Upload 2 files

app.py

@@ -0,0 +1,271 @@
+# -*- coding: utf-8 -*-
+"""
+Created on May 15 16:21:25 2023
+
+@author: luol2
+"""
+
+import streamlit as st
+from src.nn_model import bioTag_CNN,bioTag_BERT
+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="PhenoTagger_CL",
+    page_icon="🎈",
+    layout="wide",
+    menu_items={
+        'Get Help': 'https://www.ncbi.nlm.nih.gov/research/bionlp/',
+        'About': "PhenoTagger-CL"
+    }
+)
+
+
+# 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("👨‍⚕️ PhenoTagger_CL Demo")
+
+with st.expander("ℹ️ - About this app", expanded=True):
+
+    st.write(
+        """     
+-   This app is an easy-to-use interface built in Streamlit for [PhenoTagger](https://github.com/ncbi-nlp/PhenoTagger) library!
+-   PhenoTagger is a hybrid method that combines dictionary and deep learning-based methods to recognize Human Phenotype Ontology (HPO) concepts in unstructured biomedical text. Please refer to [our paper](https://doi.org/10.1093/bioinformatics/btab019) for more details.
+-   Contact: [NLM/NCBI BioNLP Research Group](https://www.ncbi.nlm.nih.gov/research/bionlp/)
+	    """
+    )
+
+    st.markdown("")
+
+st.markdown("")
+st.markdown("## 📌 Paste document ")
+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 Ontology",
+            ['CL'], #["HPO(Default)", "UBERON"],
+            #help="Bioformer is more precise, CNN is more efficient",
+        )
+
+        if ModelType == "CL":
+            # kw_model = KeyBERT(model=roberta)
+
+            #@st.cache(allow_output_mutation=True)
+            def load_model():
+                ontfiles={'dic_file':'./dict_cl/noabb_lemma.dic',
+                          'word_id_file':'./dict_cl/word_id_map.json',
+                          'id_word_file':'./dict_cl/id_word_map.json'}
+        
+
+                vocabfiles={'labelfile':'./dict_cl/lable.vocab',
+                            'checkpoint_path':'./models/bioformer-cased-v1.0/',
+                            'lowercase':False}
+                modelfile='./models/bioformer-CL.h5'
+                   
+    
+                biotag_dic=dic_ont(ontfiles)    
+    
+                nn_model=bioTag_BERT(vocabfiles)
+                nn_model.load_model(modelfile)
+                return nn_model,biotag_dic
+
+            nn_model,biotag_dic = load_model()
+
+        else:
+            pass
+            '''
+            #@st.cache(allow_output_mutation=True)
+            def load_model():
+                ontfiles={'dic_file':'./dict_uberon/noabb_lemma.dic',
+                          'word_id_file':'./dict_uberon/word_id_map.json',
+                          'id_word_file':'./dict_uberon/id_word_map.json'}
+
+                vocabfiles={'labelfile':'./dict_uberon/lable.vocab',
+                            'checkpoint_path':'./models_v1.2/bioformer-cased-v1.0/',
+                            'lowercase':False}
+                
+                modelfile='./models_v1.2/bioformer-UBERON.h5'
+        
+                biotag_dic=dic_ont(ontfiles)    
+            
+                nn_model=bioTag_BERT(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="✨ 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_result=bioTag(doc,biotag_dic,nn_model,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 HPO 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
+hpoid_count={}
+if len(tag_result)>=0:
+    for ele in tag_result:
+        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]
+        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_count.keys():
+            hpoid_count[entity_id]=1
+        else:
+            hpoid_count[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:]
+                
+else:
+    html_results=doc
+    
+st.markdown('<table border="1"><tr><td>'+html_results+'</td></tr></table>', unsafe_allow_html=True)
+
+
+#table
+data_entity=[]
+for ele in hpoid_count.keys():
+    segs=ele.split(';')
+    term_name=''
+    for seg in segs:
+        term_name+=biotag_dic.id_word[seg][0]+';'
+    temp=[ele,term_name,hpoid_count[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", "📥 Download (.csv)")
+# with c2:
+#     CSVButton2 = download_button(keywords, "Data.txt", "📥 Download (.txt)")
+# with c3:
+#     CSVButton2 = download_button(keywords, "Data.json", "📥 Download (.json)")
+
+# st.header("")
+
+df = (
+    DataFrame(data_entity, columns=["Ontology_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) 
+    

requirements.txt

@@ -0,0 +1,8 @@
+TensorFlow==2.12.0
+nltk==3.8.1
+bioc==2.0.post5
+streamlit
+numpy==1.23.5
+torch==1.11.0
+transformers
+altair==4.0