Tianjin Team Designs AI Peptide for Coronavirus Detection

Researchers at Tianjin University have computationally designed a synthetic peptide that enables modular detection of coronavirus 3C-like protease (3CLPro) activity, an enzyme essential for viral replication. Published in Engineering in Life Sciences on 22 June 2026 and reported on 13 August 2026, the work marks a proof-of-concept for cell-based assays measuring functional viral protease activity rather than merely detecting viral molecules, with applications in coronavirus diagnostics and antiviral drug screening.

The Tianjin team, led by Professors Tao Wang and Cheng Zhu, targeted the highly conserved substrate-binding pocket of 3CLPro, which shows more than 96% sequence identity across global coronavirus strains. Starting with the SARS-CoV-2 3CLPro native substrate, the team used Rosetta FastDesign and the deep-learning model ProteinMPNN to generate alternative peptide sequences, with AlphaFold3 confirming candidate structures. Their best design, PVILQYTT (designated P1), showed a Rosetta energy score of -75.8 versus -56.1 for the native sequence and was orthogonal to eukaryotic proteins. Unlike conventional PCR, antibody or antigen tests that detect viral molecules but not activity, the P1-based approach measures functional protease activity that may more closely reflect active viral replication.

The team validated three reporter architectures in HEK293T cells: a loss-of-signal Gaussia luciferase design where P1 produced a 67% signal reduction versus 23% for the native substrate; a gain-of-signal transmembrane-anchored luciferase design generating a 47% signal increase; and a fluorescence-based FlipGFP design where P1 produced a 3.9-fold fluorescence increase versus 1.2-fold. The P1-based luciferase sensor also responded dose-dependently to Pfizer’s 3CLPro inhibitor Paxlovid, supporting antiviral drug screening. Further work is needed before clinical translation.

The commercial signal is a growing convergence between AI-driven protein design and functional viral diagnostics. Activity-based coronavirus tests complement rather than replace PCR and antigen platforms. Expect antiviral developers (Pfizer with Paxlovid, Shionogi with Ensitrelvir), AI protein design specialists (Isomorphic Labs, Absci, Cradle Bio) and coronavirus diagnostic manufacturers (Roche, Abbott, Cepheid) to watch such modular sensor platforms closely through 2026 and 2027.

For the latest updates and in-depth insights into the world of Life Science, including breakthrough treatments, industry trends, and regulatory news, contact Bailey Osborne today!