search

MicrobeLab / DeepMicrobes

DeepMicrobes: taxonomic classification for metagenomics with deep learning
https://doi.org/10.1093/nargab/lqaa009
Apache License 2.0
81 stars 21 forks source link

How should I run this model in single-end mode? #32

Open stargazer-dot opened 6 months ago

MicrobeLab commented 5 months ago

For single-end reads, only one fastq file will need to be interleaved and in the model codes the prediction should be averaged across 2 samples rather than 4 samples.

Gayathri142 commented 1 month ago

Hello, can you please elaborate a bit more about this? So when trying to generate tfrec for single ended data, what would the input be? Right now it takes a -f and -r as input. When I try to give just one file it throws an error. Can you paste the command for single end data here? To generate tfrec for our sample data

MicrobeLab commented 1 month ago

Hi, it might be a good choice to directly run the python script for converting data to tfrec: seq2tfrec_kmer.py \ --input_seq={} --output_tfrec={}.${kmer}mer.tfrec \ --vocab=${vocab} --kmer=${kmer} \ --seq_type=${seq_type}

Gayathri142 commented 1 month ago

Thank you. I have generated a tfrec file for single-end sample using seq2tfrec_kmer.py. However, when I try to run 'predict_DeepMicrobes.sh' it gives me an error saying the paired-end file is missing. Can you please tell me how to perform prediction on single-end tfrec files

MicrobeLab commented 1 month ago

Hi, could you please give the command that you ran 'predict_DeepMicrobes.sh' and the exact error message?