Added make_training_sets.py which allows to automatically prepare training sets or update the existing ones. However, while --retrain, the kmers set is updated but previously prepared training sets are not recalculated unless present in --indir on considered in --groups file.
Also, added 12 new reference genomes and created some training groups for bacterial families or genera:
Achromobacter denitrificans strain PR1
Bacteroides uniformis ATCC 8492 strain 81A2
Enterococcus faecalis V583 and Enterococcus faecalis strain V583
7 Paracoccus spp.
Staphylococcus aureus strain Sa_Newman_UoM
Added a flag to control the number of Random Forest trees during the classification.
Added a flag to choose the type of kmers and hence updated makeTrain.py and makeTest.py This also indicated what kmer files should be within data/.
Added make_training_sets.py which allows to automatically prepare training sets or update the existing ones. However, while --retrain, the kmers set is updated but previously prepared training sets are not recalculated unless present in --indir on considered in --groups file. Also, added 12 new reference genomes and created some training groups for bacterial families or genera:
Added a flag to control the number of Random Forest trees during the classification. Added a flag to choose the type of kmers and hence updated makeTrain.py and makeTest.py This also indicated what kmer files should be within data/.