Module: FlnStats

Defined in:
lib/full_lengther_next/classes/fln_stats.rb

Instance Method Summary collapse

Instance Method Details

#annotation_stats(size_filter1, size_filter2) ⇒ Object 



363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
 
# File 'lib/full_lengther_next/classes/fln_stats.rb', line 363

def annotation_stats(size_filter1,size_filter2)

	seqs_number = 0
	array_of_all_accs = []
	array_of_complete_accs = []
	error_1_num = 0
	uni_500 = 0
	uni_200 = 0
	longest_one = 0

	status_array = []
	# total, status
	complete = [0,'Complete']
	putative_complete = [0,'Putative Complete']
	c_terminus = [0,'C-terminus']
	putative_c_terminus = [0,'Putative C-terminus']
	n_terminus = [0,'N-terminus']
	putative_n_terminus = [0,'Putative N-terminus']
	internal = [0,'Internal']
	cod_seq = [0,'Misassembled']

	#userdb, SwissProt, TrEMBL
	db_usage = [0,0,0]

	File.open('fln_results/dbannotated.txt').each do |line|
		line.chomp!
		(name,fasta_length,acc,db_name,status,kk1,kk2,kk3,kk4,kk5,msgs) = line.split("\t")

		if (line !~ /^Query_id\t/) && (!line.empty?)
			seqs_number += 1
			if (fasta_length.to_i > longest_one)
				longest_one = fasta_length.to_i
			end
			array_of_all_accs.push acc

			if (db_name !~ /^sp_/) && (db_name !~ /^tr_/)
				db_usage[0] += 1
			elsif (db_name =~ /^sp_/)
				db_usage[1] += 1
			elsif (db_name =~ /^tr_/)
				db_usage[2] += 1
			end

			# -------------------------------------------------------------------------
			if (fasta_length.to_i >= size_filter1)
				uni_200 += 1
			end
			if (fasta_length.to_i >= size_filter2)
				uni_500 += 1
			end
			# -------------------------------------------------------------------------
			if (msgs =~ /ERROR#1/)
				error_1_num += 1
			end
			# -------------------------------------------------------------------------
			if (status == 'Complete')
				complete[0] += 1
				array_of_complete_accs.push acc

			elsif (status == 'Putative Complete')
				putative_complete[0] += 1
			elsif (status == 'C-terminus')
				c_terminus[0] += 1
			elsif (status == 'N-terminus')
				n_terminus[0] += 1
			elsif (status == 'Putative C-terminus')
				putative_c_terminus[0] += 1
			elsif (status == 'Putative N-terminus')
				putative_n_terminus[0] += 1
			elsif (status == 'Internal')
				internal[0] += 1
			elsif (status == 'Misassembled')
				cod_seq[0] += 1
			end
			# -------------------------------------------------------------------------
		end

	end

	status_array = [complete, putative_complete, c_terminus, putative_c_terminus, n_terminus, putative_n_terminus, internal, cod_seq]

	return [status_array, db_usage, seqs_number, error_1_num, array_of_all_accs.uniq.count, array_of_complete_accs.uniq.count, uni_500, uni_200, longest_one]
end

#chimera_stats(size_filter1, size_filter2) ⇒ Object 



551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
 
# File 'lib/full_lengther_next/classes/fln_stats.rb', line 551

def chimera_stats(size_filter1,size_filter2)
	
	uni_500 = 0
	uni_200 = 0
	ch_total = 0
	longest_one = 0
	db_usage = [0,0,0]
		
	if !File.exists?('fln_results/chimeric_sequences.txt')
		return [0, 0, 0, longest_one, db_usage]
	else
		File.open('fln_results/chimeric_sequences.txt').each do |line|
			line.chomp!
			if (!line.empty?)
				(name,fasta_length,acc,db_name,status) = line.split("\t")
				if (status == 'Putative chimera')
					if (fasta_length.to_i > longest_one)
						longest_one = fasta_length.to_i
					end
					# -------------------------------------------------------------------------
					if (fasta_length.to_i >= size_filter1)
						uni_200 += 1
					end
					if (fasta_length.to_i >= size_filter2)
						uni_500 += 1
					end
					# -------------------------------------------------------------------------
					if (db_name =~ /^sp_/)
						db_usage[1] += 1
					elsif (db_name =~ /^tr_/)
						db_usage[2] += 1
					else
						db_usage[0] += 1
					end
					# -------------------------------------------------------------------------
					ch_total += 1
				end
			end
		end
	
		db_usage.each_with_index do |db,i|
			db_usage[i] = db/2
		end
	
		return [(ch_total/2), (uni_500/2), (uni_200/2), longest_one, db_usage]
	end
end

#html_code ⇒ Object 



294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
 
# File 'lib/full_lengther_next/classes/fln_stats.rb', line 294

def html_code
	html_head = '<html>
<head>
	<title>FLN Summary</title>
</head>

<body bgcolor="#FFFFFF">
	<center>
		<h1 align="center">
			Full-LengtherNEXT Summary
		</h1>'


	html_1 = '
		<h2 align="center">
			Status report
		</h2>

		<table border="2" cellspacing="0" cellpadding="2">
			<tr>
				<th colspan="2">Status</th>
				<th>Unigenes</th>
				<th>%</th>
			</tr>'

	html_2= '
		<h2 align="center">
			Unigene report
		</h2>

		<table border="2" cellspacing="0" cellpadding="2">
			<tr>
				<th></th>
				<th>Unigenes</th>
				<th>%</th>
			</tr>'

	html_3= '
		<h2 align="center">
			Database usage
		</h2>

		<table border="2" cellspacing="0" cellpadding="2">
			<tr>
				<th></th>
				<th>Unigenes</th>
				<th>%</th>
			</tr>'

	html_4= '
		<h2 align="center">
			Report guiding assembly quality
		</h2>

		<table border="2" cellspacing="0" cellpadding="2">
			<tr>
				<th></th>
				<th>Unigenes</th>
				<th>%</th>
			</tr>'

	html_5 = '	</body>
	</html>'

	return [html_head, html_1, html_2, html_3, html_4, html_5]

end

#ncrna_stats(size_filter1, size_filter2) ⇒ Object 



518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
 
# File 'lib/full_lengther_next/classes/fln_stats.rb', line 518

def ncrna_stats(size_filter1,size_filter2)

	uni_500 = 0
	uni_200 = 0
	nc_total = 0
	longest_one = 0

	File.open('fln_results/nc_rnas.txt').each do |line|
		line.chomp!
		(name,fasta_length,acc,db_name,status) = line.split("\t")

		if (status == 'Putative ncRNA')

			if (fasta_length.to_i > longest_one)
				longest_one = fasta_length.to_i
			end
			# -------------------------------------------------------------------------
			if (fasta_length.to_i >= size_filter1)
				uni_200 += 1
			end
			if (fasta_length.to_i >= size_filter2)
				uni_500 += 1
			end
			# -------------------------------------------------------------------------

			nc_total += 1

		end
	end

	return [nc_total, uni_500, uni_200, longest_one]
end

#summary_stats ⇒ Object 



4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
 
# File 'lib/full_lengther_next/classes/fln_stats.rb', line 4

def summary_stats
	stats_file = File.open('fln_results/summary_stats.html', 'w')
	
	size_filter1 = 200
	size_filter2 = 500
	
	# recogemos los trozos de html fijos
	(html_head, html_st, html_uni, html_db, html_as, html_end) = html_code
	
	total_seqs = 0
	status_suma = 0
	#recogemos los datos que necesitamos de los ficheros de resultados
	(status_array, db_usage, seqs_number1, error_1_num, seq_uniq, complete_uniq, db_uni_500, db_uni_200, db_longest_one) = annotation_stats(size_filter1,size_filter2)
	(tcode_array, seqs_number2, tc_uni_500, tc_uni_200, tc_longest_one) = testcode_stats(size_filter1,size_filter2)
	(ncrna_total, nc_uni_500, nc_uni_200, nc_longest_one)=ncrna_stats(size_filter1,size_filter2)
	(chimera_total, ch_uni_500, ch_uni_200, ch_longest_one, ch_db_usage)=chimera_stats(size_filter1,size_filter2)
	
	seqs_number1 = (seqs_number1+chimera_total.to_i)
	total_seqs = (seqs_number1 + seqs_number2 + ncrna_total.to_i)
	uni_500 = (db_uni_500 + tc_uni_500 + nc_uni_500 + ch_uni_500)
	uni_200 = (db_uni_200 + tc_uni_200 + nc_uni_200 + ch_uni_200)
	longest_one = [db_longest_one, tc_longest_one, nc_longest_one, ch_longest_one].max
	db_usage[0] += ch_db_usage[0]
	db_usage[1] += ch_db_usage[1]
	db_usage[2] += ch_db_usage[2]
	stats_file.puts html_head
	
	if (total_seqs.to_i > 0)
		# imprimimos la tabla Status Report --------------------------------------------------------------------------------------------
		stats_file.puts html_st
		status_array.each do |status|
			if (status[1] == 'Internal') || (status[1] == 'Misassembled')
			stats_file.puts '				<tr>
				<td colspan="2" align="left">'+status[1].to_s+'</td>
				<td align="right">'+status[0].to_s+'</td>
				<td align="right">'+'%.2f' % (100*status[0].to_f/total_seqs.to_f).to_s+' %</td>
			</tr>'
			elsif (status[1] =~ /^Putative/)
			stats_file.puts '				<tr>
				<td align="left">Putative</td>
				<td align="right">'+status[0].to_s+'</td>
				<td align="right">'+'%.2f' % (100*status[0].to_f/total_seqs.to_f).to_s+' %</td>
			</tr>'
			else
				stats_file.puts '				<tr>
				<td rowspan="2" align="left">'+status[1].to_s+'</td>
				<td align="left">Sure</td>
				<td align="right">'+status[0].to_s+'</td>
				<td align="right">'+'%.2f' % (100*status[0].to_f/total_seqs.to_f).to_s+' %</td>
			</tr>'
			end
			status_suma += status[0]
		end
		
		# adding chimeric seqs
		stats_file.puts '				<tr>
				<td colspan="2" align="left">Putative chimera</td>
				<td align="right">'+chimera_total.to_s+'</td>
				<td align="right">'+'%.2f' % (100*chimera_total.to_f/total_seqs.to_f).to_s+' %</td>
			</tr>'
			status_suma += chimera_total
			
		# añadimos los coding, P.coding
		tcode_array.each do |status|
			if (status[1] == 'Coding')
			stats_file.puts '				<tr>
				<td  rowspan="2" align="left">'+status[1].to_s+'</td>
				<td align="left">Sure</td>
				<td align="right">'+status[0].to_s+'</td>
				<td align="right">'+'%.2f' % (100*status[0].to_f/total_seqs.to_f).to_s+' %</td>
			</tr>'
			elsif (status[1] == 'Putative Coding')
			stats_file.puts '				<tr>
				<td align="left">Putative</td>
				<td align="right">'+status[0].to_s+'</td>
				<td align="right">'+'%.2f' % (100*status[0].to_f/total_seqs.to_f).to_s+' %</td>
			</tr>'
			end
			status_suma += status[0]
		end
		
		# se ponen los ncRNA
		stats_file.puts '				<tr>
				<td colspan="2" align="left">Putative ncRNA</td>
				<td align="right">'+ncrna_total.to_s+'</td>
				<td align="right">'+'%.2f' % (100*ncrna_total.to_f/total_seqs.to_f).to_s+' %</td>
			</tr>'
			status_suma += ncrna_total
		# se ponen los unknown
		tcode_array.each do |status|
			if (status[1] =~ /Unknown/i)
			stats_file.puts '				<tr>
				<td colspan="2" align="left">'+status[1].to_s+'</td>
				<td align="right">'+status[0].to_s+'</td>
				<td align="right">'+'%.2f' % (100*status[0].to_f/total_seqs.to_f).to_s+' %</td>
			</tr>'
			end
		end
		#se añade el total
			stats_file.puts '				<tr>
				<td colspan="2" align="left">Total</td>
				<td align="right">'+status_suma.to_s+'</td>
				<td align="right">'+'%.2f' % (100*status_suma.to_f/total_seqs.to_f).to_s+' %</td>
			</tr>
		</table>'
		
		
		# imprimimos la tabla Unigene Report --------------------------------------------------------------------------------------------
		new_genes = tcode_array[0][0] + tcode_array[1][0]
		total_uni = (seqs_number1 + new_genes + ncrna_total + tcode_array[2][0])
		stats_file.puts html_uni
			stats_file.puts '				<tr>
				<td align="left">With orthologue in DBs</td>
				<td align="right">'+seqs_number1.to_s+'</td>
				<td align="right">'+'%.2f' % (100*seqs_number1.to_f/total_seqs.to_f).to_s+' %</td>
			</tr>'
			stats_file.puts '				<tr>
				<td align="left">Putative New Genes</td>
				<td align="right">'+new_genes.to_s+'</td>
				<td align="right">'+'%.2f' % (100*new_genes.to_f/total_seqs.to_f).to_s+' %</td>
			</tr>'
			stats_file.puts '				<tr>
				<td align="left">ncRNAs</td>
				<td align="right">'+ncrna_total.to_s+'</td>
				<td align="right">'+'%.2f' % (100*ncrna_total.to_f/total_seqs.to_f).to_s+' %</td>
			</tr>'
			stats_file.puts '				<tr>
				<td align="left">Unknown</td>
				<td align="right">'+tcode_array[2][0].to_s+'</td>
				<td align="right">'+'%.2f' % (100*tcode_array[2][0].to_f/total_seqs.to_f).to_s+' %</td>
			</tr>'
			stats_file.puts '				<tr>
				<td align="left">Total</td>
				<td align="right">'+total_uni.to_s+'</td>
				<td align="right">'+'%.2f' % (100*total_uni.to_f/total_seqs.to_f).to_s+' %</td>
			</tr>
		</table>'

		# imprimimos la tabla Database Usage --------------------------------------------------------------------------------------------
		stats_file.puts html_db
		db_names=["UserDB", "SwissProt", "TrEMBL"]
		total_db = 0
		
		for i in 0..db_usage.length-1 do i
			total_db += db_usage[i]
			stats_file.puts '				<tr>
				<td align="left">'+db_names[i].to_s+'</td>
				<td align="right">'+db_usage[i].to_s+'</td>
				<td align="right">'+'%.2f' % (100*db_usage[i].to_f/total_seqs.to_f).to_s+' %</td>
			</tr>'
		end
		no_db = seqs_number2 + ncrna_total.to_i
			stats_file.puts '				<tr>
				<td align="left">None</td>
				<td align="right">'+no_db.to_s+'</td>
				<td align="right">'+'%.2f' % (100*no_db.to_f/total_seqs.to_f).to_s+' %</td>
			</tr>'
		total_db += no_db
			stats_file.puts '				<tr>
				<td align="left">Total</td>
				<td align="right">'+total_db.to_s+'</td>
				<td align="right">'+'%.2f' % (100*total_db.to_f/total_seqs.to_f).to_s+' %</td>
			</tr>
		</table>'

		# imprimimos la tabla Report guiding assembly quality -------------------------------------------------------------
		stats_file.puts html_as
			stats_file.puts '				<tr>
				<td align="left">Unigenes</td>
				<td align="right">'+total_seqs.to_s+'</td>
				<td align="right">'+'%.2f' % (100*total_seqs.to_f/total_seqs.to_f).to_s+' %</td>
			</tr>'
			stats_file.puts '				<tr>
				<td align="left">Unigenes >'+size_filter2.to_s+'pb</td>
				<td align="right">'+uni_500.to_s+'</td>
				<td align="right">'+'%.2f' % (100*uni_500.to_f/total_seqs.to_f).to_s+' %</td>
			</tr>'
			stats_file.puts '				<tr>
				<td align="left">Unigenes >'+size_filter1.to_s+'pb</td>
				<td align="right">'+uni_200.to_s+'</td>
				<td align="right">'+'%.2f' % (100*uni_200.to_f/total_seqs.to_f).to_s+' %</td>
			</tr>'
			stats_file.puts '				<tr>
				<td align="left">Longest unigene</td>
				<td align="right">'+longest_one.to_s+'</td>
				<td align="right">-</td>
			</tr>'
			stats_file.puts '				<tr>
				<td align="left">With orthologue <sup>1</sup></td>
				<td align="right">'+seqs_number1.to_s+'</td>
				<td align="right">'+'%.2f' % (100*seqs_number1.to_f/total_seqs.to_f).to_s+' %</td>
			</tr>'

		if (seqs_number1.to_i > 0)
			stats_file.puts '				<tr>
				<td align="left">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Different orthologue IDs</td>
				<td align="right">'+seq_uniq.to_s+'</td>
				<td align="right">'+'%.2f' % (100*seq_uniq.to_f/seqs_number1.to_f).to_s+' %</td>
			</tr>'
			stats_file.puts '				<tr>
				<td align="left">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Complete transcripts</td>
				<td align="right">'+status_array[0][0].to_s+'</td>
				<td align="right">'+'%.2f' % (100*status_array[0][0].to_f/seqs_number1.to_f).to_s+' %</td>
			</tr>'
			stats_file.puts '				<tr>
				<td align="left">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Different complete transcripts</td>
				<td align="right">'+complete_uniq.to_s+'</td>
				<td align="right">'+'%.2f' % (100*complete_uniq.to_f/seqs_number1.to_f).to_s+' %</td>
			</tr>'
			stats_file.puts '				<tr>
				<td align="left">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Misassembled</td>
				<td align="right">'+error_1_num.to_s+'</td>
				<td align="right">'+'%.2f' % (100*error_1_num.to_f/seqs_number1.to_f).to_s+' %</td>
			</tr>'
			stats_file.puts '				<tr>
				<td align="left">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Putative chimera</td>
				<td align="right">'+chimera_total.to_s+'</td>
				<td align="right">'+'%.2f' % (100*chimera_total.to_f/seqs_number1.to_f).to_s+' %</td>
			</tr>'
		end
			stats_file.puts '				<tr>
				<td align="left">Without orthologue <sup>1</sup></td>
				<td align="right">'+no_db.to_s+'</td>
				<td align="right">'+'%.2f' % (100*seqs_number2.to_f/total_seqs.to_f).to_s+' %</td>
			</tr>'

		if (no_db.to_i > 0) && (seqs_number2.to_i > 0)
			stats_file.puts '				<tr>
				<td align="left">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Coding (all)</td>
				<td align="right">'+tcode_array[0][0].to_s+'</td>
				<td align="right">'+'%.2f' % (100*tcode_array[0][0].to_f/no_db.to_f).to_s+' %</td>
			</tr>'
			stats_file.puts '				<tr>
				<td align="left">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Coding > '+size_filter1.to_s+'bp</td>
				<td align="right">'+tcode_array[0][2].to_s+'</td>
				<td align="right">'+'%.2f' % (100*tcode_array[0][2].to_f/no_db.to_f).to_s+' %</td>
			</tr>'
			stats_file.puts '				<tr>
				<td align="left">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Coding > '+size_filter2.to_s+'bp</td>
				<td align="right">'+tcode_array[0][3].to_s+'</td>
				<td align="right">'+'%.2f' % (100*tcode_array[0][3].to_f/no_db.to_f).to_s+' %</td>
			</tr>'
			stats_file.puts '				<tr>
				<td align="left">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Putative Coding (all)</td>
				<td align="right">'+tcode_array[1][0].to_s+'</td>
				<td align="right">'+'%.2f' % (100*tcode_array[1][0].to_f/no_db.to_f).to_s+' %</td>
			</tr>'
			stats_file.puts '				<tr>
				<td align="left">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Putative Coding > '+size_filter1.to_s+'bp</td>
				<td align="right">'+tcode_array[1][2].to_s+'</td>
				<td align="right">'+'%.2f' % (100*tcode_array[1][2].to_f/no_db.to_f).to_s+' %</td>
			</tr>'
			stats_file.puts '				<tr>
				<td align="left">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Putative Coding > '+size_filter2.to_s+'bp</td>
				<td align="right">'+tcode_array[1][3].to_s+'</td>
				<td align="right">'+'%.2f' % (100*tcode_array[1][3].to_f/no_db.to_f).to_s+' %</td>
			</tr>'
			stats_file.puts '				<tr>
				<td align="left">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Putative ncRNA</td>
				<td align="right">'+ncrna_total.to_s+'</td>
				<td align="right">'+'%.2f' % (100*ncrna_total.to_f/no_db.to_f).to_s+' %</td>
			</tr>'
			stats_file.puts '				<tr>
				<td align="left">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Unknown (all)</td>
				<td align="right">'+tcode_array[2][0].to_s+'</td>
				<td align="right">'+'%.2f' % (100*tcode_array[2][0].to_f/no_db.to_f).to_s+' %</td>
			</tr>'
			stats_file.puts '				<tr>
				<td align="left">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Unknown > '+size_filter1.to_s+'bp</td>
				<td align="right">'+tcode_array[2][2].to_s+'</td>
				<td align="right">'+'%.2f' % (100*tcode_array[2][2].to_f/no_db.to_f).to_s+' %</td>
			</tr>'
			stats_file.puts '				<tr>
				<td align="left">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Unknown > '+size_filter2.to_s+'bp</td>
				<td align="right">'+tcode_array[2][3].to_s+'</td>
				<td align="right">'+'%.2f' % (100*tcode_array[2][3].to_f/no_db.to_f).to_s+' %</td>
			</tr>'
		end
		stats_file.puts '			</table>
		<sup>1</sup> Percents for subclassifications of this category were calculated using this line as 100% reference.'
			
	end
	stats_file.puts html_end
	
	stats_file.close
end

#testcode_stats(size_filter1, size_filter2) ⇒ Object 



448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
 
# File 'lib/full_lengther_next/classes/fln_stats.rb', line 448

def testcode_stats(size_filter1,size_filter2)

	seqs_number = 0
	uni_500 = 0
	uni_200 = 0
	longest_one = 0

	# total, status
	coding_stats = [0,'Coding',0,0]
	p_coding_stats = [0,'Putative Coding',0,0]
	unknown_stats = [0,'Unknown',0,0]

	File.open('fln_results/new_coding.txt').each do |line|
		line.chomp!
		(name,fasta_length,acc,db_name,status) = line.split("\t")

		if (line !~ /^Query_id\t/) && (!line.empty?)
			seqs_number += 1

			if (fasta_length.to_i > longest_one)
				longest_one = fasta_length.to_i
			end

			# -------------------------------------------------------------------------
			if (fasta_length.to_i >= size_filter1)
				uni_200 += 1
			end
			if (fasta_length.to_i >= size_filter2)
				uni_500 += 1
			end
			# -------------------------------------------------------------------------

			if (fasta_length.to_i > size_filter1)
				if (status == 'coding')
					coding_stats[2] += 1
				elsif (status == 'putative_coding')
					p_coding_stats[2] += 1
				elsif (status == 'unknown')
					unknown_stats[2] += 1
				end
			end

			if (fasta_length.to_i > size_filter2)
				if (status == 'coding')
					coding_stats[3] += 1
				elsif (status == 'putative_coding')
					p_coding_stats[3] += 1
				elsif (status == 'unknown')
					unknown_stats[3] += 1
				end
			end

			if (status == 'coding')
				coding_stats[0] += 1
			elsif (status == 'putative_coding')
				p_coding_stats[0] += 1
			elsif (status == 'unknown')
				unknown_stats[0] += 1
			end

		end

	end

	status_array = [coding_stats, p_coding_stats, unknown_stats]

	return [status_array, seqs_number, uni_500, uni_200, longest_one]
end