An old cancer drug's degrading new look: Typically, cancer drugs that help only a small number of patients in clinical trials are not pursued. This might change in a future world of precision medicine, where biomarkers will match specific drugs to the patients most likely to respond. Han et al. identified the mechanism of action of a cancer drug called indisulam, a sulfonamide tested previously in patients with solid tumors. Indisulam and related sulfonamides killed cells by disrupting precursor mRNA splicing. The drugs targeted a specific RNA splicing factor for degradation by “gluing” it to the CUL4-DCAF15 ubiquitin ligase. Experiments with cancer cell lines suggest that future clinical trials of these drugs should focus on leukemias and lymphomas with high DCAF15 expression levels. Science , this issue p. eaal3755

Existing natural language processing (NLP) methods to convert free-text clinical notes into structured data often require problem-specific annotations and model training. This study aims to evaluate ChatGPT’s capacity to extract information from free-text medical notes efficiently and comprehensively. We developed a large language model (LLM)-based workflow, utilizing systems engineering methodology and spiral “prompt engineering” process, leveraging OpenAI’s API for batch querying ChatGPT. We evaluated the effectiveness of this method using a dataset of more than 1000 lung cancer pathology reports and a dataset of 191 pediatric osteosarcoma pathology reports, comparing the ChatGPT-3.5 (gpt-3.5-turbo-16k) outputs with expert-curated structured data. ChatGPT-3.5 demonstrated the ability to extract pathological classifications with an overall accuracy of 89%, in lung cancer dataset, outperforming the performance of two traditional NLP methods. The performance is influenced by the design of the instructive prompt. Our case analysis shows that most misclassifications were due to the lack of highly specialized pathology terminology, and erroneous interpretation of TNM staging rules. Reproducibility shows the relatively stable performance of ChatGPT-3.5 over time. In pediatric osteosarcoma dataset, ChatGPT-3.5 accurately classified both grades and margin status with accuracy of 98.6% and 100% respectively. Our study shows the feasibility of using ChatGPT to process large volumes of clinical notes for structured information extraction without requiring extensive task-specific human annotation and model training. The results underscore the potential role of LLMs in transforming unstructured healthcare data into structured formats, thereby supporting research and aiding clinical decision-making.

A community computational challenge generates algorithms to predict activity of drug combinations. Recent therapeutic successes have renewed interest in drug combinations, but experimental screening approaches are costly and often identify only small numbers of synergistic combinations. The DREAM consortium launched an open challenge to foster the development of in silico methods to computationally rank 91 compound pairs, from the most synergistic to the most antagonistic, based on gene-expression profiles of human B cells treated with individual compounds at multiple time points and concentrations. Using scoring metrics based on experimental dose-response curves, we assessed 32 methods (31 community-generated approaches and SynGen), four of which performed significantly better than random guessing. We highlight similarities between the methods. Although the accuracy of predictions was not optimal, we find that computational prediction of compound-pair activity is possible, and that community challenges can be useful to advance the field of in silico compound-synergy prediction.

Purpose: Prospectively identifying who will benefit from adjuvant chemotherapy (ACT) would improve clinical decisions for non–small cell lung cancer (NSCLC) patients. In this study, we aim to develop and validate a functional gene set that predicts the clinical benefits of ACT in NSCLC. Experimental Design: An 18-hub-gene prognosis signature was developed through a systems biology approach, and its prognostic value was evaluated in six independent cohorts. The 18-hub-gene set was then integrated with genome-wide functional (RNAi) data and genetic aberration data to derive a 12-gene predictive signature for ACT benefits in NSCLC. Results: Using a cohort of 442 stage I to III NSCLC patients who underwent surgical resection, we identified an 18-hub-gene set that robustly predicted the prognosis of patients with adenocarcinoma in all validation datasets across four microarray platforms. The hub genes, identified through a purely data-driven approach, have significant biological implications in tumor pathogenesis, including NKX2-1, Aurora Kinase A, PRC1, CDKN3, MBIP, and RRM2. The 12-gene predictive signature was successfully validated in two independent datasets (n = 90 and 176). The predicted benefit group showed significant improvement in survival after ACT (UT Lung SPORE data: HR = 0.34, P = 0.017; JBR.10 clinical trial data: HR = 0.36, P = 0.038), whereas the predicted nonbenefit group showed no survival benefit for 2 datasets (HR = 0.80, P = 0.70; HR = 0.91, P = 0.82). Conclusions: This is the first study to integrate genetic aberration, genome-wide RNAi data, and mRNA expression data to identify a functional gene set that predicts which resectable patients with non–small cell lung cancer will have a survival benefit with ACT. Clin Cancer Res; 19(6); 1577–86. ©2013 AACR.

SCLC accounts for almost 15% of lung cancer cases in the United States. Nomogram prognostic models could greatly facilitate risk stratification and treatment planning, as well as more refined enrollment criteria for clinical trials. We developed and validated a new nomogram prognostic model for SCLC patients using a large SCLC patient cohort from the National Cancer Database (NCDB). Clinical data for 24,680 SCLC patients diagnosed from 2004 to 2011 were used to develop the nomogram prognostic model. The model was then validated using an independent cohort of 9700 SCLC patients diagnosed from 2012 to 2013. The prognostic performance was evaluated using p value, concordance index and integrated area under the (time-dependent receiver operating characteristic) curve (AUC). The following variables were contained in the final prognostic model: age, sex, race, ethnicity, Charlson/Deyo score, TNM stage (assigned according to the American Joint Committee on Cancer [AJCC] eighth edition), treatment type (combination of surgery, radiation therapy, and chemotherapy), and laterality. The model was validated in an independent testing group with a concordance index of 0.722 ± 0.004 and an integrated area under the curve of 0.79. The nomogram model has a significantly higher prognostic accuracy than previously developed models, including the AJCC eighth edition TNM-staging system. We implemented the proposed nomogram and four previously published nomograms in an online webserver. We developed a nomogram prognostic model for SCLC patients, and validated the model using an independent patient cohort. The nomogram performs better than earlier models, including models using AJCC staging.

Background: Given the lack of a complete and comprehensive library of microbial reference genomes, determining the functional profile of diverse microbial communities is challenging. The available functional analysis pipelines lack several key features: (i) an integrated alignment tool, (ii) operon-level analysis, and (iii) the ability to process large datasets. Results: Here we introduce our open-sourced, stand-alone functional analysis pipeline for analyzing whole metagenomic and metatranscriptomic sequencing data, FMAP (Functional Mapping and Analysis Pipeline). FMAP performs alignment, gene family abundance calculations, and statistical analysis (three levels of analyses are provided: differentially-abundant genes, operons and pathways). The resulting output can be easily visualized with heatmaps and functional pathway diagrams. FMAP functional predictions are consistent with currently available functional analysis pipelines. Conclusion: FMAP is a comprehensive tool for providing functional analysis of metagenomic/metatranscriptomic sequencing data. With the added features of integrated alignment, operon-level analysis, and the ability to process large datasets, FMAP will be a valuable addition to the currently available functional analysis toolbox. We believe that this software will be of great value to the wider biology and bioinformatics communities.