Upload app.py

app.py

@@ -0,0 +1,883 @@
+#from turtle import shape
+import streamlit as st
+#from st_keyup import st_keyup
+import pandas as pd
+import numpy as np
+from st_aggrid import AgGrid, GridOptionsBuilder,GridUpdateMode,DataReturnMode
+
+import os
+
+st.set_page_config(layout="wide") 
+st.markdown(
+    """
+<style>
+.streamlit-expanderHeader {
+    font-size: x-large;
+}
+</style>
+""",
+    unsafe_allow_html=True,
+)
+caution = '<p style="font-family:sans-serif; color:Red; font-size: 18px;">Please note that Only one Guide (from pair) is found. Please see guides not found section for other guide</p>'
+caution1 = '<p style="font-family:sans-serif; color:Red; font-size: 18px;">Please note that Each mutated guide is reported as a sepearte line. sgID_1/2, sgRNA_1/2, chr_sgRNA_1/2 and position_sgRNA_1/2 represent values for reference/mutated guide</p>'
+caution2 = '<p style="font-family:sans-serif; color:Red; font-size: 18px;">Please Select a single/multiple guides and then select Check Box A, B or C Otherwise code will through error</p>'
+table_edit = '<p style="font-family:sans-serif; color:Green; font-size: 16px;">About Table: Please note that table can be <b>sorted by clicking on any column</b> and <b>Multiple rows can be selected</b> (by clicking check box in first column) to save only those rows.</p>'
+
+def transform(df,str):
+    # Select columns
+    #cols = st.multiselect('Please select columns to save current Table as csv file', 
+    cols = st.multiselect(str, 
+    df.columns.tolist(),
+    df.columns.tolist()
+    )
+    df = df[cols]
+    return df
+
+def convert_df(df):
+    return df.to_csv().encode('utf-8')
+def convert_df1(df):
+    return df.to_csv(index=False).encode('utf-8')
+
+
+# CSS to inject contained in a string
+hide_table_row_index = """
+            <style>
+            thead tr th:first-child {display:none}
+            tbody th {display:none}
+            </style>
+            """
+
+# Inject CSS with Markdown
+st.markdown(hide_table_row_index, unsafe_allow_html=True)
+
+
+#########TABLE DISPLAY
+def tbl_disp(dat,var,ref,flg=1):
+    dat.reset_index(drop=True, inplace=True)
+    #df = transform(dft,'Please Select columns to save whole table')
+    #fname = st.text_input('Please input file name to save Table', 'temp')
+    #fname = st_keyup("Please input file name to save Table", value='temp')
+    csv = convert_df(dat)
+    if flg==1:
+        st.download_button(
+            label="Download Full Table as CSV file",
+            data=csv,
+            file_name=var+'_'+ref+'.csv',#fname+'.csv',
+            mime='text/csv',
+        )
+    #st.table(dft)
+    #st.markdown(table_edit,unsafe_allow_html=True)
+    gb = GridOptionsBuilder.from_dataframe(dat)
+    gb.configure_pagination(enabled=False)#,paginationAutoPageSize=False)#True) #Add pagination
+    gb.configure_default_column(enablePivot=True, enableValue=True, enableRowGroup=True)
+    gb.configure_selection(selection_mode="multiple", use_checkbox=True)
+
+    gb.configure_side_bar()
+    gridOptions = gb.build()    
+
+    grid_response = AgGrid(
+            dat,
+            height=200,
+            gridOptions=gridOptions,
+            enable_enterprise_modules=True,
+            update_mode=GridUpdateMode.MODEL_CHANGED,
+            data_return_mode=DataReturnMode.FILTERED_AND_SORTED,
+            fit_columns_on_grid_load=False,
+            header_checkbox_selection_filtered_only=True,
+            use_checkbox=True,
+            width='100%'
+    )
+
+    selected = grid_response['selected_rows']   
+    if selected:
+        st.write('Selected rows')
+        
+        dfs = pd.DataFrame(selected)
+        st.dataframe(dfs[dfs.columns[1:dfs.shape[1]]])
+
+        #dfs1 = transform(dfs[dfs.columns[1:dfs.shape[1]]],'Please select columns to save selected Table')
+        csv = convert_df1(dfs[dfs.columns[1:dfs.shape[1]]])
+        #csv = convert_df1(dfs1)
+        
+
+        st.download_button(
+            label="Download data as CSV",
+            data=csv,
+            file_name=var+'_'+ref+'.csv',
+            mime='text/csv',
+        )
+        return dfs
+
+ 
+
+def assemble_tbl(t):
+    dft = pd.DataFrame(columns=['sgID_1','sgRNA_1','chr_sgRNA_1','position_sgRNA_1','sgID_2','sgRNA_2','chr_sgRNA_2','position_sgRNA_2', 'sgID_1_2'])
+    for i in range(0,t.shape[0],2):
+        l1=t.iloc[[i]]
+        l1.columns=['sgID_1','sgRNA_1','chr_sgRNA_1','position_sgRNA_1','mutated_guide',	'strand',	'num_mismatch']
+
+        l2=t.iloc[[i+1]]
+        l2.columns=['sgID_2','sgRNA_2','chr_sgRNA_2','position_sgRNA_2','mutated_guide2',	'strand2',	'num_mismatch2']
+        listA_concatenated_match_LR1=pd.concat([l1.reset_index(drop=True),l2.reset_index(drop=True)],axis=1)
+        listA_concatenated_match_LR1=listA_concatenated_match_LR1[['sgID_1','sgRNA_1','chr_sgRNA_1','position_sgRNA_1','sgID_2','sgRNA_2','chr_sgRNA_2','position_sgRNA_2']]
+        listA_concatenated_match_LR1['sgRNA_1']=listA_concatenated_match_LR1['sgRNA_1'].str.slice(0, 20)
+        listA_concatenated_match_LR1['sgRNA_2']=listA_concatenated_match_LR1['sgRNA_2'].str.slice(0, 20)
+        listA_concatenated_match_LR1['sgID_1_2']=listA_concatenated_match_LR1['sgID_1']+"|"+listA_concatenated_match_LR1['sgID_1']
+        dft=dft.append(listA_concatenated_match_LR1)
+        
+    return dft
+    
+def get_lists(ref_list,list_found_ref,list_notfound_ref):
+    a_ref=[]  
+    for i in range(len(ref_list)):
+        a_ref.append(ref_list.gene.values[i].split('|')[0])
+        a_ref.append(ref_list.gene.values[i].split('|')[1])
+    #check GRCh38
+    #st.table(a_ref)
+    set_found0_ref=[]
+    for i in range(len(a_ref)):
+        set_found0_ref.append(list_found_ref[list_found_ref['gene']==a_ref[i]])
+    list_concatenated_found_ref = pd.concat(set_found0_ref)
+    
+
+
+    #split in found and not found
+    
+    list_concatenated_match_ref = list_concatenated_found_ref[list_concatenated_found_ref.num_mismatch == 0]
+    #list_concatenated_match_ref=list_concatenated_match_ref.sort_values('position')
+    
+    #Also remove Alternate loci's data
+    list_concatenated_match_ref = list_concatenated_match_ref[list_concatenated_match_ref['chr'].str.contains('chr')]
+    
+    #also create new list with both sgRNAs in one row
+    dft=pd.DataFrame(columns=['gene','ref_guide',	'chr',	'position',	'mutated_guide',	'strand',	'num_mismatch'])
+    if list_concatenated_match_ref.shape[0]>0:
+        t=list_concatenated_match_ref.reset_index(drop=True)
+        #st.table(t)
+        
+        ##########
+        #check even/odd entries
+        if t.shape[0]==1:
+            t1=t.loc[t.index.repeat(2)].reset_index(drop=True)
+            #st.write(t1)
+            dft=assemble_tbl(t1)
+            
+        elif t.shape[0]%2==0: #even
+            dft=assemble_tbl(t)
+
+        else: #odd
+            t1 = pd.DataFrame(columns=['gene','ref_guide',	'chr',	'position',	'mutated_guide',	'strand',	'num_mismatch'])
+            i=0
+            while i <t.shape[0]:
+            #for i in range(t.shape[0]):
+                #if t.iloc[i,['gene']] == t.iloc[i+1,['gene']]:
+                #st.table(t)
+                #st.write(i)
+                if i<t.shape[0]-1:
+                    if t.iloc[i]['gene'] == t.iloc[i+1]['gene'] and t.iloc[i]['chr'] == t.iloc[i+1]['chr'] and t.iloc[i]['position'] == t.iloc[i+1]['position']:
+                        t1=t1.append(t.iloc[[i]], ignore_index = True)
+                        t1=t1.append(t.iloc[[i+1]], ignore_index = True)
+                        i=i+2
+                    else: #repeat entries
+                        t1=t1.append(t.iloc[[i]], ignore_index = True)
+                        t1=t1.append(t.iloc[[i]], ignore_index = True)
+                        #st.table(t1)
+                        i=i+1
+                else:
+                    t1=t1.append(t.iloc[[i]], ignore_index = True)
+                    t1=t1.append(t.iloc[[i]], ignore_index = True)
+                    i=i+1
+                    #st.table(t1)
+                    
+                    
+            dft=assemble_tbl(t1)
+    list_concatenated_mutated_ref = list_concatenated_found_ref[list_concatenated_found_ref.num_mismatch > 0]
+    list_concatenated_mutated_ref=list_concatenated_mutated_ref.sort_values('position')
+    
+    #Also remove Alternate loci's data
+    
+    list_concatenated_mutated_ref = list_concatenated_mutated_ref[list_concatenated_mutated_ref['chr'].str.contains('chr')]
+    dft_mut = pd.DataFrame(columns=['sgID_1','sgRNA_1','chr_sgRNA_1','position_sgRNA_1','sgID_2','sgRNA_2','chr_sgRNA_2','position_sgRNA_2', 'sgID_1_2'])
+    if list_concatenated_mutated_ref.shape[0]>0:        
+        dft_mut = get_mutated_res(list_concatenated_mutated_ref)
+    #check not found        
+    seta_notfound0_ref=list_notfound_ref[list_notfound_ref['gene']==a_ref[0]]
+    seta_notfound1_ref=list_notfound_ref[list_notfound_ref['gene']==a_ref[1]]
+    list_concatenated_notfound_ref = pd.concat([seta_notfound0_ref,seta_notfound1_ref])
+    return dft, dft_mut,list_concatenated_notfound_ref,list_concatenated_match_ref,list_concatenated_mutated_ref
+    ###########
+ 
+def get_mutated_res(list_concatenated_mutated_ref):
+    ######### 
+    #if list_concatenated_mutated_ref.shape[0]>0:
+    t=list_concatenated_mutated_ref.reset_index(drop=True)
+    #st.table(t)
+    dft_mut = pd.DataFrame(columns=['sgID_1','sgRNA_1','chr_sgRNA_1','position_sgRNA_1','sgID_2','sgRNA_2','chr_sgRNA_2','position_sgRNA_2', 'sgID_1_2'])
+    c1=['sgID_1','sgRNA_1','chr_sgRNA_1','position_sgRNA_1']
+    c2=['sgID_2','sgRNA_2','chr_sgRNA_2','position_sgRNA_2']#, 'sgID_1_2']
+    #st.table(listA_concatenated_match_ref)
+    #st.write(t.shape[0])
+    tf=0
+    #for i in range(0,t.shape[0],2):
+    for i in range(t.shape[0]):
+        l1=t.iloc[[i]]
+        l1.columns=['sgID_1','sgRNA_1','chr_sgRNA_1','position_sgRNA_1','mutated_guide',	'strand',	'num_mismatch']
+        l2=l1.copy()
+        l2.columns=['sgID_2','sgRNA_2','chr_sgRNA_2','position_sgRNA_2','mutated_guide2',	'strand2',	'num_mismatch2']
+        list_concatenated_mutated_ref1=[]
+        #listA_concatenated_mutated_ref1=pd.concat([l1.reset_index(drop=True),l2.reset_index(drop=True)],axis=1)
+        list_concatenated_mutated_ref1=pd.concat([l1.reset_index(drop=True),l2.reset_index(drop=True)],axis=1)
+        #st.table(listA_concatenated_mutated_ref1)
+        list_concatenated_mutated_ref1=list_concatenated_mutated_ref1[['sgID_1','sgRNA_1','chr_sgRNA_1','position_sgRNA_1','sgID_2','mutated_guide2','chr_sgRNA_2','position_sgRNA_2']]
+        #also change if not leading G
+        list_concatenated_mutated_ref1['sgRNA_1']='G'+list_concatenated_mutated_ref1['sgRNA_1'].str.slice(1, 20)
+        #also change name of mutated_guide2 column
+        list_concatenated_mutated_ref1.columns=['sgID_1','sgRNA_1','chr_sgRNA_1','position_sgRNA_1','sgID_2','sgRNA_2','chr_sgRNA_2','position_sgRNA_2']
+        
+        list_concatenated_mutated_ref1['sgRNA_2']='G'+list_concatenated_mutated_ref1['sgRNA_2'].str.slice(1, 20)
+        list_concatenated_mutated_ref1['sgID_1_2']=list_concatenated_mutated_ref1['sgID_1']+"|"+list_concatenated_mutated_ref1['sgID_1']
+        dft_mut=dft_mut.append(list_concatenated_mutated_ref1)
+    return dft_mut
+        
+    #########
+
+#def get_notfound():
+    
+       
+cwd=os.getcwd()+'/'+'data/'
+
+#get genes list
+#listA = pd.read_csv(cwd+"20200513_library_1_2_unbalanced_dJR051.csv",index_col=False)
+#listA = pd.read_csv(cwd+"newa1.csv",index_col=False)
+#listB = pd.read_csv(cwd+"newb1.csv",index_col=False)
+#listC = pd.read_csv(cwd+"newc1.csv",index_col=False)
+
+listA = pd.read_csv(cwd+"guides_a_new.csv",index_col=False)
+
+listB = pd.read_csv(cwd+"guides_b_new.csv",index_col=False)
+listC = pd.read_csv(cwd+"guides_c_new.csv",index_col=False)
+variantsa1=listA['gene'].unique()
+variantsb1=listB['gene'].unique()
+variantsc1=listC['gene'].unique()
+
+con = np.concatenate((variantsa1, variantsb1,variantsc1))
+
+
+#st.write(type(variantsc1))
+variants_s=sorted(np.unique(con))
+#st.write(len(variants_s))
+#also get names for non-targetting guides
+
+
+#Also read GRCh38 and LR guides for stea
+listA_found_ref = pd.read_csv(cwd+"seta_found_ref1.csv",index_col=False)
+#remove # from chr# #
+listA_found_ref['chr'] = [x.split(' ')[-0] for x in listA_found_ref['chr']]
+listA_found_ref.rename(columns = {'strnad':'strand'}, inplace = True)
+listA_notfound_ref = pd.read_csv(cwd+"seta_notfound_ref1.csv",index_col=False)
+
+listA_found_lr = pd.read_csv(cwd+"seta_found_LR1.csv",index_col=False)
+listA_found_lr.rename(columns = {'strnad':'strand'}, inplace = True)
+listA_notfound_lr = pd.read_csv(cwd+"seta_notfound_LR1.csv",index_col=False)
+
+#Also read GRCh38 and LR guides for set b
+listB_found_ref = pd.read_csv(cwd+"setb_found_ref1.csv",index_col=False)
+#remove # from chr# #
+listB_found_ref['chr'] = [x.split(' ')[-0] for x in listB_found_ref['chr']]
+listB_found_ref.rename(columns = {'strnad':'strand'}, inplace = True)
+listB_notfound_ref = pd.read_csv(cwd+"setb_notfound_ref1.csv",index_col=False)
+
+listB_found_lr = pd.read_csv(cwd+"setb_found_LR1.csv",index_col=False)
+listB_found_lr.rename(columns = {'strnad':'strand'}, inplace = True)
+listB_notfound_lr = pd.read_csv(cwd+"setb_notfound_LR1.csv",index_col=False)
+
+#Also read GRCh38 and LR guides for set c
+listC_found_ref = pd.read_csv(cwd+"setc_found_ref1.csv",index_col=False)
+#remove # from chr# #
+listC_found_ref['chr'] = [x.split(' ')[-0] for x in listC_found_ref['chr']]
+listC_found_ref.rename(columns = {'strnad':'strand'}, inplace = True)
+listC_notfound_ref = pd.read_csv(cwd+"setc_notfound_ref1.csv",index_col=False)
+
+listC_found_lr = pd.read_csv(cwd+"setc_found_LR1.csv",index_col=False)
+listC_found_lr.rename(columns = {'strnad':'strand'}, inplace = True)
+listC_notfound_lr = pd.read_csv(cwd+"setc_notfound_LR1.csv",index_col=False)
+
+
+
+st.title('Long Read Guides Search')
+#st.markdown('**Please select an option from the sidebar**')
+
+#st.write(variants)
+
+
+Calc = st.sidebar.radio(
+    "",
+    ('ReadME', 'Single Gene','Multiple Genes'))
+
+
+if Calc == 'ReadME':
+    expander = st.expander("How to use this app")   
+    #st.header('How to use this app')
+    expander.markdown('Please select **Single Gene** OR **Multiple Genes** Menue checkbox from the sidebar')
+    expander.markdown('Select a Gene (from genes dropdown list) OR Multiple genes (from table)')
+    expander.markdown('A table showing all reference gudies from three LISTS will appear in the main panel. **Please not some of the genes (for example A1BG and GJB7) have multiple guide pairs and all of these are selected.**')
+    expander.markdown('To see results for each of the selected reference guide from ListA, ListB and ListC, Please select respective checkbox')
+    expander.markdown('Results are shown as two tables, **Matched** and **Mutated** guides tables and **NOT FOUND** table if guides are not found in GRCh38 and LR reference fasta files')
+    expander.markdown('**Mutated** guides table shows the genomic postion in GRCh38 and LR Fasta file along other fields. **If a guide is found in GRCh38 but not in LR fasta, then corresponding columns will be NA**')
+    expander.markdown('**Mutated** guides table shows the genomic postion in GRCh38 and LR Fasta file along other fields. **If a guide is found in GRCh38 but not in LR fasta, then corresponding columns will be NA**')
+    
+    expander1 = st.expander('Introduction')
+    
+    expander1.markdown(
+        """ This app helps navigate all probable genomic **miss-matched/Mutations (upto 2 bp)** for a given sgRNA (from 3 lists of CRISPRi dual sgRNA libraries) in GRCh38 reference fasta and a Reference fasta generated from BAM generated against KOLF2.1J longread data.
+            """
+            )
+    expander1.markdown('Merged bam file was converted to fasta file using following steps:')
+    expander1.markdown('- samtools mpileup to generate bcf file')
+    expander1.markdown('- bcftools to generate vcf file')
+    expander1.markdown('- bcftools consensus to generate fasta file')
+    expander1.markdown('A GPU based [Cas-OFFinder](http://www.rgenome.net/cas-offinder/) tool was used to find off-target sequences (upto 2 miss-matched) for each geiven reference guide against GRCh38 and LR fasta references.')
+     
+elif Calc=='Single Gene':
+#if Calc == 'Selection Menu':
+    #ReadMe = st.sidebar.checkbox('ReadME',value=False)
+    select_variant = st.sidebar.selectbox(
+        "Please select Gene",
+        variants_s
+    )
+    #ref_sgrna=listA[listA['sgID_A']==select_variant][['protospacer_A','protospacer_B']]
+    #get all references
+    
+    ref_listA=listA[listA['gene']==select_variant][['guide_type','protospacer_A','protospacer_B','sgID_AB']]
+    ref_listA = ref_listA[['sgID_AB','guide_type','protospacer_A','protospacer_B']]
+    ref_listA.columns=['gene','guide_type','protospacer_A','protospacer_B']
+        
+    ref_listB=listB[listB['gene']==select_variant][['guide_type','protospacer_A','protospacer_B','sgID_AB']]
+    ref_listB = ref_listB[['sgID_AB','guide_type','protospacer_A','protospacer_B']]
+    ref_listB.columns=['gene','guide_type','protospacer_A','protospacer_B']
+    
+    ref_listC=listC[listC['gene']==select_variant][['guide_type','protospacer_A','protospacer_B','sgID_AB']]
+    ref_listC = ref_listC[['sgID_AB','guide_type','protospacer_A','protospacer_B']]
+    ref_listC.columns=['gene','guide_type','protospacer_A','protospacer_B']
+    listA_concatenated_orig = pd.concat([ref_listA,ref_listB,ref_listC])
+
+    st.write('**Input** Guides (all 6 from 3 sets)')
+    st.markdown(table_edit,unsafe_allow_html=True)
+    tbl_disp(listA_concatenated_orig,select_variant,'ref_guides',0)
+    #st.table(listA_concatenated_orig)
+    
+    #now search from results for list a
+    #st.write(ref_listA)
+    ListARes = st.checkbox('Results For SetA',key=1)
+    if ListARes:
+        if len(ref_listA)>0:  
+            #st.table(ref_listA)
+            
+##########
+            res,res_mut,res_notfound,list_match,list_mutated=get_lists(ref_listA,listA_found_ref,listA_notfound_ref)
+            st.write('Selected Reference Guides for **Set A**')
+            st.table(ref_listA)
+            #tbl_disp(ref_listA,select_variant,'ReferenceGuides',0)
+            if res.shape[0]>0:
+                st.write('Matched to **GRCh38** Reference Guides for **Set A**')
+                tbl_disp(res,select_variant,'SetA_GRCh38')
+            elif res_mut.shape[0]>0:
+                st.write('Mutated to **GRCh38** Reference Guides for **Set A**')
+                st.markdown(caution1,unsafe_allow_html=True)
+                tbl_disp(res_mut,select_variant,'SetA_Mutated_GRCh38')
+            if res_notfound.shape[0]>0:
+                st.write('**SetA Guides Not Found in GRCh38**')
+                #tbl_disp(dft_notfound,'select_genes','SetA_Notfound_GRCh38')
+                st.table(res_notfound)            
+##########            
+            
+            
+        #For LR
+##########
+            res_lr,res_mut_lr,res_notfound_lr,list_match_lr,list_mutated_lr=get_lists(ref_listA,listA_found_lr,listA_notfound_lr)
+            #st.write('Selected Reference Guides for **Set A**')
+            #tbl_disp(ref_listA,select_variant,'ReferenceGuides',0)
+            if res_lr.shape[0]>0:
+                st.write('Matched to **CHM13** Reference Guides for **Set A**')
+                tbl_disp(res_lr,select_variant,'SetA_CHM13')
+            elif res_mut_lr.shape[0]>0:
+                st.write('Mutated to **CHM13** Reference Guides for **Set A**')
+                st.markdown(caution1,unsafe_allow_html=True)
+                tbl_disp(res_mut_lr,select_variant,'SetA_Mutated_CHM13')
+            if res_notfound_lr.shape[0]>0:
+                st.write('**SetA Guides Not Found in CHM13**')
+                #tbl_disp(dft_notfound,'select_genes','SetA_Notfound_GRCh38')
+                st.table(res_notfound_lr)            
+##########            
+        
+        
+#######
+            #NOW MERGE FROM GRCh38 and LR
+            merged_mutated_set=pd.merge(list_mutated,list_mutated_lr, how="outer",on=["gene","ref_guide","chr"],suffixes=["_GRCh38",'_LR'])
+            merged_mutated_set = merged_mutated_set[['gene','ref_guide','chr','position_GRCh38','position_LR','strand_GRCh38','strand_LR','mutated_guide_GRCh38','mutated_guide_LR','num_mismatch_GRCh38','num_mismatch_LR']]
+            merged_match_set=pd.merge(list_match,list_match_lr, how="outer",on=["gene","ref_guide","chr"],suffixes=["_GRCh38",'_LR'])
+            merged_match_set = merged_match_set[['gene','ref_guide','chr','position_GRCh38','position_LR','strand_GRCh38','strand_LR','mutated_guide_GRCh38','mutated_guide_LR','num_mismatch_GRCh38','num_mismatch_LR']]
+            if merged_match_set.shape[0]>0:        
+                #st.write('**Matched** Guides for **Set C** (*Each guide sequence has a trailing NGG*)')
+                st.write('**Matched** Guides for **Set A** to both **GRCh38 and CHM13 references** (*Each guide sequence has a trailing NGG* and **leading G even if it is a missmatch**)')
+                tbl_disp(merged_match_set,select_variant,'SetA_Matched_GRCh38_CHM13',0)
+                
+                #st.table(merged_match_seta)
+            elif merged_mutated_set.shape[0]>0:
+                #st.write('**Missmatched** Guides **Set C** (*Each guide sequence has a trailing NGG*)')
+                st.write('**Mutated** Guides for **Set A** to both **GRCh38 and CHM13 references** (*Each guide sequence has a trailing NGG* and **leading G even if it is a missmatch**)')
+                
+                tbl_disp(merged_mutated_set,select_variant,'SetA_Mutated_GRCh38_CHM13',0)
+
+########        
+
+        else:
+            st.write('**Gene: **'+select_variant+' Not found in listA')
+
+    
+    #list B
+    ListBRes = st.checkbox('Results For SetB',key=2)  
+    if ListBRes:  
+        if len(ref_listB)>0:
+##########
+            res,res_mut,res_notfound,list_match,list_mutated=get_lists(ref_listB,listB_found_ref,listB_notfound_ref)
+            st.write('Selected Reference Guides for **Set B**')
+            st.table(ref_listB)
+            #tbl_disp(ref_listB,select_variant,'ReferenceGuides',0)
+            if res.shape[0]>0:
+                st.write('Matched to **GRCh38** Reference Guides for **Set B**')
+                tbl_disp(res,select_variant,'SetB_GRCh38')
+            elif res_mut.shape[0]>0:
+                st.write('Mutated to **GRCh38** Reference Guides for **Set B**')
+                st.markdown(caution1,unsafe_allow_html=True)
+                tbl_disp(res_mut,select_variant,'SetA_Mutated_GRCh38')
+            if res_notfound.shape[0]>0:
+                st.write('**SetB Guides Not Found in GRCh38**')
+                #tbl_disp(dft_notfound,'select_genes','SetA_Notfound_GRCh38')
+                st.table(res_notfound)            
+##########            
+            
+            
+        #For LR
+##########
+            res_lr,res_mut_lr,res_notfound_lr,list_match_lr,list_mutated_lr=get_lists(ref_listB,listB_found_lr,listB_notfound_lr)
+            #st.write('Selected Reference Guides for **Set A**')
+            #tbl_disp(ref_listA,select_variant,'ReferenceGuides',0)
+            if res_lr.shape[0]>0:
+                st.write('Matched to **CHM13** Reference Guides for **Set B**')
+                tbl_disp(res_lr,select_variant,'SetB_CHM13')
+            elif res_mut_lr.shape[0]>0:
+                st.write('Mutated to **CHM13** Reference Guides for **Set B**')
+                st.markdown(caution1,unsafe_allow_html=True)
+                tbl_disp(res_mut_lr,select_variant,'SetB_Mutated_CHM13')
+            if res_notfound_lr.shape[0]>0:
+                st.write('**SetB Guides Not Found in CHM13**')
+                #tbl_disp(dft_notfound,'select_genes','SetA_Notfound_GRCh38')
+                st.table(res_notfound_lr)            
+##########            
+        
+        
+#######
+            #NOW MERGE FROM GRCh38 and LR
+            merged_mutated_set=pd.merge(list_mutated,list_mutated_lr, how="outer",on=["gene","ref_guide","chr"],suffixes=["_GRCh38",'_LR'])
+            merged_mutated_set = merged_mutated_set[['gene','ref_guide','chr','position_GRCh38','position_LR','strand_GRCh38','strand_LR','mutated_guide_GRCh38','mutated_guide_LR','num_mismatch_GRCh38','num_mismatch_LR']]
+            merged_match_set=pd.merge(list_match,list_match_lr, how="outer",on=["gene","ref_guide","chr"],suffixes=["_GRCh38",'_LR'])
+            merged_match_set = merged_match_set[['gene','ref_guide','chr','position_GRCh38','position_LR','strand_GRCh38','strand_LR','mutated_guide_GRCh38','mutated_guide_LR','num_mismatch_GRCh38','num_mismatch_LR']]
+            if merged_match_set.shape[0]>0:        
+                #st.write('**Matched** Guides for **Set C** (*Each guide sequence has a trailing NGG*)')
+                st.write('**Matched** Guides for **Set B** to both **GRCh38 and CHM13 references** (*Each guide sequence has a trailing NGG* and **leading G even if it is a missmatch**)')
+                tbl_disp(merged_match_set,select_variant,'SetB_Matched_GRCh38_CHM13',0)
+                
+                #st.table(merged_match_seta)
+            elif merged_mutated_set.shape[0]>0:
+                #st.write('**Missmatched** Guides **Set C** (*Each guide sequence has a trailing NGG*)')
+                st.write('**Mutated** Guides for **Set B** to both **GRCh38 and CHM13 references** (*Each guide sequence has a trailing NGG* and **leading G even if it is a missmatch**)')
+                
+                tbl_disp(merged_mutated_set,select_variant,'SetB_Mutated_GRCh38_CHM13',0)
+
+########        
+
+        else:
+            st.write('**Gene: **'+select_variant+' Not found in listB')
+            
+    ### list B   
+    
+    #list C
+    ListCRes = st.checkbox('Results For SetC',key=3)  
+    if ListCRes:
+        if len(ref_listC)>0:
+##########
+            res,res_mut,res_notfound,list_match,list_mutated=get_lists(ref_listC,listC_found_ref,listC_notfound_ref)
+            st.write('Selected Reference Guides for **Set C**')
+            st.table(ref_listC)
+            #tbl_disp(ref_listC,select_variant,'ReferenceGuides',0)
+            if res.shape[0]>0:
+                st.write('Matched to **GRCh38** Reference Guides for **Set C**')
+                tbl_disp(res,select_variant,'SetC_GRCh38')
+            elif res_mut.shape[0]>0:
+                st.write('Mutated to **GRCh38** Reference Guides for **Set C**')
+                st.markdown(caution1,unsafe_allow_html=True)
+                tbl_disp(res_mut,select_variant,'SetC_Mutated_GRCh38')
+            if res_notfound.shape[0]>0:
+                st.write('**SetC Guides Not Found in GRCh38**')
+                #tbl_disp(dft_notfound,'select_genes','SetA_Notfound_GRCh38')
+                st.table(res_notfound)            
+##########            
+            
+            
+        #For LR
+##########
+            res_lr,res_mut_lr,res_notfound_lr,list_match_lr,list_mutated_lr=get_lists(ref_listC,listC_found_lr,listC_notfound_lr)
+            #st.write('Selected Reference Guides for **Set A**')
+            #tbl_disp(ref_listA,select_variant,'ReferenceGuides',0)
+            if res_lr.shape[0]>0:
+                st.write('Matched to **CHM13** Reference Guides for **Set C**')
+                tbl_disp(res_lr,select_variant,'SetC_CHM13')
+            elif res_mut_lr.shape[0]>0:
+                st.write('Mutated to **CHM13** Reference Guides for **Set C**')
+                st.markdown(caution1,unsafe_allow_html=True)
+                tbl_disp(res_mut_lr,select_variant,'SetC_Mutated_CHM13')
+            if res_notfound_lr.shape[0]>0:
+                st.write('**SetC Guides Not Found in CHM13**')
+                #tbl_disp(dft_notfound,'select_genes','SetA_Notfound_GRCh38')
+                st.table(res_notfound_lr)            
+##########            
+        
+        
+#######
+            #NOW MERGE FROM GRCh38 and LR
+            merged_mutated_set=pd.merge(list_mutated,list_mutated_lr, how="outer",on=["gene","ref_guide","chr"],suffixes=["_GRCh38",'_LR'])
+            merged_mutated_set = merged_mutated_set[['gene','ref_guide','chr','position_GRCh38','position_LR','strand_GRCh38','strand_LR','mutated_guide_GRCh38','mutated_guide_LR','num_mismatch_GRCh38','num_mismatch_LR']]
+            merged_match_set=pd.merge(list_match,list_match_lr, how="outer",on=["gene","ref_guide","chr"],suffixes=["_GRCh38",'_LR'])
+            merged_match_set = merged_match_set[['gene','ref_guide','chr','position_GRCh38','position_LR','strand_GRCh38','strand_LR','mutated_guide_GRCh38','mutated_guide_LR','num_mismatch_GRCh38','num_mismatch_LR']]
+            if merged_match_set.shape[0]>0:        
+                #st.write('**Matched** Guides for **Set C** (*Each guide sequence has a trailing NGG*)')
+                st.write('**Matched** Guides for **Set C** to both **GRCh38 and CHM13 references** (*Each guide sequence has a trailing NGG* and **leading G even if it is a missmatch**)')
+                tbl_disp(merged_match_set,select_variant,'SetC_Matched_GRCh38_CHM13',0)
+                
+                #st.table(merged_match_seta)
+            elif merged_mutated_set.shape[0]>0:
+                #st.write('**Missmatched** Guides **Set C** (*Each guide sequence has a trailing NGG*)')
+                st.write('**Mutated** Guides for **Set C** to both **GRCh38 and CHM13 references** (*Each guide sequence has a trailing NGG* and **leading G even if it is a missmatch**)')
+                
+                tbl_disp(merged_mutated_set,select_variant,'SetC_Mutated_GRCh38_CHM13',0)
+
+########        
+
+        else:
+            st.write('**Gene: **'+select_variant+' Not found in listC')
+            
+        
+    ### list C   
+else:
+    select_mode = st.radio(
+    "Please select an option",
+    ('Select Single/Multiple Genes', 'Select All'))
+    #st.write('Please Select A **Single/Multiple/SelectAll** Reference Guides')
+    #get_table = pd.DataFrame(columns=['gene','sgID_A','protospacer_A','sgID_B','protospacer_B','sgID_AB'])
+    if select_mode=='Select Single/Multiple Genes':
+        st.markdown(table_edit,unsafe_allow_html=True)
+        get_table=tbl_disp(listA[['gene','sgID_A','protospacer_A','sgID_B','protospacer_B','sgID_AB']],'SetA','ReferenceGuides',0)  
+    
+        st.markdown(caution2,unsafe_allow_html=True)  
+    else:
+        st.markdown(table_edit,unsafe_allow_html=True)
+        get_table=listA[['gene','sgID_A','protospacer_A','sgID_B','protospacer_B','sgID_AB']]
+    
+        st.markdown(caution2,unsafe_allow_html=True)  
+        
+    
+    #st.write(get_table)
+    
+    ListARes = st.checkbox('Results For SetA',key=30)  
+    if ListARes and not isinstance(get_table, type(None)):#get_table!=None:        
+    #if ListARes and get_table.shape[0]>0:        
+        variant_set=get_table[['gene']]  
+        dft_a = pd.DataFrame(columns=['gene','guide_type','protospacer_A','protospacer_B'])    
+        dft_res=pd.DataFrame(columns=['sgID_1',	'sgRNA_1',	'chr_sgRNA_1',	'position_sgRNA_1',	'sgID_2',	'sgRNA_2',	'chr_sgRNA_2',	'position_sgRNA_2',	'sgID_1_2'])  
+        dft_res_mut=pd.DataFrame(columns=['sgID_1',	'sgRNA_1',	'chr_sgRNA_1',	'position_sgRNA_1',	'sgID_2',	'sgRNA_2',	'chr_sgRNA_2',	'position_sgRNA_2',	'sgID_1_2'])  
+        dft_notfound=pd.DataFrame(columns=['gene','ref_guide'])  
+        df_matched_guides_ref = pd.DataFrame(columns=['gene','ref_guide',	'chr',	'position',	'mutated_guide',	'strand',	'num_mismatch'])
+        df_mutated_guides_ref = pd.DataFrame(columns=['gene','ref_guide',	'chr',	'position',	'mutated_guide',	'strand',	'num_mismatch'])
+        #CHECK FOR GRCh38
+        for i in range(variant_set.shape[0]):
+            ref_listA=listA[listA['gene']==variant_set.iloc[i]['gene']][['guide_type','protospacer_A','protospacer_B','sgID_AB']]
+            ref_listA = ref_listA[['sgID_AB','guide_type','protospacer_A','protospacer_B']]
+            
+            ref_listA.columns=['gene','guide_type','protospacer_A','protospacer_B']
+            res,res_mut,res_notfound,list_match,list_mutated=get_lists(ref_listA,listA_found_ref,listA_notfound_ref)
+            dft_a=dft_a.append(ref_listA)  
+            if res.shape[0]>0:
+                dft_res=dft_res.append(res)
+            if res_mut.shape[0]>0:
+                dft_res_mut=dft_res_mut.append(res_mut)
+            if res_notfound.shape[0]>0:    
+                dft_notfound= dft_notfound.append(res_notfound)
+            if list_match.shape[0]>0:    
+                df_matched_guides_ref= df_matched_guides_ref.append(list_match)
+            if list_mutated.shape[0]>0:    
+                df_mutated_guides_ref= df_mutated_guides_ref.append(list_mutated)
+        
+        st.write('Selected Reference Guides for **Set A**')
+        tbl_disp(dft_a,'All','ReferenceGuides',0)
+        if dft_res.shape[0]>0:
+            st.write('Matched to **GRCh38** Reference Guides for **Set A**')
+            tbl_disp(dft_res,'select_genes','SetA_GRCh38')
+        elif dft_res_mut.shape[0]>0:
+            st.write('Mutated to **GRCh38** Reference Guides for **Set A**')
+            st.markdown(caution1,unsafe_allow_html=True)
+            tbl_disp(dft_res_mut,'select_genes','SetA_Mutated_GRCh38')
+        if dft_notfound.shape[0]>0:
+            st.write('**SetA Guides Not Found in GRCh38**')
+            #tbl_disp(dft_notfound,'select_genes','SetA_Notfound_GRCh38')
+            st.table(dft_notfound)
+        #Now CHECK FOR CHM13
+        dft_a = pd.DataFrame(columns=['gene','guide_type','protospacer_A','protospacer_B'])    
+        dft_res=pd.DataFrame(columns=['sgID_1',	'sgRNA_1',	'chr_sgRNA_1',	'position_sgRNA_1',	'sgID_2',	'sgRNA_2',	'chr_sgRNA_2',	'position_sgRNA_2',	'sgID_1_2'])  
+        dft_res_mut=pd.DataFrame(columns=['sgID_1',	'sgRNA_1',	'chr_sgRNA_1',	'position_sgRNA_1',	'sgID_2',	'sgRNA_2',	'chr_sgRNA_2',	'position_sgRNA_2',	'sgID_1_2'])  
+        dft_notfound=pd.DataFrame(columns=['gene','ref_guide'])  
+        df_matched_guides_lr = pd.DataFrame(columns=['gene','ref_guide',	'chr',	'position',	'mutated_guide',	'strand',	'num_mismatch'])
+        df_mutated_guides_lr = pd.DataFrame(columns=['gene','ref_guide',	'chr',	'position',	'mutated_guide',	'strand',	'num_mismatch'])
+
+        for i in range(variant_set.shape[0]):
+            ref_listA=listA[listA['gene']==variant_set.iloc[i]['gene']][['guide_type','protospacer_A','protospacer_B','sgID_AB']]
+            ref_listA = ref_listA[['sgID_AB','guide_type','protospacer_A','protospacer_B']]
+            
+            ref_listA.columns=['gene','guide_type','protospacer_A','protospacer_B']
+            res,res_mut,res_notfound,list_match,list_mutated=get_lists(ref_listA,listA_found_lr,listA_notfound_lr)
+            dft_a=dft_a.append(ref_listA)  
+            if res.shape[0]>0:
+                dft_res=dft_res.append(res)
+            if res_mut.shape[0]>0:
+                dft_res_mut=dft_res_mut.append(res_mut)
+            if res_notfound.shape[0]>0:
+                dft_notfound= dft_notfound.append(res_notfound)
+            if list_match.shape[0]>0:    
+                df_matched_guides_lr= df_matched_guides_lr.append(list_match)
+            if list_mutated.shape[0]>0:    
+                df_mutated_guides_lr= df_mutated_guides_lr.append(list_mutated)
+                
+        if dft_res.shape[0]>0:
+            st.write('Matched to **CHM13** Reference Guides for **Set A**')
+            tbl_disp(dft_res,'select_genes','SetA_CHM13')
+        elif dft_res_mut.shape[0]>0:
+            st.write('Mutated to **CHM13** Reference Guides for **Set A**')
+            st.markdown(caution1,unsafe_allow_html=True)
+            tbl_disp(dft_res_mut,'select_genes','SetA_Mutated_CHM13')
+        if dft_notfound.shape[0]>0:
+            st.write('**SetA Guides Not Found in CHM13**')
+            st.table(dft_notfound)
+        #NOW MERGE FROM GRCh38 and LR
+        merged_mutated_set=pd.merge(df_mutated_guides_ref,df_mutated_guides_lr, how="outer",on=["gene","ref_guide","chr"],suffixes=["_GRCh38",'_LR'])
+        merged_mutated_set = merged_mutated_set[['gene','ref_guide','chr','position_GRCh38','position_LR','strand_GRCh38','strand_LR','mutated_guide_GRCh38','mutated_guide_LR','num_mismatch_GRCh38','num_mismatch_LR']]
+        merged_match_set=pd.merge(df_matched_guides_ref,df_matched_guides_lr, how="outer",on=["gene","ref_guide","chr"],suffixes=["_GRCh38",'_LR'])
+        merged_match_set = merged_match_set[['gene','ref_guide','chr','position_GRCh38','position_LR','strand_GRCh38','strand_LR','mutated_guide_GRCh38','mutated_guide_LR','num_mismatch_GRCh38','num_mismatch_LR']]
+        if merged_match_set.shape[0]>0:        
+            #st.write('**Matched** Guides for **Set C** (*Each guide sequence has a trailing NGG*)')
+            st.write('**Matched** Guides for **Set A** to both **GRCh38 and CHM13 references** (*Each guide sequence has a trailing NGG* and **leading G even if it is a missmatch**)')
+            tbl_disp(merged_match_set,'select_genes','SetA_Matched_GRCh38_CHM13',0)
+            
+            #st.table(merged_match_seta)
+        elif merged_mutated_set.shape[0]>0:
+            #st.write('**Missmatched** Guides **Set C** (*Each guide sequence has a trailing NGG*)')
+            st.write('**Mutated** Guides for **Set A** to both **GRCh38 and CHM13 references** (*Each guide sequence has a trailing NGG* and **leading G even if it is a missmatch**)')
+            
+            tbl_disp(merged_mutated_set,'select_genes','SetA_Mutated_GRCh38_CHM13',0)
+    elif ListARes:
+        st.write("**Please select genes from the above table to begin**")
+
+    ListBRes = st.checkbox('Results For SetB',key=40)  
+    if ListBRes and not isinstance(get_table, type(None)):#get_table!=None:        
+        variant_set=get_table[['gene']]  
+        dft_b = pd.DataFrame(columns=['gene','guide_type','protospacer_A','protospacer_B'])    
+        dft_res=pd.DataFrame(columns=['sgID_1',	'sgRNA_1',	'chr_sgRNA_1',	'position_sgRNA_1',	'sgID_2',	'sgRNA_2',	'chr_sgRNA_2',	'position_sgRNA_2',	'sgID_1_2'])  
+        dft_res_mut=pd.DataFrame(columns=['sgID_1',	'sgRNA_1',	'chr_sgRNA_1',	'position_sgRNA_1',	'sgID_2',	'sgRNA_2',	'chr_sgRNA_2',	'position_sgRNA_2',	'sgID_1_2'])  
+        dft_notfound=pd.DataFrame(columns=['gene','ref_guide'])  
+        df_matched_guides_ref = pd.DataFrame(columns=['gene','ref_guide',	'chr',	'position',	'mutated_guide',	'strand',	'num_mismatch'])
+        df_mutated_guides_ref = pd.DataFrame(columns=['gene','ref_guide',	'chr',	'position',	'mutated_guide',	'strand',	'num_mismatch'])
+        #CHECK FOR GRCh38
+        for i in range(variant_set.shape[0]):
+            ref_listB=listB[listB['gene']==variant_set.iloc[i]['gene']][['guide_type','protospacer_A','protospacer_B','sgID_AB']]
+            ref_listB =ref_listB[['sgID_AB','guide_type','protospacer_A','protospacer_B']]
+            
+            ref_listB.columns=['gene','guide_type','protospacer_A','protospacer_B']
+            res,res_mut,res_notfound,list_match,list_mutated=get_lists(ref_listB,listB_found_ref,listB_notfound_ref)
+            dft_b=dft_b.append(ref_listB)  
+            if res.shape[0]>0:
+                dft_res=dft_res.append(res)
+            if res_mut.shape[0]>0:
+                dft_res_mut=dft_res_mut.append(res_mut)
+            if res_notfound.shape[0]>0:    
+                dft_notfound= dft_notfound.append(res_notfound)
+            if list_match.shape[0]>0:    
+                df_matched_guides_ref= df_matched_guides_ref.append(list_match)
+            if list_mutated.shape[0]>0:    
+                df_mutated_guides_ref= df_mutated_guides_ref.append(list_mutated)
+        
+        st.write('Selected Reference Guides for **Set B**')
+        tbl_disp(dft_b,'All','ReferenceGuides',0)
+        if dft_res.shape[0]>0:
+            st.write('Matched to **GRCh38** Reference Guides for **Set B**')
+            tbl_disp(dft_res,'select_genes','SetB_GRCh38')
+        elif dft_res_mut.shape[0]>0:
+            st.write('Mutated to **GRCh38** Reference Guides for **Set B**')
+            st.markdown(caution1,unsafe_allow_html=True)
+            tbl_disp(dft_res_mut,'select_genes','SetB_Mutated_GRCh38')
+        if dft_notfound.shape[0]>0:
+            st.write('**SetB Guides Not Found in GRCh38**')
+            #tbl_disp(dft_notfound,'select_genes','SetA_Notfound_GRCh38')
+            st.table(dft_notfound)
+            
+        #Now CHECK FOR CHM13
+        dft_b = pd.DataFrame(columns=['gene','guide_type','protospacer_A','protospacer_B'])    
+        dft_res=pd.DataFrame(columns=['sgID_1',	'sgRNA_1',	'chr_sgRNA_1',	'position_sgRNA_1',	'sgID_2',	'sgRNA_2',	'chr_sgRNA_2',	'position_sgRNA_2',	'sgID_1_2'])  
+        dft_res_mut=pd.DataFrame(columns=['sgID_1',	'sgRNA_1',	'chr_sgRNA_1',	'position_sgRNA_1',	'sgID_2',	'sgRNA_2',	'chr_sgRNA_2',	'position_sgRNA_2',	'sgID_1_2'])  
+        dft_notfound=pd.DataFrame(columns=['gene','ref_guide'])  
+        df_matched_guides_lr = pd.DataFrame(columns=['gene','ref_guide',	'chr',	'position',	'mutated_guide',	'strand',	'num_mismatch'])
+        df_mutated_guides_lr = pd.DataFrame(columns=['gene','ref_guide',	'chr',	'position',	'mutated_guide',	'strand',	'num_mismatch'])
+
+        for i in range(variant_set.shape[0]):
+            ref_listB=listB[listB['gene']==variant_set.iloc[i]['gene']][['guide_type','protospacer_A','protospacer_B','sgID_AB']]
+            ref_listB=ref_listB[['sgID_AB','guide_type','protospacer_A','protospacer_B']]
+            
+            ref_listB.columns=['gene','guide_type','protospacer_A','protospacer_B']
+            res,res_mut,res_notfound,list_match,list_mutated=get_lists(ref_listB,listB_found_lr,listB_notfound_lr)
+            dft_b=dft_b.append(ref_listB)  
+            if res.shape[0]>0:
+                dft_res=dft_res.append(res)
+            if res_mut.shape[0]>0:
+                dft_res_mut=dft_res_mut.append(res_mut)
+            if res_notfound.shape[0]>0:
+                dft_notfound= dft_notfound.append(res_notfound)
+            if list_match.shape[0]>0:    
+                df_matched_guides_lr= df_matched_guides_lr.append(list_match)
+            if list_mutated.shape[0]>0:    
+                df_mutated_guides_lr= df_mutated_guides_lr.append(list_mutated)
+                
+        if dft_res.shape[0]>0:
+            st.write('Matched to **CHM13** Reference Guides for **Set B**')
+            tbl_disp(dft_res,'select_genes','SetB_CHM13')
+        elif dft_res_mut.shape[0]>0:
+            st.write('Mutated to **CHM13** Reference Guides for **Set B**')
+            st.markdown(caution1,unsafe_allow_html=True)
+            tbl_disp(dft_res_mut,'select_genes','SetB_Mutated_CHM13')
+        if dft_notfound.shape[0]>0:
+            st.write('**SetB Guides Not Found in CHM13**')
+            st.table(dft_notfound)
+        #NOW MERGE FROM GRCh38 and LR
+        merged_mutated_set=pd.merge(df_mutated_guides_ref,df_mutated_guides_lr, how="outer",on=["gene","ref_guide","chr"],suffixes=["_GRCh38",'_LR'])
+        merged_mutated_set = merged_mutated_set[['gene','ref_guide','chr','position_GRCh38','position_LR','strand_GRCh38','strand_LR','mutated_guide_GRCh38','mutated_guide_LR','num_mismatch_GRCh38','num_mismatch_LR']]
+        merged_match_set=pd.merge(df_matched_guides_ref,df_matched_guides_lr, how="outer",on=["gene","ref_guide","chr"],suffixes=["_GRCh38",'_LR'])
+        merged_match_set = merged_match_set[['gene','ref_guide','chr','position_GRCh38','position_LR','strand_GRCh38','strand_LR','mutated_guide_GRCh38','mutated_guide_LR','num_mismatch_GRCh38','num_mismatch_LR']]
+        if merged_match_set.shape[0]>0:        
+            #st.write('**Matched** Guides for **Set C** (*Each guide sequence has a trailing NGG*)')
+            st.write('**Matched** Guides for **Set B** to both **GRCh38 and CHM13 references** (*Each guide sequence has a trailing NGG* and **leading G even if it is a missmatch**)')
+            tbl_disp(merged_match_set,'select_genes','SetB_Matched_GRCh38_CHM13',0)
+            
+            #st.table(merged_match_seta)
+        elif merged_mutated_set.shape[0]>0:
+            #st.write('**Missmatched** Guides **Set C** (*Each guide sequence has a trailing NGG*)')
+            st.write('**Mutated** Guides for **Set B** to both **GRCh38 and CHM13 references** (*Each guide sequence has a trailing NGG* and **leading G even if it is a missmatch**)')
+            #st.markdown(caution1,unsafe_allow_html=True)
+            tbl_disp(merged_mutated_set,'select_genes','SetB_Mutated_GRCh38_CHM13',0)
+            
+    elif ListBRes:
+        st.write("**Please select genes from the above table to begin**")
+            
+    ListCRes = st.checkbox('Results For SetC',key=50)  
+    if ListCRes and not isinstance(get_table, type(None)):#get_table!=None:        
+        variant_set=get_table[['gene']]  
+        dft_c = pd.DataFrame(columns=['gene','guide_type','protospacer_A','protospacer_B'])    
+        dft_res=pd.DataFrame(columns=['sgID_1',	'sgRNA_1',	'chr_sgRNA_1',	'position_sgRNA_1',	'sgID_2',	'sgRNA_2',	'chr_sgRNA_2',	'position_sgRNA_2',	'sgID_1_2'])  
+        dft_res_mut=pd.DataFrame(columns=['sgID_1',	'sgRNA_1',	'chr_sgRNA_1',	'position_sgRNA_1',	'sgID_2',	'sgRNA_2',	'chr_sgRNA_2',	'position_sgRNA_2',	'sgID_1_2'])  
+        dft_notfound=pd.DataFrame(columns=['gene','ref_guide'])  
+        df_matched_guides_ref = pd.DataFrame(columns=['gene','ref_guide',	'chr',	'position',	'mutated_guide',	'strand',	'num_mismatch'])
+        df_mutated_guides_ref = pd.DataFrame(columns=['gene','ref_guide',	'chr',	'position',	'mutated_guide',	'strand',	'num_mismatch'])
+        #CHECK FOR GRCh38
+        for i in range(variant_set.shape[0]):
+            ref_listC=listC[listC['gene']==variant_set.iloc[i]['gene']][['guide_type','protospacer_A','protospacer_B','sgID_AB']]
+            ref_listC =ref_listC[['sgID_AB','guide_type','protospacer_A','protospacer_B']]
+            
+            ref_listC.columns=['gene','guide_type','protospacer_A','protospacer_B']
+            res,res_mut,res_notfound,list_match,list_mutated=get_lists(ref_listC,listC_found_ref,listC_notfound_ref)
+            dft_c=dft_c.append(ref_listC)  
+            if res.shape[0]>0:
+                dft_res=dft_res.append(res)
+            if res_mut.shape[0]>0:
+                dft_res_mut=dft_res_mut.append(res_mut)
+            if res_notfound.shape[0]>0:    
+                dft_notfound= dft_notfound.append(res_notfound)
+            if list_match.shape[0]>0:    
+                df_matched_guides_ref= df_matched_guides_ref.append(list_match)
+            if list_mutated.shape[0]>0:    
+                df_mutated_guides_ref= df_mutated_guides_ref.append(list_mutated)
+        
+        st.write('Selected Reference Guides for **Set B**')
+        tbl_disp(dft_c,'All','ReferenceGuides',0)
+        if dft_res.shape[0]>0:
+            st.write('Matched to **GRCh38** Reference Guides for **Set C**')
+            tbl_disp(dft_res,'select_genes','SetC_GRCh38')
+        elif dft_res_mut.shape[0]>0:
+            st.write('Mutated to **GRCh38** Reference Guides for **Set C**')
+            st.markdown(caution1,unsafe_allow_html=True)
+            tbl_disp(dft_res_mut,'select_genes','SetC_Mutated_GRCh38')
+        if dft_notfound.shape[0]>0:
+            st.write('**SetC Guides Not Found in GRCh38**')
+            #tbl_disp(dft_notfound,'select_genes','SetA_Notfound_GRCh38')
+            st.table(dft_notfound)
+            
+        #Now CHECK FOR CHM13
+        dft_c = pd.DataFrame(columns=['gene','guide_type','protospacer_A','protospacer_B'])    
+        dft_res=pd.DataFrame(columns=['sgID_1',	'sgRNA_1',	'chr_sgRNA_1',	'position_sgRNA_1',	'sgID_2',	'sgRNA_2',	'chr_sgRNA_2',	'position_sgRNA_2',	'sgID_1_2'])  
+        dft_res_mut=pd.DataFrame(columns=['sgID_1',	'sgRNA_1',	'chr_sgRNA_1',	'position_sgRNA_1',	'sgID_2',	'sgRNA_2',	'chr_sgRNA_2',	'position_sgRNA_2',	'sgID_1_2'])  
+        dft_notfound=pd.DataFrame(columns=['gene','ref_guide'])  
+        df_matched_guides_lr = pd.DataFrame(columns=['gene','ref_guide',	'chr',	'position',	'mutated_guide',	'strand',	'num_mismatch'])
+        df_mutated_guides_lr = pd.DataFrame(columns=['gene','ref_guide',	'chr',	'position',	'mutated_guide',	'strand',	'num_mismatch'])
+
+        for i in range(variant_set.shape[0]):
+            ref_listC=listC[listC['gene']==variant_set.iloc[i]['gene']][['guide_type','protospacer_A','protospacer_B','sgID_AB']]
+            ref_listC=ref_listC[['sgID_AB','guide_type','protospacer_A','protospacer_B']]
+            
+            ref_listC.columns=['gene','guide_type','protospacer_A','protospacer_B']
+            res,res_mut,res_notfound,list_match,list_mutated=get_lists(ref_listC,listC_found_lr,listC_notfound_lr)
+            dft_c=dft_c.append(ref_listC)  
+            if res.shape[0]>0:
+                dft_res=dft_res.append(res)
+            if res_mut.shape[0]>0:
+                dft_res_mut=dft_res_mut.append(res_mut)
+            if res_notfound.shape[0]>0:
+                dft_notfound= dft_notfound.append(res_notfound)
+            if list_match.shape[0]>0:    
+                df_matched_guides_lr= df_matched_guides_lr.append(list_match)
+            if list_mutated.shape[0]>0:    
+                df_mutated_guides_lr= df_mutated_guides_lr.append(list_mutated)
+                
+        if dft_res.shape[0]>0:
+            st.write('Matched to **CHM13** Reference Guides for **Set C**')
+            tbl_disp(dft_res,'select_genes','SetC_CHM13')
+        elif dft_res_mut.shape[0]>0:
+            st.write('Mutated to **CHM13** Reference Guides for **Set C**')
+            st.markdown(caution1,unsafe_allow_html=True)
+            tbl_disp(dft_res_mut,'select_genes','SetC_Mutated_CHM13')
+        if dft_notfound.shape[0]>0:
+            st.write('**SetC Guides Not Found in CHM13**')
+            st.table(dft_notfound)
+        #NOW MERGE FROM GRCh38 and LR
+        merged_mutated_set=pd.merge(df_mutated_guides_ref,df_mutated_guides_lr, how="outer",on=["gene","ref_guide","chr"],suffixes=["_GRCh38",'_LR'])
+        merged_mutated_set = merged_mutated_set[['gene','ref_guide','chr','position_GRCh38','position_LR','strand_GRCh38','strand_LR','mutated_guide_GRCh38','mutated_guide_LR','num_mismatch_GRCh38','num_mismatch_LR']]
+        merged_match_set=pd.merge(df_matched_guides_ref,df_matched_guides_lr, how="outer",on=["gene","ref_guide","chr"],suffixes=["_GRCh38",'_LR'])
+        merged_match_set = merged_match_set[['gene','ref_guide','chr','position_GRCh38','position_LR','strand_GRCh38','strand_LR','mutated_guide_GRCh38','mutated_guide_LR','num_mismatch_GRCh38','num_mismatch_LR']]
+        if merged_match_set.shape[0]>0:        
+            #st.write('**Matched** Guides for **Set C** (*Each guide sequence has a trailing NGG*)')
+            st.write('**Matched** Guides for **Set C** to both **GRCh38 and CHM13 references** (*Each guide sequence has a trailing NGG* and **leading G even if it is a missmatch**)')
+            tbl_disp(merged_match_set,'select_genes','SetC_Matched_GRCh38_CHM13',0)
+            
+            #st.table(merged_match_seta)
+        elif merged_mutated_set.shape[0]>0:
+            #st.write('**Missmatched** Guides **Set C** (*Each guide sequence has a trailing NGG*)')
+            st.write('**Mutated** Guides for **Set C** to both **GRCh38 and CHM13 references** (*Each guide sequence has a trailing NGG* and **leading G even if it is a missmatch**)')
+            #st.markdown(caution1,unsafe_allow_html=True)
+            tbl_disp(merged_mutated_set,'select_genes','SetC_Mutated_GRCh38_CHM13',0)
+    elif ListCRes:
+        st.write("**Please select genes from the above table to begin**")
+