fix

prepare.sh

@@ -7,6 +7,16 @@
 # Generate drugs embeddings
 esm-extract esm2_t33_650M_UR50D data/download/drugbank_targets.fasta data/vectors/drugbank_targets_esm2_l33_mean --repr_layers 33 --include mean
 
+
+wget https://mmseqs.com/latest/mmseqs-linux-avx2.tar.gz
+tar xvfz mmseqs-linux-avx2.tar.gz
+export PATH=$(pwd)/mmseqs/bin/:$PATH
+
+mmseqs easy-cluster data/DB.fasta clusterRes tmp --min-seq-id 0.5 -c 0.8 --cov-mode 1
+mmseqs createtsv clu_rep clu_rep clusterRes.tsv
+
+mmseqs createtsv sequenceDB sequenceDB resultsDB_clu resultsDB_clu.tsv
+
 # Install the Molecular Transformer Embeddings for proteins
 # https://github.com/mpcrlab/MolecularTransformerEmbeddings
 git clone https://github.com/mpcrlab/MolecularTransformerEmbeddings.git

src/train.py

@@ -436,7 +436,7 @@ def train_gpu(
     # # count += 1
     # df = pd.DataFrame(results)
 
-    df_avg_metrics = pd.DataFrame(fold_results).mean().to_dict()
+    df_avg_metrics = pd.DataFrame(fold_results).mean()
     print("TRAINING RESULTS")
     print(df_avg_metrics)
     return df_avg_metrics