Neil Y. C. Lin

Combination therapies are key to overcoming resistance to androgen receptor (AR) signaling inhibitors in prostate cancer. Current paradigms for developing synergistic therapies, however, remain chronically inefficient and resource‐intensive due to the prohibitive scale of the combinatorial screening space and a lack of computational frameworks for navigating signaling crosstalk. This work introduces a hybrid in silico and in vitro lead discovery platform that integrates knowledge‐augmented large language models (LLMs) with an oxygen‐supplemented 3D spheroid system. By comparing compound mechanism‐of‐action annotations with disease‐relevant signaling crosstalk, the LLM framework nominates drug pairs with predictive performance and interpretable, pathway‐based rationales. This computational pipeline is complemented by an engineered 3D spheroid model that utilizes oxygen supplementation to mitigate artifactual necrosis, a common confounder that masks synergistic signals in standard screening. Using this approach to screen 3,592 natural products, we identified berberine‐enzalutamide as an in vitro combination hit that re‐sensitized resistant prostate cancer cells to AR blockade. Molecular and transcriptomic profiling revealed changes in mTORC1 and AMPK signaling that were consistent with the pathway‐based hypothesis generated by LLM. These results establish proof of concept that mechanism‐informed language modeling coupled with 3D screening can prioritize and experimentally evaluate drug‐combination hypotheses at an early stage of discovery.

Epithelial tissues undergo dynamic transitions between fluid-like collective motion and mechanically jammed states during development, injury repair, and disease progression. However, the cellular programs that drive these transitions and regulate collective behavior remain unclear. Using a controlled crowding model integrated with live-cell imaging and time-resolved multiomics, we demonstrate that epithelial crowding triggers early metabolic changes characterized by increased mitochondrial pyruvate anaplerosis that precedes the jamming transition. Restricting mitochondrial pyruvate import increased collective cell motility and delayed jamming in crowded monolayers. This unjammed state is driven by enhanced cytoskeletal remodeling and requires RhoA-myosin II activity. Mechanistically, we show that elevated cytoskeletal signaling promotes macropinocytic uptake, which serves as a required feedback loop to maintain motility. These findings identify mitochondrial pyruvate utilization as an important regulatory input linking metabolic remodeling to the endocytic control of epithelial fluidity.

Single-cell multimodal omics offer unprecedented resolution of cellular networks, yet translating continuous computational attributions into structured, testable biological mechanisms remains a persistent bottleneck. To address this limitation, we introduce an analytical pipeline employing decision trees to discretize continuous neural network attributions into explicit regulatory thresholds. These boundaries then structurally constrain large language models, enabling them to integrate established literature with empirical data to synthesize context-specific hypotheses. Applying this continuous-to-discrete framework across sparse datasets yielded novel biological mechanisms. Specifically, the framework articulated a cytoskeletal gating hierarchy governing EGF-stimulated pathways, identified transcriptomic drivers of input resistance in cortical interneurons, and delineated translational logic predicting Ki-67 abundance within spatial transcriptomics. Retrospective benchmarking validated the capacity of the framework to autonomously reconstruct published regulatory logic. Supported by a locally deployable open-weight language model and a code-free interface, this approach establishes an auditable methodology to extract robust experimental hypotheses from high-dimensional single-cell data.

Deep learning is transforming microscopy, yet models often fail when applied to images from new instruments or acquisition settings. Conventional adversarial discriminative domain adaptation (ADDA) retrains entire networks, often disrupting learned semantic representations. Here, we overturn this paradigm by showing that adapting only the earliest convolutional layers, while freezing deeper layers, yields reliable transfer. Building on this principle, we introduce subnetwork image translation ADDA with automatic depth selection (SIT‐ADDA‐Auto), a self‐configuring framework that integrates shallow‐layer adversarial alignment with predictive uncertainty to automatically select adaptation depth without target labels. We demonstrate robustness via multimetric evaluation, blinded expert assessment, and uncertainty‐depth ablations. Across exposure and illumination shifts, cross‐instrument transfer, and multiple stains, SIT‐ADDA improves prediction fidelity and downstream segmentation over full‐encoder adaptation and nonadversarial baselines, with reduced drift of semantic features. Our results provide a design rule for label‐free adaptation in microscopy and a recipe for field settings; the code is publicly available.

Background: Artificial intelligence enhances pathology screening efficiency, yet clinical adoption remains limited because most systems operate as opaque black boxes. We aim to resolve this opacity by establishing a framework that generates transparent, evidence-linked reasoning to support diagnostic auditing. Methods: We present a framework that shifts off-the-shelf multimodal large language models from passive pattern recognition to active diagnostic reasoning. Using small labeled subsets from breast and prostate cancer datasets, we employ a two-phase self-learning process to derive diagnostic criteria without updating model weights. We integrate expert feedback from board-certified pathologists to ensure the generated descriptions align with established medical standards. Results: Here we show that our framework produces audit-ready rationales while achieving over 90% accuracy in distinguishing normal tissue from invasive carcinoma. Beyond binary classification, the model effectively differentiates complex subtypes like ductal carcinoma in situ by autonomously identifying hallmark histological features, including nuclear irregularities and structural disruption. These computer-generated descriptions closely match expert assessments. Our approach delivers substantial performance gains over conventional baselines and adapts effectively across diverse tissue types and independent foundation models. Conclusions: By uniting visual understanding with reasoning, our framework provides a promising approach for clinically trustworthy artificial intelligence. This framework helps bridge the gap between opaque classifiers and auditable systems, suggesting a viable path toward evidence-linked interpretation in medical workflows.

Epithelial tissues undergo dynamic transitions between fluid-like collective motion and mechanically jammed states during development, injury repair, and disease progression. However, the cellular programs that drive these transitions and regulate collective behavior remain unclear. Using a controlled crowding model integrated with live-cell imaging and time-resolved multi-omics, we demonstrate that epithelial crowding triggers early metabolic changes characterized by increased mitochondrial pyruvate anaplerosis that precedes the jamming transition. Functional inhibition of mitochondrial pyruvate import is sufficient to sustain collective cell motility, impeding jamming transition in crowded cells. This unjammed state is driven by enhanced cytoskeletal remodeling and requires RhoA-myosin II activity. Mechanistically, we show that elevated cytoskeletal signaling promotes macropinocytic uptake, which serves as a required feedback loop to maintain motility. These findings identify mitochondrial pyruvate utilization as a key regulator that links metabolic remodeling to the endocytic control of epithelial fluidity.

Resistance to androgen receptor inhibitors remains a primary challenge in prostate cancer treatment, yet identifying synergis-tic co-therapies is hindered by immense combinatorial search spaces and the limited interpretability of predictive computation models. Here, we developed an integrated discovery-validation axis coupling knowledge-augmented large language models with oxygen-supplemented 3D spheroid assays. By leveraging inherent model stochasticity, our framework measures the degree of consensus across independent predictions to establish a formal metric for predictive accuracy. This principle enables high-throughput assessment of complex signaling crosstalk, yielding mechanistic rationales for all predictions and defining a high-confidence zone that minimizes experimental attrition. Utilizing this approach to screen 3,592 natural products, we identified a previously unrecognized synergy between berberine and enzalutamide that re-sensitizes resistant cells. Validation confirms that berberine perturbs the PI3K/AKT/mTOR and AMPK axes, a finding consistent with the mechanistic rationales computationally derived by the framework. Integrating interpretable AI with physiologically relevant 3D screening provides a scalable methodology for the rational discovery of synergistic therapies. Significance: Integrating mechanistic AI with oxygenated 3D screening, we identify a novel berberine-enzalutamide synergy. This framework resolves complex signaling dependencies, providing a scalable, transparent methodology for the rational discovery of effective combination therapies.

AI tools in pathology have improved screening throughput, standardized quantification, and revealed prognostic patterns that inform treatment. However, adoption remains limited because most systems still lack the human-readable reasoning needed to audit decisions and prevent errors. We present RECAP-PATH, an interpretable framework that establishes a self-learning paradigm, shifting off-the-shelf multimodal large language models from passive pattern recognition to evidence-linked diagnostic reasoning. At its core is a two-phase learning process that autonomously derives diagnostic criteria: diversification expands pathology-style explanations, while optimization refines them for accuracy. This self-learning approach requires only small labeled sets and no white-box access or weight updates to generate cancer diagnoses. Evaluated on breast and prostate datasets, RECAP-PATH produced rationales aligned with expert assessment and delivered substantial gains in diagnostic accuracy over baselines. By uniting visual understanding with reasoning, RECAP-PATH provides clinically trustworthy AI and demonstrates a generalizable path toward evidence-linked interpretation.