A machine framework for extracting biologial pathway information from the literature

Supplementary datasets for the paper "A machine framework for extracting biologial pathway information from the literature". The datasets include Supplementary Data 1 (Training dataset images for training EBPI arrow detection model), Supplementary Data 2 (Test dataset images for validating EBPI arrow detection model), Supplementary Data 3 (Labeling dataset excel file for training and test dataset), Supplementary Data 4 (EBPI text classification model training dataset), Supplementary Data 5 (Collecting and processing of images illustrating biological pathways across 466 target chemicals from the bio-based chemicals map), Supplementary Data 6 (Information on reactions obtained through EBPI from images of biological pathways, focusing on target chemicals from maps of bio-based chemicals), Supplementary Data 7 (Target chemicals satisfying criteria for biosynthetic reactions not covered by biological pathway databases).