DeePaN: deep patient graph convolutional network integrating clinico-genomic evidence to stratify lung cancers for immunotherapy
Abstract Immuno-oncology (IO) therapies have transformed the therapeutic landscape of non-small cell lung cancer (NSCLC). However, patient responses to IO are variable and influenced by a heterogeneous combination of health, immune, and tumor factors. There is a pressing need to discover the distinc...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2021-02-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-021-00381-z |
| _version_ | 1827775105200029696 |
|---|---|
| author | Chao Fang Dong Xu Jing Su Jonathan R Dry Bolan Linghu |
| author_facet | Chao Fang Dong Xu Jing Su Jonathan R Dry Bolan Linghu |
| author_sort | Chao Fang |
| collection | DOAJ |
| description | Abstract Immuno-oncology (IO) therapies have transformed the therapeutic landscape of non-small cell lung cancer (NSCLC). However, patient responses to IO are variable and influenced by a heterogeneous combination of health, immune, and tumor factors. There is a pressing need to discover the distinct NSCLC subgroups that influence response. We have developed a deep patient graph convolutional network, we call “DeePaN”, to discover NSCLC complexity across data modalities impacting IO benefit. DeePaN employs high-dimensional data derived from both real-world evidence (RWE)-based electronic health records (EHRs) and genomics across 1937 IO-treated NSCLC patients. DeePaN demonstrated effectiveness to stratify patients into subgroups with significantly different (P-value of 2.2 × 10−11) overall median survival of 20.35 months and 9.42 months post-IO therapy. Significant differences in IO outcome were not seen from multiple non-graph-based unsupervised methods. Furthermore, we demonstrate that patient stratification from DeePaN has the potential to augment the emerging IO biomarker of tumor mutation burden (TMB). Characterization of the subgroups discovered by DeePaN indicates potential to inform IO therapeutic insight, including the enrichment of mutated KRAS and high blood monocyte count in the IO beneficial and IO non-beneficial subgroups, respectively. Our work has proven the concept that graph-based AI is feasible and can effectively integrate high-dimensional genomic and EHR data to meaningfully stratify cancer patients on distinct clinical outcomes, with potential to inform precision oncology. |
| first_indexed | 2024-03-11T13:47:26Z |
| format | Article |
| id | doaj.art-99ccbd25da274e779adb31be74a930d9 |
| institution | Directory Open Access Journal |
| issn | 2398-6352 |
| language | English |
| last_indexed | 2024-03-11T13:47:26Z |
| publishDate | 2021-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj.art-99ccbd25da274e779adb31be74a930d92023-11-02T10:06:47ZengNature Portfolionpj Digital Medicine2398-63522021-02-014111010.1038/s41746-021-00381-zDeePaN: deep patient graph convolutional network integrating clinico-genomic evidence to stratify lung cancers for immunotherapyChao Fang0Dong Xu1Jing Su2Jonathan R Dry3Bolan Linghu4Translational Medicine, Research and Early Development, Oncology R&D, AstraZenecaDepartment of Electrical Engineering and Computer Science, University of MissouriDepartment of Biostatistics, Indiana University School of MedicineTranslational Medicine, Research and Early Development, Oncology R&D, AstraZenecaTranslational Medicine, Research and Early Development, Oncology R&D, AstraZenecaAbstract Immuno-oncology (IO) therapies have transformed the therapeutic landscape of non-small cell lung cancer (NSCLC). However, patient responses to IO are variable and influenced by a heterogeneous combination of health, immune, and tumor factors. There is a pressing need to discover the distinct NSCLC subgroups that influence response. We have developed a deep patient graph convolutional network, we call “DeePaN”, to discover NSCLC complexity across data modalities impacting IO benefit. DeePaN employs high-dimensional data derived from both real-world evidence (RWE)-based electronic health records (EHRs) and genomics across 1937 IO-treated NSCLC patients. DeePaN demonstrated effectiveness to stratify patients into subgroups with significantly different (P-value of 2.2 × 10−11) overall median survival of 20.35 months and 9.42 months post-IO therapy. Significant differences in IO outcome were not seen from multiple non-graph-based unsupervised methods. Furthermore, we demonstrate that patient stratification from DeePaN has the potential to augment the emerging IO biomarker of tumor mutation burden (TMB). Characterization of the subgroups discovered by DeePaN indicates potential to inform IO therapeutic insight, including the enrichment of mutated KRAS and high blood monocyte count in the IO beneficial and IO non-beneficial subgroups, respectively. Our work has proven the concept that graph-based AI is feasible and can effectively integrate high-dimensional genomic and EHR data to meaningfully stratify cancer patients on distinct clinical outcomes, with potential to inform precision oncology.https://doi.org/10.1038/s41746-021-00381-z |
| spellingShingle | Chao Fang Dong Xu Jing Su Jonathan R Dry Bolan Linghu DeePaN: deep patient graph convolutional network integrating clinico-genomic evidence to stratify lung cancers for immunotherapy npj Digital Medicine |
| title | DeePaN: deep patient graph convolutional network integrating clinico-genomic evidence to stratify lung cancers for immunotherapy |
| title_full | DeePaN: deep patient graph convolutional network integrating clinico-genomic evidence to stratify lung cancers for immunotherapy |
| title_fullStr | DeePaN: deep patient graph convolutional network integrating clinico-genomic evidence to stratify lung cancers for immunotherapy |
| title_full_unstemmed | DeePaN: deep patient graph convolutional network integrating clinico-genomic evidence to stratify lung cancers for immunotherapy |
| title_short | DeePaN: deep patient graph convolutional network integrating clinico-genomic evidence to stratify lung cancers for immunotherapy |
| title_sort | deepan deep patient graph convolutional network integrating clinico genomic evidence to stratify lung cancers for immunotherapy |
| url | https://doi.org/10.1038/s41746-021-00381-z |
| work_keys_str_mv | AT chaofang deepandeeppatientgraphconvolutionalnetworkintegratingclinicogenomicevidencetostratifylungcancersforimmunotherapy AT dongxu deepandeeppatientgraphconvolutionalnetworkintegratingclinicogenomicevidencetostratifylungcancersforimmunotherapy AT jingsu deepandeeppatientgraphconvolutionalnetworkintegratingclinicogenomicevidencetostratifylungcancersforimmunotherapy AT jonathanrdry deepandeeppatientgraphconvolutionalnetworkintegratingclinicogenomicevidencetostratifylungcancersforimmunotherapy AT bolanlinghu deepandeeppatientgraphconvolutionalnetworkintegratingclinicogenomicevidencetostratifylungcancersforimmunotherapy |