About this Research Topic
Traditional medicine (TM) encompasses a wealth of knowledge and practices used in prevention, diagnosis, improvement, or treatment of physical and mental illnesses. Despite its long-standing developments, traditional medicine research on all its aspects remains essential. Important challenges include variability or poorly defined composition of the preparations used (incl. lack of standardization), limited high quality data on efficacy, and conflicting perspectives on the integration of biomedical and traditional practices into modern integrative healthcare. Recently, artificial intelligence (AI) technology has advanced rapidly and found applications across various fields, including traditional medicine. The introduction of AI technology has brought unprecedented opportunities to traditional medicine by enhancing understanding, accuracy, and efficiency in various procedures. Advanced methods, such as big data analysis, machine learning (ML), and deep learning (DL), have significantly improved the success rate of identifying active compounds, understanding complex interactions, and predicting therapeutic outcomes of specific medicines including traditional ones.
For example, deep learning algorithms like convolutional neural networks (CNNs) and graph neural networks (GNNs), and generative AI models based on the Transformer architecture, are making remarkable progress in tasks such as molecular property prediction, virtual screening of traditional compounds, and identification of therapeutic targets. In traditional medicine, AI can discover promising active ingredients from vast herbal libraries, optimize their combinations, and predict their effects, greatly improving the efficiency of developing traditional medicines. Consequently, the research and application of AI technology in traditional medicine hold vast potential, promising significant and far-reaching impacts on the field of traditional medicine, fostering further development and innovation, and bringing positive changes to global health and healthcare.
Despite its transformative potential, AI-driven research and development in traditional medicine encounters several challenges:
1. Complex Biological and Chemical Variables: Traditional medicine involves intricate biological and chemical interactions, which inherently limit the predictive capabilities of AI algorithms. Experimental validation remains crucial to confirm AI predictions.
2. The complexity of predicting effects and designing drug leads: The scientific literature is overflowing with unreliable data linked to multiple experimental and design problems. Understanding traditional remedies using requires careful consideration of the validity of the pharmacological, toxicological, clinical, pharmacognostic/biological and chemical data that feed into the analysis.
3. The complexity and variability of traditional medical preparations poses specific and significant design and implementation challenges for AI algorithms.
4. Network Analysis Limitations: Network analysis in traditional medicine is often preliminary, potentially yielding non-specific findings. Metabolites such as polyphenols can interfere with analyses, leading to false-positive results.
5. Data and Model Dependency: AI technology's effectiveness hinges on the availability of high-quality data and advanced algorithms. The robustness and generalization capability of these models may be inadequate.
To advance and enrich discussions in this field, we invite original articles and reviews on the following topics, including but not limited to:
• AI Utilization in Traditional Medicine: Exploring deep learning, machine learning, and other AI algorithms for data processing, pharmacodynamic evaluation, and other aspects of traditional medicine.
• AI and Network Analysis in Traditional Medicine: Investigating herbal network relationship mining, network target positioning, network target navigation, and uncovering the complex mechanisms of traditional medicines via AI-driven network analysis.
• AI-driven redevelopment of Traditional medicines: Analyzing novel applications of existing traditional medicines and discovering potential therapeutic targets through AI technology.
• AI in Traditional Medicine Target Prediction: Predicting interactions between active ingredients and targets, identifying potential interactions between traditional compounds and noncoding RNAs, and related research using AI.
• Using AI to predict novel combination of Traditional Medicines: Analyzing and predicting effective combinations of traditional medicines for treating diseases using AI technology.
• Prospective Studies and Reviews: Forward-looking studies and comprehensive reviews on the research and application of AI in traditional medicine.
Important Note:
All contributions to this Research Topic must follow the guideline listed in this section:
• The introduction needs to describe the background of the research object focusing on the traditional or local use of a traditional medicine and provide bibliographical references that illustrate its recent application in general healthcare.
• Network studies must critically assess the pharmacological evidence to evaluate the potential effects of a preparation / herbal (medical) product and the limitations of the evidence.
• Purely in silico/AI-based studies are outside of our scope.
• In general, network analysis must be conducted in combination with experimental pharmacology (in vitro or in vivo) or are based on a sound body of experimental pharmacology.
• Chemical anti-oxidant assays like the DPPH or ABTS assay are of no pharmacological relevance, Therefore they can only be used a chemical-analytical assays without pharmacological claims.
• Please self-assess your MS using the ConPhyMP tool (https://ga-online.org/best-practice) and submit the relevant sections of the tool with your submission. You need to follow the standards established in the ConPhyMP statement Front. Pharmacol. 13:953205).
• All the manuscripts need to fully comply with the Four Pillars of Best Practice in Ethnopharmacology (you can freely download the full version here). Importantly, please ascertain that the ethnopharmacological context is clearly described (pillar 3d) and that the material investigated is characterized in detail (pillars 2 a and b).
The topic editor Jidong Lang was employed by the Tasly Pharmaceutical Group Co., Ltd. The remaining editors declare that the proposal was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
For example, deep learning algorithms like convolutional neural networks (CNNs) and graph neural networks (GNNs), and generative AI models based on the Transformer architecture, are making remarkable progress in tasks such as molecular property prediction, virtual screening of traditional compounds, and identification of therapeutic targets. In traditional medicine, AI can discover promising active ingredients from vast herbal libraries, optimize their combinations, and predict their effects, greatly improving the efficiency of developing traditional medicines. Consequently, the research and application of AI technology in traditional medicine hold vast potential, promising significant and far-reaching impacts on the field of traditional medicine, fostering further development and innovation, and bringing positive changes to global health and healthcare.
Despite its transformative potential, AI-driven research and development in traditional medicine encounters several challenges:
1. Complex Biological and Chemical Variables: Traditional medicine involves intricate biological and chemical interactions, which inherently limit the predictive capabilities of AI algorithms. Experimental validation remains crucial to confirm AI predictions.
2. The complexity of predicting effects and designing drug leads: The scientific literature is overflowing with unreliable data linked to multiple experimental and design problems. Understanding traditional remedies using requires careful consideration of the validity of the pharmacological, toxicological, clinical, pharmacognostic/biological and chemical data that feed into the analysis.
3. The complexity and variability of traditional medical preparations poses specific and significant design and implementation challenges for AI algorithms.
4. Network Analysis Limitations: Network analysis in traditional medicine is often preliminary, potentially yielding non-specific findings. Metabolites such as polyphenols can interfere with analyses, leading to false-positive results.
5. Data and Model Dependency: AI technology's effectiveness hinges on the availability of high-quality data and advanced algorithms. The robustness and generalization capability of these models may be inadequate.
To advance and enrich discussions in this field, we invite original articles and reviews on the following topics, including but not limited to:
• AI Utilization in Traditional Medicine: Exploring deep learning, machine learning, and other AI algorithms for data processing, pharmacodynamic evaluation, and other aspects of traditional medicine.
• AI and Network Analysis in Traditional Medicine: Investigating herbal network relationship mining, network target positioning, network target navigation, and uncovering the complex mechanisms of traditional medicines via AI-driven network analysis.
• AI-driven redevelopment of Traditional medicines: Analyzing novel applications of existing traditional medicines and discovering potential therapeutic targets through AI technology.
• AI in Traditional Medicine Target Prediction: Predicting interactions between active ingredients and targets, identifying potential interactions between traditional compounds and noncoding RNAs, and related research using AI.
• Using AI to predict novel combination of Traditional Medicines: Analyzing and predicting effective combinations of traditional medicines for treating diseases using AI technology.
• Prospective Studies and Reviews: Forward-looking studies and comprehensive reviews on the research and application of AI in traditional medicine.
Important Note:
All contributions to this Research Topic must follow the guideline listed in this section:
• The introduction needs to describe the background of the research object focusing on the traditional or local use of a traditional medicine and provide bibliographical references that illustrate its recent application in general healthcare.
• Network studies must critically assess the pharmacological evidence to evaluate the potential effects of a preparation / herbal (medical) product and the limitations of the evidence.
• Purely in silico/AI-based studies are outside of our scope.
• In general, network analysis must be conducted in combination with experimental pharmacology (in vitro or in vivo) or are based on a sound body of experimental pharmacology.
• Chemical anti-oxidant assays like the DPPH or ABTS assay are of no pharmacological relevance, Therefore they can only be used a chemical-analytical assays without pharmacological claims.
• Please self-assess your MS using the ConPhyMP tool (https://ga-online.org/best-practice) and submit the relevant sections of the tool with your submission. You need to follow the standards established in the ConPhyMP statement Front. Pharmacol. 13:953205).
• All the manuscripts need to fully comply with the Four Pillars of Best Practice in Ethnopharmacology (you can freely download the full version here). Importantly, please ascertain that the ethnopharmacological context is clearly described (pillar 3d) and that the material investigated is characterized in detail (pillars 2 a and b).
The topic editor Jidong Lang was employed by the Tasly Pharmaceutical Group Co., Ltd. The remaining editors declare that the proposal was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Keywords: Artificial intelligence, Deep learning, Drug research and development, Machine learning
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
