automatic-extraction-ris-gcs.sh
26 KB
1
2
3
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
290
291
292
293
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
361
362
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
446
447
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
516
517
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
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
#!/bin/bash
# Main script for automatic extraction of regulatory interactions
#Parameters
#1: Path y nombre de archivo con las frases preprocesadas en formato de tokens (palabras)
#2: Path y nombre de archivo con las frases preprocesadas en formato trasformado (palabra|lemma|pos)
#3: Path y nombre de archivo para procesamiento con OpenIE
#4: Path de salida de archivos a1 y a2 con RIS y GCs
#5: Simplificar Y/N?
#6: Separar verbales y deverbales Y/N?
#7: Filtro de frases que contengan entidades. FILT1 = (GENE OR TU) AND TF
#8: Path con archivos a1 y a2 de referencia (RIs y GCs verdaderas)
#9: Archivo de referencia (RIs y GCs verdaderas)
#10: Path para guardar archivo de evaluación
#11: Archivo para guardar resultados de la evaluación contra referencia
#12: Archivo de sinónimos de TFs
# RUN EXTRACTION FOR L&C STM
# ./automatic-extraction-ris-gcs.sh
# /home/cmendezc/gitlab_repositories/lisen-curate-nlp-tasks/ris-extraction/features/6094508.tra.word.txt
# /home/cmendezc/gitlab_repositories/lisen-curate-nlp-tasks/ris-extraction/transformed/6094508.tra.txt
# /home/cmendezc/gitlab_repositories/lisen-curate-nlp-tasks/ris-extraction/bries-bacterial-regulatory-interaction-extraction-system/ri-openie-extraction/ris-STM.txt
# /home/cmendezc/gitlab_repositories/lisen-curate-nlp-tasks/ris-extraction/bries-bacterial-regulatory-interaction-extraction-system/predicted-ris-gcs
# Y Y FILT1
# /home/cmendezc/gitlab_repositories/lisen-curate-nlp-tasks/ris-extraction/bries-bacterial-regulatory-interaction-extraction-system/unused-reference
# unused.txt
# /home/cmendezc/gitlab_repositories/lisen-curate-nlp-tasks/ris-extraction/bries-bacterial-regulatory-interaction-extraction-system/evaluation-reports
# unused.txt
# diccionario-STM-LT2-v7.0.SYNONYMS.json
# 1>uno-STM-LC.txt
# 2>dos-STM-LC.txt
# ./automatic-extraction-ris-gcs.sh /home/cmendezc/gitlab_repositories/lisen-curate-nlp-tasks/ris-extraction/features/6094508.tra.word.txt /home/cmendezc/gitlab_repositories/lisen-curate-nlp-tasks/ris-extraction/transformed/6094508.tra.txt /home/cmendezc/gitlab_repositories/lisen-curate-nlp-tasks/ris-extraction/bries-bacterial-regulatory-interaction-extraction-system/ri-openie-extraction/ris-STM.txt /home/cmendezc/gitlab_repositories/lisen-curate-nlp-tasks/ris-extraction/bries-bacterial-regulatory-interaction-extraction-system/predicted-ris-gcs Y Y FILT1 /home/cmendezc/gitlab_repositories/lisen-curate-nlp-tasks/ris-extraction/bries-bacterial-regulatory-interaction-extraction-system/unused-reference unused.txt /home/cmendezc/gitlab_repositories/lisen-curate-nlp-tasks/ris-extraction/bries-bacterial-regulatory-interaction-extraction-system/evaluation-reports unused.txt diccionario-STM-LT2-v7.0.SYNONYMS.json 1>uno-STM-LC.txt 2>dos-STM-LC.txt
# Some help
# Filename without path: filename=$(basename "$fullfile")
# Filename extension: extension="${filename##*.}"
# Filename without extension: filename="${filename%.*}"
# Por error de muchos archivos: find . -print0 | xargs -0 grep AcrR
PATH_TO_CORENLP=/home/cmendezc/STANFORD_CORENLP/stanford-corenlp-full-2017-06-09
DICC_PATH=/home/cmendezc/terminologicalResources
ISIMP_PATH=/home/cmendezc/bitbucket_repositories/automatic-extraction-ris-gcs/rie-gce-system/automatic-extraction-ris-gcs/sentence-simplification/isimp_v2
SCRIPT_PATH=$(cd `dirname $0` && pwd)
INPUT_PATH=$1
INPUT_PATH_TRANS=$2
OUTPUT_FILE=$3
OUTPUT_PATH=$4
INPUT_NAME_EXT=$(basename "$INPUT_PATH")
INPUT_NAME="${INPUT_NAME_EXT%.*}"
# Simplify sentences?
SIMPLIFY=$5
# Separate sentences with deverbal effect?
DEVERBAL_SEPARATOR=$6
FILT=$7
TRUE_PATH=$8
TRUE_FILE=$9
PATH_EVAL=${10}
FILE_EVAL=${11}
DICC_SYNON=${12}
# CFMC 2022-03-09: tsv file with section, id sentence, sentence (Extracted from jsonpdf)
TSV_PATH=${13}
#Validate arguments
if [[ ! ("$#" == 13 ) ]]; then
echo 'Usage: ./automatic-extraction-ris-gcs.sh <inputPath_wordFile>
<inputPath_taggedFile> <outputPath_file> <simplify?> <deverbal_detector?>
<filter> <true_path> <true_file> <path_evaluation_report> <file_evaluation_report>
<dictionary_TFs_synonyms> <path_tsv_file>'
exit 1
fi
echo "********** SELECTED PARAMETERS **********"
echo "INPUT PATH: $INPUT_PATH"
echo "INPUT PATH TRANSFORMED FILE $INPUT_PATH_TRANS"
echo "OUTPUT FILE: $OUTPUT_FILE"
echo "OUTPUT PATH: $OUTPUT_PATH"
echo "SIMPLIFY SENTENCES? $SIMPLIFY"
echo "SEPARATE DEVERBAL SENTENCES? $DEVERBAL_SEPARATOR"
echo "FILTER SENTENCES WITH ENTITIES? $FILT"
echo "REFERENCE (TRUE) PATH: $TRUE_PATH"
echo "REFERENCE (TRUE) FILE: $TRUE_FILE"
echo "PATH EVALUATION REPORT: $PATH_EVAL"
echo "FILE EVALUATION REPORT: $FILE_EVAL"
echo "DICTIONARY OF SYNONYMS OF TFS: $DICC_SYNON"
echo "********** SELECTED PROCESSES **********"
CLEAN_OUTPUT=FALSE
echo " Clean output paths: $CLEAN_OUTPUT"
FILTER=TRUE
echo " Filter sentences: $FILTER"
CLEAN=TRUE
echo " Clean sentences for iSimp: $CLEAN"
SEPARATE=TRUE
echo " Separate sentences to iSimp: $SEPARATE"
SIMPLI=TRUE
echo " Simplify sentences: $SIMPLI"
DEVERBAL=TRUE
echo " Separate deverbal and verbal sentences: $DEVERBAL"
DEVTAG=TRUE # Needs DEVERBAL=TRUE
echo " Tag sentences to separate deverbal and verbal sentences: $DEVTAG"
DEVSEPAR=TRUE # Needs DEVERBAL=TRUE
echo " Do separate deverbal and verbal sentences: $DEVSEPAR"
EXTDEVERBAL=TRUE
echo " Extract RI deverbal: $EXTDEVERBAL"
OPENIE=TRUE
echo " OpenIE triplet extraction: $OPENIE"
EXTOPENIE=TRUE
echo " Extract RI verbal: $EXTOPENIE"
EXTATTRIB=TRUE
echo " Extract RI attributive: $EXTATTRIB"
EXTAUTOREG=TRUE
echo " Extract RI autoregulation: $EXTAUTOREG"
EXTGC=FALSE
echo " Extract growth conditions: $EXTGC"
EVAL=FALSE
echo " Evaluate extraction: $EVAL"
EVALGC=FALSE
echo " Evaluate growth condition extraction: $EVALGC"
#########################
# Cleaning output paths #
#########################
if [ "$CLEAN_OUTPUT" = "TRUE" ]; then
if [ -z "$(ls -A $OUTPUT_PATH/complete-ris/)" ]; then :
else
#echo "Not Empty"
# Original: rm $OUTPUT_PATH/complete-ris/*
find $OUTPUT_PATH/complete-ris -maxdepth 1 -name '*.*' -delete
fi
if [ -z "$(ls -A $OUTPUT_PATH/incomplete-ris/)" ]; then :
else
#echo "Not Empty"
# Original: rm $OUTPUT_PATH/incomplete-ris/*
find $OUTPUT_PATH/incomplete-ris -maxdepth 1 -name '*.*' -delete
fi
fi # if [ "$CLEAN_OUTPUT" = "TRUE" ]; then
################
# preliminares #
################
#Clone and update simplification pipeline
#if [ ! -d "./sentence-simplification" ]
# then
# echo Downloading sentence simplificator...
# git clone https://github.com/ezojg/sentence-simplification
# else
# cd ./sentence-simplification
# git pull origin master
# cd ..
#fi
#Check for iSimp
#if [ ! -d "./sentence-simplification/isimp_v2" ]
# then
# echo ERROR: ./sentence-simplification/isimp_v2 not found. Please manually copy iSimp to said path.
# exit 1
#fi
if [ "$FILTER" = "TRUE" ]; then
echo "********** FILTER SENTENCES **********"
###################################################
# filter sentences with entities of interest #
# and collect attributive examples ArgP-regulated #
###################################################
# INPUT:
# 1) --inputFileWord $INPUT_PATH input file transformed
# 2) --inputFileTrans $INPUT_PATH_TRANS input file of feature 'word'
# 3) --outputPath $SCRIPT_PATH/filtered-sentences
# 4) --outputFile filtered-sentences.txt output File
# 5) --filter filter $FILT
# FILT1: (GENE OR TU) AND TF
# FILT2: (GENE OR TU) AND EFFECT AND TF
# 6) --attrPath $SCRIPT_PATH/attributive-sentences Path for attributive cases: ArgP-regulated genes
# 7) --attrFile attributive-sentences.txt File for attributive cases: ArgP-regulated genes
# $DICC_PATH/normalized_Effects.json
cd $SCRIPT_PATH
if [ -z "$(ls -A ./filtered-sentences/)" ]; then :
else
#echo "Not Empty"
rm ./filtered-sentences/*
fi
if [ -z "$(ls -A ./attributive-sentences/)" ]; then :
else
#echo "Not Empty"
rm ./attributive-sentences/*
fi
if [ -z "$(ls -A ./autoregulation-sentences/)" ]; then :
else
#echo "Not Empty"
rm ./autoregulation-sentences/*
fi
# CFMC 2022-03-09: To update tsv file with filtered sentences
# python3.4 $SCRIPT_PATH/sentence-filter.py --inputFileWord $INPUT_PATH --inputFileTrans $INPUT_PATH_TRANS --outputPath $SCRIPT_PATH/filtered-sentences --outputFile filtered-sentences.txt --filter $FILT --attrPath $SCRIPT_PATH/attributive-sentences --autoPath $SCRIPT_PATH/autoregulation-sentences --dicPath $DICC_PATH --dicFile normalized_Effects.json
python3.4 $SCRIPT_PATH/sentence-filter_v02.py --tsvPath $TSV_PATH --inputFileWord $INPUT_PATH --inputFileTrans $INPUT_PATH_TRANS --outputPath $SCRIPT_PATH/filtered-sentences --outputFile filtered-sentences.txt --filter $FILT --attrPath $SCRIPT_PATH/attributive-sentences --autoPath $SCRIPT_PATH/autoregulation-sentences --dicPath $DICC_PATH --dicFile normalized_Effects.json
fi # if [ "$PRE" = "TRUE" ]; then
if [ "$CLEAN" = "TRUE" ]; then
echo "********** CLEAN SENTENCES **********"
#################################
# Clean sentences for iSimpm #
#################################
# INPUT - PREVIOUS OUTPUT: filtered sentences $SCRIPT_PATH/filtered-sentences/filtered-sentences.txt
# output path and file $SCRIPT_PATH/format/sanitized_sentences/$INPUT_NAME_EXT
if [ -z "$(ls -A ./format/sanitized_sentences/)" ]; then :
else
#echo "Not Empty"
rm ./format/sanitized_sentences/*
fi
#Original Daniel: python2 $SCRIPT_PATH/format/regex-before.py $INPUT_PATH $SCRIPT_PATH/format/sanitized_sentences/$INPUT_NAME_EXT
python2 $SCRIPT_PATH/format/regex.py $SCRIPT_PATH/filtered-sentences/filtered-sentences.txt $SCRIPT_PATH/format/sanitized_sentences/$INPUT_NAME_EXT
fi # if [ "$CLEAN" = "TRUE" ]; then
if [ "$SEPARATE" = "TRUE" ]; then
echo "********** SEPARATE SENTENCES **********"
################################
# Separate sentences for iSimp #
################################
# INPUT - PREVIOUS OUTPUT: $SCRIPT_PATH/format/sanitized_sentences/$l
# output path and file $SCRIPT_PATH/format/split_sentences/$BARE_NAME
cd $SCRIPT_PATH
if [ -z "$(ls -A ./format/split_sentences/)" ]; then :
else
rm ./format/split_sentences/*
fi
cd ./format/sanitized_sentences
for l in $(\ls $INPUT_NAME*)
do
# echo $l
BARE_NAME=$(echo $l | cut -f 1 -d '.')
BARE_NAME+="_"
LENGTH="$(wc -l < $l)"
LENGTH="$(echo "${#LENGTH}")"
split -a $LENGTH -d -l 1 --additional-suffix=.spt $SCRIPT_PATH/format/sanitized_sentences/$l $SCRIPT_PATH/format/split_sentences/$BARE_NAME
done
fi # if [ "$SEPARATE" = "TRUE" ]; then
if [ "$SIMPLI" = "TRUE" ]; then
echo "********** SIMPLIFY SENTENCES **********"
######################
# Simplify sentences #
######################
# INPUT - PREVIOUS OUTPUT: $SCRIPT_PATH/format/split_sentences
# output file $OUTPUT_FILE
# path to iSimp $ISIMP_PATH
# CALL: ./sentence-simplification/sentence-simplification-main.sh
# CALL: $ISIMP_PATH/simplify.sh $j $SCRIPT_PATH/iSimp_sentences/$(basename $j)
# CALL: $SCRIPT_PATH/simplifier.py $k $SCRIPT_PATH/algorithm_sentences/$(basename $k) $OUTPUT_INDEX_FILE_PATH
# $OUTPUT_INDEX_FILE_PATH = $OUTPUT_FILE
# OUTPUT: simplified sentences in path ./algorithm_sentences
# while true; do
# read -p "Do you wish to simplificate sentences? [Y/N]: " yn
# case $yn in
# [Yy]* ) SIMP=1; break;;
# [Nn]* ) SIMP=0; break;;
# * ) echo "Please answer yes [Y] or no [N].";;
# esac
# done
case $SIMPLIFY in
[Yy]* )
SIMP=1
;;
[Nn]* )
SIMP=0
;;
* )
SIMP=1
;;
esac
cd $SCRIPT_PATH
if [ $SIMP == 1 ]
then #USING SIMPLIFICATION
echo "********** YES SIMPLIFY SENTENCES **********"
#Copy file to sentence-simplification
#FILE_NAME=$(basename "$INPUT_PATH")
#Call simplification pipeline AND create a file with the paths for the simplificated sentences
./sentence-simplification/sentence-simplification-main.sh $SCRIPT_PATH/format/split_sentences $OUTPUT_FILE $ISIMP_PATH
#echo "entrada: $SCRIPT_PATH/format/split_sentences --salida: $OUTPUT_FILE"
#echo "Sentences simplificated. Paths to simplificated sentences saved in $OUTPUT_FILE"
else #WITHOUT SIMPLIFICACION
echo "********** NO SIMPLIFY SENTENCES **********"
if [ -z "$(ls -A ./sentence-simplification/algorithm_sentences/)" ]; then :
else
#echo "Not Empty"
rm ./sentence-simplification/algorithm_sentences/*
fi
ls $SCRIPT_PATH/format/split_sentences/* > $OUTPUT_FILE
cp $SCRIPT_PATH/format/split_sentences/* $SCRIPT_PATH/sentence-simplification/algorithm_sentences
#echo "Sentences split. Paths to split sentences saved in $OUTPUT_FILE"
fi
fi # if [ "$SIMPLI" = "TRUE" ]; then
if [ "$DEVERBAL" = "TRUE" ]; then
echo "********** SEPARATE VERBAL AND DEVERBAL SENTENCES **********"
######################
# Deverbal separator #
######################
# $PATH_TO_CORENLP
# INPUT - PREVIOUS OUTPUT: $SCRIPT_PATH/sentence-simplification/algorithm_sentences
# output path $SCRIPT_PATH/deverbal-separator/separated_sentences
# $DICC_PATH
# $DEVTAG POS taggging sentences
# $DEVSEPAR Do separate sentences
# CALL: java -cp "$PATH_TO_CORENLP/*"
# $SCRIPT_PATH/filter.py
# OUTPUT: sentences separated in two paths according to verbal/deverbal effect
case $DEVERBAL_SEPARATOR in
[Yy]* )
DEVSEP=1
;;
[Nn]* )
DEVSEP=0
;;
* )
DEVSEP=1
;;
esac
if [ $DEVSEP == 1 ]
then #USING DEVERBAL SEPARATOR
#if [ -z "$(ls -A $SCRIPT_PATH/deverbal-separator/separated_sentences/vrb/)" ]; then :
#else
#echo "Not Empty"
# Error: /bin/rm: Argument list too long: rm $SCRIPT_PATH/deverbal-separator/separated_sentences/vrb/*
# find $SCRIPT_PATH/deverbal-separator/separated_sentences/vrb -maxdepth 1 -name '*.vrb' -delete
#fi
#if [ -z "$(ls -A $SCRIPT_PATH/deverbal-separator/separated_sentences/dev/)" ]; then :
#else
#echo "Not Empty"
# Error: /bin/rm: Argument list too long: rm $SCRIPT_PATH/deverbal-separator/separated_sentences/dev/*
# find $SCRIPT_PATH/deverbal-separator/separated_sentences/dev -maxdepth 1 -name '*.dev' -delete
#fi
echo "********** YES SEPARATE VERBAL AND DEVERBAL SENTENCES **********"
# Original Daniel 2018-12-06: ./deverbal-separator/separator.sh $PATH_TO_CORENLP $SCRIPT_PATH/sentence-simplification/algorithm_sentences $SCRIPT_PATH/deverbal-separator/separated_sentences $DICC_PATH $DEVTAG $DEVSEPAR
./deverbal-separator/separator-v02.sh $PATH_TO_CORENLP $SCRIPT_PATH/sentence-simplification/algorithm_sentences $SCRIPT_PATH/deverbal-separator/separated_sentences $DICC_PATH $DEVTAG $DEVSEPAR
else #WITHOUT DEVERBAL SEPARATOR
echo "********** NO SEPARATE VERBAL AND DEVERBAL SENTENCES **********"
ls $SCRIPT_PATH/sentence-simplification/algorithm_sentences/* > $OUTPUT_FILE
#echo "Sentences split. Paths to split sentences saved in $OUTPUT_FILE"
fi # [ $DEVSEP == 1 ]
fi # if [ "$DEVERBAL" = "TRUE" ]; then
if [ "$EXTDEVERBAL" = "TRUE" ]; then
echo "********** EXTRACT RI DEVERBAL **********"
#######################
# Extract RI deverbal #
#######################
# INPUT: deverbal files $(dirname ${file}) $(basename ${file})
# output path $OUTPUT_PATH $(basename ${file%.*})
# $DICC_PATH/names_EFFECT_ONTOGENE.txt $
# DICC_PATH/names_GENE.txt
# $DICC_PATH/names_GENE_ONTOGENE.txt
# $DICC_PATH/names_GENE_SYN.txt
# $DICC_PATH/names_TU.txt
# $DICC_PATH/names_TU_ONTOGENE.txt
# $DICC_PATH/names_TF_1grams.txt
# $DICC_PATH/names_TF_2grams.txt
# $DICC_PATH/names_TF_3grams.txt
# $DICC_PATH/names_TF_4grams.txt
# $DICC_PATH/names_TF_5Moregrams.txt
# $DICC_PATH/names_TF_ONTOGENE.txt
# $DICC_PATH/normalized_Effects.json
# OUTPUT: standoff files with RIs
# PATH ALREADY TAGGED ENTITIES: $SCRIPT_PATH/filtered-sentences
# FILE ALREADY TAGGED ENTITIES: filtered-sentences.ents.json
for file in $SCRIPT_PATH/deverbal-separator/separated_sentences/dev/*.*
do
#python3 $SCRIPT_PATH/extract-ris-deverbal/EFF_DVB-regex-OriginalDaniel.py $file $OUTPUT_PATH/$(basename ${file%.*}) $DICC_PATH/names_EFFECT_ONTOGENE.txt $DICC_PATH/names_GENE.txt $DICC_PATH/names_GENE_ONTOGENE.txt $DICC_PATH/names_GENE_SYN.txt $DICC_PATH/names_TU.txt $DICC_PATH/names_TU_ONTOGENE.txt $DICC_PATH/names_TF_1grams.txt $DICC_PATH/names_TF_2grams.txt $DICC_PATH/names_TF_3grams.txt $DICC_PATH/names_TF_4grams.txt $DICC_PATH/names_TF_5Moregrams.txt $DICC_PATH/names_TF_ONTOGENE.txt
#echo "Dir file: $(dirname ${file})"
#echo "File $(basename ${file})"
#echo "OUTOUT_PATH $OUTPUT_PATH"
#echo "File $(basename ${file%.*})"
echo "Dir and files: $(dirname ${file}) $(basename ${file}) $OUTPUT_PATH $(basename ${file%.*})"
#python3 $SCRIPT_PATH/extract-ris-deverbal/EFF_DVB-regex-v02.py $(dirname ${file}) $(basename ${file}) $OUTPUT_PATH $(basename ${file%.*}) $DICC_PATH/normalized_Effects.json $SCRIPT_PATH/filtered-sentences filtered-sentences.ents.json
python3 $SCRIPT_PATH/extract-ris-deverbal/EFF_DVB-regex-v03.py $(dirname ${file}) $(basename ${file}) $OUTPUT_PATH $(basename ${file%.*}) $DICC_PATH/normalized_Effects.json $SCRIPT_PATH/filtered-sentences filtered-sentences.ents.json
done
fi # if [ "$EXTDEVERBAL" = "TRUE" ]; then
if [ "$OPENIE" = "TRUE" ]; then
echo "********** OPENIE TRIPLET EXTRACTION **********"
#########################
# OpenIE RI extraction #
#########################
# Juntamos frases verbales en archivo para OpenIE extraction
# Error: /bin/ls: Argument list too long: ls $SCRIPT_PATH/deverbal-separator/separated_sentences/vrb/* > $OUTPUT_FILE
echo " Join verbal sentences into file for OpenIE extraction"
find $SCRIPT_PATH/deverbal-separator/separated_sentences/vrb -type f -name '*' > $OUTPUT_FILE
#echo "Deberval sentences separated. Paths to verbal sentences saved in $OUTPUT_FILE"
echo " CoreNLP OpenIE..."
java -Xms2g -cp "$PATH_TO_CORENLP/*" edu.stanford.nlp.naturalli.OpenIE -filelist $OUTPUT_FILE -triple.strict false -triple.all_nominals true -format reverb > $OUTPUT_FILE.reverb
fi # if [ "$OPENIE" = "TRUE" ]; then
if [ "$EXTOPENIE" = "TRUE" ]; then
echo "********** OPENIE RI EXTRACTION **********"
#########################
# OpenIE RI extraction #
#########################
# Sustituyo oie_compress de Nacho por un programa hecho por CMC para analizar las tripletas
# y obtener aquellas que sugieran a los participantes y el efecto
#Paste input and output for fancy printing
# Original Nacho: echo " Fancy printing..."
# Original Nacho: > $OUTPUT_FILE.fuzzy
# Original Nacho: python3 oie_compress.py --oies $OUTPUT_FILE.reverb --op fuzzy --ris $DICC_PATH/normalized_Effects.json --out $OUTPUT_FILE.fuzzy
#
# --inputFile $OUTPUT_FILE.reverb file obtained with CoreNLPL
# --outputPath $OUTPUT_PATH
# --diccPath $SCRIPT_PATH/filtered-sentences Before: $DICC_PATH
# --diccFile Before: termFilesTag_RIE_GCE_SYSTEM_ECCO.json
# --diccEffect normalized_Effects.json
# --format standoff
# --diccEPAth $DICC_PATH
# OUTPUT: standoff files with RIs
# python3.4 $SCRIPT_PATH/ri-openie-extraction.py --inputFile $OUTPUT_FILE.reverb --outputPath $OUTPUT_PATH --diccPath $DICC_PATH --diccFile termFilesTag_RIE_GCE_SYSTEM_ECCO.json --diccEffect normalized_Effects.json --format standoff
python3.4 $SCRIPT_PATH/ri-openie-extraction-v02.py --inputFile $OUTPUT_FILE.reverb --outputPath $OUTPUT_PATH --diccPath $SCRIPT_PATH/filtered-sentences --diccFile filtered-sentences.ents.json --diccEffect normalized_Effects.json --diccEPAth $DICC_PATH --format standoff
#Join into single file
#Sort fuzzy
# Original Nacho: echo " Sort fuzzy..."
# Obtiene tipo de efecto
# Original Nacho: sort $OUTPUT_FILE.fuzzy -o $OUTPUT_FILE.fuzzy
#Concatenate
# CMC eliminated following lines because simplification was
#discriminated before
#if [ $SIMP == 1 ]
#then #USING SIMPLIFICATION
#ls -l $SCRIPT_PATH/sentence-simplification/algorithm_sentences/* | awk -F '/' '{print $NF}' > $OUTPUT_FILE.ils
#awk '{print $0":"}' $OUTPUT_FILE.ils > $OUTPUT_FILE.fls
#cat $SCRIPT_PATH/sentence-simplification/algorithm_sentences/* > $OUTPUT_FILE.als
#paste $OUTPUT_FILE.fls $OUTPUT_FILE.als > $OUTPUT_FILE.merger
#else #WITHOUT SIMPLIFICACION
#ls -l $SCRIPT_PATH/format/split_sentences/* | awk -F '/' '{print $NF}' > $OUTPUT_FILE.ils
#awk '{print $0":"}' $OUTPUT_FILE.ils > $OUTPUT_FILE.fls
#cat $SCRIPT_PATH/format/split_sentences/* > $OUTPUT_FILE.als
#paste $OUTPUT_FILE.fls $OUTPUT_FILE.als > $OUTPUT_FILE.merger
#fi
# Original Nacho: ls -l $SCRIPT_PATH/sentence-simplification/algorithm_sentences/* | awk -F '/' '{print $NF}' > $OUTPUT_FILE.ils
# Original Nacho: awk '{print $0":"}' $OUTPUT_FILE.ils > $OUTPUT_FILE.fls
# Original Nacho: cat $SCRIPT_PATH/sentence-simplification/algorithm_sentences/* > $OUTPUT_FILE.als
# Original Nacho: echo " Creating ils, fls and als files..."
# Original Nacho: if [ $DEVSEP == 1 ]
# Original Nacho: then #USING DEVERBAL SEPARATOR
# Original Nacho: ls -l $SCRIPT_PATH/deverbal-separator/separated_sentences/vrb/* | awk -F '/' '{print $NF}' > $OUTPUT_FILE.ils
# Original Nacho: awk '{print $0":"}' $OUTPUT_FILE.ils > $OUTPUT_FILE.fls
# Original Nacho: cat $SCRIPT_PATH/deverbal-separator/separated_sentences/vrb/* > $OUTPUT_FILE.als
# Original Nacho: else #WITHOUT DEVERBAL SEPARATOR
# Original Nacho: ls -l $SCRIPT_PATH/sentence-simplification/algorithm_sentences/* | awk -F '/' '{print $NF}' > $OUTPUT_FILE.ils
# Original Nacho: awk '{print $0":"}' $OUTPUT_FILE.ils > $OUTPUT_FILE.fls
# Original Nacho: cat $SCRIPT_PATH/sentence-simplification/algorithm_sentences/* > $OUTPUT_FILE.als
# Original Nacho: fi
# Original Nacho: echo " Paste merger..."
# Original Nacho: paste $OUTPUT_FILE.fls $OUTPUT_FILE.als > $OUTPUT_FILE.merger
# Original Nacho: echo " Create dsp file..."
# Original Nacho: awk -F "\t" 'NR==FNR{a[$1]=$0} NR>FNR && a[$1]>0{print a[$1],"\t",$2}' $OUTPUT_FILE.fuzzy $OUTPUT_FILE.merger > $OUTPUT_FILE.dsp
# Original Nacho: awk -F "\t" 'NR==FNR{a[$1]=$0} NR>FNR && a[$1]>0{print a[$1],"\t",$2}' $OUTPUT_FILE.fuzzy $OUTPUT_FILE.merger > $OUTPUT_FILE.dsp
# rm $(dirname "$OUTPUT_FILE")/*.fls
# rm $(dirname "$OUTPUT_FILE")/*.ils
# rm $(dirname "$OUTPUT_FILE")/*.als
#rm $SCRIPT_PATH/*.merger
#rm $SCRIPT_PATH/*.reverb
#rm $SCRIPT_PATH/*.fuzzy
fi # if [ "$EXTOPENIE" = "TRUE" ]; then
if [ "$EXTATTRIB" = "TRUE" ]; then
echo "********** ATTRIBUTIVE RI EXTRACTION **********"
#########################
# Attributive RI extraction #
#########################
# Attributive RI extraction, such as AraP-regulated genes aragP, aragT
#
# --inputPath $SCRIPT_PATH/attributive-sentences
# --outputPath $OUTPUT_PATH
# --diccPath $SCRIPT_PATH/filtered-sentences Before: $DICC_PATH
# --diccEffect normalized_Effects.json
# OUTPUT: standoff files with RIs
for file in $SCRIPT_PATH/attributive-sentences/*.*
do
echo "Dir file: $(dirname ${file})"
echo "File: $(basename ${file})"
# echo "OUTOUT_PATH $OUTPUT_PATH"
# echo "File $(basename ${file%.*})"
# echo "All $(dirname ${file}) $(basename ${file}) $OUTPUT_PATH $(basename ${file%.*})"
if [ "$(basename ${file})" = "*.*" ]; then
echo "None attributive sentence found"
else
python3 $SCRIPT_PATH/ri-attributive-extraction-v02.py --inputPath $(dirname ${file}) --inputFile $(basename ${file}) --outputPath $OUTPUT_PATH --diccPath $DICC_PATH --diccEffect normalized_Effects.json
fi
done
fi # if [ "$EXTATTRIB" = "TRUE" ]; then
if [ "$EXTAUTOREG" = "TRUE" ]; then
echo "********** AUTOREGULATION RI EXTRACTION **********"
#########################
# Autoregulation RI extraction #
#########################
# Autoregulation RI extraction, such as ArgP protein represses its own synthesis
#
# --inputPath $SCRIPT_PATH/autoregulation-sentences
# --outputPath $OUTPUT_PATH
# --diccPath $DICC_PATH
# --diccEffect normalized_Effects.json
# OUTPUT: standoff files with RIs
for file in $SCRIPT_PATH/autoregulation-sentences/*.*
do
echo "Dir file: $(dirname ${file})"
echo "File: $(basename ${file})"
# echo "OUTOUT_PATH $OUTPUT_PATH"
# echo "File $(basename ${file%.*})"
# echo "All $(dirname ${file}) $(basename ${file}) $OUTPUT_PATH $(basename ${file%.*})"
if [ "$(basename ${file})" = "*.*" ]; then
echo "None autoregulation sentence found"
else
python3 $SCRIPT_PATH/ri-autoregulation-extraction-v01.py --inputPath $(dirname ${file}) --inputFile $(basename ${file}) --outputPath $OUTPUT_PATH --diccPath $DICC_PATH --diccEffect normalized_Effects.json
fi
done
fi # if [ "$EXTAUTOREG" = "TRUE" ]; then
if [ "$EXTGC" = "TRUE" ]; then
echo "********** EXTRACT GROWTH CONDITIONS **********"
#############################
# Extract growth conditions #
#############################
python3.4 $SCRIPT_PATH/extract-gcs/extract-gcs-regex.py --inputPath $OUTPUT_PATH/complete-ris --outputPath $OUTPUT_PATH/complete-ris --termPath /home/cmendezc/terminologicalResources
#python3 ./GCs-regex-before.py ./ejemplo_11.spt
#/home/elwe/Documents/prueba3/RIE_reordenado/RI-searcher/GC/ejemplo_11.spt ./ejemplo_11.a2
#./names_GC_ECCO_1grams.txt ./names_GC_ECCO_2grams.txt ./names_GC_ECCO_3grams.txt
#./names_GC_ECCO_4grams.txt ./names_GC_ECCO_5Moregrams.txt
fi # if [ "$EXTGC" = "TRUE" ]; then
if [ "$EVAL" = "TRUE" ]; then
echo "********** EVALUATE EXTRACTION **********"
if [ "$EVALGC" = "TRUE" ]; then
echo "********** EVALUATE GROWTH CONDITION EXTRACTION **********"
python3.4 $SCRIPT_PATH/evaluate-ris-gcs-standoff-v04.py --truePath $TRUE_PATH --trueFile $TRUE_FILE --predictedPath $OUTPUT_PATH/complete-ris --outputPath $PATH_EVAL --outputFile $FILE_EVAL --diccPath $DICC_PATH --diccSynon $DICC_SYNON --evaluateGCs
else
echo "********** EVALUATE WITHOUT GROWTH CONDITION EXTRACTION **********"
python3.4 $SCRIPT_PATH/evaluate-ris-gcs-standoff-v04.py --truePath $TRUE_PATH --trueFile $TRUE_FILE --predictedPath $OUTPUT_PATH/complete-ris --outputPath $PATH_EVAL --outputFile $FILE_EVAL --diccPath $DICC_PATH --diccSynon $DICC_SYNON
fi # if [ "$EVALGC" = "TRUE" ]; then
fi # if [ "$EVAL" = "TRUE" ]; then