Contextualizing Genes by Using Text-Mined Co-Occurrence Features for Cancer Gene Panel Discovery

Abstract

Developing a biomedical-explainable and validatable text mining pipeline can help in cancer gene panel discovery. We create a pipeline that can contextualize genes by using text-mined co-occurrence features. We apply Biomedical Natural Language Processing (BioNLP) techniques for literature mining in the cancer gene panel. A literature-derived 4,679 × 4,630 gene term-feature matrix was built. The EGFR L858R and T790M, and BRAF V600E genetic variants are important mutation term features in text mining and are frequently mutated in cancer. We validate the cancer gene panel by the mutational landscape of different cancer types. The cosine similarity of gene frequency between text mining and a statistical result from clinical sequencing data is 80.8%. In different machine learning models, the best accuracy for the prediction of two different gene panels, including MSK-IMPACT (Memorial Sloan Kettering-Integrated Mutation Profiling of Actionable Cancer Targets), and Oncomine cancer gene panel, is 0.959, and 0.989, respectively. The receiver operating characteristic (ROC) curve analysis confirmed that the neural net model has a better prediction performance (Area under the ROC curve (AUC) = 0.992). The use of text-mined co-occurrence features can contextualize each gene. We believe the approach is to evaluate several existing gene panels, and show that we can use part of the gene panel set to predict the remaining genes for cancer discovery.

Introducing AI to the molecular tumor board: one direction toward the establishment of precision medicine using large-scale cancer clinical and biological information

“…B Schematic diagram modified from Ref. [ 168 ]. A gene panel analysis framework was developed that can discover gene panel characteristics based on BioNLP.…”

“…In the different machine learning models, the peak accuracies for the prediction of MSK-IMPACT and OCP were 0.959 and 0.989, respectively. Receiver operating characteristic curve analysis also confirmed that the neural network model had better predictive performance (AUROC = 0.992) [ 168 ]. By using text-mined post-occurrence features, the literature for each gene can be ascertained, and this approach could be used to evaluate several existing gene panels and predict the remaining genes using a portion of the gene panel set, leading to cancer detection.…”

“…Chen et al applied Biomedical Natural Language Processing (BioNLP) techniques to literature mining of cancer gene panels aimed at creating a pipeline that can contextualize genes using text-mined co-occurrence features (Fig. 6 B) [ 168 ]. The gene panel analysis framework was developed in this study.…”

Cutting-Edge AI Technologies Meet Precision Medicine to Improve Cancer Care

“…However, we could not explain the biological significance of the vector in the neural-embedding model. Table 4 [ 69 , 70 , 71 , 72 , 73 , 74 ] shows that various data-mining techniques have been used to classify gene-mutation diseases.…”

“…Our own work contextualized the genes for clinical precision medicine, presenting druggable targets, hereditary cancer syndrome mutations, and illness subgroups [ 74 ]. The hypergeometric test was used to construct the mutational landscape of the actionable cancer genome from the biomedical literature, which was then confirmed using the NGS database.…”