DEPP on ACCESS unk Sequence aligment by deep learning - run on XSEDE Yueyu Jiang Yueyu Jiang, Metin Balaban, Qiyun Zhu, Siavash Mirarab, DEPP: Deep Learning Enables Extending Species Trees using Single Genes, Systematic Biology, 2022;, syac031, https://doi.org/10.1093/sysbio/syac031 Phylogeny / Alignment depp_xsede depp_invoke perl "depp_expanse" 0 depp_training perl $specify_runtype eq "training" && !$specify_nogpus perl "" 1 depp_trainingb perl $specify_runtype eq "training" && $specify_nogpus perl "" 1 depp_distance perl $specify_runtype eq "distance" perl "" 0 training_conf perl $specify_runtype eq "training" && !$specify_nogpus scheduler.conf perl "ChargeFactor=1.0\\n" . "gpu=1\\n" . "nodes=1\\n" . "node_exclusive=0\\n" . "mem=92G\\n" . "threads_per_process=1\\n" training_nogpusconf perl $specify_runtype eq "training" && $specify_nogpus scheduler.conf perl "ChargeFactor=1.0\\n" . "nodes=1\\n" . "node_exclusive=0\\n" . "mem=12G\\n" . "threads_per_process=1\\n" distance_conf perl $specify_runtype eq "distance" scheduler.conf perl "ChargeFactor=1.0\\n" . "nodes=1\\n" . "node_exclusive=0\\n" . "mem=12G\\n" . "threads_per_process=1\\n" infile Backbone Sequence File backbone.fa all_results * runtime 1 scheduler.conf Maximum Hours to Run (up to 168 hours) 0.5 The maximum hours to run must be less than 168 perl $runtime > 168.0 The maximum hours to run must be greater than 0.05 perl $runtime < 0.05 perl "runhours=$value\\n" The job will run on 1 gpu as configured. If it runs for the entire configured time, it will consume 20 X $runtime cpu hours perl $specify_runtype eq "training" The job will run on $select_numcores processor as configured. If it runs for the entire configured time, it will consume $select_numcores X $runtime cpu hours perl $specify_runtype eq "distance" Estimate the maximum time your job will need to run. We recommend testing initially with a < 0.5hr test run because Jobs set for 0.5 h or less dependably run immediately in the "debug" queue. Once you are sure the configuration is correct, you then increase the time. The reason is that jobs > 0.5 h are submitted to the "normal" queue, where jobs configured for 1 or a few hours times may run sooner than jobs configured for the full 168 hours. specify_runtype What type of run? training distance Please select a run type perl !defined $specify_runtype backbone_treefile Select your backbone tree file perl $specify_runtype eq "training" backbone.nwk epoch_file Select your query Epoch file perl $specify_runtype eq "training" epoch-0.pth query_seqsfile Select your query sequence file perl $specify_runtype eq "distance" queryseq.fa query_modelfile Select your model file perl $specify_runtype eq "distance" model.ckpt specify_epoch Specify the number of epochs (epoch=) 1001 specify_nogpus Don't use GPUs