Thanawat Piyasawetkul

Thanawat Piyasawetkul

Pharmaceutical Sciences Student Skilled in AI

Publications

Journal Articles

AppHerb: Language Model for Recommending Traditional Thai Medicine

Published in AI, 2025

Abstract: Trust in Traditional Thai Medicine (TTM) among Thai people has been reduced due to a lack of objective standards and the susceptibility of the general population to false information. The emergence of generative artificial intelligence (Gen AI) has significantly impacted various industries, including traditional medicine. However, previous Gen AI models have primarily focused on prescription generation based on Traditional Chinese Medicine (TCM), leaving TTM unexplored. To address this gap, we propose a novel fast-learning fine-tuned language model fortified with TTM knowledge. We utilized textual data from two TTM textbooks, Wat Ratcha-orasaram Ratchaworawihan (WRO), and Tamra Osot Phra Narai (NR), to fine-tune Unsloth’s Gemma-2 with 9 billion parameters. We developed two specialized TTM tasks: treatment prediction (TrP) and herbal recipe generation (HRG). The TrP and HRG models achieved precision, recall, and F1 scores of 26.54%, 28.14%, and 24.00%, and 32.51%, 24.42%, and 24.84%, respectively. Performance evaluation against TCM-based generative models showed comparable precision, recall, and F1 results with a smaller knowledge corpus. We further addressed the challenges of utilizing Thai, a low-resource and linguistically complex language. Unlike English or Chinese, Thai lacks explicit sentence boundary markers and employs an abugida writing system without spaces between words, complicating text segmentation and generation. These characteristics pose significant difficulties for machine understanding and limit model accuracy. Despite these obstacles, our work establishes a foundation for further development of AI-assisted TTM applications and highlights both the opportunities and challenges in applying language models to traditional medicine knowledge systems in Thai language contexts.

Citation: Piyasawetkul, T., Tiyaworanant, S., & Srisongkram, T. (2025). AppHerb: Language Model for Recommending Traditional Thai Medicine. AI, 6(8), 170. https://doi.org/10.3390/ai6080170

Prediction of Spheroid Cell Death Using Fluorescence Staining and Convolutional Neural Networks

Published in Chemical Research in Toxicology, 2023

Abstract: Three-dimensional (3D) cell culture is emerging for drug design and drug screening. Skin toxicity is one of the most important assays for determining the toxicity of a compound before being used in skin application. Much work has been done to find an alternative assay without animal experiments. 3D cell culture is one of the methods that provides clinically relevant models with superior clinical translation compared to that of 2D cell culture. In this study, we developed a spheroid toxicity assay using keratinocyte HaCaT cells with propidium iodide and calcein AM. We also applied the transfer learning-containing convolutional neural network (CNN) to further determine spheroid cell death with fluorescence labeling. Our result shows that the morphologies of the spheroid are the key features in determining the apoptosis cell death of the HaCaT spheroid. Our CNN model provided good statistical measurement in terms of accuracy, precision, and recall in both validation and external test data sets. One can predict keratinocyte spheroid cell death if that spheroid image contains the fluorescence signals from propidium iodide and calcein AM. The CNN model can be accessed in the web application at https://qsarlabs.com/#spheroiddeath.

Citation: Srisongkram, T., Syahid, N. F., Piyasawetkul, T., Thirawatthanasak, P., Khamtang, P., Sawasnopparat, N., Tookkane, D., Weerapreeyakul, N., & Puthongking, P. (2023). Prediction of Spheroid Cell Death Using Fluorescence Staining and Convolutional Neural Networks. Chemical Research in Toxicology, 36(12), 1980–1989. https://doi.org/10.1021/acs.chemrestox.3c00257