Mathematical and Computational Oncology: Third International Symposium, ISMCO 2021, Virtual Event, October 11–13, 2021, Proceedings (Lecture Notes in Computer Science)

✍ Scribed by George Bebis (editor), Terry Gaasterland (editor), Mamoru Kato (editor), Mohammad Kohandel (editor), Kathleen Wilkie (editor)

• Publisher: Springer
• Year: 2021
• Tongue: English
• Leaves: 91
• Category: Library

✦ Synopsis

This book constitutes the refereed proceedings of the Third International Symposium on Mathematical and Computational Oncology, ISMCO 2021, held in October 2021. Due to COVID-19 pandemic the conference was held virtually.

The 3 full papers and 4 short papers presented were carefully reviewed and selected from 20 submissions. The papers are organized in topical sections named: statistical and machine learning methods for cancer research; mathematical modeling for cancer research; spatio-temporal tumor modeling and simulation; general cancer computational biology; mathematical modeling for cancer research; computational methods for anticancer drug development.

✦ Table of Contents

Preface
Organization
Keynote Talks
Precision Oncology via the Tumor Transcriptome
Population Genomic Approaches for Molecular Biomarker Discovery in Clinical Oncology
Three Problems in Mathematical Oncology
Towards Optimizing Therapy on a Patient Specific Basis via Imaging-Based Mathematical Modeling
Barrett’s Esophagus: Efficient Design of Multiscale Simulations for Surveillance And Treatment
Integrative Methods for Deciphering Cancer Networks
Contents
Statistical and Machine Learning Methods for Cancer Research
Image Classification of Skin Cancer: Using Deep Learning as a Tool for Skin Self-examinations
1 Introduction
2 Methods
2.1 Patient Data
2.2 Data Augmentation and Balancing Classes
2.3 Description of Models
3 Results
3.1 Accuracy of Lesion Risk Classification
3.2 Fine-Tuning for Protecting Patients Against Filtering Out High-Risk Lesions
4 Discussion
5 Conclusion
References
Predictive Signatures for Lung Adenocarcinoma Prognostic Trajectory by Multiomics Data Integration and Ensemble Learning
1 Introduction
2 Inherent Characteristics of Multi-omics Data
3 Single-Omics Prediction Model
3.1 Conventional Clinical History Based Model as a Baseline
3.2 Methylome-Based Survival Time Prediction Model
3.3 Transcriptome-Based Ensemble-Learning Model
3.4 Proteome-Based Model
4 Integrative Multi-omics Prediction Model
4.1 Integrative Modeling
4.2 Omics-Marker Cost Analysis
5 Discussion and Future Works
References
The Role of Hydrophobicity in Peptide-MHC Binding
1 Introduction
2 Methods
2.1 Data Mining
2.2 Hydrophobicity
2.3 Hydrophobicity Filtering
2.4 2 Sample t-Test
3 Results
4 Conclusion
References
Spatio-Temporal Tumor Modeling and Simulation
Simulating Cytotoxic T-Lymphocyte and Cancer Cells Interactions: An LSTM-Based Approach to Surrogate an Agent-Based Model
1 Introduction
2 Method
2.1 Dataset Generation
2.2 LSTM-Based Surrogate Model Architecture
3 Results
3.1 The Model Can Reproduce the Predictions of the ABM
3.2 The Model Can Predict Kinetics Unseen During the Training
3.3 A Reduced Dataset Size Can Be Sufficient
4 Discussion and Conclusion
References
General Cancer Computational Biology
Strategies to Reduce Long-Term Drug Resistance by Considering Effects of Differential Selective Treatments
1 Introduction
2 Background: Differential Selective Pressure Affects Long-Term Therapeutic Outcome
3 Differential-Imposed Selective Treatments Result in Different Tumor Reduction Rates
4 Differential Selective Pressures as a Factor of the Cost Function
5 Numerical Simulation Results and Discussion
6 Conclusion
References
Mathematical Modeling for Cancer Research
Improved Geometric Configuration for the Bladder Cancer BCG-Based Immunotherapy Treatment Model
1 Introduction and Related Work
2 Mathematical Modeling Extension
2.1 Model Definition
2.2 Numerical Solution
2.3 Treatment Protocol Based on Initial Tumor Distribution
3 Discussion
References
Computational Methods for Anticancer Drug Development
Run for Your Life – An Integrated Virtual Tissue Platform for Incorporating Exercise Oncology into Immunotherapy
1 Introduction
2 Methods
2.1 Model Description
2.2 Parameter Estimation and Calibration
3 Results
3.1 Model Reproduces Key Mechanisms of Immunoregulation by the TME
3.2 Incorporating Aerobic Fitness into the Personalization of Immunotherapy
4 Discussion
References
Author Index