SieveAI: An Automated Drug Discovery Pipeline

Preprint:10.1101/2025.04.20.648820

Authors

Vishal Kumar Sahu1, Isha Zafar1, Shuchi Nagar2, Amit Ranjan1#, Soumya Basu1#

1 Cancer and Translational Research Centre, Dr. D. Y. Patil Biotechnology and Bioinformatics Institute, Tathawade, Pune – 411033

2 Bioinformatics Centre, Dr. D. Y. Patil Biotechnology and Bioinformatics Institute, Tathawade, Pune – 411033

Corresponding Authors

Background

Systematic Interaction Evaluation and Virtual Enhancement Analysis Interface (SieveAI) is an automated drug discovery pipeline developed to enhance the efficiency of virtual screening and computer-aided drug discovery processes. The molecular docking workflow encompasses acquiring, modeling, and pre-processing of molecular structure files, conducting docking with various algorithms, and subsequent analysis and interpretation of the outcomes by visualising or tabulating the results. While several open-source software tools are available to assist these operations at different steps of molecular docking, they often necessitate manual user intervention at every stage. To streamline and automate this extensive manual process and develop a comprehensive solution, we have developed an innovative, fully extensible, molecular docking pipeline SieveAI (©L-129927/2023). The same has been demonstrated in this manuscript. SieveAI works with a range of open-source libraries, packages, and programs to facilitate automated drug discovery using established programs and software. The package is accessible at https://miRNA.in/SieveAI.

Automated drug discovery pipeline:

  • Processing and analysis of molecular interactions involving protein-protein, protein-small molecule, protein-RNA, protein-DNA, RNA-RNA, DNA-RNA
  • Interaction analysis like hydrogen bonds and contacts
  • Ranking based on the docking score
  • Can be extended to rescore or dock with multiple docking programs
  • Can be used as one command solution

Conclusion

The pipeline can be helpful in automating the manual workflow for molecular docking and drug discovery including rescoring and analysis of molecular interactions. Manual workload and human errors can be overcome.

Availability
Open Source

PyPi.org↗GitHub↗

Future Prospects

  • Development of Graphical User Interface
  • Hosting on web-server for public use