Research

17 pages, 1640 KiB

Open AccessArticle

A Robust Personalized Classification Method for Breast Cancer Metastasis Prediction

by Nahim Adnan, Tanzira Najnin and Jianhua Ruan

Cancers 2022, 14(21), 5327; https://0-doi-org.brum.beds.ac.uk/10.3390/cancers14215327 - 29 Oct 2022

Cited by 2 | Viewed by 972

Accurate prediction of breast cancer metastasis in the early stages of cancer diagnosis is crucial to reduce cancer-related deaths. With the availability of gene expression datasets, many machine-learning models have been proposed to predict breast cancer metastasis using thousands of genes simultaneously. However, [...] Read more.

Accurate prediction of breast cancer metastasis in the early stages of cancer diagnosis is crucial to reduce cancer-related deaths. With the availability of gene expression datasets, many machine-learning models have been proposed to predict breast cancer metastasis using thousands of genes simultaneously. However, the prediction accuracy of the models using gene expression often suffers from the diverse molecular characteristics across different datasets. Additionally, breast cancer is known to have many subtypes, which hinders the performance of the models aimed at all subtypes. To overcome the heterogeneous nature of breast cancer, we propose a method to obtain personalized classifiers that are trained on subsets of patients selected using the similarities between training and testing patients. Results on multiple independent datasets showed that our proposed approach significantly improved prediction accuracy compared to the models trained on the complete training dataset and models trained on specific cancer subtypes. Our results also showed that personalized classifiers trained on positively and negatively correlated patients outperformed classifiers trained only on positively correlated patients, highlighting the importance of selecting proper patient subsets for constructing personalized classifiers. Additionally, our proposed approach obtained more robust features than the other models and identified different features for different patients, making it a promising tool for designing personalized medicine for cancer patients. Full article

(This article belongs to the Special Issue Advance in Computational Methods in Cancer Research)

► Show Figures

Figure 1

14 pages, 3660 KiB

Open AccessArticle

CellCallEXT: Analysis of Ligand–Receptor and Transcription Factor Activities in Cell–Cell Communication of Tumor Immune Microenvironment

by Shouguo Gao, Xingmin Feng, Zhijie Wu, Sachiko Kajigaya and Neal S. Young

Cancers 2022, 14(19), 4957; https://0-doi-org.brum.beds.ac.uk/10.3390/cancers14194957 - 10 Oct 2022

Cited by 2 | Viewed by 2030

Abstract

(1) Background: Single-cell RNA sequencing (scRNA-seq) data are useful for decoding cell–cell communication. CellCall is a tool that is used to infer inter- and intracellular communication pathways by integrating paired ligand–receptor (L–R) and transcription factor (TF) activities from steady-state data and thus cannot [...] Read more.

(1) Background: Single-cell RNA sequencing (scRNA-seq) data are useful for decoding cell–cell communication. CellCall is a tool that is used to infer inter- and intracellular communication pathways by integrating paired ligand–receptor (L–R) and transcription factor (TF) activities from steady-state data and thus cannot directly handle two-condition comparisons. For tumor and healthy status, it can only individually analyze cells from tumor or healthy tissue and examine L–R pairs only identified in either tumor or healthy controls, but not both together. Furthermore, CellCall is highly affected by gene expression specificity in tissues. (2) Methods: CellCallEXT is an extension of CellCall that deconvolutes intercellular communication and related internal regulatory signals based on scRNA-seq. Information on Reactome was retrieved and integrated with prior knowledge of L–R–TF signaling and gene regulation datasets of CellCall. (3) Results: CellCallEXT was successfully applied to examine tumors and immune cell microenvironments and to identify the altered L–R pairs and downstream gene regulatory networks among immune cells. Application of CellCallEXT to scRNA-seq data from patients with deficiency of adenosine deaminase 2 demonstrated its ability to impute dysfunctional intercellular communication and related transcriptional factor activities. (4) Conclusions: CellCallEXT provides a practical tool to examine intercellular communication in disease based on scRNA-seq data. Full article

(This article belongs to the Special Issue Advance in Computational Methods in Cancer Research)

► Show Figures

Figure 1

13 pages, 5361 KiB

Open AccessArticle

Spatial Transcriptomic Analysis Reveals Associations between Genes and Cellular Topology in Breast and Prostate Cancers

by Lujain Alsaleh, Chen Li, Justin L. Couetil, Ze Ye, Kun Huang, Jie Zhang, Chao Chen and Travis S. Johnson

Cancers 2022, 14(19), 4856; https://0-doi-org.brum.beds.ac.uk/10.3390/cancers14194856 - 04 Oct 2022

Cited by 1 | Viewed by 2745

Abstract

Background: Cancer is the leading cause of death worldwide with breast and prostate cancer the most common among women and men, respectively. Gene expression and image features are independently prognostic of patient survival; but until the advent of spatial transcriptomics (ST), it was [...] Read more.

Background: Cancer is the leading cause of death worldwide with breast and prostate cancer the most common among women and men, respectively. Gene expression and image features are independently prognostic of patient survival; but until the advent of spatial transcriptomics (ST), it was not possible to determine how gene expression of cells was tied to their spatial relationships (i.e., topology). Methods: We identify topology-associated genes (TAGs) that correlate with 700 image topological features (ITFs) in breast and prostate cancer ST samples. Genes and image topological features are independently clustered and correlated with each other. Themes among genes correlated with ITFs are investigated by functional enrichment analysis. Results: Overall, topology-associated genes (TAG) corresponding to extracellular matrix (ECM) and Collagen Type I Trimer gene ontology terms are common to both prostate and breast cancer. In breast cancer specifically, we identify the ZAG-PIP Complex as a TAG. In prostate cancer, we identify distinct TAGs that are enriched for GI dysmotility and the IgA immunoglobulin complex. We identified TAGs in every ST slide regardless of cancer type. Conclusions: These TAGs are enriched for ontology terms, illustrating the biological relevance to our image topology features and their potential utility in diagnostic and prognostic models. Full article

(This article belongs to the Special Issue Advance in Computational Methods in Cancer Research)

► Show Figures

Figure 1

15 pages, 3153 KiB

Open AccessArticle

A Novel Bayesian Framework Infers Driver Activation States and Reveals Pathway-Oriented Molecular Subtypes in Head and Neck Cancer

by Zhengping Liu, Chunhui Cai, Xiaojun Ma, Jinling Liu, Lujia Chen, Vivian Wai Yan Lui, Gregory F. Cooper and Xinghua Lu

Cancers 2022, 14(19), 4825; https://0-doi-org.brum.beds.ac.uk/10.3390/cancers14194825 - 03 Oct 2022

Viewed by 1612

Abstract

Head and neck squamous cell cancer (HNSCC) is an aggressive cancer resulting from heterogeneous causes. To reveal the underlying drivers and signaling mechanisms of different HNSCC tumors, we developed a novel Bayesian framework to identify drivers of individual tumors and infer the states [...] Read more.

Head and neck squamous cell cancer (HNSCC) is an aggressive cancer resulting from heterogeneous causes. To reveal the underlying drivers and signaling mechanisms of different HNSCC tumors, we developed a novel Bayesian framework to identify drivers of individual tumors and infer the states of driver proteins in cellular signaling system in HNSCC tumors. First, we systematically identify causal relationships between somatic genome alterations (SGAs) and differentially expressed genes (DEGs) for each TCGA HNSCC tumor using the tumor-specific causal inference (TCI) model. Then, we generalize the most statistically significant driver SGAs and their regulated DEGs in TCGA HNSCC cohort. Finally, we develop machine learning models that combine genomic and transcriptomic data to infer the protein functional activation states of driver SGAs in tumors, which enable us to represent a tumor in the space of cellular signaling systems. We discovered four mechanism-oriented subtypes of HNSCC, which show distinguished patterns of activation state of HNSCC driver proteins, and importantly, this subtyping is orthogonal to previously reported transcriptomic-based molecular subtyping of HNSCC. Further, our analysis revealed driver proteins that are likely involved in oncogenic processes induced by HPV infection, even though they are not perturbed by genomic alterations in HPV+ tumors. Full article

(This article belongs to the Special Issue Advance in Computational Methods in Cancer Research)

► Show Figures

Figure 1

19 pages, 3721 KiB

Open AccessArticle

Transformer for Gene Expression Modeling (T-GEM): An Interpretable Deep Learning Model for Gene Expression-Based Phenotype Predictions

by Ting-He Zhang, Md Musaddaqul Hasib, Yu-Chiao Chiu, Zhi-Feng Han, Yu-Fang Jin, Mario Flores, Yidong Chen and Yufei Huang

Cancers 2022, 14(19), 4763; https://0-doi-org.brum.beds.ac.uk/10.3390/cancers14194763 - 29 Sep 2022

Cited by 8 | Viewed by 4335

Abstract

Deep learning has been applied in precision oncology to address a variety of gene expression-based phenotype predictions. However, gene expression data’s unique characteristics challenge the computer vision-inspired design of popular Deep Learning (DL) models such as Convolutional Neural Network (CNN) and ask for [...] Read more.

Deep learning has been applied in precision oncology to address a variety of gene expression-based phenotype predictions. However, gene expression data’s unique characteristics challenge the computer vision-inspired design of popular Deep Learning (DL) models such as Convolutional Neural Network (CNN) and ask for the need to develop interpretable DL models tailored for transcriptomics study. To address the current challenges in developing an interpretable DL model for modeling gene expression data, we propose a novel interpretable deep learning architecture called T-GEM, or Transformer for Gene Expression Modeling. We provided the detailed T-GEM model for modeling gene–gene interactions and demonstrated its utility for gene expression-based predictions of cancer-related phenotypes, including cancer type prediction and immune cell type classification. We carefully analyzed the learning mechanism of T-GEM and showed that the first layer has broader attention while higher layers focus more on phenotype-related genes. We also showed that T-GEM’s self-attention could capture important biological functions associated with the predicted phenotypes. We further devised a method to extract the regulatory network that T-GEM learns by exploiting the attributions of self-attention weights for classifications and showed that the network hub genes were likely markers for the predicted phenotypes. Full article

(This article belongs to the Special Issue Advance in Computational Methods in Cancer Research)

► Show Figures

Figure 1

15 pages, 1078 KiB

Open AccessArticle

Identification of Immuno-Targeted Combination Therapies Using Explanatory Subgroup Discovery for Cancer Patients with EGFR Wild-Type Gene

by Olha Kholod, William Basket, Danlu Liu, Jonathan Mitchem, Jussuf Kaifi, Laura Dooley and Chi-Ren Shyu

Cancers 2022, 14(19), 4759; https://0-doi-org.brum.beds.ac.uk/10.3390/cancers14194759 - 29 Sep 2022

Cited by 1 | Viewed by 1539

Abstract

(1) Background: Phenotypic and genotypic heterogeneity are characteristic features of cancer patients. To tackle patients’ heterogeneity, immune checkpoint inhibitors (ICIs) represent some the most promising therapeutic approaches. However, approximately 50% of cancer patients that are eligible for treatment with ICIs do not respond [...] Read more.

(1) Background: Phenotypic and genotypic heterogeneity are characteristic features of cancer patients. To tackle patients’ heterogeneity, immune checkpoint inhibitors (ICIs) represent some the most promising therapeutic approaches. However, approximately 50% of cancer patients that are eligible for treatment with ICIs do not respond well, especially patients with no targetable mutations. Over the years, multiple patient stratification techniques have been developed to identify homogenous patient subgroups, although matching a patient subgroup to a treatment option that can improve patients’ health outcomes remains a challenging task. (2) Methods: We extended our Subgroup Discovery algorithm to identify patient subpopulations that could potentially benefit from immuno-targeted combination therapies in four cancer types: head and neck squamous carcinoma (HNSC), lung adenocarcinoma (LUAD), lung squamous carcinoma (LUSC), and skin cutaneous melanoma (SKCM). We employed the proportional odds model to identify significant drug targets and the corresponding compounds that increased the likelihood of stable disease versus progressive disease in cancer patients with the EGFR wild-type (WT) gene. (3) Results: Our pipeline identified six significant drug targets and thirteen specific compounds for cancer patients with the EGFR WT gene. Three out of six drug targets—FCGR2B, IGF1R, and KIT—substantially increased the odds of having stable disease versus progressive disease. Progression-free survival (PFS) of more than 6 months was a common feature among the investigated subgroups. (4) Conclusions: Our approach could help to better select responders for immuno-targeted combination therapies and improve health outcomes for cancer patients with no targetable mutations. Full article

(This article belongs to the Special Issue Advance in Computational Methods in Cancer Research)

► Show Figures

Figure 1

13 pages, 2887 KiB

Open AccessArticle

Clone Phylogenetics Reveals Metastatic Tumor Migrations, Maps, and Models

by Antonia Chroni, Sayaka Miura, Lauren Hamilton, Tracy Vu, Stephen G. Gaffney, Vivian Aly, Sajjad Karim, Maxwell Sanderford, Jeffrey P. Townsend and Sudhir Kumar

Cancers 2022, 14(17), 4326; https://0-doi-org.brum.beds.ac.uk/10.3390/cancers14174326 - 04 Sep 2022

Cited by 4 | Viewed by 2509

Abstract

Dispersal routes of metastatic cells are not medically detected or even visible. A molecular evolutionary analysis of tumor variation provides a way to retrospectively infer metastatic migration histories and answer questions such as whether the majority of metastases are seeded from clones within [...] Read more.

Dispersal routes of metastatic cells are not medically detected or even visible. A molecular evolutionary analysis of tumor variation provides a way to retrospectively infer metastatic migration histories and answer questions such as whether the majority of metastases are seeded from clones within primary tumors or seeded from clones within pre-existing metastases, as well as whether the evolution of metastases is generally consistent with any proposed models. We seek answers to these fundamental questions through a systematic patient-centric retrospective analysis that maps the dynamic evolutionary history of tumor cell migrations in many cancers. We analyzed tumor genetic heterogeneity in 51 cancer patients and found that most metastatic migration histories were best described by a hybrid of models of metastatic tumor evolution. Synthesizing across metastatic migration histories, we found new tumor seedings arising from clones of pre-existing metastases as often as they arose from clones from primary tumors. There were also many clone exchanges between the source and recipient tumors. Therefore, a molecular phylogenetic analysis of tumor variation provides a retrospective glimpse into general patterns of metastatic migration histories in cancer patients. Full article

(This article belongs to the Special Issue Advance in Computational Methods in Cancer Research)

► Show Figures

Figure 1

19 pages, 2711 KiB

Open AccessArticle

Risk Stratification for Breast Cancer Patient by Simultaneous Learning of Molecular Subtype and Survival Outcome Using Genetic Algorithm-Based Gene Set Selection

by Bonil Koo, Dohoon Lee, Sangseon Lee, Inyoung Sung, Sun Kim and Sunho Lee

Cancers 2022, 14(17), 4120; https://0-doi-org.brum.beds.ac.uk/10.3390/cancers14174120 - 25 Aug 2022

Viewed by 2101

Abstract

Patient stratification is a clinically important task because it allows us to establish and develop efficient treatment strategies for particular groups of patients. Molecular subtypes have been successfully defined using transcriptomic profiles, and they are used effectively in clinical practice, e.g., PAM50 subtypes [...] Read more.

Patient stratification is a clinically important task because it allows us to establish and develop efficient treatment strategies for particular groups of patients. Molecular subtypes have been successfully defined using transcriptomic profiles, and they are used effectively in clinical practice, e.g., PAM50 subtypes of breast cancer. Survival prediction contributed to understanding diseases and also identifying genes related to prognosis. It is desirable to stratify patients considering these two aspects simultaneously. However, there are no methods for patient stratification that consider molecular subtypes and survival outcomes at once. Here, we propose a methodology to deal with the problem. A genetic algorithm is used to select a gene set from transcriptome data, and their expression quantities are utilized to assign a risk score to each patient. The patients are ordered and stratified according to the score. A gene set was selected by our method on a breast cancer cohort (TCGA-BRCA), and we examined its clinical utility using an independent cohort (SCAN-B). In this experiment, our method was successful in stratifying patients with respect to both molecular subtype and survival outcome. We demonstrated that the orders of patients were consistent across repeated experiments, and prognostic genes were successfully nominated. Additionally, it was observed that the risk score can be used to evaluate the molecular aggressiveness of individual patients. Full article

(This article belongs to the Special Issue Advance in Computational Methods in Cancer Research)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Advance in Computational Methods in Cancer Research

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (8 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI