<?xml version="1.0" encoding="UTF-8" ?>
<xml>
<records>
<record>
<title>TraitGenePathAna: The AI-Powered biological trait analysis platform</title>
<authors>
<author>WenJun Zhang</author>
</authors>
<affiliations>
<affiliation>
School of Life Sciences, Sun Yat-sen University, Guangzhou, China
</affiliation>
</affiliations>
<journal>Network Biology</journal>
<issn>ISSN 2220-8879</issn>
<homepage>http://www.iaees.org/publications/journals/nb/online-version.asp</homepage>
<year>2026</year>
<volume>16</volume>
<issue>2</issue>
<startpage>49</startpage>
<endpage>81</endpage>
<publisher>International Academy of Ecology and Environmental Sciences</publisher>
<location>Hong Kong</location>
<date>
<received>6 December 2025</received>
<accepted>18 December 2025</accepted>
<published>1 June 2026</published>
</date>
<keywords>
<keyword>Artificial Intelligence (AI)</keyword>
<keyword>biological trait</keyword>
<keyword>genes, pathways</keyword>
<keyword>web-based tool</keyword>
</keywords>
<abstract>
The AI-Powered biological trait analysis platform, TraitGenePathAna, is a single-page web application that helps a user explore the biology behind a trait (e.g., longevity, disease resistance) for a chosen species (e.g., Homo sapiens, Drosophila melanogaster). It does this by sending a structured prompt to an LLM provider (DeepSeek or Google Gemini, etc.) and then presenting the model's response in a multi-tab results UI: (1) Overview: summary, significance, broad context; (2) Genetics: key genes, loci, heritability and gene-level discussion; (3) Pathways: molecular mechanisms, signaling cascades, network view; (4) Interventions: potential strategies and caveats (research, ethics, feasibility). In addition, the platform can conduct inferences on hidden rules, patterns, and relationships.
</abstract>
<url>http://www.iaees.org/publications/journals/nb/articles/2026-16(2)/TraitGenePathAna.pdf</url>
</record>
</records>
</xml>
