The model student: GPT-4 performance on graduate biomedical science exams.

The GPT-4 large language model (LLM) and ChatGPT chatbot have emerged as accessible and capable tools for generating English-language text in a variety of formats. GPT-4 has previously performed well when applied to questions from multiple standardized examinations. However, further evaluation of trustworthiness and accuracy of GPT-4 responses across various knowledge domains is essential before its use as a reference resource. Here, we assess GPT-4 performance on nine graduate-level examinations in the biomedical sciences (seven blinded), finding that GPT-4 scores exceed the student average in seven of nine cases and exceed all student scores for four exams. GPT-4 performed very well on fill-in-the-blank, short-answer, and essay questions, and correctly answered several questions on figures sourced from published manuscripts. Conversely, GPT-4 performed poorly on questions with figures containing simulated data and those requiring a hand-drawn answer. Two GPT-4 answer-sets were flagged as plagiarism based on answer similarity and some model responses included detailed hallucinations. In addition to assessing GPT-4 performance, we discuss patterns and limitations in GPT-4 capabilities with the goal of informing design of future academic examinations in the chatbot era.

Peptide-based capture-and-release purification of extracellular vesicles and statistical algorithm enabled quality assessment.

Circulating extracellular vesicles (EVs) have gained significant attention for discovering tumor biomarkers. However, isolating EVs with well-defined homogeneous populations from complex biological samples is challenging. Different isolation methods have been found to derive different EV populations carrying different molecular contents, which confounds current investigations and hinders subsequent clinical translation. Therefore, standardizing and building a rigorous assessment of isolated EV quality associated with downstream molecular analysis is essential. To address this need, we introduce a statistical algorithm (ExoQuality Index, EQI) by integrating multiple EV characterizations (size, particle concentration, zeta potential, total protein, and RNA), enabling direct EV quality assessment and comparisons between different isolation methods. We also introduced a novel capture-release isolation approach using a pH-responsive peptide conjugated with NanoPom magnetic beads (ExCy) for simple, fast, and homogeneous EV isolation from various biological fluids. Bioinformatic analysis of next-generation sequencing (NGS) data of EV total RNAs from pancreatic cancer patient plasma samples using our novel EV isolation approach and quality index strategy illuminates how this approach improves the identification of tumor associated molecular markers. Results showed higher human mRNA coverage compared to existing isolation approaches in terms of both pancreatic cancer pathways and EV cellular component pathways using gProfiler pathway analysis. This study provides a valuable resource for researchers, establishing a workflow to prepare and analyze EV samples carefully and contributing to the advancement of reliable and rigorous EV quality assessment and clinical translation.

Towards artificial intelligence-enabled extracellular vesicle precision drug delivery.

Extracellular Vesicles (EVs), particularly exosomes, recently exploded into nanomedicine as an emerging drug delivery approach due to their superior biocompatibility, circulating stability, and bioavailability in vivo. However, EV heterogeneity makes molecular targeting precision a critical challenge. Deciphering key molecular drivers for controlling EV tissue targeting specificity is in great need. Artificial intelligence (AI) brings powerful prediction ability for guiding the rational design of engineered EVs in precision control for drug delivery. This review focuses on cutting-edge nano-delivery via integrating large-scale EV data with AI to develop AI-directed EV therapies and illuminate the clinical translation potential. We briefly review the current status of EVs in drug delivery, including the current frontier, limitations, and considerations to advance the field. Subsequently, we detail the future of AI in drug delivery and its impact on precision EV delivery. Our review discusses the current universal challenge of standardization and critical considerations when using AI combined with EVs for precision drug delivery. Finally, we will conclude this review with a perspective on future clinical translation led by a combined effort of AI and EV research.