RefAI: a GPT-powered retrieval-augmented generative tool for biomedical literature recommendation and summarization.

OBJECTIVES: Precise literature recommendation and summarization are crucial for biomedical professionals. While the latest iteration of generative pretrained transformer (GPT) incorporates 2 distinct modes-real-time search and pretrained model utilization-it encounters challenges in dealing with these tasks. Specifically, the real-time search can pinpoint some relevant articles but occasionally provides fabricated papers, whereas the pretrained model excels in generating well-structured summaries but struggles to cite specific sources. In response, this study introduces RefAI, an innovative retrieval-augmented generative tool designed to synergize the strengths of large language models (LLMs) while overcoming their limitations. MATERIALS AND METHODS: RefAI utilized PubMed for systematic literature retrieval, employed a novel multivariable algorithm for article recommendation, and leveraged GPT-4 turbo for summarization. Ten queries under 2 prevalent topics ("cancer immunotherapy and target therapy" and "LLMs in medicine") were chosen as use cases and 3 established counterparts (ChatGPT-4, ScholarAI, and Gemini) as our baselines. The evaluation was conducted by 10 domain experts through standard statistical analyses for performance comparison. RESULTS: The overall performance of RefAI surpassed that of the baselines across 5 evaluated dimensions-relevance and quality for literature recommendation, accuracy, comprehensiveness, and reference integration for summarization, with the majority exhibiting statistically significant improvements (P-values <.05). DISCUSSION: RefAI demonstrated substantial improvements in literature recommendation and summarization over existing tools, addressing issues like fabricated papers, metadata inaccuracies, restricted recommendations, and poor reference integration. CONCLUSION: By augmenting LLM with external resources and a novel ranking algorithm, RefAI is uniquely capable of recommending high-quality literature and generating well-structured summaries, holding the potential to meet the critical needs of biomedical professionals in navigating and synthesizing vast amounts of scientific literature.

Design, synthesis, and antitumor efficacy of novel 5-deazaflavin derivatives backed by kinase screening, docking, and ADME studies.

Novel 5-deazaflavins were designed as potential anticancer candidates. Compounds 4j, 4k, 5b, 5i, and 9f demonstrated high cytotoxicity against MCF-7 cell line with IC50 of 0.5-190nM. Compounds 8c and 9g showed preferential activity against Hela cells (IC50: 1.69 and 1.52 µM respectively). However, compound 5d showed notable potency against MCF-7 and Hela cell lines of 0.1 nM and 1.26 µM respectively. Kinase profiling for 4e showed the highest inhibition against a 20 kinase panel. Additionally, ADME prediction studies exhibited that compounds 4j, 5d, 5f, and 9f have drug-likeness criteria to be considered promising antitumor agents deserving of further investigation. SAR study showed that substitutions with 2-benzylidene hydra zino have a better fitting into PTK with enhanced antiproliferative potency. Noteworthy, the incorporation of hydrazino or ethanolamine moieties at position 2 along with small alkyl or phenyl at N-10, respectively revealed an extraordinary potency against MCF-7 cells with IC50 values in the nanomolar range.

Assessment of a Spatiotemporal Deep Learning Approach for Soil Moisture Prediction and Filling the Gaps in Between Soil Moisture Observations.

Soil moisture (SM) plays a significant role in determining the probability of flooding in a given area. Currently, SM is most commonly modeled using physically-based numerical hydrologic models. Modeling the natural processes that take place in the soil is difficult and requires assumptions. Besides, hydrologic model runtime is highly impacted by the extent and resolution of the study domain. In this study, we propose a data-driven modeling approach using Deep Learning (DL) models. There are different types of DL algorithms that serve different purposes. For example, the Convolutional Neural Network (CNN) algorithm is well suited for capturing and learning spatial patterns, while the Long Short-Term Memory (LSTM) algorithm is designed to utilize time-series information and to learn from past observations. A DL algorithm that combines the capabilities of CNN and LSTM called ConvLSTM was recently developed. In this study, we investigate the applicability of the ConvLSTM algorithm in predicting SM in a study area located in south Louisiana in the United States. This study reveals that ConvLSTM significantly outperformed CNN in predicting SM. We tested the performance of ConvLSTM based models by using a combination of different sets of predictors and different LSTM sequence lengths. The study results show that ConvLSTM models can predict SM with a mean areal Root Mean Squared Error (RMSE) of 2.5% and mean areal correlation coefficients of 0.9 for our study area. ConvLSTM models can also provide predictions between discrete SM observations, making them potentially useful for applications such as filling observational gaps between satellite overpasses.