From 12fe89247c01ab72245fe73e0251ba1dcb8de106 Mon Sep 17 00:00:00 2001
From: Svetlana Kutuzova <galkina.s.a@gmail.com>
Date: Mon, 14 Aug 2023 15:40:43 +0200
Subject: [PATCH] fix: default algorithm

---
 vamb/__main__.py                              |  2 +-
 .../src/shortread_CAMI2_reassembled.sh        | 28 +++++++++++++++++++
 2 files changed, 29 insertions(+), 1 deletion(-)
 create mode 100755 workflow_vaevae/src/shortread_CAMI2_reassembled.sh

diff --git a/vamb/__main__.py b/vamb/__main__.py
index 867fb6de..00d5f6c2 100755
--- a/vamb/__main__.py
+++ b/vamb/__main__.py
@@ -1924,7 +1924,7 @@ def main():
         "--algorithm",
         metavar="",
         type=str,
-        default="",
+        default="kmeans",
         help="which reclustering algorithm to use ('kmeans', 'dbscan'). DBSCAN requires a taxonomy predictions file [kmeans]",
     )
 
diff --git a/workflow_vaevae/src/shortread_CAMI2_reassembled.sh b/workflow_vaevae/src/shortread_CAMI2_reassembled.sh
new file mode 100755
index 00000000..1e0322e1
--- /dev/null
+++ b/workflow_vaevae/src/shortread_CAMI2_reassembled.sh
@@ -0,0 +1,28 @@
+#!/usr/bin/bash
+dataset=$1
+run_id=$2
+
+vamb \
+    --model vaevae \
+    --outdir /home/projects/cpr_10006/people/svekut/cami2_${dataset}_reassembled_${run_id} \
+    --fasta /home/projects/cpr_10006/projects/semi_vamb/data/cami_errorfree/${dataset}/contigs.fna \
+    --rpkm /home/projects/cpr_10006/projects/semi_vamb/data/cami_errorfree/${dataset}/vambout/abundance.npz \
+    --taxonomy /home/projects/cpr_10006/people/paupie/vaevae/mmseq2_annotations/ptracker/${dataset}_taxonomy.tsv \
+    -l 32 \
+    -e 500 \
+    -q 25 75 150 \
+    -pe 100 \
+    -pq 25 75 \
+    -o C \
+    --cuda \
+    --minfasta 200000
+
+vamb \
+    --model reclustering \
+    --latent_path /home/projects/cpr_10006/people/svekut/cami2_${dataset}_reassembled_${run_id}/vaevae_latent.npy \
+    --clusters_path /home/projects/cpr_10006/people/svekut/cami2_${dataset}_reassembled_${run_id}/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_${dataset}_reclustering_reassembled_${run_id} \
+    --algorithm kmeans \
+    --minfasta 200000