AI Guided Protein Design for Next‐Generation Autogenic Engineered Living Materials

Engineered living materials (ELM) enable the fabrication of innovative, self‐regenerating, and self‐healing functional materials with new physicochemical and biological properties for diverse applications in sensing, therapeutics, and structural engineering. Through advances in protein engineering, microbial cells can be programmed to produce, secrete, and assemble proteinaceous scaffolds, forming a robust and customizable platform for functional materials. This perspective outlines a transformative vision for expanding the design space of autogenic ELM via AI‐guided protein engineering. Specifically, it highlights how de novo protein design can generate entirely new structural building blocks and establish direct links between scaffold composition and macroscopic material performance. Current scaffold engineering strategies, including N‐terminal, C‐terminal, and coupled terminal fusion, as well as core modifications, that have enabled initial functionalization and mechanical programmability of the ELM scaffold are reviewed. However, these methods often face limitations due to fibril destabilization and misfolding of appended domains, restricting material tunability. Recent breakthroughs in deep‐learning‐based structure prediction and protein sequence design now allow for generating de novo protein building blocks that expand beyond natural sequence and structure constraints. These developments set the stage for a new generation of genetically programmable protein scaffolds with customizable mechanical properties and advanced functionality.

Authors

Hoda M. Hammad; Anna M. Duraj‐Thatte

Published

Apr 1, 2026

Journal or venue

Advanced Intelligent Systems

DOI

10.1002/aisy.202501021

Paper type

journal article

Source

Crossref