Trying out this:
INPUT=veba_output/preprocess/S4/output/joined.fastq.gz
OUTPUT=test_output
DMND_DB_DIR=veba_output/misc/diamond_database/
NUM_THREADS=1
humann --input ${INPUT} --output ${OUTPUT} --protein-database ${DMND_DB_DIR} --threads ${NUM_THREADS} --bypass-nucleotide-search --input-format fastq.gz --translated-identity-threshold 50 --translated-query-coverage-threshold 80 --search-mode uniref50 --id-mapping veba_output/misc/humann_uniref_annotations.tsv
but I’m getting this error:
CRITICAL ERROR: The directory provided for the translated database contains files ( all_proteins.faa.dmnd ) that are not of the expected version. Please install the latest version of the database: 201901b
Here’s my files:
(VEBA-profile_env) [jespinoz@exp-15-01 TestVEBA]$ ls -lhS veba_output/misc/diamond_database/
total 52M
-rw-rw---- 1 jespinoz jcl110 52M Oct 12 15:04 all_proteins.faa.dmnd
(VEBA-profile_env) [jespinoz@exp-15-01 TestVEBA]$ head veba_output/misc/humann_uniref_annotations.tsv
S1__NODE_166_length_33212_cov_10.244534_32964:33209(+) UniRef50_Q41093 82 c__Bacillariophyceae;o__Naviculales;f__Phaeodactylaceae;g__Phaeodactylum;s__Phaeodactylum tricornutum [CCAP 1055/1];t__S1__METABAT2__E.1__bin.1
S1__NODE_229_length_28347_cov_10.467447_5060:5751(-) UniRef50_Q41093 196 c__Bacillariophyceae;o__Naviculales;f__Phaeodactylaceae;g__Phaeodactylum;s__Phaeodactylum tricornutum [CCAP 1055/1];t__S1__METABAT2__E.1__bin.1
S1__NODE_298_length_24477_cov_10.374539_11070:11663(+) UniRef50_Q41093 198 c__Bacillariophyceae;o__Naviculales;f__Phaeodactylaceae;g__Phaeodactylum;s__Phaeodactylum tricornutum [CCAP 1055/1];t__S1__METABAT2__E.1__bin.1
S1__NODE_56_length_52126_cov_10.433043_49957:50562(+) UniRef50_Q41093 202 c__Bacillariophyceae;o__Naviculales;f__Phaeodactylaceae;g__Phaeodactylum;s__Phaeodactylum tricornutum [CCAP 1055/1];t__S1__METABAT2__E.1__bin.1
S1__NODE_56_length_52126_cov_10.433043_50725:52123(-) UniRef50_Q41093 338 c__Bacillariophyceae;o__Naviculales;f__Phaeodactylaceae;g__Phaeodactylum;s__Phaeodactylum tricornutum [CCAP 1055/1];t__S1__METABAT2__E.1__bin.1
S1__NODE_743_length_9370_cov_9.617391_5:550(+) UniRef50_Q41093 182 c__Bacillariophyceae;o__Naviculales;f__Phaeodactylaceae;g__Phaeodactylum;s__Phaeodactylum tricornutum [CCAP 1055/1];t__S1__METABAT2__E.1__bin.1
S1__NODE_14_length_79184_cov_10.324875_17207:17686(+) UniRef50_A0A1Z5JXG7 160 c__Bacillariophyceae;o__Naviculales;f__Phaeodactylaceae;g__Phaeodactylum;s__Phaeodactylum tricornutum [CCAP 1055/1];t__S1__METABAT2__E.1__bin.1
S1__NODE_646_length_11435_cov_10.486731_5428:5952(-) UniRef50_A0A1Z5JXG7 175 c__Bacillariophyceae;o__Naviculales;f__Phaeodactylaceae;g__Phaeodactylum;s__Phaeodactylum tricornutum [CCAP 1055/1];t__S1__METABAT2__E.1__bin.1
S1__NODE_674_length_10805_cov_9.362977_3661:4200(-) UniRef50_A0A1Z5JXG7 180 c__Bacillariophyceae;o__Naviculales;f__Phaeodactylaceae;g__Phaeodactylum;s__Phaeodactylum tricornutum [CCAP 1055/1];t__S1__METABAT2__E.1__bin.1
S1__NODE_8_length_86326_cov_10.138192_57293:57772(+) UniRef50_A0A1Z5JXG7 160 c__Bacillariophyceae;o__Naviculales;f__Phaeodactylaceae;g__Phaeodactylum;s__Phaeodactylum tricornutum [CCAP 1055/1];t__S1__METABAT2__E.1__bin.1
Here’s my versions:
(VEBA-profile_env) [jespinoz@exp-15-01 TestVEBA]$ conda list | grep -E "humann|diamond"
diamond 2.1.8 h43eeafb_0 bioconda
humann 3.8 pyh7cba7a3_0 bioconda