The data used for training our generator model and the HT-SELEX data used for comparing with other methods. The size of the compressed file is about 1.8GB.
Additional_file_1.zipNucleic acid sequences generated by our model, AptaSim, and random generator for four proteins (DRGX, GCM1, OLIG1 and RXRB).
Additional_file_2.zipNucleic acid sequences and their binding specificity to target proteins (NFATC1, NFKB1 and MBNL1), constructed by our model.
Additional_file_3.zipAn aptamer binding to NFATC1, two aptamers binding to NFKB1, and two aptamers binding to MBNL1.
Additional_file_4.fastaNFATC1-binding motifs and NFKB1-binding motifs found in the DNA sequences generated by AptaSim and by a set of programs in AptaSuite.
Additional_file_5.zip