Synthetic Biology and Artificial Intelligence – synbai

We develop new antimicrobial peptides and engineer cells via designer peptides
Research
We, the synbai team, combine molecular and synthetic biology with predictive and generative machine learning to develop
- de novo antimicrobial peptides against multi-drug resistant pathogens.
- phase-separating peptides for cellular engineering.
Experimentally, we use molecular and synthetic biology tools, including biosensors (Pandi et al. 2019, Voyvodic et al. 2019), gene circuits (Pandi & Koch et al. 2019, Pandi & Diehl et al. 2022), phage display and cell -free transcription-translation systems (Greco et al. 2021, Pandi et al. 2023), to engineer biological sequences and systems.
Computationally, we apply predictive and generative deep learning models to understand and design biological sequences (Pandi et al. 2023, Fallahpour & Gureghian et al. 2024, MohammadHosseini & Teimouri et al. 2025)

Antimicrobial peptides on demand
To design and screen de novo antimicrobial peptides on demand that are pathogen-specific and proteolytically stable.

Phase-separating peptides
To design de novo phase-separating peptides for synthetic biology applications, e.g., bottom-up cellular assemblies.

Gene expression language models
To develop codon and gene expression language models for optimal production of de novo peptides/proteins.
Publications
- MohammadHosseini AM*, Teimouri H*, Gureghian V, Najjar R, Lindner AB‡, Pandi A‡. Generalizable prediction of liquid-liquid phase separation from protein sequence. bioRxiv. 2025. Link.
- Fallahpour A*, Gureghian V*, Filion GJ‡ , Lindner AB‡ , Pandi A‡ . CodonTransformer: a multispecies codon optimizer using context-aware neural networks. bioRxiv. 2024. Link.
- Pandi A‡ , Adam D, Zare A, Trinh VT, Schaefer SL, Burt M, …, Erb TJ‡ . Cell-free biosynthesis combined with deep learning accelerates de novo-development of antimicrobial peptides. Nature Communications. 2023 Nov 8;14(1):7197. Link.
- Pandi A*‡ , Diehl C*, Yazdizadeh Kharrazi A, …, Erb TJ‡ . A versatile active learning workflow for optimization of genetic and metabolic networks. Nature Communications. 2022 Jul 5;13(1):3876. Link.
- Greco FV, Pandi A, Erb TJ, Grierson CS, Gorochowski TE‡ . Harnessing the central dogma for stringent multi-level control of gene expression. Nature communications. 2021 Mar 19;12(1):1738. Link.
- Pandi A*, Koch M*, Voyvodic PL, Soudier P, Bonnet J, Kushwaha M‡ , Faulon JL‡ . Metabolic perceptrons for neural computing in biological systems. Nature communications. 2019 Aug 28;10(1):3880. Link.
- Pandi A, Grigoras I, Borkowski O, Faulon JL‡ . Optimizing cell-free biosensors to monitor enzymatic production. ACS synthetic biology . 2019 Jul 23;8(8):1952-7. Link.
- Voyvodic PL, Pandi A, Koch M, Conejero I, Valjent E, Courtet P, Renard E, Faulon JL‡ , Bonnet J‡ . Plug-and-play metabolic transducers expand the chemical detection space of cell-free biosensors. Nature communications. 2019 Apr 12;10(1):1697. Link.
* and ‡ denote co-first and corresponding authors, respectively.
All publications are available here .