Identification of Genomic Signatures for Colorectal Cancer Survival Using Exploratory Data Mining
Clinicopathological presentations are critical for establishing a postoperative treatment regimen in Colorectal Cancer (CRC), although the prognostic value is low in Stage 2 CRC. We implemented a novel exploratory algorithm based on artificial intelligence (explainable artificial intelligence, XAI)...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-03-01
|
| Series: | International Journal of Molecular Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1422-0067/25/6/3220 |
| _version_ | 1797240787329613824 |
|---|---|
| author | Justin J. Hummel Danlu Liu Erin Tallon John Snyder Wesley Warren Chi-Ren Shyu Jonathan Mitchem Rene Cortese |
| author_facet | Justin J. Hummel Danlu Liu Erin Tallon John Snyder Wesley Warren Chi-Ren Shyu Jonathan Mitchem Rene Cortese |
| author_sort | Justin J. Hummel |
| collection | DOAJ |
| description | Clinicopathological presentations are critical for establishing a postoperative treatment regimen in Colorectal Cancer (CRC), although the prognostic value is low in Stage 2 CRC. We implemented a novel exploratory algorithm based on artificial intelligence (explainable artificial intelligence, XAI) that integrates mutational and clinical features to identify genomic signatures by repurposing the FoundationOne Companion Diagnostic (F1CDx) assay. The training data set (<i>n</i> = 378) consisted of subjects with recurrent and non-recurrent Stage 2 or 3 CRC retrieved from TCGA. Genomic signatures were built for identifying subgroups in Stage 2 and 3 CRC patients according to recurrence using genomic parameters and further associations with the clinical presentation. The summarization of the top-performing genomic signatures resulted in a 32-gene genomic signature that could predict tumor recurrence in CRC Stage 2 patients with high precision. The genomic signature was further validated using an independent dataset (<i>n</i> = 149), resulting in high-precision prognosis (AUC: 0.952; PPV = 0.974; NPV = 0.923). We anticipate that our genomic signatures and NCCN guidelines will improve recurrence predictions in CRC molecular stratification. |
| first_indexed | 2024-04-24T18:12:59Z |
| format | Article |
| id | doaj.art-ee7a66e8f37a4935a584c6301db21a6a |
| institution | Directory Open Access Journal |
| issn | 1661-6596 1422-0067 |
| language | English |
| last_indexed | 2024-04-24T18:12:59Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | International Journal of Molecular Sciences |
| spelling | doaj.art-ee7a66e8f37a4935a584c6301db21a6a2024-03-27T13:45:23ZengMDPI AGInternational Journal of Molecular Sciences1661-65961422-00672024-03-01256322010.3390/ijms25063220Identification of Genomic Signatures for Colorectal Cancer Survival Using Exploratory Data MiningJustin J. Hummel0Danlu Liu1Erin Tallon2John Snyder3Wesley Warren4Chi-Ren Shyu5Jonathan Mitchem6Rene Cortese7Institute for Data Science and Informatics, University of Missouri, Columbia, MO 65212, USADepartment of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO 65212, USAInstitute for Data Science and Informatics, University of Missouri, Columbia, MO 65212, USADepartment of Statistics, University of Missouri, Columbia, MO 65212, USAInstitute for Data Science and Informatics, University of Missouri, Columbia, MO 65212, USAInstitute for Data Science and Informatics, University of Missouri, Columbia, MO 65212, USAInstitute for Data Science and Informatics, University of Missouri, Columbia, MO 65212, USAInstitute for Data Science and Informatics, University of Missouri, Columbia, MO 65212, USAClinicopathological presentations are critical for establishing a postoperative treatment regimen in Colorectal Cancer (CRC), although the prognostic value is low in Stage 2 CRC. We implemented a novel exploratory algorithm based on artificial intelligence (explainable artificial intelligence, XAI) that integrates mutational and clinical features to identify genomic signatures by repurposing the FoundationOne Companion Diagnostic (F1CDx) assay. The training data set (<i>n</i> = 378) consisted of subjects with recurrent and non-recurrent Stage 2 or 3 CRC retrieved from TCGA. Genomic signatures were built for identifying subgroups in Stage 2 and 3 CRC patients according to recurrence using genomic parameters and further associations with the clinical presentation. The summarization of the top-performing genomic signatures resulted in a 32-gene genomic signature that could predict tumor recurrence in CRC Stage 2 patients with high precision. The genomic signature was further validated using an independent dataset (<i>n</i> = 149), resulting in high-precision prognosis (AUC: 0.952; PPV = 0.974; NPV = 0.923). We anticipate that our genomic signatures and NCCN guidelines will improve recurrence predictions in CRC molecular stratification.https://www.mdpi.com/1422-0067/25/6/3220colorectal cancerprognosisF1CDx repurposingexplainable artificial intelligencegenomic signature |
| spellingShingle | Justin J. Hummel Danlu Liu Erin Tallon John Snyder Wesley Warren Chi-Ren Shyu Jonathan Mitchem Rene Cortese Identification of Genomic Signatures for Colorectal Cancer Survival Using Exploratory Data Mining International Journal of Molecular Sciences colorectal cancer prognosis F1CDx repurposing explainable artificial intelligence genomic signature |
| title | Identification of Genomic Signatures for Colorectal Cancer Survival Using Exploratory Data Mining |
| title_full | Identification of Genomic Signatures for Colorectal Cancer Survival Using Exploratory Data Mining |
| title_fullStr | Identification of Genomic Signatures for Colorectal Cancer Survival Using Exploratory Data Mining |
| title_full_unstemmed | Identification of Genomic Signatures for Colorectal Cancer Survival Using Exploratory Data Mining |
| title_short | Identification of Genomic Signatures for Colorectal Cancer Survival Using Exploratory Data Mining |
| title_sort | identification of genomic signatures for colorectal cancer survival using exploratory data mining |
| topic | colorectal cancer prognosis F1CDx repurposing explainable artificial intelligence genomic signature |
| url | https://www.mdpi.com/1422-0067/25/6/3220 |
| work_keys_str_mv | AT justinjhummel identificationofgenomicsignaturesforcolorectalcancersurvivalusingexploratorydatamining AT danluliu identificationofgenomicsignaturesforcolorectalcancersurvivalusingexploratorydatamining AT erintallon identificationofgenomicsignaturesforcolorectalcancersurvivalusingexploratorydatamining AT johnsnyder identificationofgenomicsignaturesforcolorectalcancersurvivalusingexploratorydatamining AT wesleywarren identificationofgenomicsignaturesforcolorectalcancersurvivalusingexploratorydatamining AT chirenshyu identificationofgenomicsignaturesforcolorectalcancersurvivalusingexploratorydatamining AT jonathanmitchem identificationofgenomicsignaturesforcolorectalcancersurvivalusingexploratorydatamining AT renecortese identificationofgenomicsignaturesforcolorectalcancersurvivalusingexploratorydatamining |