Network Analysis and Natural Language Processing to Obtain a Landscape of the Scientific Literature on Materials Applications

Using network analysis and large-language models to obtain a landscape of the literature on dressing materials for wound healing: The predominance of chitosan and other biomacromolecules: A review

We present an overview of the literature on dressing materials for wound healing, combining network analysis and natural language processing using large language models. Contributions to this field come from a variety of research areas and journals, so we employed multiple strategies for searching the OpenAlex database to ensure that the most relevant papers were covered, while also focusing on the specific topic of interest. Citation networks were created from the retrieved papers, identifying clusters that represent major topics. Starting with broad searches on 'wound' and 'wound healing' we refined the focus to dressing materials by incorporating expert knowledge into the analysis. This approach also allowed for a comparison with fully automated analyses. The resulting landscape shows significant growth in this area in recent years, with most contributions coming from the Northern Hemisphere, particularly China and the USA. The most commonly used materials include gauze, hydrocolloids, chitosan-based hydrogels, foams, alginates, hydrofibers (e.g., those containing nanomaterials such as silver nanoparticles), composites, biomaterials, and skin substitutes. Research primarily focuses on the antibacterial properties of these materials and their application in treating burn-related wounds, which, along with diabetes, are common causes of chronic wounds.

Complexed hyaluronic acid-based nanoparticles in cancer therapy and diagnosis: Research trends by natural language processing

Hyaluronic acid (HA) is a popular surface modifier in targeted cancer delivery due to its receptor-binding abilities. However, HA alone faces limitations in lipid solubility, biocompatibility, and cell internalization, making it less effective as a standalone delivery system. This comprehensive study aimed to explore a dynamic landscape of complexation in HA-based nanoparticles in cancer therapy, examining diverse aspects from influential modifiers to emerging trends in cancer diagnostics. We discovered that certain active substances, such as 5-aminolevulinic acid, adamantane, and protamine, have been on trend in terms of their usage over the past decade. Dextran, streptavidin, and catechol emerge as intriguing conjugates for HA, coupled with nanostar, quantum dots, and nanoprobe structures for optimal drug delivery and diagnostics. Strategies like hypoxic conditioning, dual responsiveness, and pulse laser activation enhance controlled release, targeted delivery, and real-time diagnostic techniques like ultrasound imaging and X-ray computed tomography (X-ray CT). Based on our findings, conventional bibliometric tools fail to highlight relevant topics in this area, instead producing merely abstract and broad-meaning keywords. Extraction using Named Entity Recognition and topic search with Latent Dirichlet Allocation successfully revealed five representative topics with the ability to exclude irrelevant keywords. A shift in research focuses from optimizing chemical toxicity to particular targeting tactics and precise release mechanisms is evident. These findings reflect the dynamic landscape of HA-based nanoparticle research in cancer therapy, emphasizing advancements in targeted drug delivery, therapeutic efficacy, and multimodal diagnostic approaches to improve overall patient outcomes.

Quantitative Topic Analysis of Materials Science Literature Using Natural Language Processing

Materials science research has garnered extensive attention from industry, society, policy, and academia. However, understanding the research landscape and extracting strategic insights are challenging due to the increasing diversity and volume of publications. This study proposes a natural language processing-based protocol for extracting text-encoded topics from a large volume of scientific literature, uncovering research interests of scientific communities, as well as convergence trends. We report a topic map, representing the materials science research landscape with text-mined 257 topics regarding biocompatible materials, structural materials, electrochemistry, or photonics. We analyze the topic map in terms of national research interests in materials science, revealing competitive positions and strategies of active nations. For example, it is found that the increasing trend of research interest in machine learning topic was captured in the United States earlier than other nations. Similarly, our journal-level analyses serve as reference information for journal recommendations and trend guidance, showing that the main topics and research interests of materials science journals slightly changed over time. Moreover, we build the topic association network which can highlight the status and future potential of interdisciplinary research, revealing research fields with high centrality in the network such as machine learning-enabled composite modeling, energy policy, or wearable electronics. This study offers insightful results on current and near-future materials science research landscapes, facilitating the understanding of stakeholders, amidst the fast-evolving and diverse knowledge of materials science.

Artificial Intelligence Agents for Materials Sciences

The artificial intelligence (AI) tools based on large-language models may serve as a demonstration that we are reaching a groundbreaking new paradigm in which machines themselves will generate knowledge autonomously. This statement is based on the assumption that the ability to master natural languages is the ultimate frontier for this new paradigm and perhaps an essential step to achieving the so-called general artificial intelligence. Autonomous knowledge generation implies that a machine will be able, for instance, to retrieve and understand the contents of the scientific literature and provide interpretations for existing data, allowing it to propose and address new scientific problems. While one may assume that the continued development of AI tools exploiting large-language models, with more data used for training, may lead these systems to learn autonomously, this learning can be accelerated by devising human-assisted strategies to deal with specific tasks. For example, strategies may be implemented for AI tools to emulate the analysis of multivariate data by human experts or in identifying and explaining patterns in temporal series. In addition to generic AI tools, such as Chat AIs, one may conceive personal AI agents, potentially working together, that are likely to serve end users in the near future. In this perspective paper, we discuss the development of this type of agent, focusing on its architecture and requirements. As a proof-of-concept, we exemplify how such an AI agent could work to assist researchers in materials sciences.