Abstract Scientific inference of higher-order biological, environmental, ecological, and therapeutic states remains challenging because traditional laboratory methods often rely on isolated analyte measurements that fail to capture dynamic, multivariable, and interaction-driven system behavior. This technical report introduces systems and methods for inferring these states from optical interaction signatures and their temporal dynamics using high-frequency, distributed, and l

Abstract Scientific reproducibility remains a major challenge across laboratory research, decentralized diagnostics, pharmaceutical manufacturing, autonomous laboratories, and industrial quality-control systems. Existing electronic laboratory notebooks (ELNs), laboratory information management systems (LIMS), and automation frameworks primarily record endpoint results or commanded actions, but frequently fail to capture the full contextual and executable state of experimental

Abstract Natural products represent a vast and underutilized source of therapeutic candidates across multiple disease domains. However, traditional discovery approaches often prioritize isolated potency or target affinity without sufficient consideration of human physiology, delivery constraints, or translational feasibility. We present a physiology-first AI framework for natural compound discovery that integrates multi-source data, multi-model ranking, and human-guided arb

Abstract Many chronic and heterogeneous diseases are driven by multiple interacting biological processes, yet both clinical care and therapeutic development are often organized around single-target paradigms. While reductionist approaches have generated important advances, they may be insufficient when parallel pathways sustain pathology, when patient subgroups differ biologically, or when existing regimens already partially cover selected targets. This paper is also availab

Abstract Recent advances in AI-driven drug discovery have led to widespread narratives suggesting that a single model or platform can generate viable therapeutic candidates and, when combined with automated laboratory systems, rapidly progress to clinical development. These narratives often imply that AI-driven design coupled with robotic execution can substantially compress the path to Phase I trials and accelerate the treatment of complex diseases within a few years. Howeve

Intellicite Labs traces its origins back to late 2023, before the current wave of large language model–driven systems had fully taken shape. In November 2023, Dr. Melinda B. Chu developed and documented an early architecture for what would later become known as an “autonomous scientist” system—an integrated, multi-model framework designed to emulate how real scientific discovery occurs across domains. This work was formalized in a USPTO provisional filing and submitted the f