Categories \ Biology
Saanvi Dogra, Jason Gao, Dishti Wadhwani, Risha Guha, Nithika Vivek, Lauren Chen, Anwita Bandaru, Shawn Kim, David Lanster
The field of synthetic biology makes significant contributions to healthcare, environmental engineering, and technology through the manipulation of cellular macromolecules and whole organisms. Oftentimes, these advancements are dependent upon biosensors to report on an activity of interest within a cell or to detect extracellular cues and report on them in a measurable way. This project undertaken as part of iGEM 2024 (Internationally Genetic Engineered Machines Competition 2024) centered around the choice of 10 small molecules related to environmental and human health with the goal of developing transcriptional biosensors to report on their concentrations. Each molecule was screened against a library of over 2000 promoter-GFP constructs in search of promoters responsive to each molecule. Further, a Deep Learning model was used to predict active promoter-molecule pairs and in silico putative hits from the screen were analyzed with molecular docking. While no robust biosensor hits were found for the molecules of interest, our work demonstrates a useful pipeline for further small molecule biosensor development.
10.69831/4a63597f50
Ryan Mehra, Anshoo Mehra
Large-language-model (LLM) “hallucinations” are usually condemned as reliability faults because they generate confident yet false statements [1]. Emerging research, however, finds that such confabulations mirror divergent thinking and can seed novel hypotheses [2, 3]. This study is conducted by an independent investigators with no physical laboratory but unlimited API access to OpenAI models(4o, 4o-mini, 4.1, 4.1-mini)—tests whether deliberately elicited hallucinations can accelerate medical innovation. We target three translational aims: (i) epistemological creativity for medicine, where speculative errors inspire fresh research questions; (ii) generative biomedical design, exemplified by hallucinated protein and drug candidates later validated in vitro [4]; and (iii) speculative clinical engineering, where imaginative missteps suggest prototypes such as infection resistant catheters [5]. A controlled prompt-engineering experiment compares a truth-constrained baseline to a hallucination-promoting condition across the four OpenAI models. Crucially, all outputs are scored for novelty and prospective clinical utility by an autonomous LLM-based “judge” system, adapted from recent self-evaluation frameworks [6], instead of human experts. The LLM judge reports that hallucination-friendly prompts yield 2–3× more ideas rated simultaneously novel and potentially useful, albeit with increased low-quality noise. These findings illustrate a cost-effective workflow in which consumer-accessible LLMs act both as idea generator and evaluator, expanding the biomedical creative search space while automated convergence techniques preserve epistemic rigor—reframing hallucination from flaw to feature in at-home medical R&D.
10.69831/e59eafc04e