectoryFormat)
+    SurpiSampleSheet, SurpiSampleSheetFormat, SurpiSampleSheetDirectoryFormat,
+    surpi_count_fp_to_df)
 
 
 plugin = Plugin(
@@ -41,7 +42,7 @@ def _1(ff: SurpiCountTableFormat) -> pandas.DataFrame:
 @plugin.register_transformer
 # load a SurpiSampleSheetFormat into a dataframe
 def _2(ff: SurpiSampleSheetFormat) -> pandas.DataFrame:
-    result = pandas.read_csv(str(ff), sep='\t', header=0)
+    result = surpi_count_fp_to_df(str(ff))
     return result
 
 

q2_surpi/tests/data/surpi_sample_info.csv

@@ -0,0 +1,101 @@
+[Header],,,,,,,,,
+,,,,,,,,,
+IEMFileVersion,4,,,,,,,,
+,,,,,,,,,
+Investigator Name,VS,,,,,,,,
+,,,,,,,,,
+Experiment Name,WW_NS_230126_qiime,,,,,,,,
+,,,,,,,,,
+Date,1/26/23,,,,,,,,
+,,,,,,,,,
+Workflow,GenerateFASTQ,,,,,,,,
+,,,,,,,,,
+Application,FASTQ Only,,,,,,,,
+,,,,,,,,,
+Assay,NEB,,,,,,,,
+,,,,,,,,,
+Description,,,,,,,,,
+,,,,,,,,,
+Chemistry,Amplicon,,,,,,,,
+,,,,,,,,,
+,,,,,,,,,
+,,,,,,,,,
+[Reads],,,,,,,,,
+,,,,,,,,,
+150,,,,,,,,,
+,,,,,,,,,
+,,,,,,,,,
+,,,,,,,,,
+[Settings],,,,,,,,,
+,,,,,,,,,
+ReverseComplement,0,,,,,,,,
+,,,,,,,,,
+,,,,,,,,,
+,,,,,,,,,
+[Data],,,,,,,,,
+,,,,,,,,,
+Sample_ID,Sample_Name,Sample_Plate,Sample_Well,I7_Index_ID,index,I5_Index_ID,index2,Prep,Type
+,,,,,,,,,
+sample-R-A1,sample-R-A1,A6,A6,7-337,AGTAGTAA,5-386,TACTGATA,RNA,Analytical
+,,,,,,,,,
+sample-R-B1,sample-R-B1,B6,B6,7-338,TACTAAGG,5-387,CTGACTCG,RNA,Analytical
+,,,,,,,,,
+sample-R-C1,sample-R-C1,C6,C6,7-339,CATTCGGA,5-388,GATGGAAA,RNA,Analytical
+,,,,,,,,,
+sample-R-D1,sample-R-D1,D6,D6,7-340,AATCGTCA,5-389,AGTTAAAG,RNA,Analytical
+,,,,,,,,,
+sample-R-E1,sample-R-E1,E6,E6,7-341,GCTGATTT,5-390,ATAGAGGC,RNA,Analytical
+,,,,,,,,,
+sample-R-F1,sample-R-F1,F6,F6,7-342,CGCGAAAG,5-391,AAAGGAGG,RNA,Analytical
+,,,,,,,,,
+sample-R-G1,sample-R-G1,G6,G6,7-343,TTGCCACT,5-392,GGGAACTG,RNA,Analytical
+,,,,,,,,,
+sample-R-H1,sample-R-H1,H6,H6,7-344,TTCGTGGA,5-393,ACAAGGTA,RNA,Analytical
+,,,,,,,,,
+sample-R-A2,sample-R-A2,A7,A7,7-345,AGTCCCGG,5-297,GCAGAAGT,RNA,Analytical
+,,,,,,,,,
+sample-R-B2,sample-R-B2,B7,B7,7-346,TCCTGGAC,5-298,CTGCTTAA,RNA,Analytical
+,,,,,,,,,
+sample-R-C2,sample-R-C2,C7,C7,7-347,CTACATGA,5-299,GATTTGAT,RNA,Analytical
+,,,,,,,,,
+sample-R-D2,sample-R-D2,D7,D7,7-348,CCGGATAG,5-300,GACTCAAA,RNA,Analytical
+,,,,,,,,,
+sample-R-E2,sample-R-E2,E7,E7,7-349,AACCCGCC,5-301,GAGGATTT,RNA,Analytical
+,,,,,,,,,
+sample-R-F2,sample-R-F2,F7,F7,7-350,CGAACGTG,5-302,CATCTGTA,RNA,Analytical
+,,,,,,,,,
+sample-R-G2,sample-R-G2,G7,G7,7-351,CCGTAGAA,5-303,TGCGCTTA,RNA,Analytical
+,,,,,,,,,
+sample-R-H2,sample-R-H2,H7,H7,7-352,CATCTACT,5-304,TTCCGTTG,RNA,Analytical
+,,,,,,,,,
+sample-D-A1,sample-D-A1,A8,A8,7-353,AGTCTGCT,5-305,TCCAGGCT,DNA,Analytical
+,,,,,,,,,
+sample-D-B1,sample-D-B1,B8,B8,7-354,GCCGAATC,5-306,CTGTCCTC,DNA,Analytical
+,,,,,,,,,
+sample-D-C1,sample-D-C1,C8,C8,7-355,ACTATGAT,5-307,TTCGATAG,DNA,Analytical
+,,,,,,,,,
+sample-D-D1,sample-D-D1,D8,D8,7-356,CCCTATCT,5-308,GTTAGTGA,DNA,Analytical
+,,,,,,,,,
+sample-D-E1,sample-D-E1,E8,E8,7-357,CGTTGTCC,5-309,CTTATCGA,DNA,Analytical
+,,,,,,,,,
+sample-D-F1,sample-D-F1,F8,F8,7-358,TGGAACGG,5-310,GAATAAAG,DNA,Analytical
+,,,,,,,,,
+sample-D-G1,sample-D-G1,G8,G8,7-359,CCCTTCGG,5-311,GAAGGCAG,DNA,Analytical
+,,,,,,,,,
+sample-D-H1,sample-D-H1,H8,H8,7-360,TGTCCAAA,5-312,TTGGTTGT,DNA,Analytical
+,,,,,,,,,
+sample-D-A2,sample-D-A2,A9,A9,7-361,AGTACAAG,5-313,CCCATTGC,DNA,Analytical
+,,,,,,,,,
+sample-D-B2,sample-D-B2,B9,B9,7-362,TACTGTGA,5-314,GTGTCCAG,DNA,Analytical
+,,,,,,,,,
+sample-D-C2,sample-D-C2,C9,C9,7-363,CCGGAATT,5-315,GCATACTT,DNA,Analytical
+,,,,,,,,,
+sample-D-D2,sample-D-D2,D9,D9,7-364,TCGCTCGG,5-316,CCATCGGA,DNA,Analytical
+,,,,,,,,,
+sample-D-E2,sample-D-E2,E9,E9,7-365,AGTGCGGA,5-317,CCGTTGTC,DNA,Analytical
+,,,,,,,,,
+sample-D-F2,sample-D-F2,F9,F9,7-366,GCTTCACA,5-318,TAAAGCTA,DNA,Analytical
+,,,,,,,,,
+sample-D-G2,sample-D-G2,G9,G9,7-367,CCGATCGT,5-319,GACTGTTT,DNA,Analytical
+,,,,,,,,,
+sample-D-H2,sample-D-H2,H9,H9,7-368,CCGTAAGC,5-320,AGTGAGGT,DNA,Analytical

q2_surpi/tests/data/surpi_sample_info_empty_data.csv

@@ -0,0 +1,36 @@
+[Header],,,,,,,,,
+,,,,,,,,,
+IEMFileVersion,4,,,,,,,,
+,,,,,,,,,
+Investigator Name,VS,,,,,,,,
+,,,,,,,,,
+Experiment Name,WW_NS_230126_qiime,,,,,,,,
+,,,,,,,,,
+Date,1/26/23,,,,,,,,
+,,,,,,,,,
+Workflow,GenerateFASTQ,,,,,,,,
+,,,,,,,,,
+Application,FASTQ Only,,,,,,,,
+,,,,,,,,,
+Assay,NEB,,,,,,,,
+,,,,,,,,,
+Description,,,,,,,,,
+,,,,,,,,,
+Chemistry,Amplicon,,,,,,,,
+,,,,,,,,,
+,,,,,,,,,
+,,,,,,,,,
+[Reads],,,,,,,,,
+,,,,,,,,,
+150,,,,,,,,,
+,,,,,,,,,
+,,,,,,,,,
+,,,,,,,,,
+[Settings],,,,,,,,,
+,,,,,,,,,
+ReverseComplement,0,,,,,,,,
+,,,,,,,,,
+,,,,,,,,,
+,,,,,,,,,
+[Data],,,,,,,,,
+,,,,,,,,,