moducomp 0.7.13__py3-none-any.whl → 0.7.16__py3-none-any.whl

moducomp/__init__.py

@@ -2,7 +2,7 @@
 moducomp: metabolic module completeness and complementarity for microbiomes.
 """
 
-__version__ = "0.7.13"
+__version__ = "0.7.16"
 __author__ = "Juan C. Villada"
 __email__ = "jvillada@lbl.gov"
 __title__ = "moducomp"

moducomp/moducomp.py

@@ -145,15 +145,23 @@ def require_eggnog_data_dir(eggnog_data_dir: Optional[str], logger: Optional[log
     if eggnog_data_dir:
         os.environ["EGGNOG_DATA_DIR"] = eggnog_data_dir
 
-    env_value = os.environ.get("EGGNOG_DATA_DIR", "")
-    if not env_value.strip():
-        message = (
-            "EGGNOG_DATA_DIR is required to run eggNOG-mapper. "
-            "Set the EGGNOG_DATA_DIR environment variable or pass --eggnog-data-dir. "
-            "Download the data with: download_eggnog_data.py or moducomp download-eggnog-data"
-        )
-        emit_error(message, logger)
-        raise typer.Exit(1)
+    env_value = os.environ.get("EGGNOG_DATA_DIR", "").strip()
+    if not env_value:
+        default_dir = default_eggnog_data_dir()
+        if default_dir.exists() and default_dir.is_dir() and any(default_dir.iterdir()):
+            os.environ["EGGNOG_DATA_DIR"] = str(default_dir)
+            env_value = str(default_dir)
+            if logger:
+                logger.info("EGGNOG_DATA_DIR not set; using default %s", env_value)
+        else:
+            message = (
+                "EGGNOG_DATA_DIR is required to run eggNOG-mapper. "
+                "Set the EGGNOG_DATA_DIR environment variable or pass --eggnog-data-dir. "
+                f"Default location is {default_dir}. "
+                "Download the data with: download_eggnog_data.py or moducomp download-eggnog-data"
+            )
+            emit_error(message, logger)
+            raise typer.Exit(1)
 
     data_dir = Path(env_value).expanduser().resolve()
     if not data_dir.exists() or not data_dir.is_dir():
@@ -3264,7 +3272,7 @@ def pipeline(
                  help="Complementarity size to compute (0 disables).",
              ),
              lowmem: bool = typer.Option(
-                 False,
+                 True,
                  "--lowmem/--fullmem",
                  "--low-mem/--full-mem",
                  help="Run eggNOG-mapper with reduced memory footprint by omitting --dbmem.",
@@ -3441,6 +3449,7 @@ def _run_pipeline_core(
     tmp_emapper_output_dir = f"{get_tmp_dir(savedir)}/emapper_output"
     tmp_emapper_file = f"{tmp_emapper_output_dir}/emapper_out.emapper.annotations"
     ko_matrix_path = f"{savedir}/kos_matrix.csv"
+    kpct_outprefix = "output_give_completeness"
 
     # Process annotations and create KO matrix
     if os.path.exists(ko_matrix_path):
@@ -3509,7 +3518,6 @@ def _run_pipeline_core(
         )
     else:
         # Set up KPCT processing
-        kpct_outprefix = "output_give_completeness"
         kpct_input_file = os.path.join(savedir, "ko_file_for_kpct.txt")
 
         # Check if KPCT output already exists
@@ -3594,7 +3602,7 @@ def _run_pipeline_core(
         try:
             validate(
                 savedir=savedir,
-                mode="ko-matrix",
+                mode="pipeline",
                 calculate_complementarity=calculate_complementarity,
                 kpct_outprefix=kpct_outprefix,
                 strict=validate_strict,
@@ -4143,24 +4151,32 @@ def analyze_ko_matrix(
         # Generate final resource usage summary
         log_final_resource_summary(resource_log_file, start_time, logger, verbose)
 
-        # Display pipeline completion summary
-        display_pipeline_completion_summary(start_time, savedir, logger, verbose)
-
         if run_validation:
             logger.info("Running post-run validation checks.")
             report_path = None
             if validation_report:
                 report_path = os.path.join(savedir, "validation_report.json")
-            validate(
-                savedir=savedir,
-                mode="ko-matrix",
-                calculate_complementarity=calculate_complementarity,
-                kpct_outprefix=kpct_outprefix,
-                strict=validate_strict,
-                report=report_path,
-                verbose=verbose,
-                log_level=log_level,
-            )
+            try:
+                validate(
+                    savedir=savedir,
+                    mode="ko-matrix",
+                    calculate_complementarity=calculate_complementarity,
+                    kpct_outprefix=kpct_outprefix,
+                    strict=validate_strict,
+                    report=report_path,
+                    verbose=verbose,
+                    log_level=log_level,
+                )
+            except typer.Exit as exc:
+                if logger:
+                    logger.error("Validation failed with exit code %s.", exc.exit_code)
+                    logger.error("Outputs written to: %s", savedir)
+                    if report_path:
+                        logger.error("Validation report: %s", report_path)
+                raise
+
+        # Display pipeline completion summary
+        display_pipeline_completion_summary(start_time, savedir, logger, verbose)
 
     except Exception as e:
         if logger:
@@ -4745,7 +4761,7 @@ def validate(
             )
 
     # Complementarity checks
-    comp_pattern = re.compile(r"module_completeness_complementarity_(\\d+)member\\.tsv$")
+    comp_pattern = re.compile(r"module_completeness_complementarity_(\d+)member\.tsv$")
     comp_files: Dict[int, Path] = {}
     for file_path in Path(savedir).glob("module_completeness_complementarity_*member.tsv"):
         match = comp_pattern.match(file_path.name)

{moducomp-0.7.13.dist-info → moducomp-0.7.16.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: moducomp
-Version: 0.7.13
+Version: 0.7.16
 Summary: moducomp: metabolic module completeness and complementarity for microbiomes.
 Keywords: bioinformatics,microbiome,metabolic,kegg,genomics
 Author-email: "Juan C. Villada" <jvillada@lbl.gov>
@@ -62,6 +62,14 @@ pixi global install \
 
 `moducomp` needs the eggNOG-mapper database to run. The primary (recommended) way to download it is using the `download_eggnog_data.py` wrapper, which mirrors the upstream downloader behavior. For upstream details, see the eggNOG-mapper setup guide: [eggNOG-mapper database setup](https://github.com/eggnogdb/eggnog-mapper/wiki/eggNOG-mapper-v2.1.5-to-v2.1.13#user-content-Setup).
 
+```bash
+download_eggnog_data.py
+```
+
+By default, the data are stored in `${XDG_DATA_HOME:-~/.local/share}/moducomp/eggnog`, and `moducomp` will auto-detect that location without needing `EGGNOG_DATA_DIR`.
+
+To use a custom location:
+
 ```bash
 export EGGNOG_DATA_DIR="/path/to/eggnog-data"
 download_eggnog_data.py --eggnog-data-dir "$EGGNOG_DATA_DIR"
@@ -69,8 +77,6 @@ download_eggnog_data.py --eggnog-data-dir "$EGGNOG_DATA_DIR"
 # moducomp download-eggnog-data --eggnog-data-dir "$EGGNOG_DATA_DIR"
 ```
 
-If `EGGNOG_DATA_DIR` is not set, the downloader defaults to `${XDG_DATA_HOME:-~/.local/share}/moducomp/eggnog`.
-
 ### Quick test
 
 Small test data sets ship with `moducomp`. After installation you can confirm the pipeline by running:
@@ -147,7 +153,7 @@ This section lists all CLI options implemented today, along with their default v
 | `--calculate-complementarity`, `-c` | `0` | Complementarity size to compute (0 disables). |
 | `--adapt-headers/--no-adapt-headers` | `false` | Adapt FASTA headers to `genome|protein_N`. |
 | `--del-tmp/--keep-tmp` | `true` | Delete temporary files after completion. |
-| `--lowmem/--fullmem` (`--low-mem/--full-mem`) | `fullmem` | Run eggNOG-mapper without `--dbmem` to reduce RAM. |
+| `--lowmem/--fullmem` (`--low-mem/--full-mem`) | `lowmem` | Run eggNOG-mapper without `--dbmem` to reduce RAM. |
 | `--verbose/--quiet` | `false` | Enable verbose progress output. |
 | `--validate/--no-validate` | `validate` | Run post-run validation checks. |
 | `--validate-report/--no-validate-report` | `validate-report` | Write `validation_report.json` in the output directory. |
@@ -253,7 +259,7 @@ moducomp validate /path/to/output --strict
 
 ### ⚠️ Important note 2
 
-`moducomp` is specifically designed for large scale analysis of microbiomes with hundreds of members, and works on Linux systems with at least **64GB of RAM**. Nevertheless, it can be run on **smaller systems with less RAM, using the flag `--lowmem` (`--low-mem`) when running the `pipeline` command**. The `test` command uses low-memory mode by default and can be switched to full memory with `--fullmem` (`--full-mem`).
+`moducomp` is specifically designed for large scale analysis of microbiomes with hundreds of members, and works on Linux systems with at least **64GB of RAM**. For robustness, **low-memory mode is now the default** for `pipeline` and `test`. If you have ample RAM and want full-memory mode, add `--fullmem` (`--full-mem`).
 
 ### Notes on bundled test data
 
@@ -290,7 +296,7 @@ moducomp pipeline \
     --ncpus <number_of_cpus_to_use> \
     --calculate-complementarity <N>  # 0 to disable, 2 for 2-member, 3 for 3-member complementarity.
     # Optional flags:
-    # --lowmem/--fullmem          # Optional: Use low-mem if you have less than 64GB of RAM (default is full mem)
+    # --fullmem                  # Optional: Use full-mem if you have ample RAM (default is low-mem)
     # --adapt-headers             # If your FASTA headers need modification
     # --del-tmp/--keep-tmp        # Delete or keep temporary files
     # --eggnog-data-dir /path     # If EGGNOG_DATA_DIR is not set
@@ -343,8 +349,11 @@ moducomp pipeline ./large_genome_collection ./output_large --ncpus 32 --calculat
 # For moderate datasets with verbose output
 moducomp analyze-ko-matrix ./ko_matrix.csv ./output_moderate --ncpus 16 --calculate-complementarity 2 --verbose
 
-# For systems with limited memory
-moducomp pipeline ./genomes ./output_lowmem --ncpus 8 --lowmem --calculate-complementarity 2
+# For systems with limited memory (default behavior)
+moducomp pipeline ./genomes ./output_lowmem --ncpus 8 --calculate-complementarity 2
+
+# For systems with ample RAM
+moducomp pipeline ./genomes ./output_fullmem --ncpus 8 --fullmem --calculate-complementarity 2
 ```
 
 ## Expected outputs

{moducomp-0.7.13.dist-info → moducomp-0.7.16.dist-info}/RECORD

@@ -1,11 +1,11 @@
-moducomp/__init__.py,sha256=4JZhb_CRk2p0sYjkmp2gH__rAKsrR1CdZshT9XGbXEg,659
+moducomp/__init__.py,sha256=cuhC_H9napqaM3ggu_0MSW9Aq99fUGDL8jKS2UL9FfE,659
 moducomp/__main__.py,sha256=1O2pv6IGjUgqnbqsiMLtVqjxWQpRtZUjp8LDljZ1bsI,185
-moducomp/moducomp.py,sha256=ntC6RHC1yb5Pa3WFFEASfkvG6z_fSc0q12PDbjGxsLQ,178488
+moducomp/moducomp.py,sha256=z3-PBUK15nbthjbfMRU8R4Hkw2NMEbrNd2aZ8S2S0Uk,179334
 moducomp/data/test_genomes/IMG2562617132.faa,sha256=gZPh-08pMRdAWJRr3__TbnU1F68CdkDb3gxtpaCLTTc,356863
 moducomp/data/test_genomes/IMG2568526683.faa,sha256=PxFJwe-68UGw7il1hGlNhZt4-2WzzxXxGE1GTskDnow,343109
 moducomp/data/test_genomes/IMG2740892217.faa,sha256=WsId4sIPxENbqF6tYFouAgDCy6T0SXNY6TywxBNe-3E,548954
-moducomp-0.7.13.dist-info/entry_points.txt,sha256=oIUiacp53fiOCWDXpc2rpq5hS4wDdpasx24EXit3daE,181
-moducomp-0.7.13.dist-info/licenses/LICENSE.txt,sha256=pt0cfIq9Wop21KDZYyQgP0M1YWYvKG0PomA5cUDC4TI,1536
-moducomp-0.7.13.dist-info/WHEEL,sha256=_2ozNFCLWc93bK4WKHCO-eDUENDlo-dgc9cU3qokYO4,82
-moducomp-0.7.13.dist-info/METADATA,sha256=Aj9sjpYv4eFd1dbRJsyot2NKp_-RMi3x1K2SlXy9wYg,21520
-moducomp-0.7.13.dist-info/RECORD,,
+moducomp-0.7.16.dist-info/entry_points.txt,sha256=oIUiacp53fiOCWDXpc2rpq5hS4wDdpasx24EXit3daE,181
+moducomp-0.7.16.dist-info/licenses/LICENSE.txt,sha256=pt0cfIq9Wop21KDZYyQgP0M1YWYvKG0PomA5cUDC4TI,1536
+moducomp-0.7.16.dist-info/WHEEL,sha256=_2ozNFCLWc93bK4WKHCO-eDUENDlo-dgc9cU3qokYO4,82
+moducomp-0.7.16.dist-info/METADATA,sha256=nB3DHs6ZjL8rlxcjqAUnnf5LbhdAW7hfqU1usNmfBs8,21662
+moducomp-0.7.16.dist-info/RECORD,,