msahraeian

@llevar I am happy to see your interest in NeuSomatic. Currently, NeuSomatic supports g++ 5.4.0. We plan to adapt it for later g++ versions in future releases.

@GolfDeltaFox Happy to see your interest in our work. The CGC links are not public yet. We are working to make it public ASAP. I will inform you once it...

Thanks for your interest in NeuSomatic. Currently, NeuSomatic can only support tumor-normal somatic mutation detection. We plan to extend it to tumor-only mode in near future.

@amit21AIT I guess methods like MuTect2 and VarDict can perform tumor-only calling, although they may have difficulty in filtering some FPs and germline calls without normal match.

@chrissype happy to see your interest in NeuSomatic. Yes, you can train on multiple samples as follows: 1. For each sample run `preprocess.py`. This will you give you per sample...

@JunhakAhn Thanks for your interest in NeuSomatic. 1. I guess you are running `somaticseq_parallel.py` in single sample mode (tumor-only). But, you need to run it in tumor-normal paired mode. You...

@kokyriakidis I am happy to see your interest in NeuSomatic. As noted in the [README](https://github.com/bioinform/neusomatic#trained-network-models), similar to DeepVariant, we provide a set of pre-trained NeuSomatic network models for general purpose...

@yueyangtime hi, would you please explain for which sample you are interested in the truth vcf file?

@yueyangtime If you want to train NeuSomatic on your sample of interest, you should have a truth `.vcf` for that sample. We have not released the truth files for our...

@jingmeng-bioinformatics It depends on your sample coverages. For me, I usually run on a 28-threads cluster and it will take a couple of hours. So, If you run on 1...