Martino

multi-gpu inference?

5

Hi Chris, I'd like to harness the power of multiple GPUs for basecalling. Can you comment if this is possible/easily implementable? I noticed @kishwarshafin seems to have this implemented in...

Installation issue with pytorch

1

Hello! Trying to install locally, hitting the following error: `ERROR: Could not find a version that satisfies the requirement torch==1.10.0 (from versions: 1.11.0, 1.12.0, 1.12.1, 1.13.0, 1.13.1, 2.0.0) ERROR: No...

invalid feature coordinates from long read 'collapsed' assembly

3

So I 'collapsed' some long read data into a gtf with : `/home/apps/stringtie2.1.4/stringtie ${BAMLIST} -p ${THREADS} -L -R -o hg38_merged.gtf` I then try to quantify each sample/bam against this cleaned...

CUDAPolisher core dumps

1

I've been trying to get racon-gpu to run on my data (2x ~1kb contigs) but keep hitting a wall `$ racon -m 8 -x -6 -g -8 -c 1 reads.fastq...

I think MinKNOW's local 1D base calling (albacore?) saves data in the fast5 files differently to metrichor / nanonet basecalling. Indeed, when trying to run many poretools commands, I get...

Using node-local storage speeds up IO heavy tasks significantly on SGE/PBS systems. The Trinity mods make use of this, however as a list of commands is intrinsically being generated by...

I thought it might be nice to have a counter next to or after the checkpoints in the log files. I think this might interesting for anxious people like me...