python $PLMBLAST_PATH/embeddings.py merged.proteomes.csv merged.proteomes -embedder pt -cname sequence --gpu -bs -1 --asdir
I get back:
File "/bin/pLM-BLAST/embedders/parser.py", line 173, in make_iterator
if startbatch[-1] != seqnum:
IndexError: list index out of range
The "merged.proteomes.csv" was generated from a "merged.proteomes.fasta" using the "makeindex.py" script.
For context, the "merged.proteome.fasta" contains 6821190 sequences, while the "merged.proteomes.csv" contains 7360055 lines (so 538865 more lines than the number of sequences--is this expected?)
When I run the command:
python $PLMBLAST_PATH/embeddings.py merged.proteomes.csv merged.proteomes -embedder pt -cname sequence --gpu -bs -1 --asdir
I get back:The "merged.proteomes.csv" was generated from a "merged.proteomes.fasta" using the "makeindex.py" script.
For context, the "merged.proteome.fasta" contains 6821190 sequences, while the "merged.proteomes.csv" contains 7360055 lines (so 538865 more lines than the number of sequences--is this expected?)