chore: runs

RasmussenLab · Oct 24, 2023 · 058fc88 · 058fc88
1 parent 77803ca
commit 058fc88
Show file tree

Hide file tree

Showing 17 changed files with 250 additions and 149 deletions.
diff --git a/workflow_vaevae/src/longread_human.sh b/workflow_vaevae/src/longread_human.sh
@@ -1,31 +1,36 @@
 #!/usr/bin/bash
+annotator=$1
+thres=$2
     # --taxonomy_predictions /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/vaevaeout/results_taxonomy_predictor.csv \
 
 
-vamb \
-    --model vaevae \
-    --outdir /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/vaevaeout_dadam \
-    --fasta /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/contigs_2kbp.fna \
-    --rpkm /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/vambout/abundance.npz \
-    --taxonomy /home/projects/cpr_10006/people/svekut/mmseq2/longread_taxonomy_2023.tsv \
-    -l 64 \
-    -e 1000 \
-    -q  \
-    -pe 100 \
-    -pq  \
-    -o C \
-    --cuda \
-    --minfasta 200000
+# vamb \
+#     --model vaevae \
+#     --outdir /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/vaevae_${annotator}_predictor_${thres} \
+#     --fasta /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/contigs_2kbp.fna \
+#     --rpkm /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/vambout/abundance.npz \
+#     --taxonomy /home/projects/cpr_10006/people/svekut/04_mmseq2/taxonomy_cami_kfold/human_longread_taxonomy_${annotator}.tsv \
+#     -l 64 \
+#     -e 1000 \
+#     -t 1024 \
+#     -q  \
+#     -pe 100 \
+#     -pt 1024 \
+#     -pq  \
+#     -pthr ${thres} \
+#     -o C \
+#     --cuda \
+#     --minfasta 200000
 
 vamb \
     --model reclustering \
-    --latent_path /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/vaevaeout_dadam/vaevae_latent.npy \
-    --clusters_path /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/vaevaeout_dadam/vaevae_clusters.tsv  \
+    --latent_path /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/vaevae_${annotator}_predictor_${thres}/vaevae_latent.npy \
+    --clusters_path /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/vaevae_${annotator}_predictor_${thres}/vaevae_clusters.tsv  \
     --fasta /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/contigs_2kbp.fna \
     --rpkm /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/vambout/abundance.npz \
-    --outdir /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/vaevaeout_dadam_reclustering \
+    --outdir /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/vaevae_${annotator}_predictor_${thres}_reclustering \
     --hmmout_path /home/projects/cpr_10006/projects/semi_vamb/data/marker_genes/markers_human.hmmout \
-    --taxonomy_predictions /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/vaevaeout/results_taxonomy_predictor.csv \
+    --taxonomy_predictions /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/vaevae_${annotator}_predictor_${thres}/results_taxonomy_predictor.csv \
     --algorithm dbscan \
     --minfasta 200000
 
diff --git a/workflow_vaevae/src/longread_human_no_predictor.sh b/workflow_vaevae/src/longread_human_no_predictor.sh
@@ -1,4 +1,7 @@
 #!/usr/bin/bash
+annotator=$1
+thres=$2
+
     # --taxonomy_predictions /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/vaevaeout/results_taxonomy_predictor.csv \
     # --taxonomy /home/projects/cpr_10006/people/svekut/mmseq2/longread_taxonomy_2023.tsv \
 
@@ -7,10 +10,10 @@
 
 vamb \
     --model vaevae \
-    --outdir /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/vaevae_flat_softmax__fix2 \
+    --outdir /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/vaevae_${annotator} \
     --fasta /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/contigs_2kbp.fna \
     --rpkm /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/vambout/abundance.npz \
-    --taxonomy /home/projects/cpr_10006/people/svekut/04_mmseq2/taxonomy_cami_kfold/human_longread_taxonomy_metabuli_otu.tsv \
+    --taxonomy /home/projects/cpr_10006/people/svekut/04_mmseq2/taxonomy_cami_kfold/human_longread_taxonomy_${annotator}.tsv \
     --no_predictor \
     -l 64 \
     -e 500 \

diff --git a/workflow_vaevae/src/longread_human_predictor.sh b/workflow_vaevae/src/longread_human_predictor.sh
@@ -5,10 +5,10 @@ run_id=$1
 
 vamb \
     --model taxonomy_predictor \
-    --outdir /home/projects/cpr_10006/people/svekut/long_read_human_kfold_predictor_flat_softmax_${run_id} \
+    --outdir /home/projects/cpr_10006/people/svekut/long_read_human_kfold_predictor_v207_${run_id} \
     --fasta /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/contigs_2kbp.fna \
     --rpkm /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/vambout/abundance.npz \
-    --taxonomy /home/projects/cpr_10006/people/svekut/04_mmseq2/taxonomy_cami_kfold/long_read_human_taxonomy_${run_id}.tsv \
+    --taxonomy /home/projects/cpr_10006/people/svekut/04_mmseq2/taxonomy_cami_kfold/human_longread_${run_id}.tsv \
     -pe 100 \
     -pq  \
     -pt 1024 \

diff --git a/workflow_vaevae/src/longread_human_vamb.sh b/workflow_vaevae/src/longread_human_vamb.sh
@@ -1,23 +1,24 @@
 #!/usr/bin/bash
 
-vamb \
-    --outdir /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/vambout64 \
-    --fasta /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/contigs_2kbp.fna \
-    --rpkm /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/vambout/abundance.npz \
-    -l 64 \
-    -e 1000 \
-    -q 25 75 150 500 \
-    -o C \
-    --cuda \
-    --minfasta 200000
+# vamb \
+#     --outdir /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/vambout64_20102023 \
+#     --fasta /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/contigs_2kbp.fna \
+#     --rpkm /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/vambout/abundance.npz \
+#     -l 64 \
+#     -e 500 \
+#     -q 25 75 150 \
+#     -o C \
+#     --cuda \
+#     --minfasta 200000
 
 vamb \
     --model reclustering \
-    --latent_path /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/vambout64/latent.npy \
-    --clusters_path /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/vambout64/vae_clusters.tsv  \
+    --latent_path /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/vambout64_20102023/latent.npz \
+    --clusters_path /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/vambout64_20102023/vae_clusters.tsv  \
     --fasta /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/contigs_2kbp.fna \
     --rpkm /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/vambout/abundance.npz \
-    --outdir /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/vambout64_reclustering \
+    --outdir /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/vambout64_20102023_reclustering \
     --hmmout_path /home/projects/cpr_10006/projects/semi_vamb/data/marker_genes/markers_human.hmmout \
+    --taxonomy_predictions /home/projects/cpr_10006/projects/semi_vamb/data/human_longread/vaevae_full_predictor_0.5/results_taxonomy_predictor.csv \
     --algorithm dbscan \
     --minfasta 200000
diff --git a/workflow_vaevae/src/longread_sludge.sh b/workflow_vaevae/src/longread_sludge.sh
@@ -1,31 +1,35 @@
 #!/usr/bin/bash
-
+annotator=$1
+thres=$2
     # --taxonomy_predictions /home/projects/cpr_10006/projects/semi_vamb/data/sludge/vaevaeout_sp100/results_taxonomy_predictor.csv \
 
 
-vamb \
-    --outdir /home/projects/cpr_10006/projects/semi_vamb/data/sludge/vaevaeout_dadam \
-    --fasta /home/projects/cpr_10006/projects/semi_vamb/data/sludge/contigs_2kbp.fna \
-    --rpkm /home/projects/cpr_10006/projects/semi_vamb/data/sludge/vambout/abundance.npz \
-    --taxonomy /home/projects/cpr_10006/people/paupie/vaevae/mmseq2_annotations/long_read_sludge/lr_sludge_taxonomy.tsv \
-    -l 64 \
-    -e 500 \
-    -q  \
-    -pe 100 \
-    -pq  \
-    --n_species 100 \
-    -o C \
-    --cuda \
-    --minfasta 200000
+# vamb \
+#     --model vaevae \
+#     --outdir /home/projects/cpr_10006/projects/semi_vamb/data/sludge/vaevae_${annotator}_predictor_${thres} \
+#     --fasta /home/projects/cpr_10006/projects/semi_vamb/data/sludge/contigs_2kbp.fna \
+#     --rpkm /home/projects/cpr_10006/projects/semi_vamb/data/sludge/vambout/abundance.npz \
+#     --taxonomy /home/projects/cpr_10006/people/svekut/04_mmseq2/taxonomy_cami_kfold/sludge_taxonomy_${annotator}.tsv \
+#     -l 64 \
+#     -e 1000 \
+#     -t 1024 \
+#     -q  \
+#     -pe 100 \
+#     -pt 1024 \
+#     -pq  \
+#     -pthr ${thres} \
+#     -o C \
+#     --cuda \
+#     --minfasta 200000
 
 vamb \
     --model reclustering \
-    --latent_path /home/projects/cpr_10006/projects/semi_vamb/data/sludge/vaevaeout_dadam/vaevae_latent.npy \
-    --clusters_path /home/projects/cpr_10006/projects/semi_vamb/data/sludge/vaevaeout_dadam/vaevae_clusters.tsv  \
+    --latent_path /home/projects/cpr_10006/projects/semi_vamb/data/sludge/vaevae_${annotator}_predictor_${thres}/vaevae_latent.npy \
+    --clusters_path /home/projects/cpr_10006/projects/semi_vamb/data/sludge/vaevae_${annotator}_predictor_${thres}/vaevae_clusters.tsv  \
     --fasta /home/projects/cpr_10006/projects/semi_vamb/data/sludge/contigs_2kbp.fna \
     --rpkm /home/projects/cpr_10006/projects/semi_vamb/data/sludge/vambout/abundance.npz \
-    --outdir /home/projects/cpr_10006/projects/semi_vamb/data/sludge/vaevaeout_dadam_reclustering \
+    --outdir /home/projects/cpr_10006/projects/semi_vamb/data/sludge/vaevae_${annotator}_predictor_${thres}_reclustering \
     --hmmout_path /home/projects/cpr_10006/projects/semi_vamb/data/marker_genes/markers_sludge.hmmout \
-    --taxonomy_predictions /home/projects/cpr_10006/people/svekut/vamb/results_taxonomy_predictor_sludge.csv \
+    --taxonomy_predictions /home/projects/cpr_10006/projects/semi_vamb/data/sludge/vaevae_${annotator}_predictor_${thres}/results_taxonomy_predictor.csv \
     --algorithm dbscan \
     --minfasta 200000
diff --git a/workflow_vaevae/src/longread_sludge_no_predictor.sh b/workflow_vaevae/src/longread_sludge_no_predictor.sh
@@ -1,18 +1,18 @@
 #!/usr/bin/bash
-
+annotator=$1
     # --taxonomy_predictions /home/projects/cpr_10006/projects/semi_vamb/data/sludge/vaevaeout_sp100/results_taxonomy_predictor.csv \
 
 
 vamb \
     --model vaevae \
-    --outdir /home/projects/cpr_10006/projects/semi_vamb/data/sludge/vaevaeout_metabuli_flatsoftmax_500 \
+    --outdir /home/projects/cpr_10006/projects/semi_vamb/data/sludge/vaevae_${annotator} \
     --fasta /home/projects/cpr_10006/projects/semi_vamb/data/sludge/contigs_2kbp.fna \
     --rpkm /home/projects/cpr_10006/projects/semi_vamb/data/sludge/vambout/abundance.npz \
-    --taxonomy /home/projects/cpr_10006/people/svekut/04_mmseq2/taxonomy_cami_kfold/sludge_taxonomy_metabuli_otu.tsv \
+    --taxonomy /home/projects/cpr_10006/people/svekut/04_mmseq2/taxonomy_cami_kfold/sludge_taxonomy_${annotator}.tsv \
     --no_predictor \
     -l 64 \
     -e 500 \
-    -t 512 \
+    -t 1024 \
     -q  \
     -o C \
     --cuda \

diff --git a/workflow_vaevae/src/longread_sludge_predictor.sh b/workflow_vaevae/src/longread_sludge_predictor.sh
@@ -5,10 +5,10 @@ run_id=$1
 
 vamb \
     --model taxonomy_predictor \
-    --outdir /home/projects/cpr_10006/people/svekut/long_read_sludge_kfold_predictor_flat_softmax_${run_id} \
+    --outdir /home/projects/cpr_10006/people/svekut/long_read_sludge_kfold_predictor_v207_${run_id} \
     --fasta /home/projects/cpr_10006/projects/semi_vamb/data/sludge/contigs_2kbp.fna \
     --rpkm /home/projects/cpr_10006/projects/semi_vamb/data/sludge/vambout/abundance.npz \
-    --taxonomy /home/projects/cpr_10006/people/svekut/04_mmseq2/taxonomy_cami_kfold/long_read_sludge_taxonomy_${run_id}.tsv \
+    --taxonomy /home/projects/cpr_10006/people/svekut/04_mmseq2/taxonomy_cami_kfold/sludge_${run_id}.tsv \
     -pe 100 \
     -pq  \
     -pt 1024 \

diff --git a/workflow_vaevae/src/longread_sludge_vamb.sh b/workflow_vaevae/src/longread_sludge_vamb.sh
@@ -2,23 +2,24 @@
 
 
 # vamb \
-#     --outdir /home/projects/cpr_10006/projects/semi_vamb/data/sludge/vambout64 \
+#     --outdir /home/projects/cpr_10006/projects/semi_vamb/data/sludge/vambout64_20102023 \
 #     --fasta /home/projects/cpr_10006/projects/semi_vamb/data/sludge/contigs_2kbp.fna \
 #     --rpkm /home/projects/cpr_10006/projects/semi_vamb/data/sludge/vambout/abundance.npz \
 #     -l 64 \
 #     -e 500 \
-#     -q 150 \
+#     -q 25 75 150 \
 #     -o C \
 #     --cuda \
 #     --minfasta 200000
 
 vamb \
     --model reclustering \
-    --latent_path /home/projects/cpr_10006/projects/semi_vamb/data/sludge/vambout64/latent.npy \
-    --clusters_path /home/projects/cpr_10006/projects/semi_vamb/data/sludge/vambout64/vae_clusters.tsv  \
+    --latent_path /home/projects/cpr_10006/projects/semi_vamb/data/sludge/vambout64_20102023/latent.npz \
+    --clusters_path /home/projects/cpr_10006/projects/semi_vamb/data/sludge/vambout64_20102023/vae_clusters.tsv  \
     --fasta /home/projects/cpr_10006/projects/semi_vamb/data/sludge/contigs_2kbp.fna \
     --rpkm /home/projects/cpr_10006/projects/semi_vamb/data/sludge/vambout/abundance.npz \
-    --outdir /home/projects/cpr_10006/projects/semi_vamb/data/sludge/vambout64_reclustering \
+    --outdir /home/projects/cpr_10006/projects/semi_vamb/data/sludge/vambout64_20102023_reclustering \
     --hmmout_path /home/projects/cpr_10006/projects/semi_vamb/data/marker_genes/markers_sludge.hmmout \
+    --taxonomy_predictions /home/projects/cpr_10006/projects/semi_vamb/data/sludge/vaevae_full_predictor_0.5/results_taxonomy_predictor.csv \
     --algorithm dbscan \
-    --minfasta 200000
+    --minfasta 200000
diff --git a/workflow_vaevae/src/shortread_CAMI2.sh b/workflow_vaevae/src/shortread_CAMI2.sh
@@ -1,37 +1,37 @@
 #!/usr/bin/bash
 dataset=$1
-run_id=$2
-keyword=$3
+annotator=$2
+thres=$3
 
     # --taxonomy /home/projects/cpr_10006/people/svekut/mmseq2/${dataset}_taxonomy_2023.tsv \
     # --taxonomy_predictions /home/projects/cpr_10006/people/svekut/cami2_urog_out_32_667/results_taxonomy_predictor.csv
     # --taxonomy /home/projects/cpr_10006/people/svekut/mmseq2/${dataset}_taxonomy.tsv \
 
-vamb \
-    --model vaevae \
-    --outdir /home/projects/cpr_10006/people/svekut/cami2_${dataset}_out_32_${run_id}_${keyword} \
-    --fasta /home/projects/cpr_10006/projects/vamb/data/datasets/cami2_${dataset}/contigs_2kbp.fna.gz \
-    --rpkm /home/projects/cpr_10006/projects/vamb/data/datasets/cami2_${dataset}/abundance.npz \
-    --taxonomy /home/projects/cpr_10006/people/svekut/04_mmseq2/taxonomy_cami_kfold/${dataset}_taxonomy_${run_id}.tsv \
-    -l 32 \
-    -e 200 \
-    -q  \
-    -t 1024 \
-    -pe 100 \
-    -pq  \
-    -pt 1024 \
-    -o C \
-    -ploss ${keyword} \
-    --cuda \
-    --minfasta 200000
+# vamb \
+#     --model vaevae \
+#     --outdir /home/projects/cpr_10006/people/svekut/cami2_${dataset}_${annotator}_${thres}_test \
+#     --fasta /home/projects/cpr_10006/projects/vamb/data/datasets/cami2_${dataset}/contigs_2kbp.fna.gz \
+#     --rpkm /home/projects/cpr_10006/projects/vamb/data/datasets/cami2_${dataset}/abundance.npz \
+#     --taxonomy /home/projects/cpr_10006/people/svekut/04_mmseq2/taxonomy_cami_kfold/${dataset}_taxonomy_${annotator}.tsv \
+#     -l 32 \
+#     -e 300 \
+#     -q  \
+#     -t 1024 \
+#     -pe 100 \
+#     -pq  \
+#     -pt 1024 \
+#     -pthr ${thres} \
+#     -o C \
+#     --cuda \
+#     --minfasta 200000
 
 vamb \
     --model reclustering \
-    --latent_path /home/projects/cpr_10006/people/svekut/cami2_${dataset}_out_32_${run_id}_${keyword}/vaevae_latent.npy \
-    --clusters_path /home/projects/cpr_10006/people/svekut/cami2_${dataset}_out_32_${run_id}_${keyword}/vaevae_clusters.tsv  \
+    --latent_path /home/projects/cpr_10006/people/svekut/cami2_${dataset}_${annotator}_${thres}/vaevae_latent.npy \
+    --clusters_path /home/projects/cpr_10006/people/svekut/cami2_${dataset}_${annotator}_${thres}/vaevae_clusters.tsv  \
     --fasta /home/projects/cpr_10006/projects/vamb/data/datasets/cami2_${dataset}/contigs_2kbp.fna.gz \
     --rpkm /home/projects/cpr_10006/projects/vamb/data/datasets/cami2_${dataset}/abundance.npz \
-    --outdir /home/projects/cpr_10006/people/svekut/cami2_${dataset}_out_32_reclustering_${run_id}_${keyword} \
+    --outdir /home/projects/cpr_10006/people/svekut/cami2_${dataset}_reclustering_${annotator}_${thres}_test \
     --hmmout_path /home/projects/cpr_10006/projects/semi_vamb/data/marker_genes/markers_cami_${dataset}.hmmout \
     --algorithm kmeans \
     --minfasta 200000
diff --git a/workflow_vaevae/src/shortread_CAMI2_no_predictor.sh b/workflow_vaevae/src/shortread_CAMI2_no_predictor.sh
@@ -13,27 +13,27 @@ keyword=$3
 
 vamb \
     --model vaevae \
-    --outdir /home/projects/cpr_10006/people/svekut/cami2_${dataset}_out_32_no_predictor_${run_id}_${keyword}_abs \
+    --outdir /home/projects/cpr_10006/people/svekut/cami2_${dataset}_no_predictor_${run_id}_${keyword} \
     --fasta /home/projects/cpr_10006/projects/vamb/data/datasets/cami2_${dataset}/contigs_2kbp.fna.gz \
     --rpkm /home/projects/cpr_10006/projects/vamb/data/datasets/cami2_${dataset}/abundance.npz \
     --taxonomy /home/projects/cpr_10006/people/svekut/04_mmseq2/taxonomy_cami_kfold/${dataset}_taxonomy_${run_id}.tsv \
     --no_predictor \
     -l 32 \
-    -e 1000 \
+    -e 300 \
     -t 1024 \
     -pq  \
     -q  \
     -o C \
     --cuda \
     --minfasta 200000
 
-# vamb \
-#     --model reclustering \
-#     --latent_path /home/projects/cpr_10006/people/svekut/cami2_${dataset}_out_32_no_predictor_${run_id}_${keyword}_1000/vaevae_latent.npy \
-#     --clusters_path /home/projects/cpr_10006/people/svekut/cami2_${dataset}_out_32_no_predictor_${run_id}_${keyword}_1000/vaevae_clusters.tsv  \
-#     --fasta /home/projects/cpr_10006/projects/vamb/data/datasets/cami2_${dataset}/contigs_2kbp.fna.gz \
-#     --rpkm /home/projects/cpr_10006/projects/vamb/data/datasets/cami2_${dataset}/abundance.npz \
-#     --outdir /home/projects/cpr_10006/people/svekut/cami2_${dataset}_out_32_no_predictor_reclustering_${run_id}_${keyword}_1000 \
-#     --hmmout_path /home/projects/cpr_10006/projects/semi_vamb/data/marker_genes/markers_cami_${dataset}.hmmout \
-#     --algorithm kmeans \
-#     --minfasta 200000
+vamb \
+    --model reclustering \
+    --latent_path /home/projects/cpr_10006/people/svekut/cami2_${dataset}_no_predictor_${run_id}_${keyword}/vaevae_latent.npy \
+    --clusters_path /home/projects/cpr_10006/people/svekut/cami2_${dataset}_no_predictor_${run_id}_${keyword}/vaevae_clusters.tsv  \
+    --fasta /home/projects/cpr_10006/projects/vamb/data/datasets/cami2_${dataset}/contigs_2kbp.fna.gz \
+    --rpkm /home/projects/cpr_10006/projects/vamb/data/datasets/cami2_${dataset}/abundance.npz \
+    --outdir /home/projects/cpr_10006/people/svekut/cami2_${dataset}_no_predictor_reclustering_${run_id}_${keyword} \
+    --hmmout_path /home/projects/cpr_10006/projects/semi_vamb/data/marker_genes/markers_cami_${dataset}.hmmout \
+    --algorithm kmeans \
+    --minfasta 200000
diff --git a/workflow_vaevae/src/shortread_CAMI2_predictor.sh b/workflow_vaevae/src/shortread_CAMI2_predictor.sh
@@ -8,12 +8,13 @@ keyword=$3
 # 
 vamb \
     --model taxonomy_predictor \
-    --outdir /home/projects/cpr_10006/people/svekut/cami2_${dataset}_predictor_${keyword}_${run_id}_abs_in \
+    --outdir /home/projects/cpr_10006/people/svekut/cami2_${dataset}_predictor_${keyword}_${run_id}_t \
     --fasta /home/projects/cpr_10006/projects/vamb/data/datasets/cami2_${dataset}/contigs_2kbp.fna.gz \
     --rpkm /home/projects/cpr_10006/projects/vamb/data/datasets/cami2_${dataset}/abundance.npz \
     --taxonomy /home/projects/cpr_10006/people/svekut/04_mmseq2/taxonomy_cami_kfold/${dataset}_taxonomy_${run_id}.tsv \
     -pe 100 \
     -pq  \
     -pt 1024 \
-    --cuda \
     -ploss ${keyword}
+
+    # --cuda \
diff --git a/workflow_vaevae/src/shortread_CAMI2_vamb.sh b/workflow_vaevae/src/shortread_CAMI2_vamb.sh
@@ -0,0 +1,28 @@
+#!/usr/bin/bash
+dataset=$1
+
+    # --taxonomy /home/projects/cpr_10006/people/svekut/mmseq2/${dataset}_taxonomy_2023.tsv \
+    # --taxonomy_predictions /home/projects/cpr_10006/people/svekut/cami2_urog_out_32_667/results_taxonomy_predictor.csv
+    # --taxonomy /home/projects/cpr_10006/people/svekut/mmseq2/${dataset}_taxonomy.tsv \
+
+# vamb \
+#     --outdir /home/projects/cpr_10006/people/svekut/cami2_${dataset}_vamb \
+#     --fasta /home/projects/cpr_10006/projects/vamb/data/datasets/cami2_${dataset}/contigs_2kbp.fna.gz \
+#     --rpkm /home/projects/cpr_10006/projects/vamb/data/datasets/cami2_${dataset}/abundance.npz \
+#     -l 32 \
+#     -e 300 \
+#     -q 25 75 150 \
+#     -o C \
+#     --cuda \
+#     --minfasta 200000
+
+vamb \
+    --model reclustering \
+    --latent_path /home/projects/cpr_10006/people/svekut/cami2_${dataset}_vamb/latent.npz \
+    --clusters_path /home/projects/cpr_10006/people/svekut/cami2_${dataset}_vamb/vae_clusters.tsv  \
+    --fasta /home/projects/cpr_10006/projects/vamb/data/datasets/cami2_${dataset}/contigs_2kbp.fna.gz \
+    --rpkm /home/projects/cpr_10006/projects/vamb/data/datasets/cami2_${dataset}/abundance.npz \
+    --outdir /home/projects/cpr_10006/people/svekut/cami2_${dataset}_reclustering_vamb \
+    --hmmout_path /home/projects/cpr_10006/projects/semi_vamb/data/marker_genes/markers_cami_${dataset}.hmmout \
+    --algorithm kmeans \
+    --minfasta 200000