Oops, you're using an old version of your browser so some of the features on this page may not be displaying properly.

MINIMAL Requirements: Google Chrome 24+Mozilla Firefox 20+Internet Explorer 11Opera 15–18Apple Safari 7SeaMonkey 2.15-2.23

Poster Display

240P - AMU: Using mRNA Embedding in Transformer Network to Predict Melanoma Immune Checkpoint Inhibitor Response

Date

08 Dec 2022

Session

Poster Display

Presenters

Yi Yin

Citation

Annals of Oncology (2022) 16 (suppl_1): 100103-100103. 10.1016/iotech/iotech100103

Authors

Y. Yin1, Y.J. Huang2, X. Xie3, M.Z. Wang3

Author affiliations

  • 1 Fujian Cancer Hospital and Fujian Medical University Cancer Hospital, Fuzhou/CN
  • 2 Clinical Oncology School of Fujian Medical University, Fujian Cancer Hospital, Fuzhou/CN
  • 3 The First Affiliated Hospital of Fujian Medical University, Fuzhou/CN

Resources

Login to get immediate access to this content.

If you do not have an ESMO account, please create one for free.

Abstract 240P

Background

Melanoma immune checkpoint inhibitor (ICI) response is related to complex biological pathways. A deep learning (DL) model has powerful fitting ability and transformer structure has interactive information extraction function. We designed a transformer neural network fed with multi-gene mRNA expression quantities to predict melanoma ICI response and explored gene interactions from the embedding layer.

Methods

We built our training/validation/testing datasets from four open databases, 208 pre-ICI and 58 post-ICI samples were included in training/validation dataset and testing dataset, respectively. Every sample has 160-dimension mRNA expression quantities sequenced from tumor tissues. The 160 genes were previously described as potentially associated with melanoma, inflammation, immunity, and the PD-L1/CTLA4 pathways. We designed a DL model named AMU with the transformer encoder followed by a convolutional neural network (CNN). We applied the method of upsampling for data enhancement and set the 20-dimension gene embeddings. SVM, Random Forest, AdaBoost, XGBoost and a simple CNN we designed were token as competing models. In model interpretation work, gene feature vectors were extracted from the embedding layer and gene interactions were calculated by t-distributed Stochastic Neighbor Embedding (t-SNE) algorithm, then the gene interactions were compared with that inquired in the Functional Protein Association Network (STRING, https://cn.string-db.org/).

Results

AMU showed the preferred performance with the area under the curve (AUC) of 0.941 and the mean average precision (mAP) of 0.960 in validation dataset and AUC of 0.672, mAP of 0.800 in testing dataset, respectively. In model interpretation, the TNF-TNFRSF1A pathway was indicated as a key pathway to influence melanoma ICI response. Further, gene features learned from AMU showed a local similarity with STRING.

Conclusions

The DL model built with transformer encoder structure has strong power to process mRNA expression data and precisely predicted the melanoma ICI response. Meanwhile, gene vector representation learned from trainable embedding layer is promising for DL application in the biomedical field.

Legal entity responsible for the study

Y. Yin.

Funding

Has not received any funding.

Disclosure

All authors have declared no conflicts of interest.

This site uses cookies. Some of these cookies are essential, while others help us improve your experience by providing insights into how the site is being used.

For more detailed information on the cookies we use, please check our Privacy Policy.

Customise settings
  • Necessary cookies enable core functionality. The website cannot function properly without these cookies, and you can only disable them by changing your browser preferences.