SecMPNN: 3-Party Privacy-Preserving Molecular Structure Properties Inference

Compound screening is a key step in the development of new drugs. Current high-throughput screening methods cannot be widely adopted by laboratories due to their expensive equipment and low efficiency. The booming deep learning in recent years has provided a new answer to this question. The message...

Full description

Saved in:
Bibliographic Details
Main Authors: Liao, Xinying, Xue, Jiaye, Yu, Shengxing, Liu, Ximeng, Shu, Jiangang
Format: Conference Proceeding
Language:English
Subjects:
Cryptography
Message passing
Molecular Structure Properties Inference
MPNN
Neural networks
Outsourcing
Privacy
Privacy-preserving
Secret Sharing
Servers
Signal processing
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Compound screening is a key step in the development of new drugs. Current high-throughput screening methods cannot be widely adopted by laboratories due to their expensive equipment and low efficiency. The booming deep learning in recent years has provided a new answer to this question. The message passing neural network (MPNN) can directly predict molecular properties from molecular structure so that compound screening can be completed without experimentation. In the face of large-scale molecular data, outsourcing this task to a professional cloud server can further accelerate prediction efficiency and reduce costs. In order to solve the privacy protection problem of computing on cloud servers, we propose a 3-party molecular structure properties inference privacy protection framework SecMPNN based on additive secret sharing. We design brand-new cryptographic protocols to ensure the privacy and security in the prediction process, and through experiments show that the single inference time of our protocol on different networks is 40.85% faster than CRYPTEN and 18.5% faster than SecureNN.
ISSN:2379-190X
DOI:10.1109/ICASSP43922.2022.9746075