Improved prediction of immune checkpoint blockade efficacy across multiple cancer types

Chowell, Diego; Yoo, Seong Keun; Valero, Cristina; Pastore, Alessandro; Krishna, Chirag; Lee, Mark; Hoen, Douglas R.; Shi, Hongyu; Kelly, Daniel; Patel, Neal; Makarov, Vladimir; Ma, Xiaoxiao; Vuong, Lynda; Sabio, Erich; Weiss, Kate; Kuo, Fengshen; Lenz, Tobias; Samstein, Robert M.; Riaz, Nadeem; Adusumilli, Prasad S.; Balachandran, Vinod P.; Plitas, George; Hakimi, A. Ari; Abdel‐Wahab, Omar; Shoushtari, Alexander N.; Postow, Michael A.; Motzer, Robert J.; Ladanyi, Marc; Zehir, Ahmet; Berger, Michael F.; Gönen, Mithat; Morris, Luc G.T.; Weinhold, Nils; Chan, Timothy A.

doi:10.1038/s41587-021-01070-8

Cited by 164 publications

(174 citation statements)

References 74 publications

Supporting

Mentioning

141

Contrasting

Order By: Relevance

“…In advanced melanoma, radiographic response may not be apparent for months after ICI initiation due to pseudo-progression or residual fibrous tissue 61,62 , limiting the sensitivity of imaging to detect meaningful changes in tumor burden. Further, the absence of biomarkers that predict which patients will respond to therapy can lead to excess or futile treatment in unselected populations 63 . Liquid biopsy can improve ICI care by providing faster readouts of response, orthogonal measurement of TF trends, and longitudinal noninvasive TF surveillance.…”

Section: Resultsmentioning

confidence: 99%

“…In contrast, MRD-EDGE required only plasma, and produced performance on par with a comparable tumor-informed panel. MRD-EDGE allowed for early and accurate assessment of response to ICI, a challenging clinical setting for prognostication 63,64 . Future large-scale interventional studies will be critical to demonstrate the value of rapid and quantitative estimation of ICI response to inform real-time clinical decision making.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning guided signal enrichment for ultrasensitive plasma tumor burden monitoring

Widman

Shah

Øgaard

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

In solid tumor oncology, circulating tumor DNA (ctDNA) is poised to transform care through accurate assessment of minimal residual disease (MRD) and therapeutic response monitoring. To overcome the sparsity of ctDNA fragments in low tumor fraction (TF) settings and increase MRD sensitivity, we previously leveraged genome-wide mutational integration through plasma whole genome sequencing (WGS). We now introduce MRD-EDGE, a composite machine learning-guided WGS ctDNA single nucleotide variant (SNV) and copy number variant (CNV) detection platform designed to increase signal enrichment. MRD-EDGE uses deep learning and a ctDNA-specific feature space to increase SNV signal to noise enrichment in WGS by 300X compared to our previous noise suppression platform MRDetect. MRD-EDGE also reduces the degree of aneuploidy needed for ultrasensitive CNV detection through WGS from 1Gb to 200Mb, thereby expanding its applicability to a wider range of solid tumors. We harness the improved performance to track changes in tumor burden in response to neoadjuvant immunotherapy in non-small cell lung cancer and demonstrate ctDNA shedding in precancerous colorectal adenomas. Finally, the radical signal to noise enrichment in MRD-EDGE enables de novo mutation calling in melanoma without matched tumor, yielding clinically informative TF monitoring for patients on immune checkpoint inhibition.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Machine learning guided signal enrichment for ultrasensitive plasma tumor burden monitoring

Widman

Shah

Øgaard

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…First, despite the improved predictive performance of random forest classi ers, RF and similar methods are more complex and often less interpretable for clinical use. Nevertheless, this is not the rst study demonstrating that non-linear classi cation methods can signi cantly improve prediction of ICI bene t 50 . Incorporating clinical features to train random forest models may potentially further improve the performance obtained in this work, when data becomes available 50 .…”

Section: Discussionmentioning

confidence: 79%

“…Nevertheless, this is not the rst study demonstrating that non-linear classi cation methods can signi cantly improve prediction of ICI bene t 50 . Incorporating clinical features to train random forest models may potentially further improve the performance obtained in this work, when data becomes available 50 . In addition, future developments may dissect the biological processes distinguished in this work to identify candidate targets to enhance treatment sensitivity.…”

Section: Discussionmentioning

confidence: 79%

Mutated Processes Predict Immune Checkpoint Inhibitor Therapy Benefit in Metastatic Melanoma

Patterson¹,

Auslander

2022

Preprint

View full text Add to dashboard Cite

Immune Checkpoint Inhibitor (ICI) therapy has revolutionized treatment for advanced melanoma; however, only a subset of patients benefit from this treatment. Despite considerable efforts, the Tumor Mutation Burden (TMB) is the only U.S. Food and Drug Administration (FDA) approved biomarker for ICI treatment in melanoma. However, the mechanisms underlying TMB association with prolonged ICI survival are not entirely understood and may depend on numerous confounding factors. To identify more interpretable ICI response biomarkers based on tumor mutations, we trained classifiers using mutations within distinct biological processes. We evaluated a variety of feature selection and classification methods, and identified key mutated biological processes that provide improved predictive capability compared to the TMB. The top mutated processes identified are leukocyte and T-cell proliferation regulation; importantly, these processes demonstrate stable predictive performance across different data cohorts of melanoma patients treated with ICI. This study provides new methodology to construct biologically interpretable genomic predictors for ICI response with substantially improved predictive performance over the TMB.

show abstract

“…Although a dynamic multiparameter model might outperform the predictive ability of any single feature, incorporating different components relies on the harmonization of diverse assays and multiple selective biomarkers will be crucial. Incorporating non-liquid components like radiomic imaging analysis and tumor features ( 73 ), coupled with multidimensional approaches involving blood-based proteomic testing ( 74 ) and mechanistic learning ( 75 , 76 ), is also required. Additionally, consistent cross-study validation and standardization of each model are required before any implementation in routine clinical use to improve personalized medicine approaches, which could be addressed through ongoing prospective collaborative molecular response-adaptive clinical trials ( Table 1 ).…”

Section: On the Horizon Challenges To Be Overcomementioning

confidence: 99%

Applications of Circulating Tumor DNA in Immune Checkpoint Inhibition: Emerging Roles and Future Perspectives

et al. 2022

View full text Add to dashboard Cite

Immune checkpoint inhibitors (ICIs), especially anti-programmed death 1 (PD-1)/programmed death ligand 1 (PD-L1) antibodies, have made dramatic progress in the treatment of lung cancer, especially for patients with cancers not driven by oncogenes. However, responses are limited to a subset of patients, and which subset of patients will optimally benefit from ICI remains unknown. With the advantage of being minimally invasive and dynamic, noninvasive biomarkers are promising candidates to predict response, monitor resistance, and track the evolution of lung cancer during ICI treatment. In this review, we focus on the application of circulating tumor DNA (ctDNA) in plasma in immunotherapy. We examine the potential of pre- and on-treatment features of ctDNA as biomarkers, and following multiparameter analysis, we determine the potential clinical value of integrating predictive liquid biomarkers of ICIs to optimize patient management. We further discuss the role of ctDNA in monitoring treatment resistance, as well as challenges in clinical translation.

show abstract

Improved prediction of immune checkpoint blockade efficacy across multiple cancer types

Cited by 164 publications

References 74 publications

Machine learning guided signal enrichment for ultrasensitive plasma tumor burden monitoring

Machine learning guided signal enrichment for ultrasensitive plasma tumor burden monitoring

Mutated Processes Predict Immune Checkpoint Inhibitor Therapy Benefit in Metastatic Melanoma

Applications of Circulating Tumor DNA in Immune Checkpoint Inhibition: Emerging Roles and Future Perspectives

Contact Info

Product

Resources

About