+ added read structure for new parser
[qpalma.git] / qpalma / Configuration.py
index d35c6c4..3d06aa0 100644 (file)
@@ -422,9 +422,21 @@ training_end      = 1500
 prediction_begin  = 1500
 prediction_end    = 2200
 
-dna_filename         = '/fml/ag-raetsch/share/projects/qpalma/solexa/allGenes.pickle'
-est_filename         = '/fml/ag-raetsch/share/projects/qpalma/solexa/filteredReads_recent'
-tair7_seq_filename   = '/fml/ag-raetsch/share/projects/qpalma/solexa/tair7_seq.pickle'
+joinp = os.path.join
+
+data_path      = '/fml/ag-raetsch/share/projects/qpalma/solexa'  
+
+dna_filename   = joinp(data_path,'allGenes.pickle')
+est_filename   = joinp(data_path,'remapped_solexa_data/map_best_hit.18.unambig')
+
+remapped_path  = joinp(data_path,'remapped_solexa_data')
+annot_path     = joinp(data_path,'annotation_data')
+original_path  = joinp(data_path,'original_solexa_data')
+
+import tools
+from tools.parseGff import createGffPickle
+
+createGffPickle(joinp(annot_path,'TAIR7_GFF3_genes_Chr1.gff_v1'),dna_filename)
 
 ###############################################################################
 #
@@ -439,5 +451,5 @@ assert numQualSuppPoints   > 1
 
 assert os.path.exists(dna_filename), 'DNA data does not exist!'
 assert os.path.exists(est_filename), 'EST/Reads data does not exist!'
-assert os.path.exists(tair7_seq_filename), 'Sequence data does not exist!'
+#assert os.path.exists(tair7_seq_filename), 'Sequence data does not exist!'