Is there other way to download data set?[speed restriction] about deepbgc HOT 5 CLOSED

You can look for these lines:

INFO    10/10 11:48:16   Checking: /home/mima123456/.local/share/deepbgc/data/0.1.0/detector/deepbgc.pkl
INFO    10/10 11:48:16   Downloading: https://github.com/Merck/deepbgc/releases/download/v0.1.0/deepbgc.pkl

The first line shows the expected location, the second line shows the URL to download

I'm sorry to reply you so late. I download all the required file from the URL, and download the Escherichia coli genome from NCBI. Then I follow the software tips to tap deepbgc pipeline ./mySeq.fa. Fortunately, I got some of the results.

By the way, The results of the software output recorded in my log file are as follows, but compared with the file DeepBGC_Example_Result.ipyn, my results seem to be missing two files.

DeepBGC
================================================================================
/home/b12/miniconda3/bin/deepbgc pipeline ./GCF_000005845.2_ASM584v2_genomic.fna
================================================================================
LOG.txt Log output of DeepBGC
GCF_000005845.2_ASM584v2_genomic.bgc.gbk Sequences and features of all detected BGCs in GenBank format
GCF_000005845.2_ASM584v2_genomic.bgc.tsv Table of detected BGCs and their properties
GCF_000005845.2_ASM584v2_genomic.full.gbk Fully annotated input sequence with proteins, Pfam domains (PFAM_domain features) and BGCs (cluster features)
GCF_000005845.2_ASM584v2_genomic.pfam.tsv Table of Pfam domains (pfam_id) from given sequence (sequence_id) in genomic order, with BGC detection scores
evaluation/GCF_000005845.2_ASM584v2_genomic.bgc.png Detected BGCs plotted by their nucleotide coordinates
evaluation/GCF_000005845.2_ASM584v2_genomic.pr.png Precision-Recall curve based on predicted per-Pfam BGC scores
evaluation/GCF_000005845.2_ASM584v2_genomic.roc.png ROC curve based on predicted per-Pfam BGC scores
evaluation/GCF_000005845.2_ASM584v2_genomic.score.png BGC detection scores of each Pfam domain in genomic order

Does this have any impact? And output is as follow:
E_coli.zip

Thank you for developing such a powerful software.👍

from deepbgc.

Hi @Bollie15, you can download https://github.com/Merck/deepbgc/releases/download/v0.1.0/deepbgc.pkl yourself and put in this location: /home/mima123456/.local/share/deepbgc/data/0.1.0/detector/deepbgc.pkl.

from deepbgc.

Hi @Bollie15, you can download https://github.com/Merck/deepbgc/releases/download/v0.1.0/deepbgc.pkl yourself and put in this location: /home/mima123456/.local/share/deepbgc/data/0.1.0/detector/deepbgc.pkl.

It' help for me. But I cannot download other file again. Can you tell me how many files I should download manually? Downloading in the terminal is not as fast as manually downloading in the browser.

(base) b12@PC:~/.local/share/deepbgc/data/0.1.0/detector$ ls -l
total 12876
-rw-r--r-- 1 b12 b12  1143329 Oct 14 19:07 clusterfinder_geneborder.pkl
-rw-r--r-- 1 b12 b12   298106 Oct 14 18:36 clusterfinder_original.pkl
-rw-r--r-- 1 b12 b12   408102 Oct 14 18:37 clusterfinder_retrained.pkl
-rw-r--r-- 1 b12 b12 16778662 Oct 14 18:35 deepbgc.pkl

from deepbgc.

You can look for these lines:

INFO    10/10 11:48:16   Checking: /home/mima123456/.local/share/deepbgc/data/0.1.0/detector/deepbgc.pkl
INFO    10/10 11:48:16   Downloading: https://github.com/Merck/deepbgc/releases/download/v0.1.0/deepbgc.pkl

The first line shows the expected location, the second line shows the URL to download

from deepbgc.

Hi @Bollie15, that's great news. The pr.png and roc.png files are only present during validation, so these are expected to be missing. I'm closing this issue, let me know if you encounter anything else.

from deepbgc.