Competitions & evaluations

This competition challenges scientists, molecular biologists, and early-career researchers to push the boundaries of plasmid design by creating innovative, functionally optimized plasmid construct blueprints using advanced AI-assisted methodologies. Participants will leverage the Plasmid Construct GPT—a sophisticated master prompt optimizer that structures user requests through Lyra 4-D analysis and generates operational plasmid construct blueprints—to design novel genetic constructs for research, therapeutic, or educational applications. This challenge aims to foster innovation in synthetic biology and genetic engineering by demonstrating how AI-assisted design can enhance the precision, functionality, and creativity of plasmid construction. Participants will develop valuable skills in prompt engineering, structured biological design thinking, and AI-collaborative molecular biology while contributing to the advancement of genetic construct design methodologies. The competition emphasizes the creative application of prompt optimization techniques to transform abstract biological objectives into concrete, implementable plasmid construct blueprints that address real-world research or therapeutic challenges. By participating in this competition, researchers will explore the intersection of computational design and molecular biology, demonstrating how systematic thinking frameworks can optimize genetic construct architecture for enhanced expression, stability, safety, and functionality. Winning designs will showcase plasmid constructs that are not only scientifically sound but also innovative in their approach to solving complex biological engineering challenges.

This competition challenges scientists, biosafety officers, laboratory managers, and early-career researchers to develop comprehensive, evidence-based biosafety risk assessments using advanced AI-assisted methodologies. Participants will leverage the Biosafety Levels (BSL) weblet—an expert biosafety consultant providing guidance aligned with CDC, WHO, and NIH standards—to create rigorous risk assessments and containment protocols for complex laboratory scenarios involving infectious agents, recombinant DNA, or emerging pathogens. This challenge aims to foster excellence in laboratory safety practices by demonstrating how AI-assisted consultation can enhance the precision, comprehensiveness, and regulatory compliance of biosafety risk assessments. Participants will develop valuable skills in biosafety analysis, regulatory interpretation, containment protocol design, and evidence-based risk mitigation while contributing to the advancement of laboratory safety methodologies. The competition emphasizes the creative application of AI consultation to transform complex biosafety scenarios into actionable, compliant safety protocols that protect researchers, communities, and the environment. By participating in this competition, researchers will explore how systematic biosafety consultation frameworks can optimize laboratory safety practices, ensure regulatory compliance across multiple jurisdictions, and address emerging challenges in infectious disease research, synthetic biology, and gain-of-function studies. Winning submissions will showcase risk assessments that are not only scientifically rigorous and regulatory-compliant but also innovative in their approach to addressing complex biosafety challenges in modern research environments.

This competition challenges scientists, epidemiologists, public health analysts, and mathematical modellers to develop sophisticated, evidence-based epidemiological models using advanced AI-assisted methodologies. Participants will leverage the Epidemiological Modelling weblet—a domain-specific reasoning engine trained on mathematical models of infectious disease dynamics, real-world outbreak data, WHO/CDC guidelines, Bayesian inference, spatial simulations, and health policy frameworks—to create rigorous predictive models and policy recommendations for complex infectious disease scenarios. This challenge aims to foster excellence in epidemiological modelling by demonstrating how AI-assisted analysis can enhance the precision, robustness, and policy relevance of infectious disease models. Participants will develop valuable skills in mathematical modelling, Bayesian inference, spatial epidemiology, parameter estimation, uncertainty quantification, and evidence-based policy formulation while contributing to the advancement of public health decision-making methodologies. By participating in this competition, researchers will explore how systematic AI-assisted modelling frameworks can optimize outbreak response strategies, improve epidemic forecasting accuracy, inform resource allocation decisions, and evaluate intervention effectiveness across diverse epidemiological contexts. Winning submissions will showcase models that are not only mathematically rigorous and empirically validated but also innovative in their approach to addressing complex public health challenges such as emerging infectious diseases, vaccine distribution optimization, or spatial transmission dynamics. The competition emphasizes the creative application of AI consultation to transform complex epidemiological questions into actionable mathematical models that inform evidence-based health policy. Participants will demonstrate how sophisticated modelling approaches combined with AI-assisted reasoning can provide critical insights for pandemic preparedness, outbreak control, and public health intervention design.

This competition challenges doctoral candidates, computational biologists, geneticists, and statistical geneticists to develop sophisticated, evidence-based genomic analyses using advanced AI-assisted methodologies. Participants will leverage the Statistical Genomics weblet—a specialized interactive tool for Genome-wide Association Studies (GWAS) and Quantitative Trait Loci (QTL) analysis—to identify meaningful associations between genetic markers and complex traits, uncover novel genetic architectures, and translate findings into biological insights relevant for precision medicine and agricultural genomics. This challenge aims to foster excellence in statistical genomics by demonstrating how AI-assisted analysis can enhance the rigor, reproducibility, and biological interpretability of GWAS and QTL studies. Participants will develop valuable skills in genomic data analysis, statistical association testing, multiple testing correction, population structure analysis, heritability estimation, polygenic risk scoring, and functional annotation while contributing to the advancement of genomic discovery methodologies. By participating in this competition, researchers will explore how systematic AI-assisted genomic analysis frameworks can optimize variant discovery, improve statistical power, control for confounding factors, and translate genetic associations into actionable biological knowledge. Winning submissions will showcase analyses that are not only statistically rigorous and computationally sound but also innovative in their approach to addressing complex challenges in human genetics, plant breeding, or evolutionary genomics. The competition emphasizes the creative application of AI consultation to transform raw genomic data into meaningful biological discoveries that advance our understanding of genotype-phenotype relationships. Participants will demonstrate how sophisticated statistical genomics approaches combined with AI-assisted reasoning can provide critical insights for disease risk prediction, drug target identification, crop improvement, and personalized medicine.

This competition challenges doctoral candidates, computational biologists, single-cell genomics specialists, and bioinformaticians to develop sophisticated, accurate cell type annotation strategies for single-cell RNA sequencing (scRNA-seq) datasets using advanced AI-assisted methodologies. Participants will leverage the Cell Type Annotations weblet—a specialized tool for automating cell type identification using marker gene information across various tissues and species—to accurately classify cellular identities, discover novel cell states, and advance our understanding of cellular heterogeneity in complex biological systems. This challenge aims to foster excellence in single-cell data analysis by demonstrating how AI-assisted annotation can enhance the accuracy, consistency, and biological interpretability of cell type identification. Participants will develop valuable skills in scRNA-seq data preprocessing, dimensionality reduction, clustering, marker gene identification, cell type annotation, trajectory inference, and biological interpretation while contributing to the advancement of single-cell genomics methodologies. By participating in this competition, researchers will explore how systematic AI-assisted annotation frameworks can optimize cell type classification, improve annotation consistency across datasets, identify rare cell populations, and translate cellular heterogeneity into biological insights relevant for developmental biology, immunology, cancer research, and regenerative medicine. Winning submissions will showcase analyses that are not only computationally rigorous and biologically accurate but also innovative in their approach to addressing complex challenges in cellular identity determination. The competition emphasizes the creative application of AI consultation to transform raw single-cell transcriptomic data into comprehensive cellular atlases that advance our understanding of tissue organization, cell state transitions, and disease mechanisms. Participants will demonstrate how sophisticated single-cell analysis approaches combined with AI-assisted reasoning can provide critical insights for cell fate mapping, biomarker discovery, therapeutic target identification, and precision medicine.

This competition challenges early-career researchers, and advanced practitioners to develop production-ready industrial design solutions by drawing inspiration from the intricate and highly optimized systems found in nature. Participants will leverage the Bio-Inspired Industrial Design Custom GPT, a specialized AI tool, to translate principles of biophilia, biomimicry, and biodesign into tangible, manufacturable products. The goal of this challenge is to foster a new generation of design that not only meets human needs but also operates in harmony with ecological systems. By bridging the gap between biological science and industrial application, this competition seeks to uncover innovative solutions that are efficient, sustainable, and resilient. Successful submissions will represent the highest level of academic rigor and creative excellence, demonstrating the transformative potential of bio-inspired design in shaping a more sustainable future.