Patient recruitment is challenging for clinical trials. We introduce TrialGPT, an end-to-end framework for zero-shot patient-to-trial matching with large language models. TrialGPT comprises three modules: it first performs large-scale filtering to retrieve candidate trials (TrialGPT-Retrieval); then predicts criterion-level patient eligibility (TrialGPT-Matching); and finally generates trial-level scores (TrialGPT-Ranking). We evaluate TrialGPT on three cohorts of 183 synthetic patients with over 75,000 trial annotations. TrialGPT-Retrieval can recall over 90% of relevant trials using less than 6% of the initial collection. Manual evaluations on 1015 patient-criterion pairs show that TrialGPT-Matching achieves an accuracy of 87.3% with faithful explanations, close to the expert performance. The TrialGPT-Ranking scores are highly correlated with human judgments and outperform the best-competing models by 43.8% in ranking and excluding trials. Furthermore, our user study reveals that TrialGPT can reduce the screening time by 42.6% in patient recruitment. Overall, these results have demonstrated promising opportunities for patient-to-trial matching with TrialGPT.

Background: Antitumor vaccines targeting tumor-associated antigens (TAAs) can generate antitumor immune response. A novel vaccine platform using adenovirus 5 (Ad5) vectors [E1–, E2b–] targeting three TAAs—prostate-specific antigen (PSA), brachyury, and MUC-1—has been developed. Both brachyury and the C-terminus of MUC-1 are overexpressed in metastatic castration-resistant prostate cancer (mCRPC) and have been shown to play an important role in resistance to chemotherapy, epithelial–mesenchymal transition, and metastasis. The transgenes for PSA, brachyury, and MUC-1 all contain epitope modifications for the expression of CD8+ T-cell enhancer agonist epitopes. We report here the first-in-human trial of this vaccine platform. Methods: Patients with mCRPC were given concurrently three vaccines targeting PSA, brachyury, and MUC-1 at 5×10¹¹ viral particles (VP) each, subcutaneously every 3 weeks for a maximum of three doses (dose de-escalation cohort), followed by a booster vaccine every 8 weeks for 1 year (dose-expansion cohort only). The primary objective was to determine the safety and the recommended phase II dose. Immune assays and clinical responses were evaluated. Results: Eighteen patients with mCRPC were enrolled between July 2018 and September 2019 and received at least one vaccination. Median PSA was 25.58 ng/mL (range, 0.65–1006 ng/mL). The vaccine was tolerable and safe, and no grade >3 treatment-related adverse events or dose-limiting toxicities (DLTs) were observed. One patient had a partial response, while five patients had confirmed PSA decline and five had stable disease for >6 months. Median progression-free survival was 22 weeks (95% CI: 19.1 to 34). Seventeen (100%) of 17 patients mounted T-cell responses to at least one TAA, whereras 8 (47%) of 17 patients mounted immune responses to all three TAAs. Multifunctional T-cell responses to PSA, MUC-1, and brachyury were also detected after vaccination in the majority of the patients. Conclusions: Ad5 PSA/MUC-1/brachyury vaccine is well tolerated. The primary end points were met and there were no DLTs. The recommended phase II dose is 5×10¹¹ VP. The vaccine demonstrated clinical activity, including one partial response and confirmed PSA responses in five patients. Three patients with prolonged PSA responses received palliative radiation therapy. Further research is needed to evaluate the clinical benefit and immunogenicity of this vaccine in combination with other immuno-oncology agents and/or palliative radiation therapy. Trial registration number: NCT03481816.

The capability of large language models (LLMs) to understand and generate human-readable text has prompted the investigation of their potential as educational and management tools for patients with cancer and healthcare providers. We conducted a cross-sectional study aimed at evaluating the ability of ChatGPT-4, ChatGPT-3.5, and Google Bard to answer questions related to 4 domains of immuno-oncology (Mechanisms, Indications, Toxicities, and Prognosis). We generated 60 open-ended questions (15 for each section). Questions were manually submitted to LLMs, and responses were collected on June 30, 2023. Two reviewers evaluated the answers independently. ChatGPT-4 and ChatGPT-3.5 answered all questions, whereas Google Bard answered only 53.3% (P < .0001). The number of questions with reproducible answers was higher for ChatGPT-4 (95%) and ChatGPT3.5 (88.3%) than for Google Bard (50%) (P < .0001). In terms of accuracy, the number of answers deemed fully correct were 75.4%, 58.5%, and 43.8% for ChatGPT-4, ChatGPT-3.5, and Google Bard, respectively (P = .03). Furthermore, the number of responses deemed highly relevant was 71.9%, 77.4%, and 43.8% for ChatGPT-4, ChatGPT-3.5, and Google Bard, respectively (P = .04). Regarding readability, the number of highly readable was higher for ChatGPT-4 and ChatGPT-3.5 (98.1%) and (100%) compared to Google Bard (87.5%) (P = .02). ChatGPT-4 and ChatGPT-3.5 are potentially powerful tools in immuno-oncology, whereas Google Bard demonstrated relatively poorer performance. However, the risk of inaccuracy or incompleteness in the responses was evident in all 3 LLMs, highlighting the importance of expert-driven verification of the outputs returned by these technologies.

Background: MVA-BN-brachyury-TRICOM is a recombinant vector-based therapeutic cancer vaccine designed to induce an immune response against brachyury. Brachyury, a transcription factor overexpressed in advanced cancers, has been associated with treatment resistance, epithelial-to-mesenchymal transition, and metastatic potential. MVA-BN-brachyury-TRICOM has demonstrated immunogenicity and safety in previous clinical trials of subcutaneously administered vaccine. Preclinical studies have suggested that intravenous administration of therapeutic vaccines can induce superior CD8⁺ T cell responses, higher levels of systemic cytokine release, and stronger natural killer cell activation and proliferation. This is the first-in-human study of the intravenous administration of MVA-BN-brachyury-TRICOM. Methods: Between January 2020 and March 2021, 13 patients were treated on a phase 1, open-label, 3+3 design, dose-escalation study at the National Institutes of Health Clinical Center. The study population was adults with advanced solid tumors and was enriched for chordoma, a rare sarcoma of the notochord that overexpresses brachyury. Vaccine was administered intravenously at three DLs on days 1, 22, and 43. Blood samples were taken to assess drug pharmacokinetics and immune activation. Imaging was conducted at baseline, 1 month, and 3 months post-treatment. The primary endpoint was safety and tolerability as determined by the frequency of dose-limiting toxicities; a secondary endpoint was determination of the recommended phase 2 dose. Results: No dose-limiting toxicities were observed and no serious adverse events were attributed to the vaccine. Vaccine-related toxicities were consistent with class profile (ie, influenza-like symptoms). Cytokine release syndrome up to grade 2 was observed with no adverse outcomes. Dose-effect trend was observed for fever, chills/rigor, and hypotension. Efficacy analysis of objective response rate per RECIST 1.1 at the end of study showed one patient with a partial response, four with stable disease, and eight with progressive disease. Three patients with stable disease experienced clinical benefit in the form of improvement in pain. Immune correlatives showed T cell activation against brachyury and other tumor-associated cascade antigens. Conclusions: Intravenous administration of MVA-BN-brachyury-TRICOM vaccine was safe and tolerable. Maximum tolerated dose was not reached. The maximum administered dose was 10⁹ infectious units every 3 weeks for three doses. This dose was selected as the recommended phase 2 dose. Trial registration number: NCT04134312.

IMPORTANCE: Patients who experience progression of advanced human papillomavirus (HPV)–associated cancers and who have previously received first-line systemic treatment have a poor prognosis and limited therapeutic options.OBJECTIVE: To assess the clinical activity of the combination of the HPV type 16 therapeutic vaccine PDS0101, the tumor-targeting interleukin 12 antibody-drug conjugate PDS01ADC, and the bifunctional anti–programmed cell death ligand 1 (PD-L1)/transforming growth factor β (TGF-β) bintrafusp alfa in advanced HPV-associated cancers.DESIGN, Setting, and Participants: This nonrandomized clinical trial was phase 1/2 and investigator initiated, and was conducted at a single US cancer research center between June 2020 and July 2022. Patients with advanced or metastatic HPV-associated cancers were eligible, including patients who were both immune checkpoint blockade (ICB) naive and ICB resistant. The cutoff date for data analysis was May 13, 2024.INTERVENTION: Patients received 1 mL of PDS0101 subcutaneously every 4 weeks for 6 doses then every 12 weeks for 2 additional doses, PDS01ADC, 16.8 µg/kg, subcutaneously every 4 weeks or PDS01ADC, 8 µg/kg, subcutaneously every 2 weeks, and bintrafusp alfa, 1200 mg, intravenously every 2 weeks.MAIN OUTCOMES AND MEASURES: Objective response rate (ORR) by Response Evaluation Criteria in Solid Tumors version 1.1 in ICB-naive patients.RESULTS: Of the 50 eligible patients, 26 (52%) were men and the median age was 56 years (range, 28-80 years). The median (IQR) follow-up was 37.7 (30.6-42.0) months. Fourteen patients (28%) were ICB naive, with an ORR of 35.7% (95% CI, 12.8%-64.9%), and median overall survival (OS) 42.4 months (95% CI, 8.3 months-not estimable); in ICB-resistant patients, the ORR was 16.7% (6 of 36 patients; 95% CI, 6.4%-32.8%) and median OS was 15.8 months (95% CI, 9.0-21.3 months). Among patients with HPV-16–positive tumors (37 patients [74%]), in the ICB-naive group (8 patients [21.6%]) the ORR was 62.5% (95% CI, 24.5%-91.5%) and a median OS measure was not reached. Grade 3 and 4 treatment-related adverse events occurred in 26 of 50 patients (52%). There were no treatment-related deaths.CONCLUSIONS AND RELEVANCE: In this trial, the combination of PDS0101, PDS01ADC, and bintrafusp alfa showed an acceptable safety profile and promising antitumor activity and improved OS in patients with HPV-16–positive cancers, in both ICB-naive and ICB-resistant patients, warranting further evaluation of the combination of PDS0101 and PDS01ADC with simultaneous PD-L1/TGF-β inhibition in these populations.Trial Registration: ClinicalTrials.gov Identifier: NCT04287868

The application of messenger RNA (mRNA) technology in antigen-based immuno-oncology therapies represents a significant advancement in cancer treatment. Cancer vaccines are an effective combinatorial partner to sensitize the host immune system to the tumor and boost the efficacy of immune therapies. Selecting suitable tumor antigens is the key step to devising effective vaccinations and amplifying the immune response. Tumor neoantigens are de novo epitopes derived from somatic mutations, avoiding T-cell central tolerance of self-epitopes and inducing immune responses to tumors. The identification and prioritization of patient-specific tumor neoantigens are based on advanced computational algorithms taking advantage of the profiling with next-generation sequencing considering factors involved in human leukocyte antigen (HLA)-peptide-T-cell receptor (TCR) complex formation, including peptide presentation, HLA-peptide affinity, and TCR recognition. This review discusses the development and clinical application of mRNA vaccines in oncology, with a particular focus on recent clinical trials and the computational workflows and methodologies for identifying both shared and individual antigens. While this review centers on therapeutic mRNA vaccines targeting existing tumors, it does not cover preventative vaccines. Preclinical experimental validations are crucial in cancer vaccine development, but we emphasize the computational approaches that facilitate neoantigen selection and design, highlighting their role in advancing mRNA vaccine development. The versatility and rapid development potential of mRNA make it an ideal platform for personalized neoantigen immunotherapy. We explore various strategies for antigen target identification, including tumor-associated and tumor-specific antigens and the computational tools used to predict epitopes capable of eliciting strong immune responses. We address key design considerations for enhancing the immunogenicity and stability of mRNA vaccines, as well as emerging trends and challenges in the field. This comprehensive overview highlights the therapeutic potential of mRNA-based cancer vaccines and underscores ongoing research efforts aimed at optimizing these therapies for improved clinical outcomes.