bactopia 2.1.6__tar.gz → 2.2.0__tar.gz

{bactopia-2.1.6 → bactopia-2.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: bactopia
-Version: 2.1.6
+Version: 2.2.0
 Summary: A Python package for working with Bactopia
 License: MIT
 License-File: LICENSE
@@ -20,6 +20,7 @@ Requires-Dist: jinja2 (>=3.1.6)
 Requires-Dist: openpyxl (>=3.1.0)
 Requires-Dist: pandas (>=2.2.0)
 Requires-Dist: psutil (>=5.9.0)
+Requires-Dist: pysradb (>=2.2.0)
 Requires-Dist: pyyaml (>=6.0)
 Requires-Dist: rauth (>=0.7.3)
 Requires-Dist: requests (>=2.28.2)

{bactopia-2.1.6 → bactopia-2.2.0}/bactopia/cli/common.py

@@ -26,7 +26,7 @@ def common_options(fn):
 def setup_logging(verbose: bool, silent: bool) -> None:
     """Configure root logger with RichHandler at the appropriate level."""
     logging.basicConfig(
-        format="%(asctime)s:%(name)s:%(levelname)s - %(message)s",
+        format="%(message)s",
         datefmt="%Y-%m-%d %H:%M:%S",
         handlers=[
             RichHandler(rich_tracebacks=True, console=rich.console.Console(stderr=True))

{bactopia-2.1.6 → bactopia-2.2.0}/bactopia/cli/search.py

@@ -30,6 +30,8 @@ click.rich_click.OPTION_GROUPS = {
             "name": "Query Options",
             "options": [
                 "--exact-taxon",
+                "--provider",
+                "--only-provider",
                 "--limit",
                 "--accession-limit",
                 "--biosample-subset",
@@ -192,6 +194,9 @@ def parse_query(q, accession_limit, exact_taxon=False):
     run_accessions = []
 
     for query in queries:
+        query = query.strip()
+        if not query:
+            continue
         try:
             taxon_id = int(query)
             if exact_taxon:
@@ -244,6 +249,18 @@ def parse_query(q, accession_limit, exact_taxon=False):
     help="Taxon ID or Study, BioSample, or Run accession (can also be comma separated or a file of accessions)",
 )
 @click.option("--exact-taxon", is_flag=True, help="Exclude Taxon ID descendants")
+@click.option(
+    "--provider",
+    default="ena",
+    show_default=True,
+    type=click.Choice(["ena", "sra"], case_sensitive=False),
+    help="Provider to query first, falls back to the other",
+)
+@click.option(
+    "--only-provider",
+    is_flag=True,
+    help="Only query the given --provider, skip fallback",
+)
 @click.option(
     "--outdir", "-o", default="./", show_default=True, help="Directory to write output"
 )
@@ -316,6 +333,8 @@ def parse_query(q, accession_limit, exact_taxon=False):
 def search(
     query,
     exact_taxon,
+    provider,
+    only_provider,
     outdir,
     prefix,
     limit,
@@ -379,12 +398,31 @@ def search(
     accessions_file = f"{outdir}/{prefix}-accessions.txt".replace("//", "/")
     filtered_file = f"{outdir}/{prefix}-filtered.txt".replace("//", "/")
     summary_file = f"{outdir}/{prefix}-search.txt".replace("//", "/")
+
+    if not force:
+        existing = [
+            f
+            for f in [metadata_file, accessions_file, filtered_file, summary_file]
+            if Path(f).exists()
+        ]
+        if existing:
+            logging.error(
+                f"Output files already exist: {', '.join(existing)}. "
+                "Use --force to overwrite."
+            )
+            sys.exit(1)
+
     genome_sizes = get_ncbi_genome_size() if use_ncbi_genome_size else None
     for query_type, ena_query, sra_query in queries:
         logging.info(f"Submitting query (type - {query_type})")
         is_accession = True if query_type.endswith("accession") else False
-        success, query_results = get_run_info(
-            sra_query, ena_query, is_accession, limit=limit
+        success, query_results, source = get_run_info(
+            sra_query,
+            ena_query,
+            is_accession,
+            limit=limit,
+            provider=provider,
+            only_provider=only_provider,
         )
         results += query_results
         if success:
@@ -395,8 +433,35 @@ def search(
                 genome_size=genome_size,
                 genome_sizes=genome_sizes,
             )
+
+            # Fallback: provider returned results but none passed filtering
+            if not query_accessions and not only_provider:
+                fallback = "sra" if source == "ena" else "ena"
+                logging.info(
+                    f"Accession found on {source.upper()}, but missing "
+                    f"metadata, checking {fallback.upper()}..."
+                )
+                fb_success, fb_results, fb_source = get_run_info(
+                    sra_query,
+                    ena_query,
+                    is_accession,
+                    limit=limit,
+                    provider=fallback,
+                    only_provider=True,
+                )
+                if fb_success:
+                    results += fb_results
+                    source = fb_source
+                    query_accessions, query_filtered = parse_accessions(
+                        fb_results,
+                        min_read_length=min_read_length,
+                        min_base_count=min_base_count,
+                        genome_size=genome_size,
+                        genome_sizes=genome_sizes,
+                    )
+
+            WARNING_MESSAGE = None
             if len(query_accessions):
-                WARNING_MESSAGE = None
                 if query_type == "biosample" and biosample_subset > 0:
                     if len(query_accessions) > biosample_subset:
                         WARNING_MESSAGE = f"WARNING: Selected {biosample_subset} Experiment accession(s) from a total of {len(query_accessions)}"
@@ -404,20 +469,19 @@ def search(
                             query_accessions, biosample_subset
                         )
                 accessions = list(set(accessions + query_accessions))
-                filtered["min_base_count"] += query_filtered["min_base_count"]
-                filtered["min_read_length"] += query_filtered["min_read_length"]
-                filtered["technical"] += query_filtered["technical"]
-                for filtered_sample in query_filtered["filtered"]:
-                    filtered["filtered"][filtered_sample["accession"]] = (
-                        filtered_sample["reason"]
-                    )
             else:
                 if query_results:
-                    WARNING_MESSAGE = f"WARNING: {query} did not return any Illumina or Ont results from ENA."
+                    WARNING_MESSAGE = f"WARNING: {query} did not return any Illumina or Ont results from {source.upper()}."
                 else:
-                    WARNING_MESSAGE = (
-                        f"WARNING: {query} did not return any results from ENA."
-                    )
+                    WARNING_MESSAGE = f"WARNING: {query} did not return any results from {source.upper()}."
+
+            filtered["min_base_count"] += query_filtered["min_base_count"]
+            filtered["min_read_length"] += query_filtered["min_read_length"]
+            filtered["technical"] += query_filtered["technical"]
+            for filtered_sample in query_filtered["filtered"]:
+                filtered["filtered"][filtered_sample["accession"]] = filtered_sample[
+                    "reason"
+                ]
 
             # Create Summary
             query_string = query
@@ -435,6 +499,7 @@ def search(
             summary.append(
                 f"DATE: {datetime.datetime.now().replace(microsecond=0).isoformat()}"
             )
+            summary.append(f"PROVIDER: {source.upper()}")
             summary.append(f"LIMIT: {limit}")
             summary.append(f"RESULTS: {len(results)} ({metadata_file})")
             summary.append(
@@ -462,6 +527,10 @@ def search(
         else:
             logging.error(f"ERROR: Unable to retrieve metadata for query ({query})")
 
+    if not results:
+        logging.error("No results found, skipping output files.")
+        sys.exit(1)
+
     # Output the results
     logging.info(f"Writing results to {metadata_file}")
     with open(metadata_file, "w") as output_fh:

bactopia-2.2.0/bactopia/databases/ena.py

@@ -0,0 +1,118 @@
+import logging
+
+import requests
+
+ENA_URL = "https://www.ebi.ac.uk/ena/portal/api/search"
+
+
+def get_ena_metadata(query: str, is_accession: bool, limit: int):
+    """Fetch metadata from ENA.
+    https://docs.google.com/document/d/1CwoY84MuZ3SdKYocqssumghBF88PWxUZ/edit#heading=h.ag0eqy2wfin5
+
+    Args:
+        query (str): The query to search for.
+        is_accession (bool): If the query is an accession or not.
+        limit (int): The maximum number of records to return.
+
+    Returns:
+        list: Records associated with the accession.
+    """
+    data = {
+        "dataPortal": "ena",
+        "dccDataOnly": "false",
+        "download": "false",
+        "result": "read_run",
+        "format": "tsv",
+        "limit": limit,
+        "fields": "all",
+    }
+
+    if is_accession:
+        data["includeAccessions"] = query
+    else:
+        data["query"] = (
+            f'"{query} AND library_source=GENOMIC AND '
+            "(library_strategy=OTHER OR library_strategy=WGS OR "
+            "library_strategy=WGA) AND (library_selection=MNase OR "
+            "library_selection=RANDOM OR library_selection=unspecified OR "
+            'library_selection="size fractionation")"'
+        )
+
+    headers = {"accept": "*/*", "Content-type": "application/x-www-form-urlencoded"}
+
+    r = requests.post(ENA_URL, headers=headers, data=data)
+    if r.status_code == requests.codes.ok:
+        data = []
+        col_names = None
+        for line in r.text.split("\n"):
+            cols = line.split("\t")
+            if line:
+                if col_names:
+                    data.append(dict(zip(col_names, cols)))
+                else:
+                    col_names = cols
+        return [True, data]
+    else:
+        return [False, [r.status_code, r.text]]
+
+
+def get_run_info(
+    sra_query: str,
+    ena_query: str,
+    is_accession: bool,
+    limit: int = 1000000,
+    provider: str = "ena",
+    only_provider: bool = False,
+) -> tuple:
+    """Retrieve a list of samples available from ENA and/or SRA.
+
+    By default, the provider is queried first and the other is used as fallback. When
+    only_provider is True, no fallback is attempted.
+
+    Args:
+        sra_query: A formatted query for SRA searches.
+        ena_query: A formatted query for ENA searches.
+        is_accession: If the query is an accession or not.
+        limit: The maximum number of records to return.
+        provider: Which provider to query first ("ena" or "sra").
+        only_provider: If True, skip fallback to the other provider.
+
+    Returns:
+        tuple: (success, data, source) where source is "ena", "sra", or "none".
+    """
+    from bactopia.databases.sra import get_sra_metadata
+
+    fallback = "sra" if provider == "ena" else "ena"
+
+    def _query_ena():
+        logging.debug("Querying ENA for metadata...")
+        success, data = get_ena_metadata(ena_query, is_accession, limit=limit)
+        if success and data:
+            return True, data
+        if not success:
+            logging.warning(f"ENA query failed (status {data[0]}).")
+        else:
+            logging.debug("ENA query returned no results.")
+        return False, []
+
+    def _query_sra():
+        logging.debug("Querying SRA for metadata...")
+        return get_sra_metadata(sra_query, is_accession, limit=limit)
+
+    query_fn = {"ena": _query_ena, "sra": _query_sra}
+
+    success, data = query_fn[provider]()
+    if success:
+        return True, data, provider
+
+    if only_provider:
+        logging.error(f"{provider.upper()} returned no results (--only-provider).")
+        return False, [], "none"
+
+    logging.info(f"No results from {provider.upper()}, checking {fallback.upper()}...")
+    success, data = query_fn[fallback]()
+    if success:
+        return True, data, fallback
+
+    logging.error("Both ENA and SRA returned no results.")
+    return False, [], "none"

bactopia-2.2.0/bactopia/databases/sra.py

@@ -0,0 +1,103 @@
+import logging
+
+from pysradb.sraweb import SRAweb
+
+INSTRUMENT_PLATFORM_MAP = {
+    "illumina": "ILLUMINA",
+    "nextseq": "ILLUMINA",
+    "hiseq": "ILLUMINA",
+    "miseq": "ILLUMINA",
+    "novaseq": "ILLUMINA",
+    "miniseq": "ILLUMINA",
+    "genome analyzer": "ILLUMINA",
+    "minion": "OXFORD_NANOPORE",
+    "gridion": "OXFORD_NANOPORE",
+    "promethion": "OXFORD_NANOPORE",
+    "nanopore": "OXFORD_NANOPORE",
+    "pacbio": "PACBIO_SMRT",
+    "sequel": "PACBIO_SMRT",
+    "revio": "PACBIO_SMRT",
+    "ion torrent": "ION_TORRENT",
+}
+
+SRA_TO_ENA_FIELDS = {
+    "run_total_bases": "base_count",
+    "run_total_spots": "read_count",
+    "organism_taxid": "tax_id",
+    "organism_name": "scientific_name",
+}
+
+
+def instrument_to_platform(instrument: str) -> str:
+    """Map an SRA instrument model name to the ENA platform constant.
+
+    Args:
+        instrument: Instrument model name from SRA (e.g. "Illumina MiniSeq").
+
+    Returns:
+        str: Platform constant (e.g. "ILLUMINA") or the original value if unknown.
+    """
+    lower = instrument.lower()
+    for key, platform in INSTRUMENT_PLATFORM_MAP.items():
+        if key in lower:
+            return platform
+    return instrument
+
+
+def normalize_sra_fields(records: list[dict]) -> list[dict]:
+    """Rename SRA fields to their ENA equivalents so parse_accessions() works unchanged.
+
+    Args:
+        records: List of dicts from pysradb search results.
+
+    Returns:
+        list[dict]: Records with critical fields renamed in place.
+    """
+    for record in records:
+        for sra_field, ena_field in SRA_TO_ENA_FIELDS.items():
+            if sra_field in record:
+                record[ena_field] = record.pop(sra_field)
+
+        if "instrument" in record and "instrument_model_desc" not in record:
+            record["instrument_model_desc"] = instrument_to_platform(
+                record["instrument"]
+            )
+
+        layout = record.get("library_layout", "SINGLE").upper()
+        record["fastq_bytes"] = "0;0" if layout == "PAIRED" else "0"
+
+    return records
+
+
+def get_sra_metadata(query: str, is_accession: bool, limit: int) -> list:
+    """Fetch metadata from SRA via pysradb.
+
+    Args:
+        query: The query to search for (accession or NCBI query string).
+        is_accession: If the query is an accession or not.
+        limit: The maximum number of records to return.
+
+    Returns:
+        list: [success: bool, data: list[dict]]
+    """
+    try:
+        db = SRAweb()
+        df = db.search_sra(
+            query,
+            detailed=True,
+            sample_attribute=True,
+            expand_sample_attributes=True,
+        )
+        if df is None or df.empty:
+            logging.debug(f"SRA query returned no results for: {query}")
+            return [False, []]
+
+        if len(df) > limit:
+            logging.debug(f"SRA returned {len(df)} results, truncating to {limit}")
+            df = df.head(limit)
+
+        records = df.to_dict(orient="records")
+        return [True, normalize_sra_fields(records)]
+    except Exception as e:
+        logging.error(f"Error querying SRA: {e}")
+        return [False, []]

{bactopia-2.1.6 → bactopia-2.2.0}/bactopia/lint/docs.py

@@ -61,7 +61,7 @@ _NEXTFLOW_INFORMATIONAL_RE = re.compile(
     re.IGNORECASE,
 )
 
-# nextflow.config: nextflowVersion = '>=25.04.6'
+# nextflow.config: nextflowVersion = '>=26.04.0'
 _NEXTFLOW_CONFIG_RE = re.compile(
     r"nextflowVersion\s*=\s*['\"][^\d]*(\d+\.\d+(?:\.\d+)?)"
 )

{bactopia-2.1.6 → bactopia-2.2.0}/bactopia/templates/nextflow/nextflow.config.j2

@@ -5,7 +5,7 @@ manifest {
     homePage = 'https://github.com/bactopia/bactopia'
     description = 'An extensive workflow for processing sequencing of bacterial genomes.'
     mainScript = 'main.nf'
-    version = '4.0.0'
+    version = '4.0.1'
     nextflowVersion = '>=26.04.0'
 }
 
@@ -21,7 +21,7 @@ params {
 }
 
 // Version
-params.bactopia_version = '4.0.0'
+params.bactopia_version = '4.0.1'
 manifest.version = "${params.bactopia_version}"
 
 // Includes
@@ -93,7 +93,7 @@ dag {
 
 // Plugins
 plugins {
-    id 'nf-bactopia@2.1.1'
+    id 'nf-bactopia@2.1.5'
 }
 
 bactopia {

{bactopia-2.1.6 → bactopia-2.2.0}/bactopia/templates/scaffold/module/tests/nextflow.config.j2

@@ -10,7 +10,7 @@ params {
         ext = "fna"
     }
 
-    bactopia_version = '4.0.0'
+    bactopia_version = '4.0.1'
     bactopia_cache = System.getenv("BACTOPIA_CACHEDIR") ?: "${System.getenv('HOME')}/.bactopia"
     condadir = "${params.bactopia_cache}/conda"
     wf = params.workflow.name

{bactopia-2.1.6 → bactopia-2.2.0}/bactopia/templates/scaffold/subworkflow/tests/nextflow.config.j2

@@ -9,7 +9,7 @@ params {
         description = "{{ description }}"
         ext = "fna"
     }
-    bactopia_version = '4.0.0'
+    bactopia_version = '4.0.1'
     bactopia_cache = System.getenv("BACTOPIA_CACHEDIR") ?: "${System.getenv('HOME')}/.bactopia"
     condadir = "${params.bactopia_cache}/conda"
     wf = params.workflow.name
@@ -38,5 +38,5 @@ includeConfig "../../../conf/profiles.config"
 
 // Plugin
 plugins {
-    id 'nf-bactopia@2.0.2'
+    id 'nf-bactopia@2.1.5'
 }

{bactopia-2.1.6 → bactopia-2.2.0}/bactopia/templates/scaffold/workflow/nextflow.config.j2

@@ -5,8 +5,8 @@ manifest {
     homePage = 'https://github.com/bactopia/bactopia'
     description = 'An extensive workflow for processing sequencing of bacterial genomes.'
     mainScript = 'main.nf'
-    version = '4.0.0'
-    nextflowVersion = '>=25.04.6'
+    version = '4.0.1'
+    nextflowVersion = '>=26.04.0'
 }
 
 params {
@@ -19,7 +19,7 @@ params {
 }
 
 // Version
-params.bactopia_version = '4.0.0'
+params.bactopia_version = '4.0.1'
 manifest.version = "${params.bactopia_version}"
 
 // Includes
@@ -85,7 +85,7 @@ dag {
 
 // Plugins
 plugins {
-    id 'nf-bactopia@2.0.2'
+    id 'nf-bactopia@2.1.5'
 }
 
 bactopia {

{bactopia-2.1.6 → bactopia-2.2.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "bactopia"
-version = "2.1.6"
+version = "2.2.0"
 description = "A Python package for working with Bactopia"
 authors = [
     "Robert A. Petit III <robbie.petit@gmail.com>",
@@ -57,6 +57,7 @@ pyyaml = ">=6.0"
 biopython = ">=1.80"
 openpyxl = ">=3.1.0"
 psutil = ">=5.9.0"
+pysradb = ">=2.2.0"
 
 [tool.poetry.group.dev.dependencies]
 ruff = "^0.9"

bactopia-2.1.6/bactopia/databases/ena.py

@@ -1,86 +0,0 @@
-import logging
-import sys
-
-import requests
-
-ENA_URL = "https://www.ebi.ac.uk/ena/portal/api/search"
-
-
-def get_ena_metadata(query: str, is_accession: bool, limit: int):
-    """Fetch metadata from ENA.
-    https://docs.google.com/document/d/1CwoY84MuZ3SdKYocqssumghBF88PWxUZ/edit#heading=h.ag0eqy2wfin5
-
-    Args:
-        query (str): The query to search for.
-        is_accession (bool): If the query is an accession or not.
-        limit (int): The maximum number of records to return.
-
-    Returns:
-        list: Records associated with the accession.
-    """
-    data = {
-        "dataPortal": "ena",
-        "dccDataOnly": "false",
-        "download": "false",
-        "result": "read_run",
-        "format": "tsv",
-        "limit": limit,
-        "fields": "all",
-    }
-
-    if is_accession:
-        data["includeAccessions"] = query
-    else:
-        data["query"] = (
-            f'"{query} AND library_source=GENOMIC AND '
-            "(library_strategy=OTHER OR library_strategy=WGS OR "
-            "library_strategy=WGA) AND (library_selection=MNase OR "
-            "library_selection=RANDOM OR library_selection=unspecified OR "
-            'library_selection="size fractionation")"'
-        )
-
-    headers = {"accept": "*/*", "Content-type": "application/x-www-form-urlencoded"}
-
-    r = requests.post(ENA_URL, headers=headers, data=data)
-    if r.status_code == requests.codes.ok:
-        data = []
-        col_names = None
-        for line in r.text.split("\n"):
-            cols = line.split("\t")
-            if line:
-                if col_names:
-                    data.append(dict(zip(col_names, cols)))
-                else:
-                    col_names = cols
-        return [True, data]
-    else:
-        return [False, [r.status_code, r.text]]
-
-
-def get_run_info(
-    sra_query: str, ena_query: str, is_accession: bool, limit: int = 1000000
-) -> tuple:
-    """Retrieve a list of samples available from ENA.
-
-    The first attempt will be against ENA, and if that fails, SRA will be queried. This should
-    capture those samples not yet synced between ENA and SRA.
-
-    Args:
-        sra_query (str): A formatted query for SRA searches.
-        ena_query (str): A formatted query for ENA searches.
-        is_accession (bool): If the query is an accession or not.
-        limit (int): The maximum number of records to return.
-
-    Returns:
-        tuple: Records associated with the accession.
-    """
-
-    logging.debug("Querying ENA for metadata...")
-    success, ena_data = get_ena_metadata(ena_query, is_accession, limit=limit)
-    if success:
-        return success, ena_data
-    else:
-        logging.error("There was an issue querying ENA, exiting...")
-        logging.error(f"STATUS: {ena_data[0]}")
-        logging.error(f"TEXT: {ena_data[1]}")
-        sys.exit(1)