salmopredict 0.2.0__tar.gz → 0.3.0__tar.gz

{salmopredict-0.2.0 → salmopredict-0.3.0}/MANIFEST.in

@@ -6,3 +6,4 @@ recursive-include salmopredict/gui/assets *.png
 include LICENSE
 include environment.yml
 include examples/*.csv
+include examples/README.md

{salmopredict-0.2.0/salmopredict.egg-info → salmopredict-0.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: salmopredict
-Version: 0.2.0
+Version: 0.3.0
 Summary: AutoGluon-based Incidence predictor for Salmonella virulence-factor gene-frequency features
 Author-email: Dongyan Shao <563608176@qq.com>
 License: PolyForm-Noncommercial-1.0.0
@@ -14,7 +14,8 @@ Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
 Requires-Python: <3.11,>=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: autogluon.tabular==1.1.1
+Requires-Dist: autogluon.tabular[fastai]==1.1.1
+Requires-Dist: setuptools<81
 Requires-Dist: pandas>=2.0
 Requires-Dist: openpyxl>=3.0
 Requires-Dist: rich-argparse>=1.4
@@ -40,8 +41,8 @@ single prediction file. It reproduces the alignment used by the original
 (`/` and `-` become `.`), genes the model expects but the input lacks are filled
 with `0` (a missing gene means frequency 0), and extra input columns are ignored.
 
-**Input/output contract** — one input CSV in, one output CSV out. The output
-columns depend on whether the input has a `Sample` column:
+**Feature CSV input/output** — the output columns depend on whether the input
+has a `Sample` column:
 
 | Input | Output columns |
 |-------|----------------|
@@ -58,36 +59,78 @@ salmopredict runs on **Python 3.10** and loads its model with **AutoGluon
 1.1.1** — both are hard requirements, because the model is pickled with that
 exact stack.
 
-**From PyPI (recommended).** In a Python 3.10 environment:
+**New installation from this source directory.** Run these commands from the
+directory containing `pyproject.toml`:
 
 ```bash
-pip install salmopredict
+conda create -n salmopredict python=3.10
+conda activate salmopredict
+python -m pip install .
+salmopredict check
 ```
 
-This pulls in AutoGluon 1.1.1, the Streamlit GUI, and the bundled prediction
-model, so both interfaces work out of the box:
+This installs AutoGluon 1.1.1 with its **Torch and FastAI backends**, compatible
+`setuptools<81`, the Streamlit GUI, and the bundled prediction model. The
+backends are required by the bundled ensemble; base `autogluon.tabular` alone
+does not install them. AutoGluon 1.1.1 also needs `pkg_resources`, which newer
+setuptools releases no longer provide.
+
+Both interfaces are then available:
 
 ```bash
 salmopredict run -i features.csv -o results/   # command line
 salmopredict gui                                # browser GUI
 ```
 
-No Python 3.10 environment yet? Create one first, e.g.
-`conda create -n salmopredict python=3.10 && conda activate salmopredict`.
-
-**Reproducible environment (from a clone).** Pins Python 3.10 and installs
+**Conda environment (alternative, from this source directory).** Pins Python 3.10 and installs
 AutoGluon via pip inside the env (conda-installed AutoGluon does not resolve
 cleanly for this project):
 
 ```bash
 conda env create -f environment.yml
 conda activate salmopredict
+salmopredict check
 ```
 
 **Editable / development install (from a clone).**
 
 ```bash
-pip install -e .          # installs the CLI and the Streamlit GUI
+python -m pip install -e .          # installs the CLI and the Streamlit GUI
+```
+
+**Install the updated local wheel.** In a Python 3.10 environment:
+
+```bash
+python -m pip install --upgrade dist/salmopredict-0.3.0-py3-none-any.whl
+salmopredict check
+```
+
+**Update an existing source installation.** Stop a running GUI with `Ctrl+C`,
+then run from this source directory:
+
+```bash
+conda activate salmopredict
+python -m pip install --upgrade -e .
+salmopredict check
+salmopredict gui
+```
+
+**PyPI installation / upgrade.** In a Python 3.10 environment:
+
+```bash
+python -m pip install --upgrade "salmopredict>=0.3.0"
+salmopredict check
+```
+
+Version 0.3.0 includes two-table prediction and installs the required Torch,
+FastAI and compatible setuptools dependencies automatically.
+
+If the page opens but prediction reports `No module named 'pkg_resources'`,
+`torch`, or `fastai`, use the update/repair command above and restart the GUI.
+To verify actual prediction from a source checkout (use a new output folder):
+
+```bash
+salmopredict run -i examples/example_features.csv -o results_install_check/
 ```
 
 ## The model
@@ -130,12 +173,55 @@ salmopredict gui
 salmopredict check --model /path/to/model
 ```
 
-Each run writes one `pred_<input-stem>.csv` to the output directory; the
+Each feature-input run writes one `pred_<input-stem>.csv` to the output directory; the
 prediction column is `Incidence(%)`. Features filled with `0` (genes the model
 expects but the input lacks) are always reported, and a prominent warning
 appears when more than `--missing-warn-frac` (default 0.3) of the model's
 features are missing.
 
+## Predict from samples and gene frequencies
+
+Supply two CSV files instead of calculating features yourself:
+
+* **Samples**: `Sample,dose_cfu,serotype`. `dose_cfu` contains raw CFU, e.g.
+  `1000`, not `3`. Each Sample must be nonblank and unique.
+* **Gene frequencies**: `Serotype` plus one column per gene, one row per
+  serotype, with numeric frequencies from 0 to 1. This accepts the layout of
+  `02_gene_frequencies.csv` directly.
+
+```bash
+salmopredict run \
+  --samples examples/example_samples.csv \
+  --gene-frequencies examples/example_gene_frequencies.csv \
+  -o results_two_tables/
+```
+
+For each sample, the program looks up its serotype and calculates
+`gene_frequency × log10(dose_cfu)`, then predicts incidence. It writes:
+
+* `features_example_samples.csv`: `Sample` and the calculated gene features.
+* `pred_example_samples.csv`: `Sample,dose_cfu,serotype,Incidence(%)`.
+
+Sample order and identifier strings (including leading zeros) are preserved.
+Required header names are case-insensitive. Serotype values match exactly after
+trimming outer spaces; synonyms and spelling differences are not guessed.
+Missing serotypes stop the run and list affected samples. Duplicate sample IDs
+or serotypes, blank required values, nonfinite/nonpositive doses, and frequencies
+outside [0, 1] also stop the run. Additional sample columns are ignored. Missing
+model genes use the existing fill-and-warning behavior.
+
+`--samples` and `--gene-frequencies` must be used together and cannot be combined
+with `-i` or `--attach`. Use `--force` to replace existing output files.
+
+In the **GUI**, choose **Samples + gene frequencies** under **Input mode**,
+upload both CSVs, inspect their previews, choose an output folder and click
+**Run prediction**. The result table and both CSV download buttons appear after
+success. **Feature CSV** selects the existing single-table workflow.
+
+The two example inputs were reconstructed from the matching sample/dose metadata
+and dose-weighted features. See [examples/README.md](examples/README.md) for their
+provenance and rounding tolerance.
+
 ## License
 
 Licensed under the [PolyForm Noncommercial License 1.0.0](LICENSE): free to use,

{salmopredict-0.2.0 → salmopredict-0.3.0}/README.md

@@ -15,8 +15,8 @@ single prediction file. It reproduces the alignment used by the original
 (`/` and `-` become `.`), genes the model expects but the input lacks are filled
 with `0` (a missing gene means frequency 0), and extra input columns are ignored.
 
-**Input/output contract** — one input CSV in, one output CSV out. The output
-columns depend on whether the input has a `Sample` column:
+**Feature CSV input/output** — the output columns depend on whether the input
+has a `Sample` column:
 
 | Input | Output columns |
 |-------|----------------|
@@ -33,36 +33,78 @@ salmopredict runs on **Python 3.10** and loads its model with **AutoGluon
 1.1.1** — both are hard requirements, because the model is pickled with that
 exact stack.
 
-**From PyPI (recommended).** In a Python 3.10 environment:
+**New installation from this source directory.** Run these commands from the
+directory containing `pyproject.toml`:
 
 ```bash
-pip install salmopredict
+conda create -n salmopredict python=3.10
+conda activate salmopredict
+python -m pip install .
+salmopredict check
 ```
 
-This pulls in AutoGluon 1.1.1, the Streamlit GUI, and the bundled prediction
-model, so both interfaces work out of the box:
+This installs AutoGluon 1.1.1 with its **Torch and FastAI backends**, compatible
+`setuptools<81`, the Streamlit GUI, and the bundled prediction model. The
+backends are required by the bundled ensemble; base `autogluon.tabular` alone
+does not install them. AutoGluon 1.1.1 also needs `pkg_resources`, which newer
+setuptools releases no longer provide.
+
+Both interfaces are then available:
 
 ```bash
 salmopredict run -i features.csv -o results/   # command line
 salmopredict gui                                # browser GUI
 ```
 
-No Python 3.10 environment yet? Create one first, e.g.
-`conda create -n salmopredict python=3.10 && conda activate salmopredict`.
-
-**Reproducible environment (from a clone).** Pins Python 3.10 and installs
+**Conda environment (alternative, from this source directory).** Pins Python 3.10 and installs
 AutoGluon via pip inside the env (conda-installed AutoGluon does not resolve
 cleanly for this project):
 
 ```bash
 conda env create -f environment.yml
 conda activate salmopredict
+salmopredict check
 ```
 
 **Editable / development install (from a clone).**
 
 ```bash
-pip install -e .          # installs the CLI and the Streamlit GUI
+python -m pip install -e .          # installs the CLI and the Streamlit GUI
+```
+
+**Install the updated local wheel.** In a Python 3.10 environment:
+
+```bash
+python -m pip install --upgrade dist/salmopredict-0.3.0-py3-none-any.whl
+salmopredict check
+```
+
+**Update an existing source installation.** Stop a running GUI with `Ctrl+C`,
+then run from this source directory:
+
+```bash
+conda activate salmopredict
+python -m pip install --upgrade -e .
+salmopredict check
+salmopredict gui
+```
+
+**PyPI installation / upgrade.** In a Python 3.10 environment:
+
+```bash
+python -m pip install --upgrade "salmopredict>=0.3.0"
+salmopredict check
+```
+
+Version 0.3.0 includes two-table prediction and installs the required Torch,
+FastAI and compatible setuptools dependencies automatically.
+
+If the page opens but prediction reports `No module named 'pkg_resources'`,
+`torch`, or `fastai`, use the update/repair command above and restart the GUI.
+To verify actual prediction from a source checkout (use a new output folder):
+
+```bash
+salmopredict run -i examples/example_features.csv -o results_install_check/
 ```
 
 ## The model
@@ -105,12 +147,55 @@ salmopredict gui
 salmopredict check --model /path/to/model
 ```
 
-Each run writes one `pred_<input-stem>.csv` to the output directory; the
+Each feature-input run writes one `pred_<input-stem>.csv` to the output directory; the
 prediction column is `Incidence(%)`. Features filled with `0` (genes the model
 expects but the input lacks) are always reported, and a prominent warning
 appears when more than `--missing-warn-frac` (default 0.3) of the model's
 features are missing.
 
+## Predict from samples and gene frequencies
+
+Supply two CSV files instead of calculating features yourself:
+
+* **Samples**: `Sample,dose_cfu,serotype`. `dose_cfu` contains raw CFU, e.g.
+  `1000`, not `3`. Each Sample must be nonblank and unique.
+* **Gene frequencies**: `Serotype` plus one column per gene, one row per
+  serotype, with numeric frequencies from 0 to 1. This accepts the layout of
+  `02_gene_frequencies.csv` directly.
+
+```bash
+salmopredict run \
+  --samples examples/example_samples.csv \
+  --gene-frequencies examples/example_gene_frequencies.csv \
+  -o results_two_tables/
+```
+
+For each sample, the program looks up its serotype and calculates
+`gene_frequency × log10(dose_cfu)`, then predicts incidence. It writes:
+
+* `features_example_samples.csv`: `Sample` and the calculated gene features.
+* `pred_example_samples.csv`: `Sample,dose_cfu,serotype,Incidence(%)`.
+
+Sample order and identifier strings (including leading zeros) are preserved.
+Required header names are case-insensitive. Serotype values match exactly after
+trimming outer spaces; synonyms and spelling differences are not guessed.
+Missing serotypes stop the run and list affected samples. Duplicate sample IDs
+or serotypes, blank required values, nonfinite/nonpositive doses, and frequencies
+outside [0, 1] also stop the run. Additional sample columns are ignored. Missing
+model genes use the existing fill-and-warning behavior.
+
+`--samples` and `--gene-frequencies` must be used together and cannot be combined
+with `-i` or `--attach`. Use `--force` to replace existing output files.
+
+In the **GUI**, choose **Samples + gene frequencies** under **Input mode**,
+upload both CSVs, inspect their previews, choose an output folder and click
+**Run prediction**. The result table and both CSV download buttons appear after
+success. **Feature CSV** selects the existing single-table workflow.
+
+The two example inputs were reconstructed from the matching sample/dose metadata
+and dose-weighted features. See [examples/README.md](examples/README.md) for their
+provenance and rounding tolerance.
+
 ## License
 
 Licensed under the [PolyForm Noncommercial License 1.0.0](LICENSE): free to use,

{salmopredict-0.2.0 → salmopredict-0.3.0}/environment.yml

@@ -8,9 +8,5 @@ dependencies:
   - python=3.10
   - pip
   - pip:
-      - autogluon.tabular==1.1.1
-      - pandas>=2.0
-      - openpyxl>=3.0
-      - rich-argparse>=1.4
-      - streamlit>=1.30
+      # pyproject.toml includes the Torch/FastAI backends and setuptools<81.
       - -e .

salmopredict-0.3.0/examples/README.md

@@ -0,0 +1,83 @@
+# Example inputs
+
+Three ready-to-run files that cover the two input types and the metadata attach.
+Feature values are built the way the model was trained:
+
+```
+feature = gene_frequency(serotype, gene)  ×  log10(CFU dose)
+```
+
+so the same serotype at a higher CFU has larger feature values and a higher
+predicted incidence. All files share the same 10 samples — two serotypes
+(Enteritidis, Typhimurium) each at CFU = 500 / 1 000 / 2 000 / 10 000 / 100 000.
+Gene column names keep the original biological form (`mig-5`, `spiC/ssaB`, …);
+salmopredict normalises them to the model's names (`mig-5` → `mig.5`).
+
+| File | Rows × cols | Type | Output when run |
+|------|-------------|------|-----------------|
+| `example_features.csv` | 10 × 123 | **Type 1** — features only, **no `Sample`** column (just the 123 genes the model uses) | `Incidence(%)` |
+| `example_with_sample.csv` | 10 × 348 | **Type 2** — a `Sample` column + all 347 genes (the ~224 extra genes are ignored) | `Sample`, `Incidence(%)` |
+| `example_meta.csv` | 10 × 5 | Metadata to **attach** — `Sample` + `serotype`, `dose_cfu`, `source`, `region` | joined onto a Type-2 run by the `Sample` key |
+
+## Run them
+
+```bash
+# Type 1: features only -> a single Incidence(%) column
+salmopredict run -i examples/example_features.csv -o results/
+
+# Type 2: a Sample column -> Sample, Incidence(%)
+salmopredict run -i examples/example_with_sample.csv -o results/
+
+# Type 2 + attach: metadata joined on Sample -> Sample, Incidence(%), + meta columns
+salmopredict run -i examples/example_with_sample.csv -o results/ \
+  --attach examples/example_meta.csv
+```
+
+The attached run shows the dose–response, since `example_meta.csv` carries the
+`dose_cfu` alongside each `Sample`:
+
+```
+Sample,Incidence(%),serotype,dose_cfu,source,region
+S001,12.39,Enteritidis,500,retail chicken,North
+S002,14.15,Enteritidis,1000,retail pork,East
+...
+S005,37.43,Enteritidis,100000,retail pork,West
+```
+
+Rules for attaching metadata:
+
+* the **input** must have a `Sample` column (Type 2), and so must the
+  **metadata** file — the two are joined on `Sample`;
+* the metadata's `Sample` values should be unique (duplicates are rejected);
+* every metadata column except `Sample` is appended to the output.
+
+In the GUI (`salmopredict gui`), the **Attach metadata** box only appears once
+the chosen input is detected to have a `Sample` column.
+
+## Rebuilding these files
+
+The values come from the per-serotype gene-frequency table used to train the
+model (`results/02_gene_frequencies.csv` in the assembly project) multiplied by
+`log10(dose)`, reproducing `multiply_CFU_geneFreq.R`. To change the serotypes or
+CFU values, edit that grid and recompute `gene_frequency × log10(CFU)` for every
+gene column — do not edit a dose value alone, or the features and the dose will
+disagree.
+
+## Two-table input examples
+
+`example_samples.csv` contains 10 samples with raw `dose_cfu` and `serotype`.
+`example_gene_frequencies.csv` has 2 serotypes and 123 model gene columns.
+Both are also saved in the sibling `../test/` folder requested for verification.
+
+These files were reconstructed from `../test/pred_example_with_sample.csv`
+(sample IDs, serotypes and doses only) and `../test/example_features.csv`
+(weighted features), pairing rows in their original order. The prediction column
+is not used to derive frequencies. For each serotype, the 1000-CFU row gives
+`frequency = feature / log10(1000) = feature / 3`. All five dose rows per serotype
+were checked against that frequency. The maximum reconstructed feature error
+is less than 5e-7, consistent with six-decimal rounding in the original features.
+
+```bash
+salmopredict run --samples examples/example_samples.csv \
+  --gene-frequencies examples/example_gene_frequencies.csv -o results_two_tables/
+```

salmopredict-0.3.0/examples/example_gene_frequencies.csv

@@ -0,0 +1,3 @@
+Serotype,SEAG_RS23305,SEAG_RS23320,SEN_RS22090,SG_RS05215,SG_RS05220,SG_RS05300,SG_RS24060,STM0266,STM0267,STM0268,STM0270,STM0271,STM0272,STM0273,STM0274,STM0275,STM0276,STM0278,STM0279,STM0280,STM0281,STM0282,STM0283,STM0284,STM0285,STM0286,STM0287,STM0289,STM0290,STM0306,STM3026,STM4261,STY_RS21720,STY_RS21730,apeE,avrA,bcfB,cheA,cheB,cheM,cheW,csgB,csgD,fimC,fimY,flgD,flgG,fliC,fliD,fliF,fliG,fliI,fliK,fliL,fliM,fliP,fljB,gogB,hilC,hilD,invA,iroB,iroC,iroD,iroN,lpfA,lpfD,mig-5,motB,nmpC,pefA,pefB,pefC,pefD,pegA,pegB,pegC,pipB,pltA,ratB,rck,rpoS,safA,safB,safC,safD,sefA,sefB,sefC,sefD,shdA,sifB,sinH,sipD,sodCI,sopA,sopD2,sopE,spiC/ssaB,spvB,spvC,spvD,ssaT,ssaU,sseI/srfH,sseK1,sseK2,sseL,sspH1,sspH2,staA,staB,stcA,stcD,stdB,steC,steD,steF,stkA,tae4,tcfA,tcfD,tlde1
+Enteritidis,0,0,0.9,0.9,1,0,0.9,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0.9,1,0,0,1,1,1,1,1,1,1,1,1,1,1,1,1,0,0,1,1,1,1,1,1,1,0,0,0.9,1,1,1,1,1,1,1,1,0.7,1,1,0,0.6,0.6,0.6,1,1,1,1,0,1,0.5,1,1,1,1,1,1,0.9,0.9,0.9,0,0.9,0,1,1,1,0.9,1,1,0.7,0.7,0.6,1,1,1,0.6,0.9,1,0,0.9,0,0,0,0,1,1,1,1,0,0,0,0,1
+Typhimurium,1,1,0,0,0,0,0,1,1,1,1,1,1,1,1,0.9848,0.8333,0.9848,0.8333,1,1,1,0.9848,0.9545,1,1,1,1,1,0.9848,0.9848,0.8939,0,0,1,1,1,1,1,1,1,1,0.9848,1,0.9848,1,1,0.9848,1,1,1,1,1,1,1,1,0.9242,0.1515,0.9848,0.9848,1,1,1,1,1,1,0.9848,0.1061,1,1,0.0909,0.0909,0.0909,0.0909,0,0,0,0.9848,0,1,0.0455,1,0.9697,1,1,1,0,0,0,0,0.1212,0.9394,1,1,0.9697,0.9848,0.9394,0,0.9848,0.1061,0.0909,0.1061,0.9848,0.9848,0.9242,0.9394,0.9848,0.9697,0.0152,0.9697,0,0,0.9848,0.9848,1,0.9848,0,0,0,0.9848,0,0,1

salmopredict-0.3.0/examples/example_samples.csv

@@ -0,0 +1,11 @@
+Sample,dose_cfu,serotype
+S001,500,Enteritidis
+S002,1000,Enteritidis
+S003,2000,Enteritidis
+S004,10000,Enteritidis
+S005,100000,Enteritidis
+S006,500,Typhimurium
+S007,1000,Typhimurium
+S008,2000,Typhimurium
+S009,10000,Typhimurium
+S010,100000,Typhimurium

{salmopredict-0.2.0 → salmopredict-0.3.0}/pyproject.toml

@@ -18,7 +18,10 @@ classifiers = [
     "Topic :: Scientific/Engineering :: Bio-Informatics",
 ]
 dependencies = [
-    "autogluon.tabular==1.1.1",
+    # The bundled ensemble uses both Torch and FastAI neural networks.
+    "autogluon.tabular[fastai]==1.1.1",
+    # AutoGluon 1.1.1 imports pkg_resources, removed in newer setuptools.
+    "setuptools<81",
     "pandas>=2.0",
     "openpyxl>=3.0",
     "rich-argparse>=1.4",

{salmopredict-0.2.0 → salmopredict-0.3.0}/salmopredict/__init__.py

@@ -13,7 +13,7 @@ salmopredict:
 The same core is shared by a command-line interface and a Streamlit GUI.
 """
 
-__version__ = "0.2.0"
+__version__ = "0.3.0"
 
 # One-paragraph summary shown in both the CLI help and the GUI, so the two
 # interfaces describe the tool with identical wording.

{salmopredict-0.2.0 → salmopredict-0.3.0}/salmopredict/cli.py

@@ -1,7 +1,7 @@
 """Command-line interface for salmopredict.
 
 Commands:
-    salmopredict run          -- predict Incidence for one or more feature CSVs
+    salmopredict run          -- predict from features or samples + gene frequencies
     salmopredict gui          -- launch the Streamlit graphical interface
     salmopredict check        -- verify dependencies and the model
     salmopredict build-model  -- clone a full AutoGluon model into a slim deploy copy
@@ -73,12 +73,18 @@ def build_parser() -> argparse.ArgumentParser:
 
     default_model = default_model_path()
 
-    run = sub.add_parser("run", help="Predict Incidence for one feature CSV.",
+    run = sub.add_parser("run", help="Predict from features or samples + gene frequencies.",
                          formatter_class=_HelpFormatter)
-    run.add_argument("-i", "--input", required=True,
+    inputs = run.add_mutually_exclusive_group(required=True)
+    inputs.add_argument("-i", "--input",
                      help="One feature CSV file. If it has a 'Sample' column, the "
                           "output carries Sample + the prediction; otherwise it is "
                           "the prediction column only.")
+    inputs.add_argument("--samples", help="Sample CSV with Sample, dose_cfu (raw CFU), "
+                        "and serotype. Requires --gene-frequencies.")
+    run.add_argument("--gene-frequencies", help="CSV with Serotype and gene columns "
+                     "containing frequencies in [0, 1]. Used only with --samples; "
+                     "also writes features_<samples-stem>.csv.")
     run.add_argument("-o", "--output", required=True,
                      help="Output directory (created if missing); the result is "
                           "written there as pred_<input-stem>.csv.")
@@ -128,8 +134,10 @@ def build_parser() -> argparse.ArgumentParser:
 
 
 def _cmd_run(args: argparse.Namespace) -> int:
+    if bool(args.samples) != bool(args.gene_frequencies):
+        raise ValueError("--samples and --gene-frequencies must be supplied together.")
     config = PredictConfig(
-        input_path=Path(args.input),
+        input_path=Path(args.samples or args.input),
         output_dir=Path(args.output),
         model_path=Path(args.model) if args.model else None,
         ensemble_model=args.model_name,
@@ -137,6 +145,7 @@ def _cmd_run(args: argparse.Namespace) -> int:
         missing_warn_fraction=args.missing_warn_frac,
         attach_metadata=Path(args.attach) if args.attach else None,
         force=args.force,
+        gene_frequencies=Path(args.gene_frequencies) if args.gene_frequencies else None,
     )
 
     # Imported here so 'check'/'gui' work even if autogluon is absent.
@@ -147,6 +156,8 @@ def _cmd_run(args: argparse.Namespace) -> int:
     cols = ", ".join(result.predictions.columns)
     print(f"\nDone. label={result.label}  model={result.model_used}")
     print(f"  {result.input_path.name}: {result.n_rows} rows -> {result.output_path}")
+    if result.features_path is not None:
+        print(f"    weighted features: {result.features_path}")
     print(f"    Sample column: {'yes' if result.has_sample else 'no'}"
           + ("  (metadata attached)" if result.attached else ""))
     print(f"    output columns: {cols}")

{salmopredict-0.2.0 → salmopredict-0.3.0}/salmopredict/config.py

@@ -71,6 +71,10 @@ class PredictConfig:
     One input feature CSV is aligned to the model and predicted, producing one
     output file ``pred_<input-stem>.csv`` in ``output_dir``.
 
+    With ``gene_frequencies``, input_path instead contains Sample, dose_cfu and
+    serotype. The run also exports ``features_<input-stem>.csv`` and includes
+    those three sample columns in the prediction output.
+
     Output columns depend on the input:
       * no ``Sample`` column  -> just the prediction (``Incidence(%)``);
       * a ``Sample`` column    -> ``Sample`` + ``Incidence(%)``, and, if
@@ -90,6 +94,9 @@ class PredictConfig:
 
     force: bool = False
 
+    # When provided, input_path is a Sample/dose_cfu/serotype table.
+    gene_frequencies: Optional[Path] = None
+
     def __post_init__(self) -> None:
         self.input_path = Path(self.input_path)
         self.output_dir = Path(self.output_dir)
@@ -97,6 +104,11 @@ class PredictConfig:
             self.model_path = Path(self.model_path)
         if self.attach_metadata is not None:
             self.attach_metadata = Path(self.attach_metadata)
+        if self.gene_frequencies is not None:
+            self.gene_frequencies = Path(self.gene_frequencies)
+            if self.attach_metadata is not None:
+                raise ValueError("--attach is only supported with feature CSV input; "
+                                 "two-table input already includes sample metadata.")
         if not 0.0 <= float(self.missing_warn_fraction) <= 1.0:
             raise ValueError("missing_warn_fraction must be between 0 and 1")
         self.missing_warn_fraction = float(self.missing_warn_fraction)