Conor Messer

All Publications

• Detection of heterogeneous resistance mechanisms to tyrosine kinase inhibitors from cell-free DNA CELL GENOMICS Parsons, H. A., Messer, C., Santos, K., Weiss, J., Merrell, D., Danysh, B. P., Hughes, M. E., Kirkner, G. J., Patel, A., Hess, J., Sendrick, K., Stewart, C., Grant, E., Schlueter-Kuck, K., Grinshpun, A., Wagle, N., Veeraraghavan, J., Leone, J., Freedman, R. A., Metzger, O., Schiff, R., Winer, E. P., Tolaney, S. M., Rimawi, M., Krop, I. E., Getz, G., Lin, N. U. 2025; 5 (12): 100987

  Abstract

  Though there has been substantial progress in the development of anti-human epidermal growth factor receptor 2 (HER2) therapies to treat HER2-positive metastatic breast cancer (MBC) within the past two decades, most patients still experience disease progression and cancer-related death. HER2-directed tyrosine kinase inhibitors can be highly effective therapies for patients with HER2-positive MBC; however, an understanding of resistance mechanisms is needed to better inform treatment approaches. We performed whole-exome sequencing on 111 patients with 73 tumor biopsies and 120 cell-free DNA samples to assess mechanisms of resistance. In 11 of 26 patients with acquired resistance, we identified alterations in previously characterized genes, such as PIK3CA and ERBB2, that could explain treatment resistance. Mutations in growing subclones identified potential mechanisms of resistance in 5 of 26 patients and included alterations in ESR1, FGFR2, and FGFR4. Additional studies are needed to assess the functional role and clinical utility of these alterations in driving resistance.

  View details for DOI 10.1016/j.xgen.2025.100987

  View details for Web of Science ID 001641070900001

  View details for PubMedID 40930104

• Red teaming ChatGPT in medicine to yield real-world insights on model behavior. NPJ digital medicine Chang, C. T., Farah, H., Gui, H., Rezaei, S. J., Bou-Khalil, C., Park, Y. J., Swaminathan, A., Omiye, J. A., Kolluri, A., Chaurasia, A., Lozano, A., Heiman, A., Jia, A. S., Kaushal, A., Jia, A., Iacovelli, A., Yang, A., Salles, A., Singhal, A., Narasimhan, B., Belai, B., Jacobson, B. H., Li, B., Poe, C. H., Sanghera, C., Zheng, C., Messer, C., Kettud, D. V., Pandya, D., Kaur, D., Hla, D., Dindoust, D., Moehrle, D., Ross, D., Chou, E., Lin, E., Haredasht, F. N., Cheng, G., Gao, I., Chang, J., Silberg, J., Fries, J. A., Xu, J., Jamison, J., Tamaresis, J. S., Chen, J. H., Lazaro, J., Banda, J. M., Lee, J. J., Matthys, K. E., Steffner, K. R., Tian, L., Pegolotti, L., Srinivasan, M., Manimaran, M., Schwede, M., Zhang, M., Nguyen, M., Fathzadeh, M., Zhao, Q., Bajra, R., Khurana, R., Azam, R., Bartlett, R., Truong, S. T., Fleming, S. L., Raj, S., Behr, S., Onyeka, S., Muppidi, S., Bandali, T., Eulalio, T. Y., Chen, W., Zhou, X., Ding, Y., Cui, Y., Tan, Y., Liu, Y., Shah, N., Daneshjou, R. 2025; 8 (1): 149

  Abstract

  Red teaming, the practice of adversarially exposing unexpected or undesired model behaviors, is critical towards improving equity and accuracy of large language models, but non-model creator-affiliated red teaming is scant in healthcare. We convened teams of clinicians, medical and engineering students, and technical professionals (80 participants total) to stress-test models with real-world clinical cases and categorize inappropriate responses along axes of safety, privacy, hallucinations/accuracy, and bias. Six medically-trained reviewers re-analyzed prompt-response pairs and added qualitative annotations. Of 376 unique prompts (1504 responses), 20.1% were inappropriate (GPT-3.5: 25.8%; GPT-4.0: 16%; GPT-4.0 with Internet: 17.8%). Subsequently, we show the utility of our benchmark by testing GPT-4o, a model released after our event (20.4% inappropriate). 21.5% of responses appropriate with GPT-3.5 were inappropriate in updated models. We share insights for constructing red teaming prompts, and present our benchmark for iterative model assessments.

  View details for DOI 10.1038/s41746-025-01542-0

  View details for PubMedID 40055532

  View details for PubMedCentralID 10564921