Ten quick tips for harnessing the power of ChatGPT in computational biology

Lubiana, Tiago; Silva, Rafael Lopes Paixão da; Silva, Juan Carlo Santos e; Gonçalves, André Nicolau Aquime; Maracaja-Coutinho, Vinícius; Nakaya, Hidehiko

doi:10.1371/journal.pcbi.1011319

Cited by 34 publications

(21 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lubiana et al (2023) did an initial attempt to organize scientifically all the information going around about chatbots in computational biology (bioinformatics). This is a very important endeavour since as those chatbots gain attention, also false claims and exaggerations may come to the surface and it is possible to find unrealistic expectations.…”

Section: Literature Reviewmentioning

confidence: 99%

Robodoc: a conversational-AI based app for medical conversations

Guerra Pires

2024

Preprint

View full text Add to dashboard Cite

Artificial Intelligence (AI) evolved in trends. Currently, the trend is Conversational Artificial Intelligence (CAI). Those models of AI are focused on text-related tasks, and their commonest applications are chatbots. On this paper, we explore a smart chatbot using the Large Language Models (LLMs) from openAI. I have used a tool called Teachable Machine (TM) from Google to apply transfer learning and create image-based models. I have built two image-based model: for X-ray and for OCT. The model of X-ray is able to detect viral and bacterial pneumonia, whereas the Optical coherence tomography (OCT) model can detect Drusen, Choroidal Neovascularization (CNV) and (Diabetic Macular Edema DME) conditions on the patient’s eyes image. I have also used TensorFlow.js from Google to create a diabetes detection model. All those models are integrated into a chatbot, that according to the message entered by a user, is able to use the models intelligently. Our results show a good integration between the models and the chatbot, with slight deviations from the expected behaviors. For the OCT model, we have also tested a stub function for medical appointments done by the bot, based on how serious is the patient condition. The future of artificial intelligence are public APIs, as I have shown that a complex model can be built, without a complex research infrastructure, and with low costs. Bioinformatics may have gained a new supporter towards more friendly interfaces on bioinformatics.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Robodoc: a conversational-AI based app for medical conversations

Guerra Pires

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…ChatGPT, often regarded as a Swiss Army Knife for educators, embodies a multifaceted tool capable of transforming educational practices across lesson planning, instruction, assessment, and communication [20]; [21]; [22]; [23]. It helps the teacher in lesson planning [24]; [25].…”

Section: Genai Serves Both Teachers and Students In Different Waysmentioning

confidence: 99%

Comparative Analysis of Generative Pre-Trained Transformers Responses to Coastal Ecosystem Questions: Implications for GenAI in Environmental Education

Gopal,

Toshniwal,

Kaufman

et al. 2024

Preprint

View full text Add to dashboard Cite

This study presents a comparative analysis of two leading large language models (LLMs), Google’s Bard, powered by the Gemini model, and OpenAI’s ChatGPT 4.0, in the context of their responses to coastal ecosystem science undergraduate student education. Fifty questions related to coastal ecosystem management were posed to each LLM. Expert assessments evaluated the responses of the LLMs based on five key metrics: accuracy, relevance, depth, creativity, and semantic clarity. Knowledge graphs provided a structured framework for assessing and visualizing the AI responses. The analysis identified the strengths and weaknesses of each LLM in addressing complex environmental issues. The findings contribute to a deeper understanding of LLMs’ potential applications in environmental science education and scientific communication. This study acknowledges limitations, such as the inherent subjectivity of expert assessments and the potential for bias within the knowledge graphs used for evaluation. Future research directions include investigating the effectiveness of LLMs in personalized learning environments and exploring their potential for generating educational content tailored to diverse audiences.

show abstract

“…Meeting the growing demand for large data sets requires the development of more efficient and accurate methods, as well as deeper investigations into the integration of artificial intelligence and machine learning technologies into phylogenetic tree construction. Encouragingly, the use of advanced large language models (LLMs) [119], such as OpenAI's ChatGPT [120], known for its exceptional language processing and programming capabilities, offers promising prospects for advancing phylogenetic research. Continued optimization of existing phylogenetic analysis methods and exploration of new techniques within the R programming environment will enable researchers to harness large amounts of data for iterative analysis, resulting in the construction of more robust and comprehensive phylogenetic trees that accurately reflect the evolutionary relationships between species.…”

Section: Summary and Perspectivesmentioning

confidence: 99%

Common Methods for Phylogenetic Tree Construction and Their Implementation in R

Zou,

Zhang,

Zeng

et al. 2024

Bioengineering

View full text Add to dashboard Cite

A phylogenetic tree can reflect the evolutionary relationships between species or gene families, and they play a critical role in modern biological research. In this review, we summarize common methods for constructing phylogenetic trees, including distance methods, maximum parsimony, maximum likelihood, Bayesian inference, and tree-integration methods (supermatrix and supertree). Here we discuss the advantages, shortcomings, and applications of each method and offer relevant codes to construct phylogenetic trees from molecular data using packages and algorithms in R. This review aims to provide comprehensive guidance and reference for researchers seeking to construct phylogenetic trees while also promoting further development and innovation in this field. By offering a clear and concise overview of the different methods available, we hope to enable researchers to select the most appropriate approach for their specific research questions and datasets.

show abstract

Ten quick tips for harnessing the power of ChatGPT in computational biology

Cited by 34 publications

References 22 publications

Robodoc: a conversational-AI based app for medical conversations

Robodoc: a conversational-AI based app for medical conversations

Comparative Analysis of Generative Pre-Trained Transformers Responses to Coastal Ecosystem Questions: Implications for GenAI in Environmental Education

Common Methods for Phylogenetic Tree Construction and Their Implementation in R

Contact Info

Product

Resources

About