Skip to content

Develop issue91: National request for table size change #96

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
xiaoliz0 wants to merge 7 commits into
base: main
Choose a base branch
from
Open

Develop issue91: National request for table size change #96

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
9278f15
Add new function to split the table generated in the end of the repor…
xiaoliz0 Jan 9, 2026
813bfdf
Update header information for the table in the end based on the comme…
xiaoliz0 Jan 13, 2026
64d8093
Update codes based on comments from Matin. Merge the two functions of…
xiaoliz0 Jan 20, 2026
7d76914
Merge branch 'main' into develop_issue91
xiaoliz0 Jan 21, 2026
995f7a8
Update codes based on the comments from Martin.
xiaoliz0 Jan 27, 2026
18362bc
Remove the return value for total number of added slides for the tabl…
xiaoliz0 Jan 27, 2026
48d78e2
Merge branch 'develop_issue91' of https://github.com/InPreD/PRONTO in…
xiaoliz0 Jan 27, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions Config/configure_PRONTO.ini
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,8 @@ data_path = /data/sample_data/analysis_results/
encoding_sys = utf-8
;Specify the number of columns you want to do the filtering (NB: this will also make the script to generate the number of output tables):
filter_col_nu = 5
;Specify the number of max rows of the table per slide starting from the 8th slide in report. This is used to split long tables.
table_max_rows_per_slide = 14
;Please modify this for local env if you use MTF files to import the clinical data into meta file. Specify the version of year of the MTF files.
material_file_version = 2026

Expand Down
111 changes: 64 additions & 47 deletions Script/PRONTO.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -731,13 +731,12 @@ def insert_image_to_ppt(DNA_sampleID,DNA_normal_sampleID,RNA_sampleID,DNA_image_
ppt.save(output_ppt_file)


def insert_table_to_ppt(table_data_file,slide_n,table_name,left_h,top_h,width_h,left_t,top_t,width_t,height_t,font_size,table_header,output_ppt_file,if_print_rowNo,table_column_width):
def insert_table_to_ppt(table_data_file,slide_n,table_name,left_h,top_h,width_h,left_t,top_t,width_t,height_t,font_size,table_header,output_ppt_file,if_print_rowNo,table_column_width,table_max_rows_per_slide):
table_file = open(table_data_file)
lines = table_file.readlines()
if not lines:
return
first_line = lines[0]
rows = len(lines)
first_line_cells = first_line.split('\t')
cols = len(table_header)
header_not_exist_in_table = []
Expand All @@ -747,51 +746,68 @@ def insert_table_to_ppt(table_data_file,slide_n,table_name,left_h,top_h,width_h,
if_exist = True
if not if_exist:
header_not_exist_in_table.append(n)
data_rows = []
for line in lines[1:]:
line_cells = line.split('\t')
if header_not_exist_in_table:
for num in header_not_exist_in_table:
line_cells.insert(num," ")
row_data = [cell.strip() for cell in line.split('\t')]
data_rows.append(row_data)
total_rows = len(data_rows)

ppt = Presentation(output_ppt_file)
try:
slide = ppt.slides[slide_n-1]
except:
slide = ppt.slides.add_slide(ppt.slide_layouts[6])
shapes = slide.shapes
left = Inches(left_t)
top = Inches(top_t)
width = Inches(width_t)
height = Inches(height_t)
table = shapes.add_table(rows,cols,left,top,width,height).table
table_rows = rows-1
col_protein_change_short_position = table_header.index("Protein_change_short")
for c in range(cols):
if table_column_width:
table.columns[c].width = Inches(table_column_width[c])
table.cell(0,c).text = table_header[c]
table.cell(0,c).text_frame.paragraphs[0].font.size = Pt(font_size)

row = 1
for line in open(table_data_file):
if(line != first_line):
line_cells = line.split('\t')
if header_not_exist_in_table:
for num in header_not_exist_in_table:
line_cells.insert(num," ")
if(line_cells[col_protein_change_short_position].endswith('X')):
line_cells[col_protein_change_short_position] = line_cells[col_protein_change_short_position][:-1] + '*'
for j in range(len(line_cells) - 1):
table.cell(row,j).text = str(line_cells[j])
table.cell(row,j).text_frame.paragraphs[0].font.size = Pt(font_size)
row += 1
textbox = slide.shapes.add_textbox(Inches(left_h),Inches(top_h),Inches(width_h),Inches(0.25))
tf = textbox.text_frame
if(if_print_rowNo == True):
tf.paragraphs[0].text = table_name +" (N=" + str(table_rows) + ")"
if(table_max_rows_per_slide is None or total_rows <= table_max_rows_per_slide):
total_slides_needed = 1
rows_per_page = total_rows
start_slide_index = slide_n
else:
tf.paragraphs[0].text = table_name
tf.paragraphs[0].font.size = Pt(8)
tf.paragraphs[0].font.bold = True
tf.paragraphs[0].alignment = PP_ALIGN.CENTER
total_slides_needed = (total_rows + table_max_rows_per_slide -1) // table_max_rows_per_slide
rows_per_page = table_max_rows_per_slide
start_slide_index = None

for page_num in range(total_slides_needed):
start_idx = page_num * rows_per_page
end_idx = min(start_idx + rows_per_page, total_rows)
current_page_data = data_rows[start_idx:end_idx]
current_page_rows = len(current_page_data)
if(start_slide_index is not None and page_num == 0):
slide = ppt.slides[slide_n - 1]
else:
slide = ppt.slides.add_slide(ppt.slide_layouts[6])
shapes = slide.shapes
left = Inches(left_t)
top = Inches(top_t)
width = Inches(width_t)
height = Inches(height_t)
table_rows = current_page_rows + 1
table = shapes.add_table(table_rows,cols,left,top,width,height).table
for c in range(cols):
if table_column_width:
table.columns[c].width = Inches(table_column_width[c])
table.cell(0,c).text = table_header[c]
table.cell(0,c).text_frame.paragraphs[0].font.size = Pt(font_size)

for row_idx, row_data in enumerate(current_page_data, start=1):
for col_idx in range(cols):
table.cell(row_idx,col_idx).text = str(row_data[col_idx])
table.cell(row_idx,col_idx).text_frame.paragraphs[0].font.size = Pt(font_size)

textbox = slide.shapes.add_textbox(Inches(left_h),Inches(top_h),Inches(width_h),Inches(0.25))
tf = textbox.text_frame
if(if_print_rowNo == True):
if(table_max_rows_per_slide is not None):
tf.paragraphs[0].text = table_name +" (N=" + str(total_rows) + ", Page " + str(page_num+1) + "/" + str(total_slides_needed) + ")"
else:
tf.paragraphs[0].text = table_name +" (N=" + str(total_rows) + ")"
else:
tf.paragraphs[0].text = table_name
tf.paragraphs[0].font.size = Pt(8)
tf.paragraphs[0].font.bold = True
tf.paragraphs[0].alignment = PP_ALIGN.CENTER

ppt.save(output_ppt_file)
data_nrows = table_rows
return data_nrows
return total_rows


def update_ppt_variant_summary_table(data_nrows,DNA_sampleID,RNA_sampleID,TMB_DRUP_nr,TMB_DRUP_str,DNA_variant_summary_file,RNA_variant_summary_file,output_file_preMTB_AppendixTable,output_table_file_filterResults_AllReporVariants_CodingRegion,output_ppt_file):
Expand Down Expand Up @@ -1524,7 +1540,7 @@ def main(argv):
slide6_table_font_size = 7
if_print_rowNo = False
for table_index in slide6_table_ppSlide:
slide6_table_nrows = insert_table_to_ppt(slide6_table_data_file,table_index,slide6_table_name,slide6_header_left,slide6_header_top,slide6_header_width,slide6_table_left,slide6_table_top,slide6_table_width,slide6_table_height,slide6_table_font_size,slide6_table_header,output_ppt_file,if_print_rowNo,[])
slide6_table_nrows = insert_table_to_ppt(slide6_table_data_file,table_index,slide6_table_name,slide6_header_left,slide6_header_top,slide6_header_width,slide6_table_left,slide6_table_top,slide6_table_width,slide6_table_height,slide6_table_font_size,slide6_table_header,output_ppt_file,if_print_rowNo,[],table_max_rows_per_slide=None)
output_file_preMTB_AppendixTable = output_file_preMTB_table_path + "_preMTBTable_Appendix.txt"
output_table_file_filterResults_AllReporVariants_CodingRegion = output_file_preMTB_table_path + "_AllReporVariants_CodingRegion.txt"
stable_text = update_ppt_variant_summary_table(slide6_table_nrows,DNA_sampleID,RNA_sampleID,TMB_DRUP,TMB_DRUP_str,DNA_variant_summary_file,RNA_variant_summary_file,output_file_preMTB_AppendixTable,output_table_file_filterResults_AllReporVariants_CodingRegion,output_ppt_file)
Expand All @@ -1544,7 +1560,8 @@ def main(argv):
slide8_table_font_size = 7
if_print_rowNo = True
table8_column_width = [0.54, 0.96, 0.96, 0.51, 0.73, 1.12, 2.26, 0.79, 0.81, 0.53]
slide8_table_nrows = insert_table_to_ppt(slide8_table_data_file,slide8_table_ppSlide,slide8_table_name,slide8_header_left,slide8_header_top,slide8_header_width,slide8_table_left,slide8_table_top,slide8_table_width,slide8_table_height,slide8_table_font_size,slide8_table_header,output_ppt_file,if_print_rowNo,table8_column_width)
table_max_rows_per_slide = int(cfg.get("INPUT", "table_max_rows_per_slide"))
insert_table_to_ppt(slide8_table_data_file,slide8_table_ppSlide,slide8_table_name,slide8_header_left,slide8_header_top,slide8_header_width,slide8_table_left,slide8_table_top,slide8_table_width,slide8_table_height,slide8_table_font_size,slide8_table_header,output_ppt_file,if_print_rowNo,table8_column_width,table_max_rows_per_slide)

# Insert the CNV_overveiw_plots pictures A2, B3 and C1 into report.
A2_to_extract=[2]
Expand All @@ -1555,12 +1572,12 @@ def main(argv):
B3_C1_to_extract = [4, 5]
pdf_page_image_to_ppt(CNV_overview_plots_pdf,output_ppt_file,B3_C1_to_extract,width_scale=1,height_scale=0.5)

# Change slides order.
# Change slides order.
ppt = Presentation(output_ppt_file)
slides = ppt.slides._sldIdLst
slides_list = list(slides)
slides.remove(slides_list[7])
slides.insert(12,slides_list[7])
slides.append(slides_list[7])
ppt.save(output_ppt_file)
print("Generate report for " + DNA_sampleID)
ppt_nr += 1
Expand Down