Develop

.github/workflows/docs.yml

@@ -4,7 +4,6 @@ on:
   push:
     tags:
       - 'v*.*.*'
-      - 'test*'
   workflow_dispatch:
 
 permissions:

src/pmotools/pmo_builder/metatable_to_pmo.py

@@ -157,7 +157,7 @@ def library_sample_info_table_to_pmo(
         library_prep_plate_position_col,
         meta_json,
         copy_contents,
-        "specimen_name",
+        "library_sample_name",
         "library_prep_plate_info",
     )
     meta_json = add_parasite_density_info(
@@ -166,7 +166,7 @@ def library_sample_info_table_to_pmo(
         meta_json,
         copy_contents,
         "library_sample_name",
-        entry_name="parasite_density_info",
+        entry_name="qpcr_parasite_density_info",
     )
     # listify columns that contain values that could be list, are delimited by the argument list_values_library_values_delimiter
     primitives = (int, float, str, bool, complex)
@@ -494,7 +494,7 @@ def add_plate_info(
     plate_position_col,
     meta_json,
     df,
-    specimen_name_col,
+    match_col,
     entry_name="plate_info",
 ):
     if all(
@@ -531,7 +531,7 @@ def add_plate_info(
                 ) from e
 
     for row in meta_json:
-        content_row = df[df[specimen_name_col] == row[specimen_name_col]]
+        content_row = df[df[match_col] == row[match_col]]
         plate_name_val = content_row[plate_name_col].iloc[0] if plate_name_col else None
         plate_row_val = (
             content_row[plate_row_col].iloc[0].upper() if plate_row_col else None
@@ -560,7 +560,7 @@ def add_parasite_density_info(
     parasite_density_method_col,
     meta_json,
     df,
-    specimen_name_col,
+    match_col,
     entry_name,
 ):
     density_method_pairs = []
@@ -608,7 +608,7 @@ def add_parasite_density_info(
 
     # Add parasite density info to meta_json
     for row in meta_json:
-        content_row = df[df[specimen_name_col] == row[specimen_name_col]]
+        content_row = df[df[match_col] == row[match_col]]
         density_infos = []
         for density_col, method_col in density_method_pairs:
             density_val = content_row[density_col].iloc[0] if density_col else None

src/pmotools/pmo_builder/mhap_table_to_pmo.py

@@ -26,6 +26,13 @@ def mhap_table_to_pmo(
     masking_delim: str = ",",
     microhaplotype_name_col: str | None = None,
     pseudocigar_col: str | None = None,
+    pseudocigar_chrom_col: str | None = None,
+    pseudocigar_start_col: str | None = None,
+    pseudocigar_end_col: str | None = None,
+    pseudocigar_ref_seq_col: str | None = None,
+    pseudocigar_strand_col: str | None = None,
+    pseudocigar_genome_id: int | None = None,
+    pseudocigar_generation_description_col: str | None = None,
     quality_col: str | None = None,
     additional_representative_mhap_cols: list | None = None,
     additional_mhap_detected_cols: list | None = None,
@@ -73,6 +80,20 @@ def mhap_table_to_pmo(
     :type microhaplotype_name_col: str, optional
     :param pseudocigar_col: the name of the column containing a pseudocigar for the microhaplotype
     :type pseudocigar_col: str, optional
+    :param pseudocigar_chrom_col: column for the pseudocigar ref_loc chromosome; defaults to chrom_col
+    :type pseudocigar_chrom_col: str, optional
+    :param pseudocigar_start_col: column for the pseudocigar ref_loc start (required if pseudocigar_col is set)
+    :type pseudocigar_start_col: str, optional
+    :param pseudocigar_end_col: column for the pseudocigar ref_loc end (required if pseudocigar_col is set)
+    :type pseudocigar_end_col: str, optional
+    :param pseudocigar_ref_seq_col: optional column for the pseudocigar ref_loc reference sequence
+    :type pseudocigar_ref_seq_col: str, optional
+    :param pseudocigar_strand_col: optional column for the pseudocigar ref_loc strand
+    :type pseudocigar_strand_col: str, optional
+    :param pseudocigar_genome_id: genome id for the pseudocigar ref_loc; defaults to genome_id
+    :type pseudocigar_genome_id: int, optional
+    :param pseudocigar_generation_description_col: optional column describing how the pseudocigar was generated
+    :type pseudocigar_generation_description_col: str, optional
     :param quality_col: the name of the column containing the ANSI FASTQ per-base quality score for this sequence
     :type quality_col: str, optional
     :param additional_representative_mhap_cols: additional columns to add to the representative microhaplotypes table
@@ -100,6 +121,13 @@ def mhap_table_to_pmo(
         masking_delim=masking_delim,
         microhaplotype_name_col=microhaplotype_name_col,
         pseudocigar_col=pseudocigar_col,
+        pseudocigar_chrom_col=pseudocigar_chrom_col,
+        pseudocigar_start_col=pseudocigar_start_col,
+        pseudocigar_end_col=pseudocigar_end_col,
+        pseudocigar_ref_seq_col=pseudocigar_ref_seq_col,
+        pseudocigar_strand_col=pseudocigar_strand_col,
+        pseudocigar_genome_id=pseudocigar_genome_id,
+        pseudocigar_generation_description_col=pseudocigar_generation_description_col,
         quality_col=quality_col,
         additional_representative_mhap_cols=additional_representative_mhap_cols,
     )
@@ -160,6 +188,13 @@ def create_representative_microhaplotype_dict(
     masking_delim: str = ",",
     microhaplotype_name_col: str | None = None,
     pseudocigar_col: str | None = None,
+    pseudocigar_chrom_col: str | None = None,
+    pseudocigar_start_col: str | None = None,
+    pseudocigar_end_col: str | None = None,
+    pseudocigar_ref_seq_col: str | None = None,
+    pseudocigar_strand_col: str | None = None,
+    pseudocigar_genome_id: int | None = None,
+    pseudocigar_generation_description_col: str | None = None,
     quality_col: str | None = None,
     additional_representative_mhap_cols: list[str] | None = None,
 ):
@@ -198,6 +233,20 @@ def create_representative_microhaplotype_dict(
     :type microhaplotype_name_col: str, optional
     :param pseudocigar_col: the name of the column containing a pseudocigar for the microhaplotype
     :type pseudocigar_col: str, optional
+    :param pseudocigar_chrom_col: column for the pseudocigar ref_loc chromosome; defaults to chrom_col
+    :type pseudocigar_chrom_col: str, optional
+    :param pseudocigar_start_col: column for the pseudocigar ref_loc start (required if pseudocigar_col is set)
+    :type pseudocigar_start_col: str, optional
+    :param pseudocigar_end_col: column for the pseudocigar ref_loc end (required if pseudocigar_col is set)
+    :type pseudocigar_end_col: str, optional
+    :param pseudocigar_ref_seq_col: optional column for the pseudocigar ref_loc reference sequence
+    :type pseudocigar_ref_seq_col: str, optional
+    :param pseudocigar_strand_col: optional column for the pseudocigar ref_loc strand
+    :type pseudocigar_strand_col: str, optional
+    :param pseudocigar_genome_id: genome id for the pseudocigar ref_loc; defaults to genome_id
+    :type pseudocigar_genome_id: int, optional
+    :param pseudocigar_generation_description_col: optional column describing how the pseudocigar was generated
+    :type pseudocigar_generation_description_col: str, optional
     :param quality_col: the name of the column containing the ANSI FASTQ per-base quality score for this sequence
     :type quality_col: str, optional
     :param additional_representative_mhap_cols: additional columns to add to the representative microhaplotypes table
@@ -211,6 +260,23 @@ def create_representative_microhaplotype_dict(
             microhaplotype_table, additional_representative_mhap_cols
         )
 
+    # the pseudocigar ref_loc shares the chromosome / genome with the
+    # microhaplotype location by default, but each may use its own column
+    pseudocigar_chrom_col = (
+        pseudocigar_chrom_col if pseudocigar_chrom_col else chrom_col
+    )
+    ps_genome_id = (
+        pseudocigar_genome_id if pseudocigar_genome_id is not None else genome_id
+    )
+    if pseudocigar_col and not (
+        pseudocigar_chrom_col and pseudocigar_start_col and pseudocigar_end_col
+    ):
+        raise ValueError(
+            "pseudocigar_col is set, so a Pseudocigar ref_loc must be "
+            "constructable: set a chromosome (pseudocigar_chrom_col or "
+            "chrom_col), pseudocigar_start_col, and pseudocigar_end_col."
+        )
+
     def get_if_present(row, col):
         return row[col] if col and pd.notna(row[col]) else None
 
@@ -263,6 +329,12 @@ def warn_if_duplicated_seqs(df, target_col, seq_col):
         alt_annotations_col,
         microhaplotype_name_col,
         pseudocigar_col,
+        pseudocigar_chrom_col,
+        pseudocigar_start_col,
+        pseudocigar_end_col,
+        pseudocigar_ref_seq_col,
+        pseudocigar_strand_col,
+        pseudocigar_generation_description_col,
         quality_col,
     ]
     masking_cols = [
@@ -319,7 +391,34 @@ def warn_if_duplicated_seqs(df, target_col, seq_col):
             if val := get_if_present(row, microhaplotype_name_col):
                 mhap["microhaplotype_name"] = val
             if val := get_if_present(row, pseudocigar_col):
-                mhap["pseudo_cigar"] = val
+                if not (
+                    pd.notna(row[pseudocigar_chrom_col])
+                    and pd.notna(row[pseudocigar_start_col])
+                    and pd.notna(row[pseudocigar_end_col])
+                ):
+                    raise ValueError(
+                        f"pseudocigar present for target {target}, seq "
+                        f"{row[seq_col]} but its ref_loc chrom/start/end "
+                        "is missing"
+                    )
+                ref_loc = {
+                    "genome_id": ps_genome_id,
+                    "chrom": row[pseudocigar_chrom_col],
+                    "start": row[pseudocigar_start_col],
+                    "end": row[pseudocigar_end_col],
+                }
+                if pseudocigar_ref_seq_col and pd.notna(row[pseudocigar_ref_seq_col]):
+                    ref_loc["ref_seq"] = row[pseudocigar_ref_seq_col]
+                if pseudocigar_strand_col and pd.notna(row[pseudocigar_strand_col]):
+                    ref_loc["strand"] = row[pseudocigar_strand_col]
+                pseudocigar = {"pseudocigar_seq": val, "ref_loc": ref_loc}
+                if pseudocigar_generation_description_col and pd.notna(
+                    row[pseudocigar_generation_description_col]
+                ):
+                    pseudocigar["pseudocigar_generation_description"] = row[
+                        pseudocigar_generation_description_col
+                    ]
+                mhap["pseudocigar"] = pseudocigar
             if val := get_if_present(row, quality_col):
                 mhap["quality"] = val
             if additional_representative_mhap_cols:

src/pmotools/pmo_builder/panel_information_to_pmo.py

@@ -332,8 +332,8 @@ def build_target_info_dict(
                 fwd_primer_dict["location"] = {
                     "genome_id": genome_id,
                     "chrom": row[chrom_col],
-                    "end": int(row[forward_primers_start_col]),
-                    "start": int(row[forward_primers_end_col]),
+                    "start": int(row[forward_primers_start_col]),
+                    "end": int(row[forward_primers_end_col]),
                 }
                 if strand_col and pd.notna(row[strand_col]):
                     fwd_primer_dict["location"]["strand"] = row[strand_col]

src/pmotools/pmo_engine/pmo_exporter.py

@@ -121,10 +121,14 @@ def export_specimen_meta_table(pmodata, separator: str = ",") -> pd.DataFrame:
         for specimen in pmodata["specimen_info"]:
             export_row = {}
             for key, value in specimen.items():
-                if "project_id" == key:
+                if "project_id" == key and "project_info" in pmodata:
                     export_row["project_name"] = pmodata["project_info"][value][
                         "project_name"
                     ]
+                elif "project_id" == key:
+                    # project_info is optional as of schema v1.1.0; keep the raw id
+                    # rather than failing to resolve a name that isn't available
+                    export_row[key] = value
                 elif PMOExporter._is_primitive(value):
                     export_row[key] = value
                 elif PMOExporter._is_primitive_list(value):
@@ -145,10 +149,14 @@ def export_library_sample_meta_table(pmodata, separator: str = ",") -> pd.DataFr
         for library_sample in pmodata["library_sample_info"]:
             export_row = {}
             for key, value in library_sample.items():
-                if "sequencing_info_id" == key:
+                if "sequencing_info_id" == key and "sequencing_info" in pmodata:
                     export_row["sequencing_info_name"] = pmodata["sequencing_info"][
                         value
                     ]["sequencing_info_name"]
+                elif "sequencing_info_id" == key:
+                    # sequencing_info is optional as of schema v1.1.0; keep the raw id
+                    # rather than failing to resolve a name that isn't available
+                    export_row[key] = value
                 elif "specimen_id" == key:
                     export_row["specimen_name"] = pmodata["specimen_info"][value][
                         "specimen_name"
@@ -451,6 +459,7 @@ def write_bed_locs(bed_locs: list[BedLoc], fnp, add_header: bool = False):
                         ]
                     )
                 )
+                f.write("\n")
             for bed_loc in bed_locs:
                 f.write(
                     "\t".join(
@@ -540,11 +549,10 @@ def extract_panels_insert_bed_loc(
         :param sort_output: whether to sort output by genomic location
         :return: a list of target inserts, with named tuples with fields: chrom, start, end, name, score, strand, ref_seq, extra_info
         """
-        bed_loc_out = {}
+        bed_loc_out = []
         if select_panel_ids is None:
             select_panel_ids = list(range(len(pmodata["panel_info"])))
         for panel_id in select_panel_ids:
-            bed_loc_out_per_panel = []
             for reaction_id in range(len(pmodata["panel_info"][panel_id]["reactions"])):
                 for target_id in pmodata["panel_info"][panel_id]["reactions"][
                     reaction_id
@@ -589,7 +597,7 @@ def extract_panels_insert_bed_loc(
                         if "ref_seq" not in tar["insert_location"]
                         else tar["insert_location"]["ref_seq"]
                     )
-                    bed_loc_out_per_panel.append(
+                    bed_loc_out.append(
                         BedLoc(
                             tar["insert_location"]["chrom"],
                             tar["insert_location"]["start"],
@@ -602,12 +610,8 @@ def extract_panels_insert_bed_loc(
                             extra_info,
                         )
                     )
-                if sort_output:
-                    return sorted(
-                        bed_loc_out_per_panel,
-                        key=lambda bed: (bed.chrom, bed.start, bed.end),
-                    )
-            bed_loc_out[panel_id] = bed_loc_out_per_panel
+        if sort_output:
+            return sorted(bed_loc_out, key=lambda bed: (bed.chrom, bed.start, bed.end))
         return bed_loc_out
 
     @staticmethod