Molecular Innovations and AI Integration


Research

We are leveraging the advanced capabilities of LLMs to revolutionize the field of molecular biology. Traditionally associated with natural language processing, LLMs are now being employed to comprehend and manipulate sequence-based biological data, particularly protein sequences. Our research focuses on utilizing these models to extract abstract representations from Singapore’s rich biodiversity genomics datasets, aiming to streamline and optimize the generation of functional protein sequences. This innovative approach holds significant promise for advancing environmental sustainability, molecular biology, and therapeutic interventions.

One notable project in our lab involves the application of protein language models to design novel sweet-tasting proteins. Given the increasing health concerns associated with sugar consumption, brazzein—a naturally sweet protein with high thermostability and a favorable safety profile—emerges as a viable alternative. Our A*STAR wide collborative team has successfully demonstrated the potential of protein language models to engineer new brazzein homologs with enhanced properties. These newly designed proteins exhibit improved thermostability and potentially increased sweetness, surpassing the capabilities of conventional protein engineering methods. Our methodology involved identifying unexpected mutations that broaden the scope of protein engineering. To facilitate the characterization of these brazzein mutants, we developed a streamlined procedure utilizing Lactococcus lactis, a generally recognized as safe (GRAS) bacterium, for efficient purification. Additionally, taste receptor assays were employed to evaluate sweetness. This process culminated in the creation of a more heat-resistant and potentially sweeter brazzein variant, V23, underscoring the efficacy of computational design in optimizing protein sequences. 

BII_Research-BSFD-MIAII_figure-1

Nicholas Chua, B.; Mei Guo, W.; Teng Wong, H.; Siak-Wei Ow, D.; Leng Ho, P.; Koh, W.; Koay, A.; Tian Wong, F. A Sweeter Future: Using Protein Language Models for Exploring Sweeter Brazzein Homologs. Food Chemistry 2023, 426, 136580. . 

Members

Senior Scientist KOH Lian Chye Winston   |    [View Bio]
Lead Research Officer KONG Kiat Whye 
Senior Research Officer POH Si En 

Selected Publications

  1. D. W. P. Tay, L. L. Tan, E. Heng, N. Zulkarnain, K. C. Ching, M. Wibowo, E. J. Chin, Z. Y. Q. Tan, C. Y. Leong, V. W. P. Ng, L. K. Yang, D. C. S. Seow, Y. W. Lim, W. Koh, L. Koduru, Y. Kanagasundaram, S. B. Ng, Y. H. Lim, F. T. Wong, Exploring a general multi-pronged activation strategy for natural product discovery in Actinomycetes. Commun Biol 7, 1–13 (2024). 

  2. E. Tiong, Y. S. Koo, J. Bi, L. Koduru, W. Koh, Y. H. Lim, F. T. Wong, Expression and engineering of PET-degrading enzymes from Microbispora, Nonomuraea, and Micromonospora. Applied and Environmental Microbiology 89, e00632-23 (2023).

  3. B. Nicholas Chua, W. Mei Guo, H. Teng Wong, D. Siak-Wei Ow, P. Leng Ho, W. Koh, A. Koay, F. Tian Wong, A sweeter future: Using protein language models for exploring sweeter brazzein homologs. Food Chemistry 426, 136580 (2023).

  4. W. L. C. Koh, S. E. Poh, C. K. Lee, T. H. M. Chan, G. Yan, K. W. Kong, L. Lau, W. Y. T. Lee, C. Cheng, S. Hoon, Y. Seow, Towards a Rapid-Turnaround Low-Depth Unbiased Metagenomics Sequencing Workflow on the Illumina Platforms. Bioengineering 10, 520 (2023).

  5. L. C. W. Koh, Y. Seow, K. W. Kong, M. L. L. Lau, S. K. Kumar, G. Yan, C. K. Lee, B. Yan, P. A. Tambyah, S. Hoon, Sub genomic analysis of SARS-CoV-2 using short read amplicon-based sequencing. Frontiers in Genetics 14, 1086865 (2023).

  6. W. Chua, C. O. Marsh, S. E. Poh, W. LC. Koh, M. L. Y. Lee, L. F. Koh, X.-Z. E. Tang, P. See, Z. Ser, S. M. Wang, R. M. Sobota, T. L. Dawson, Y. W. Yew, S. Thng, A. J. O’Donoghue, H. H. Oon, J. E. Common, H. Li, A Malassezia pseudoprotease dominates the secreted hydrolase landscape and is a potential allergen on skin. Biochimie, doi: 10.1016/j.biochi.2023.09.023 (2023).

  7. C. N. Mattar, W. Koh, Y. Seow, S. Hoon, A. Venkatesh, P. Dashraath, L. M. Lim, J. Ong, R. Lee, N. Johana, BNT162B2 COVID-19 mRNA vaccination did not promote substantial anti-syncytin-1 antibody production nor mRNA transfer to breast milk in an exploratory pilot study. Annals of the Academy of Medicine, òòò½Íø51, 309–312 (2022).

  8. W. Koh, S. Hoon, MapCell: learning a comparative cell type distance metric with siamese neural nets with applications toward cell-type identification across experimental datasets. Frontiers in Cell and Developmental Biology 9, 767897 (2021).