| import gradio as gr | |
| import subprocess as sp | |
| from sincfold.utils import ct2dot | |
| import shutil | |
| import os | |
| def fold(sequence): | |
| sequence = sequence.upper().replace(" ", "").replace("\n", "").replace("T", "U") | |
| if len(sequence) > 512: | |
| return "", "Max sequence length is 512", "", "" | |
| if len(sequence) < 3: | |
| return "", "Min sequence length is 3", "", "" | |
| shutil.rmtree("output", ignore_errors=True) | |
| ct_file = f"output/pred_id.ct" | |
| structure_draw = f"output/pred_id.png" | |
| fasta_file = f"output/pred_id.fasta" | |
| resolution = 1 | |
| if len(sequence)>100: | |
| resolution = 10 | |
| elif len(sequence)>50: | |
| resolution = 5 | |
| sp.run(f"sincFold pred {sequence} -o output --draw --draw-resolution {resolution}", shell=True) | |
| dotbracket = ct2dot(ct_file) | |
| if not dotbracket: | |
| dotbracket = None | |
| structure_draw = None | |
| dotbracket = "CT to dotbracket conversion failed (.ct file should be ok)" | |
| with open(fasta_file, "w") as f: | |
| f.write(f">seq\n{sequence}\n{dotbracket}") | |
| return ct_file, dotbracket, structure_draw, fasta_file | |
| def run(): | |
| demo = gr.Interface( | |
| title='sincFold: an end-to-end deep learning approach for RNA structure prediction', | |
| description='sincFold is an end-to-end deep learning approach that predicts the nucleotides contact matrix using only the RNA sequence as input. This demo provides a sincFold model pre-trained with known RNAs secondary structures. Input RNA sequences of up to 512 nucleotides can be processed with this demo. To process sequences longer than 512 nucleotides you can either install the package (via pip) or clone the entire repository.\n\nWebdemo: https://sinc.unl.edu.ar/web-demo/sincFold/\nSource-code: https://github.com/sinc-lab/sincFold.\nPaper: https://academic.oup.com/bib/article/25/4/bbae271/7690295', | |
| fn=fold, | |
| examples=[ | |
| ["AACCGGGUCAGGUCCGGAAGGAAGCAGCCCUAA"], | |
| ["CCACGGCGACUAUAUCCCUGGUGUUCACCUCUUCCCAUUCCGAACAGAGUCGUUAAGCCCAGGAGAGCCGAUGGUACUGCUUUAUUGCGGGAGAGUAGGUCGUCGCCGAGU"], | |
| ["GAUAAACCUUUAGCAAUAAACGAAAGUUUAACUAAGCCAUACUAACCCCAGGGUUGGUCAAUUUCGUGCCAGCCACCGCGGUCACACGAUUAACCCAAGCCAAUAGAAAUCGGCGUAAAGAGUGUUUUAGAUCAAUCCCCCAAUAAAGCUAAAAUUCACCUG"], | |
| ], | |
| inputs=[ | |
| gr.Textbox(label="RNA Sequence", | |
| value="GAUAAACCUUUAGCAAUAAACGAAAGUUUAACUAAGCCAUACUAACCCCAGGGUUGGUCAAUUUCGUGCCAGCCACCGCGGUCACACGAUUAACCCAAGCCAAUAGAAAUCGGCGUAAAGAGUGUUUUAGAUCAAUCCCCCAAUAAAGCUAAAAUUCACCUG")], | |
| outputs=[ | |
| gr.File(label="Model output"), | |
| gr.Textbox(label="Dot-bracket"), | |
| gr.Image(label="Structure"), | |
| gr.File(label="Fasta format"), | |
| ], | |
| allow_flagging="never") | |
| demo.launch(server_name="0.0.0.0", server_port=7860) | |
| if __name__ == "__main__": | |
| run() |