File size: 11,612 Bytes
411342e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# -*- coding: utf-8 -*-
"""
Created on Mon Nov 21 16:21:25 2022

@author: luol2
"""

import streamlit as st
from src.nn_model import bioTag_CNN,bioTag_Bioformer
from src.dic_ner import dic_ont
from src.tagging_text import bioTag
import os
import json
from pandas import DataFrame
import nltk 
nltk.download('punkt')
nltk.download('averaged_perceptron_tagger')
nltk.download('wordnet')

st.set_page_config(
    page_title="Demo",
    page_icon="🎈",
    layout="wide",
    menu_items={
    }
)


# def _max_width_():
#     max_width_str = f"max-width: 2400px;"
#     st.markdown(
#         f"""
#     <style>
#     .reportview-container .main .block-container{{
#         {max_width_str}
#     }}
#     </style>    
#     """,
#         unsafe_allow_html=True,
#     )


# _max_width_()

# c30, c31, c32 = st.columns([2.5, 1, 3])

# with c30:
#     # st.image("logo.png", width=400)
st.title("Demo")

with st.expander("🎈 About this demo", expanded=True):

    st.write(
        """     
-   This demo is an extension work using [PhenoTagger](https://github.com/ncbi-nlp/PhenoTagger) library
-   Hackathon: Nonaworks - Gingko Problem 2
	    """
    )

    st.markdown("")

st.markdown("")
st.markdown("## βœ‚ Paste your text ")
with st.form(key="my_form"):


    ce, c1, ce, c2, c3 = st.columns([0.07, 1, 0.07, 4, 0.07])
    with c1:
        ModelType = st.radio(
            "Choose your model",
            ["Bioformer(Default)"],
            help="Bioformer is more precise, CNN is more efficient",
        )

        if ModelType == "Bioformer(Default)":
            # kw_model = KeyBERT(model=roberta)

            @st.cache(allow_output_mutation=True)
            def load_model(model='hpo'):
                if model =='1':
                    ontfiles = {'dic_file': './dict_new_fyeco/noabb_lemma.dic',
                                'word_hpo_file': './dict_new_fyeco/word_id_map.json',
                                'hpo_word_file': './dict_new_fyeco/id_word_map.json'}

                    vocabfiles = {'labelfile': './dict_new_fyeco/lable.vocab',
                                  'config_path': './vocab/bioformer-cased-v1.0/bert_config.json',
                                  'checkpoint_path': './vocab/bioformer-cased-v1.0/bioformer-cased-v1.0-model.ckpt-2000000',
                                  'vocab_path': './vocab/bioformer-cased-v1.0/vocab.txt'}

                    modelfile = './vocab/bioformer.h5'

                elif model == '2':
                    vocabfiles = {'labelfile': './dict_new_hpo/lable.vocab',
                                  'config_path': './vocab/bioformer-cased-v1.0/bert_config.json',
                                  'checkpoint_path': './vocab/bioformer-cased-v1.0/bioformer-cased-v1.0-model.ckpt-2000000',
                                  'vocab_path': './vocab/bioformer-cased-v1.0/vocab.txt'}

                    ontfiles = {'dic_file': './dict_new_hpo/noabb_lemma.dic',
                                'word_hpo_file': './dict_new_hpo/word_id_map.json',
                                'hpo_word_file': './dict_new_hpo/id_word_map.json'}

                    modelfile='./vocab/bioformer_p5n5_b64_1e-5_95_hponew3.h5'

                biotag_dic=dic_ont(ontfiles)    
    
                nn_model=bioTag_Bioformer(vocabfiles)
                nn_model.load_model(modelfile)
                return nn_model,biotag_dic

            nn_model1, biotag_dic1 = load_model(model='1')
            nn_model2, biotag_dic2 = load_model(model='2')

        else:
            @st.cache(allow_output_mutation=True)
            def load_model():
                ontfiles={'dic_file':'./dict_new/noabb_lemma.dic',
                  'word_hpo_file':'./dict_new/word_id_map.json',
                  'hpo_word_file':'./dict_new/id_word_map.json'}
        

                vocabfiles={'w2vfile':'./vocab/bio_embedding_intrinsic.d200',   
                            'charfile':'./vocab/char.vocab',
                            'labelfile':'./dict_new/lable.vocab',
                            'posfile':'./vocab/pos.vocab'}
                modelfile='./vocab/cnn_p5n5_b128_95_hponew1.h5'
        
                biotag_dic=dic_ont(ontfiles)    
            
                nn_model=bioTag_CNN(vocabfiles)
                nn_model.load_model(modelfile)
            
                return nn_model,biotag_dic

            nn_model,biotag_dic = load_model()
        
        para_overlap = st.checkbox(
            "Overlap concept",
            value=False,
            help="Tick this box to identify overlapping concepts",
        )
        para_abbr = st.checkbox(
            "Abbreviaitons",
            value=True,
            help="Tick this box to identify abbreviations",
        )        
        
        para_threshold = st.slider(
            "Threshold",
            min_value=0.5,
            max_value=1.0,
            value=0.95,
            step=0.05,
            help="Retrun the preditions which socre over the threshold.",
        )
      



    with c2:
        
            
        doc = st.text_area(
              "Paste your text below",
              value = 'The clinical features of Angelman syndrome (AS) comprise severe mental retardation, postnatal microcephaly, macrostomia and prognathia, absence of speech, ataxia, and a happy disposition. We report on seven patients who lack most of these features, but presented with obesity, muscular hypotonia and mild mental retardation. Based on the latter findings, the patients were initially suspected of having Prader-Willi syndrome. DNA methylation analysis of SNRPN and D15S63, however, revealed an AS pattern, ie the maternal band was faint or absent. Cytogenetic studies and microsatellite analysis demonstrated apparently normal chromosomes 15 of biparental inheritance. We conclude that these patients have an imprinting defect and a previously unrecognised form of AS. The mild phenotype may be explained by an incomplete imprinting defect or by cellular mosaicism.',
              height=400,
        )
        

        # MAX_WORDS = 500
        # import re
        # res = len(re.findall(r"\w+", doc))
        # if res > MAX_WORDS:
        #     st.warning(
        #         "⚠️ Your text contains "
        #         + str(res)
        #         + " words."
        #         + " Only the first 500 words will be reviewed. Stay tuned as increased allowance is coming! 😊"
        #     )

        #     doc = doc[:MAX_WORDS]

        submit_button = st.form_submit_button(label="πŸ–±οΈ Submit!")


if not submit_button:
    st.stop()

#st.write(para_overlap,para_abbr,para_threshold)
para_set={
          #model_type':para_model, # cnn or bioformer
          'onlyLongest': not para_overlap, # False: return overlap concepts, True only longgest
          'abbrRecog':para_abbr,# False: don't identify abbr, True: identify abbr
          'ML_Threshold':para_threshold,# the Threshold of deep learning model
          }
st.markdown("")
st.markdown("## ⏳ Tagging results:")
with st.spinner('Wait for tagging...'):

    tag_result1=bioTag(doc,biotag_dic1,nn_model1,onlyLongest=para_set['onlyLongest'], abbrRecog=para_set['abbrRecog'],Threshold=para_set['ML_Threshold'])
    tag_result2=bioTag(doc,biotag_dic2,nn_model2,onlyLongest=para_set['onlyLongest'], abbrRecog=para_set['abbrRecog'],Threshold=para_set['ML_Threshold'])


st.markdown('<font style="color: rgb(128, 128, 128);">Move the mouse over the entity to display the id.</font>', unsafe_allow_html=True)
# print('dic...........:',biotag_dic.keys())
# st.write('parameters:', para_overlap,para_abbr,para_threshold)

html_results=''
text_results=doc+'\n'
entity_end=0

# poid_counts = []

hpoid_count1={}
hpoid_count2 = {}

tag_display = {}

flag = False
if len(tag_result1)>=0:
    for ele in tag_result1:
        entity_start=int(ele[0])
        #html_results+=doc[entity_end:entity_start]
        entity_end=int(ele[1])
        entity_id=ele[2]
        entity_score=ele[3]
        tag_display[entity_start] = (entity_end, entity_id, "1")
        text_results+=ele[0]+'\t'+ele[1]+'\t'+doc[entity_start:entity_end]+'\t'+ele[2]+'\t'+format(float(ele[3]),'.2f')+'\n'

        if entity_id not in hpoid_count1.keys():
            hpoid_count1[entity_id]=1
        else:
            hpoid_count1[entity_id]+=1
        
        #html_results+='<font style="background-color: rgb(255, 204, 0)'+';" title="'+entity_id+'">'+doc[entity_start:entity_end]+'</font>'
    #html_results+=doc[entity_end:]

    flag = True

if len(tag_result2) >= 0:
    entity_end = 0
    for ele in tag_result2:
        entity_start = int(ele[0])
        #html_results += doc[entity_end:entity_start]
        entity_end = int(ele[1])
        entity_id = ele[2]
        entity_score = ele[3]
        tag_display[entity_start] = (entity_end, entity_id, "2")
        text_results += ele[0] + '\t' + ele[1] + '\t' + doc[entity_start:entity_end] + '\t' + ele[2] + '\t' + format(
            float(ele[3]), '.2f') + '\n'

        if entity_id not in hpoid_count2.keys():
            hpoid_count2[entity_id] = 1
        else:
            hpoid_count2[entity_id] += 1

       # html_results += '<font style="background-color: rgb(255, 0, 0)' + ';" title="' + entity_id + '">' + doc[entity_start:entity_end] + '</font>'
    #html_results += doc[entity_end:]

    flag = True

if not flag:
    html_results = doc
else:
    myKeys = list(tag_display.keys())
    myKeys.sort()
    sorted_tag_display = {i: tag_display[i] for i in myKeys}
    entity_end = 0

    for entity_start, value in sorted_tag_display.items():
        html_results += doc[entity_end:entity_start]
        entity_end = value[0]
        entity_id = value[1]
        type = value[2]
        if type == "1":
            html_results += '<font style="background-color: rgb(255, 204, 0)' + ';" title="' + entity_id + '">' + doc[entity_start:entity_end] + '</font>'
        elif type == "2":
            html_results += '<font style="background-color: rgb(255, 0, 0)' + ';" title="' + entity_id + '">' + doc[entity_start:entity_end] + '</font>'
    html_results += doc[entity_end:]
    
    st.markdown('<table border="1"><tr><td>'+html_results+'</td></tr></table>', unsafe_allow_html=True)


#table
data_entity=[]
for ele in hpoid_count1.keys():
    segs=ele.split(';')
    term_name=''
    for seg in segs:
        term_name+=biotag_dic1.hpo_word[seg][0]+';'
    temp=[ele,term_name,hpoid_count1[ele]] #hpoid, term name, count
    data_entity.append(temp)

for ele in hpoid_count2.keys():
    segs=ele.split(';')
    term_name=''
    for seg in segs:
        term_name+=biotag_dic2.hpo_word[seg][0]+';'
    temp=[ele,term_name,hpoid_count2[ele]] #hpoid, term name, count
    data_entity.append(temp)

st.markdown("")
st.markdown("")
# st.markdown("## Table output:")

# cs, c1, c2, c3, cLast = st.columns([2, 1.5, 1.5, 1.5, 2])

# with c1:
#     CSVButton2 = download_button(keywords, "Data.csv", "πŸ“₯ Download (.csv)")
# with c2:
#     CSVButton2 = download_button(keywords, "Data.txt", "πŸ“₯ Download (.txt)")
# with c3:
#     CSVButton2 = download_button(keywords, "Data.json", "πŸ“₯ Download (.json)")

# st.header("")

df = (
    DataFrame(data_entity, columns=["Phenotype ID", "Term Name","Frequency"])
    .sort_values(by="Frequency", ascending=False)
    .reset_index(drop=True)
)

df.index += 1

c1, c2, c3 = st.columns([1, 4, 1])

# format_dictionary = {
#     "Relevancy": "{:.1%}",
# }

# df = df.format(format_dictionary)

with c2:
    st.table(df)
    
c1, c2, c3 = st.columns([1, 1, 1])
with c2:
    st.download_button('Download annotations', text_results)