Multiple instance neural networks based on sparse attention for cancer detection using T-cell receptor sequences

  title={Multiple instance neural networks based on sparse attention for cancer detection using T-cell receptor sequences},
  author={Younghoon Kim and Tao Wang and Danyi Xiong and Xinlei Wang and Seong Ik Park},
  journal={BMC Bioinformatics},
Early detection of cancers has been much explored due to its paramount importance in biomedical fields. Among different types of data used to answer this biological question, studies based on T cell receptors (TCRs) are under recent spotlight due to the growing appreciation of the roles of the host immunity system in tumor biology. However, the one-to-many correspondence between a patient and multiple TCR sequences hinders researchers from simply adopting classical statistical/machine learning… 



DeepLION: Deep Multi-Instance Learning Improves the Prediction of Cancer-Associated T Cell Receptors for Accurate Cancer Detection

A deep multi-instance learning method, named DeepLION, to improve the prediction of cancer-associated TCRs by considering the correlations among T CRs in the same repertoire, which are often ignored by the existing methods.

Convolutional neural network models for cancer type prediction based on gene expression

Novel CNN designs for accurate and simultaneous cancer/normal and cancer types prediction based on gene expression profiles, and unique model interpretation scheme to elucidate biologically relevance of cancer marker genes after eliminating the effects of tissue-of-origin are presented.

De novo prediction of cancer-associated T cell receptors for noninvasive cancer detection

A deep learning method called DeepCAT is developed to enable de novo prediction of cancer-associated T cell receptors (TCRs) and sets the stage for using the peripheral blood TCR repertoire for noninvasive cancer detection.

Recent advancement in cancer detection using machine learning: Systematic survey of decades, comparisons and challenges.

  • T. Saba
  • Computer Science
    Journal of infection and public health
  • 2020

Deep learning-based prediction of the T cell receptor-antigen binding specificity

A transfer learning-based model is built, named pMHC-TCR binding prediction network (pMTnet), to predict TCR-binding specificities of neoantigens, and T cell antigens in general, presented by class I major histocompatibility complexes (pMHCs).

Cancer classification using gene expression data

Classication of SNPs for breast cancer diagnosis using neural-network-based association rules

A new hybrid intelligent technique based on Association Rule Mining and Neural Networks which uses an Evolutionary Algorithm (EA) is proposed to deal with the dimensionality problem for the diagnosis of breast cancer.

Bayesian multiple instance regression for modeling immunogenic neoantigens

A Bayesian multiple instance regression method, named BMIR, using a Gaussian distribution to address continuous responses and latent binary variables to model primary instances in bags, which can learn a function for predicting the bag-level responses and for identifying the primary instances within bags and give access to Bayesian statistical inference, which are elusive in existing works.

SMILE: Sparse-Attention based Multiple Instance Contrastive Learning for Glioma Sub-Type Classification Using Pathological Images

A Sparse-attention based Multiple Instance contrastive LEarning (SMILE) method for glioma sub-type classification that uses contrastive learning to extract meaningful representations from pathological images and validate the proposed SMILE method using a gliomas dataset from The Cancer Genome Atlas.