Adds one-hot and k-mer encoder for DNA sequences#1845
Adds one-hot and k-mer encoder for DNA sequences#1845pavanvidem merged 20 commits intobgruening:masterfrom
Conversation
| --num_classes '$encoder_type.num_classes' | ||
| #end if | ||
| #else | ||
| --fasta_path '$encoder_type.fasta_path' |
There was a problem hiding this comment.
Maybe symlinking the fasta to working dir before runnig the script might resolve the issue.
There was a problem hiding this comment.
Thanks @pavanvidem .. this suggestion fixed the issue.
However, test related to a different tool fails:
Can you restart the CI? thanks!
| </conditional> | ||
| </conditional> | ||
| <output name="outfile_matrix" file="dna_ohe_output.h5" ftype="h5" compare="sim_size" delta="32" /> | ||
| <output name="outfile" file="dna_ohe_output.tabular" ftype="tabular" /> |
There was a problem hiding this comment.
can you please user asserts here. Also for h5.
| </conditional> | ||
| </conditional> | ||
| <output name="outfile_matrix" file="dna_ohe_output_same_len.h5" ftype="h5" compare="sim_size" delta="32" /> | ||
| <output name="outfile" file="dna_ohe_output_same_len.tabular" ftype="tabular" /> |
There was a problem hiding this comment.
same here. please use asserts.
| </conditional> | ||
| </conditional> | ||
| <output name="outfile" file="dna_kmer_output_k3.tabular" ftype="tabular" /> | ||
| <output name="outfile_vocab" file="dna_kmer_vocab_k3.json" ftype="json" /> |
There was a problem hiding this comment.
there are json asserts too :)
| </conditional> | ||
| </conditional> | ||
| <output name="outfile" file="dna_kmer_sanitized_output_k3.tabular" ftype="tabular" /> | ||
| <output name="outfile_vocab" file="dna_kmer_sanitized_vocab_k3.json" ftype="json" /> |
|
Can you please cleanup the other output files that are not used in any test. Then we are ready to merge. |
done, thanks! |
2 participants
No description provided.