Mercurial > repos > greg > draw_amr_matrix

comparison draw_amr_matrix.py @ 11:da1c9c1be421 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author greg
date Mon, 27 Mar 2023 19:41:30 +0000
parents 03240ffe969a
children aa2b737102dc
comparison
equal deleted inserted replaced
10:03240ffe969a 11:da1c9c1be421
63 ofh = open('process_log', 'w') 63 ofh = open('process_log', 'w')
64 64
65 # Read amr_feature_hits_files. 65 # Read amr_feature_hits_files.
66 amr_feature_hits = pandas.Series(dtype=object) 66 amr_feature_hits = pandas.Series(dtype=object)
67 for amr_feature_hits_file in amr_feature_hits_files: 67 for amr_feature_hits_file in amr_feature_hits_files:
68 ofh.write("\namr_feature_hits_file: %s\n" % amr_feature_hits_file)
68 feature_name = os.path.basename(amr_feature_hits_file) 69 feature_name = os.path.basename(amr_feature_hits_file)
70 ofh.write("\nfeature_name: %s\n" % feature_name)
69 # Make sure the file is not empty. 71 # Make sure the file is not empty.
70 if os.path.isfile(amr_feature_hits_file) and os.path.getsize(amr_feature_hits_file) > 0: 72 if os.path.isfile(amr_feature_hits_file) and os.path.getsize(amr_feature_hits_file) > 0:
71 best_hits = pandas.read_csv(filepath_or_buffer=amr_feature_hits_file, sep='\t', header=None) 73 best_hits = pandas.read_csv(filepath_or_buffer=amr_feature_hits_file, sep='\t', header=None)
72 ofh.write("\nFeature file %s will be processed\n" % os.path.basename(amr_feature_hits_file)) 74 ofh.write("\nFeature file %s will be processed\n" % os.path.basename(amr_feature_hits_file))
73 else: 75 else:
146 ofh.write("\ncmd:\n%s\n" % cmd) 148 ofh.write("\ncmd:\n%s\n" % cmd)
147 run_command(cmd) 149 run_command(cmd)
148 try: 150 try:
149 ofh.write("After running command, os.path.getsize((region_mutations_tsv): %s\n" % str(os.path.getsize(region_mutations_tsv))) 151 ofh.write("After running command, os.path.getsize((region_mutations_tsv): %s\n" % str(os.path.getsize(region_mutations_tsv)))
150 region_mutations = pandas.read_csv(region_mutations_tsv, sep='\t', header=0, index_col=False) 152 region_mutations = pandas.read_csv(region_mutations_tsv, sep='\t', header=0, index_col=False)
153 ofh.write("\nregion_mutations: %s\n" % region_mutations)
151 except Exception: 154 except Exception:
152 continue 155 continue
153 # Figure out what kind of mutations are in this region. 156 # Figure out what kind of mutations are in this region.
154 region_mutation_types = pandas.Series(['snp'] * region_mutations.shape[0], name='TYPE', index=region_mutations.index) 157 region_mutation_types = pandas.Series(['snp'] * region_mutations.shape[0], name='TYPE', index=region_mutations.index)
155 region_mutation_types[region_mutations['REF'].str.len() != region_mutations['ALT'].str.len()] = 'small-indel' 158 region_mutation_types[region_mutations['REF'].str.len() != region_mutations['ALT'].str.len()] = 'small-indel'
158 region_mutations = pandas.concat([region_mutations, region_mutation_types, region_mutation_drugs, region_notes], axis=1) 161 region_mutations = pandas.concat([region_mutations, region_mutation_types, region_mutation_drugs, region_notes], axis=1)
159 region_mutations = region_mutations[['#CHROM', 'POS', 'TYPE', 'REF', 'ALT', 'DRUG', 'NOTE']] 162 region_mutations = region_mutations[['#CHROM', 'POS', 'TYPE', 'REF', 'ALT', 'DRUG', 'NOTE']]
160 amr_mutations[region['name']] = region_mutations 163 amr_mutations[region['name']] = region_mutations
161 else: 164 else:
162 ofh.write("\nMutation region BED file not received.\n") 165 ofh.write("\nMutation region BED file not received.\n")
166 ofh.write("\nAfter processing mutations, amr_mutations: %s\n" % str(amr_mutations))
163 # Roll up potentially resistance conferring mutations. 167 # Roll up potentially resistance conferring mutations.
164 ofh.write("\n##### Rolling up potentially resistance conferring mutations..\n") 168 ofh.write("\n##### Rolling up potentially resistance conferring mutations..\n")
165 for mutation_region, mutation_hits in amr_mutations.iteritems(): 169 for mutation_region, mutation_hits in amr_mutations.iteritems():
166 ofh.write("mutation_region: %s\n" % str(mutation_region)) 170 ofh.write("mutation_region: %s\n" % str(mutation_region))
167 ofh.write("mutation_hits: %s\n" % str(mutation_hits)) 171 ofh.write("mutation_hits: %s\n" % str(mutation_hits))
169 ofh.write("mutation_idx: %s\n" % str(mutation_idx)) 173 ofh.write("mutation_idx: %s\n" % str(mutation_idx))
170 ofh.write("mutation_hit: %s\n" % str(mutation_hit)) 174 ofh.write("mutation_hit: %s\n" % str(mutation_hit))
171 mutation_name = mutation_region + ' ' + mutation_hit['REF'] + '->' + mutation_hit['ALT'] 175 mutation_name = mutation_region + ' ' + mutation_hit['REF'] + '->' + mutation_hit['ALT']
172 ofh.write("mutation_name: %s\n" % str(mutation_name)) 176 ofh.write("mutation_name: %s\n" % str(mutation_name))
173 amr_to_draw = amr_to_draw.append(pandas.Series([mutation_name, mutation_hit['DRUG']], name=amr_to_draw.shape[0], index=amr_to_draw.columns)) 177 amr_to_draw = amr_to_draw.append(pandas.Series([mutation_name, mutation_hit['DRUG']], name=amr_to_draw.shape[0], index=amr_to_draw.columns))
178 ofh.write("\nAfter processing mutations, amr_to_draw: %s\n" % str(amr_to_draw))
179 ofh.write("\nAfter processing mutations, amr_to_draw.shape[0]: %s\n" % str(amr_to_draw.shape[0]))
174 180
175 if amr_deletions_file not in [None, 'None'] and os.path.getsize(amr_deletions_file) > 0: 181 if amr_deletions_file not in [None, 'None'] and os.path.getsize(amr_deletions_file) > 0:
176 # Roll up deletions that might confer resistance. 182 # Roll up deletions that might confer resistance.
177 try: 183 try:
178 amr_deletions = pandas.read_csv(filepath_or_buffer=amr_deletions_file, sep='\t', header=None) 184 amr_deletions = pandas.read_csv(filepath_or_buffer=amr_deletions_file, sep='\t', header=None)
181 if amr_deletions.shape[0] > 0: 187 if amr_deletions.shape[0] > 0:
182 amr_deletions.columns = ['contig', 'start', 'stop', 'name', 'type', 'drug', 'note'] 188 amr_deletions.columns = ['contig', 'start', 'stop', 'name', 'type', 'drug', 'note']
183 amr_deletions = amr_deletions.loc[amr_deletions['type'].isin(['large-deletion', 'any']), :] 189 amr_deletions = amr_deletions.loc[amr_deletions['type'].isin(['large-deletion', 'any']), :]
184 for deletion_idx, deleted_gene in amr_deletions.iterrows(): 190 for deletion_idx, deleted_gene in amr_deletions.iterrows():
185 amr_to_draw = amr_to_draw.append(pandas.Series(['\u0394' + deleted_gene[3], deleted_gene[5]], name=amr_to_draw.shape[0], index=amr_to_draw.columns)) 191 amr_to_draw = amr_to_draw.append(pandas.Series(['\u0394' + deleted_gene[3], deleted_gene[5]], name=amr_to_draw.shape[0], index=amr_to_draw.columns))
186 192 ofh.write("\nAfter processing deletions, amr_to_draw: %s\n" % str(amr_to_draw))
187 if amr_to_draw.shape[0] > 1: 193
194 ofh.write("\namr_to_draw.shape[0]: %s\n" % str(amr_to_draw.shape[0]))
195 if amr_to_draw.shape[0] > 0:
188 ofh.write("\nDrawing AMR matrix...\n") 196 ofh.write("\nDrawing AMR matrix...\n")
189 present_genes = amr_to_draw['gene'].unique() 197 present_genes = amr_to_draw['gene'].unique()
190 present_drugs = amr_to_draw['drug'].unique() 198 present_drugs = amr_to_draw['drug'].unique()
191 amr_matrix = pandas.DataFrame(0, index=present_genes, columns=present_drugs) 199 amr_matrix = pandas.DataFrame(0, index=present_genes, columns=present_drugs)
192 for hit_idx, hit in amr_to_draw.iterrows(): 200 for hit_idx, hit in amr_to_draw.iterrows():