Laboratory for Medical Science Mathematics

Professor Tatsuhiko Tsunoda
E-mail: tsunoda{at}bs.s.u-tokyo.ac.jp
Lab HP

Introduction

【Key Words】Genomic Medicine, Precision Medicine, Tumor microenvironment, Deep learning, Mathematical simulation

Understand Life Phenomena and Diseases with Advanced Mathematical Science and Molecular Observation Technology

　 In our laboratory, we aim to understand the dynamics of diseases and immunity at the molecular level to overcome diseases, such as cancer. It is expected that medical care will shift towards patient specific optimal therapies and drug dosages to treat and prevent disease. To achieve this, we analyze big data such as patient omics (e.g. genomes), diagnostic images, and clinical data to discover the causes of diseases. Then, by conducting integrated omics analysis, we can understand the disease mechanism as a system. In this way, we conduct biomedical science research, making full use of state-of-the-art omics profiling technologies, mathematics, and computational science.

Understand Tumor-microenvironments

By investigating the relationship between cancer cell populations and their microenvironment, such as the immune system, we can model and predict response to treatment, side effects, and the acquisition of resistance on an individual basis (Figure 1). For example, recently, we analyzed the whole genome sequence of liver cancer cells from 300 patients and found a cluster with mutations within a novel cancer-related gene [1]. Patients in this cluster have a good prognosis with a lower chance of recurrence after surgery. We have also discovered a new cluster in colorectal cancer [2]. Further detailed analysis revealed that the population characteristics of cancer cells and their relationship with the microenvironment, such as immunity, vary greatly among clusters. Cancer cells are abnormal versions of our own cells which can be recognized as non-self, and therefore be eliminated by the immune system. However, selective pressures can drive cancer cells to change and evade elimination. The individuality of the cancer cells and microenvironment, as well as the treatment implemented, will affect the future development of the tumor. For most cancers, the higher the immune activity, the better the prognosis. In surprising contrast, for cancers in immune-privileged sites, such as uveal melanoma and low-grade gliomas, we found that the higher the immune activity, the worse the overall survival, and we have elucidated the mechanism [3]. We aim to clarify the mechanisms that cause these differences through the analysis of omics and pathological images, and to create a model for predicting the effects of treatment using mathematical simulations, with the aim of providing precision medicine that allows treatment to be optimized for each patient.

Figure 1. Unravel and predict diseases with patients’ omics, clinical, and pathological image data.

Methodology for original analysis with deep learning

Figure 2. (a) Our new technique that converts omics into images and inputs them into deep learning [4]. (b) Analyze what deep learning sees when identifying cancer types [5].

Figure 3. (a) Prediction of anticancer drug response by multi-omics and deep learning [6]. (b) Differential gene patterns involved in non-response (left) and response (right) to the anticancer drug paclitaxel.

Various people gather and research

Our laboratories are also located in RIKEN, in addition to the University of Tokyo, and we are involved in much collaborative research. Our lab includes bioinformatics researchers, clinical doctors, genetics researchers, sequence analysis staff, network analysis researchers, and mathematics researchers from Japan and abroad, sharing their expertise and knowledge to further our research every day.

References:

[1] Fujimoto A, Tsunoda T, et al. Whole genome mutational landscape and characterization of non-coding and structural mutations in liver cancer. Nature Genetics, 48, 500-509 (2016).
[2] Sugawara T, Miya F, Ishikawa T, Lysenko A, Nishino J, Kamatani T, Takemoto A, Boroevich KA, Kakimi K, Kinugasa Y, Tanabe M, Tsunoda T. Immune subtypes and neoantigen-related immune evasion in advanced colorectal cancer. iScience, 25, 1003740 (2022).
[3] Sharma A, Vans E, Shigemizu D, Boroevich KA, Tsunoda T. DeepInsight: A methodology to transform a non-image data to an image for convolution neural network architecture. Scientific Reports, 9, 11399 (2019).
[4] Sharma A, Lysenko A, Boroevich KA, Vans E, Tsunoda T. DeepFeature: feature selection in nonimage data using convolutional neural network. Briefings in Bioinformatics, 22, bbab297 (2021).
[5] Sharma A, Lysenko A, Boroevich KA, Vans E, Tsunoda T. DeepFeature: feature selection in nonimage data using convolutional neural network. Briefings in Bioinformatics, 22, bbab297 (2021).
[6] Sharma A, Lysenko A, Boroevich KA, Tsunoda T. DeepInsight-3D architecture for anti-cancer drug response prediction with deep-learning on multi-omics. Scientific Reports, 13, 2483 (2023).