fix: CLI pipelines

RasmussenLab · Oct 26, 2023 · 8de0b73 · 8de0b73
1 parent 6ab6d0f
commit 8de0b73
Show file tree

Hide file tree

Showing 2 changed files with 31 additions and 14 deletions.
diff --git a/.github/workflows/cli_vamb.yml b/.github/workflows/cli_vamb.yml
@@ -45,14 +45,19 @@ jobs:
         vamb bin taxvamb --outdir outdir_taxvamb --fasta catalogue_mock.fna.gz --rpkm abundance_mock.npz --taxonomy taxonomy_mock.tsv -pe 10 -pt 10 -e 10 -q -t 10 -o C --minfasta 200000
         ls -la outdir_vamb
         cat outdir_vamb/log.txt
-        vamb bin taxvamb --outdir outdir_taxvamb_no_predict --no_predictor --fasta catalogue_mock.fna.gz --rpkm abundance_mock.npz --taxonomy taxonomy_mock.tsv e 10 -q -t 10 -o C --minfasta 200000
+        vamb bin taxvamb --outdir outdir_taxvamb_no_predict --no_predictor --fasta catalogue_mock.fna.gz --rpkm abundance_mock.npz --taxonomy taxonomy_mock.tsv -e 10 -q -t 10 -o C --minfasta 200000
         ls -la outdir_vamb_no_predict
         cat outdir_vamb_no_predict/log.txt
-        vamb bin taxvamb --outdir outdir_taxvamb_preds --fasta catalogue_mock.fna.gz --rpkm abundance_mock.npz --taxonomy_predictions outdir_taxvamb/results_taxonomy_predictor.csv e 10 -q -t 10 -o C --minfasta 200000
+        vamb bin taxvamb --outdir outdir_taxvamb_preds --fasta catalogue_mock.fna.gz --rpkm abundance_mock.npz --taxonomy_predictions outdir_taxvamb/results_taxonomy_predictor.csv -e 10 -q -t 10 -o C --minfasta 200000
         ls -la outdir_vamb_preds
         cat outdir_vamb_preds/log.txt
     - name: Run Taxometer
       run: |
         vamb taxometer --outdir outdir_taxometer --fasta catalogue_mock.fna.gz --rpkm abundance_mock.npz --taxonomy taxonomy_mock.tsv -pe 10 -pt 10
         ls -la outdir_taxometer
         cat outdir_taxometer/log.txt
+    - name: Run k-means reclustering
+      run: |
+        vamb recluster --outdir outdir_recluster --fasta catalogue_mock.fna.gz --rpkm abundance_mock.npz --latent_path outdir_taxvamb/vaevae_latent.npy --clusters_path outdir_taxvamb/vaevae_clusters.tsv --algorithm kmeans --minfasta 200000
+        ls -la outdir_recluster
+        cat outdir_recluster/log.txt
diff --git a/vamb/__main__.py b/vamb/__main__.py
@@ -1553,7 +1553,9 @@ class TaxometerArguments(BasicArguments):
     def __init__(self, args):
         super(TaxometerArguments, self).__init__(args)
         self.taxonomy_options = TaxonomyOptions(
+            taxonomy_predictions_path=None,
             taxonomy_path=args.taxonomy,
+            no_predictor=None,
         )
         self.predictor_training_options = PredictorTrainingOptions(
             nepochs=args.pred_nepochs,
@@ -1641,20 +1643,31 @@ def run_inner(self, logfile):
         )
 
 
-class VAEArguments(VAEAAEArguments):
+class VAEArguments(BinnerArguments):
     def __init__(self, args):
         super(VAEArguments, self).__init__(args)
-        self.aae_options = None
-        self.aae_training_options = None
-        self.init_encoder_and_training()
-
+        self.encoder_options = EncoderOptions(
+            vae_options=self.vae_options,
+            aae_options=None,
+            alpha=self.args.alpha,
+        )
+        self.training_options = TrainingOptions(
+            encoder_options=self.encoder_options,
+            vae_options=self.vae_training_options,
+            aae_options=None,
+            lrate=self.args.lrate,
+        )
 
-class AAEArguments(VAEAAEArguments):
-    def __init__(self, args):
-        super(AAEArguments, self).__init__(args)
-        self.vae_options = None
-        self.vae_training_options = None
-        self.init_encoder_and_training()
+    def run_inner(self, logfile):
+        run(
+            vamb_options=self.vamb_options,
+            comp_options=self.comp_options,
+            abundance_options=self.abundance_options,
+            encoder_options=self.encoder_options,
+            training_options=self.training_options,
+            cluster_options=self.cluster_options,
+            logfile=logfile,
+        )
 
 
 class VAEVAEArguments(BinnerArguments):
@@ -2241,7 +2254,6 @@ def main():
     add_input_output_arguments(vae_parser)
     add_vae_arguments(vae_parser)
     add_clustering_arguments(vae_parser)
-    add_predictor_arguments(vae_parser)
 
     vaevae_parser = subparsers_model.add_parser(
         TAXVAMB,