←
Ryan Chow106 posts
Ryan Chow avatar

Ryan Chow

@ScienceChow

Heme/onc fellow @PennCancer, Jane Coffin Childs postdoc fellow in AI peptide design @pranamanam | @YaleMed MD/PhD | Harvard '16 | ryanchow.org

◷ Joined October 2019▧ 17 Photos and videos
OncLive.com avatar
⟳ Ryan Chow retweeted
OncLive.com@OncLive·Feb 3

Real-World Analysis Supports Rethinking Upfront Dose Intensity of Enfortumab Vedotin in Advanced Urothelial Cancer @ScienceChow @PennCancer @Ron_cology @ramsedhom #blcsm hubs.ly/Q041HfMF0

Dra. María Natalia Gandur Quiroga avatar
⟳ Ryan Chow retweeted
Dra. María Natalia Gandur Quiroga@nataliagandur·Jan 6

💫🌟🚨 New real-world evidence on EV dose reduction in advanced urothelial cancer🌟💫 🎓 @JAMAOnc study shows that starting treatment with reduced-dose enfortumab vedotin in 1L EV+pembrolizumab: 🔵 Cuts treatment interruptions by ~50% (better tolerability) 🔵 Maintains overall survival — no compromise on outcomes 🔵 Benefits remain consistent in older & physiologically vulnerable patients 💡 Take-home: “Start low, go slow” may be a safe and practical strategy to keep patients on therapy without losing effectiveness. jamanetwork.com/journals/jam… @OncoAlert @myESMO @ASCO @BladderCaJrnl @MedicalwatchHQ #BladderCancer #UrothelialCancer #OncoAlert #GUOncology #EV302

Post attachmentPost attachmentPost attachment
JAMA Oncology avatar
⟳ Ryan Chow retweeted
JAMA Oncology@JAMAOnc·Jan 6

Among patients with advanced urothelial cancer, upfront enfortumab vedotin dose reduction was linked to a 50% reduction in treatment interruption risk but did not compromise overall survival. ja.ma/3Lw71JH

Post attachment
Penn Medicine Cancer avatar
⟳ Ryan Chow retweeted
Penn Medicine Cancer@PennCancer·17 Dec 2025

A retrospective cohort study led by @ScienceChow & team supports reducing the dose of the antibody-drug conjugate enfortumab vedotin when patients receive it as first-line therapy + pembrolizumab for the most common form of bladder cancer. @ASCOPost spr.ly/60157h5QH

JAMA Oncology avatar
⟳ Ryan Chow retweeted
JAMA Oncology@JAMAOnc·15 Nov 2025

Among patients with advanced urothelial cancer, upfront enfortumab vedotin dose reduction was linked to a 50% reduction in treatment interruption risk but did not compromise overall survival. ja.ma/47L9DdG

Post attachment
Raffaele Colombo avatar
⟳ Ryan Chow retweeted
Raffaele Colombo@raffcolo·7 Aug 2025

Is there a synergistic effect between enfortumab vedotin (EV) and pembrolizumab (P) for untreated advanced urothelial carcinoma in clinical setting? This analysis suggests no! EV+P seems to follow a an independent drug action model with no evidence of synergy

Post attachment
Ryan Chow avatar
Ryan Chow@ScienceChow·6 Aug 2025

These findings suggest that distinct patient subgroups respond to EV vs pembro, as opposed to an emergent synergistic effect with combination EV+P. Important implications for drug development in this setting! @PennCancer (4/4)

Ryan Chow avatar
Ryan Chow@ScienceChow·6 Aug 2025

In an exploratory analysis, we also evaluated patients with PD-L1 CPS >10, who are more likely to respond to pembro. In this biomarker-selected group, observed PFS for EV-302 was again well-explained by independent activity of EV and pembro. (3/4)

Post attachment
Ryan Chow avatar
Ryan Chow@ScienceChow·6 Aug 2025

Inspired by pioneering work from @ac_palmer, we calculated the predicted PFS curve for combo EV+P, assuming independent activity of EV and pembro. Amazingly, predicted PFS for EV+P was essentially indistinguishable from what was observed in the EV-302 trial. @tompowles1 (2/4)

Post attachment
Ravi B. Parikh avatar
⟳ Ryan Chow retweeted
Ravi B. Parikh@ravi_b_parikh·21 Oct 2024

New @Nature_NPJ paper by @ScienceChow co-mentored w/ @KLNathanson @BasserBRCA on reliability of #deeplearning to predict variant pathogenicity. #AI recapitulate ClinVar classifications for pathogenic variants, but poorly predict pathogenicity for VUS's #breastcancer

Post attachment

#DeepLearning models have been developed to predict missense variant pathogenicity -- but how well do these models perform in a real-world clinical setting? Thrilled to share our latest in npj Precision Oncology! @Nature_NPJ | nature.com/articles/s41698-0… (1/8)

Biology+AI Daily avatar
⟳ Ryan Chow retweeted
Biology+AI Daily@BiologyAIDaily·20 Oct 2024

Phenotypic Evaluation of Deep Learning Models for Classifying Germline Variant Pathogenicity @Nature_NPJ • This study evaluates the real-world utility of three state-of-the-art deep learning models—AlphaMissense, EVE, and ESM1b—in classifying germline variants associated with hereditary cancer risks. • Using data from 469,623 UK Biobank participants, the study focuses on missense variants in key cancer-related genes, including BRCA1, BRCA2, ATM, CHEK2, and PALB2. • AlphaMissense and ESM1b models were able to identify pathogenic BRCA1 and BRCA2 variants that conferred increased risk for breast and ovarian cancer, but they struggled with certain other genes like ATM and CHEK2. • Notably, AlphaMissense identified potentially pathogenic PALB2 variants, which were previously categorized as variants of uncertain significance (VUS) by ClinVar, hinting at the models’ potential for refining variant classification. • Despite their success with some genes, all models exhibited limited accuracy in distinguishing VUSs associated with increased cancer risk, underscoring the need for cautious interpretation in clinical practice. • Composite classifiers that combined ClinVar annotations with deep learning predictions reduced the proportion of participants classified as VUS carriers, though at the cost of predictive power. • The study highlights the importance of gene-specific thresholds, as a uniform cutoff reduced model accuracy across multiple genes, indicating that custom thresholds may improve performance. • The authors emphasize the need for diverse genomic data to mitigate biases in current models, especially since VUSs are more prevalent in non-European populations. • While the study shows promise for integrating deep learning in clinical settings, it concludes that deep learning models are not yet ready to fully replace traditional variant classification methods for clinical decision-making. @ravi_b_parikh @KLNathanson @ScienceChow 💻Code: github.com/rdchow/UKB_pathog… 📜Paper: nature.com/articles/s41698-0…

Post attachment