Bridging Excellence in AI Science

Confirmed Speakers

1. Dr. Hiroaki Kitano, Chairman, SBI Japan

2. Dr. Ravindranath K, Founder, Global University Foundation, India

3. Dr. Jun Seita, Team Leader, RIKEN, Japan

4. Dr. Ajay Sethi, Founder, Open Science Stack, India

5. Dr. Tavpritesh Sethi, Associate Professor, Computational Biology, IIIT-Delhi, India

6. Dr. Ganesh Bagler, Professor, IIIT-Delhi, India

7. Satish Kottapalli, Chief Innovation Officer, Global Innovation Hub, India

8. Dr. Daniel Evans-Yamamoto, Researcher, The Systems Biology Institute, Japan

9. Dr. Johan Nyström-Persson, CEO, JNP Solutions, Japan

10. Dr. Jihun Choi, Research Scientist, Sony AI, Japan

11. Dr. Moreno Zolfo, Research Scientist, OIST, Japan

Other Attendees

1. Ilya Kulyatin, Founder, Tokyo AI

2. Dr. Jun Kanno,  Honorary Member, National Institute of Health Sciences and Medical Director, Nissan Tamagawa Hospital, Pathology Department and Senior Researcher, SBI, Japan

3. Dr. AISAKI Ken-ichi, National Institute of Health Sciences (NIHS), Japan

4. Ajay Patil, CTO, Combinatics Inc., Japan

5. Gangadhara Naga Sai, Waseda University, Tokyo

6. Sou Miyake, Ph.D., Head of Venture Investment, Corundum Systems Biology Inc., Japan

7. Researchers of SBI, Japan

The list will be updated as additional invitees confirm their participation.

Flash Talk Abstracts

Speaker: Anton Kratz, Ph.D
Title: AI-Guided Interpretation of DDR Assemblies in Aging
Abstract: The DNA damage response (DDR) ensures error-free DNA replication and transcription and is disrupted in numerous diseases. An ongoing challenge is to determine the proteins orchestrating DDR and their organization into complexes, including constitutive interactions and those responding to genomic insult. Here, we use multi-conditional network analysis to systematically map DDR assemblies at multiple scales. Affinity purifications of 21 DDR proteins, with/without genotoxin exposure, are combined with multi-omics data to reveal a hierarchical organization of 605 proteins into 109 assemblies. The map captures canonical repair mechanisms and proposes new DDR-associated proteins extending to stress, transport, and chromatin functions. We find that protein assemblies closely align with genetic dependencies in processing specific genotoxins and that proteins in multiple assemblies typically act in multiple genotoxin responses. Follow-up by DDR functional readouts newly implicates 12 assembly members in double-strand-break repair.

The central role of DDR in aging is now increasingly appreciated. We shaped a Deep Learning network architecture according to the DDR assemblies map and trained it to predict chronological age given somatic mutations and copy-number variations (CNVs) from The Cancer Genome Atlas, thus making the Deep Learning network interpretable.

Speaker: Harikeshav P

Title: Leveraging AI in Cancer Care to Reduce Poverty Induced by Healthcare Costs in LMICs 

Abstract: Artificial Intelligence (AI) holds immense promise in transforming cancer care in low- and middle-income countries (LMICs) by mitigating poverty driven by high healthcare expenditures. Through innovative AI-driven methods such as early detection tools, predictive analytics for disease management, telemedicine services, and optimized treatment plans, healthcare costs can be substantially reduced. This presentation examines AI-driven interventions, shares practical case studies, identifies implementation challenges, and proposes strategies for sustainable AI integration within LMIC healthcare systems.

Speaker: Ashwini Patil, CEO, Combinatics, Japan.
Title: AI landscape in single-cell transcriptomics data analysis

Abstract: The advent of techniques to measure gene expression patterns (transcriptomics) at single cell resolution has revolutionized the study of complex tissues and their cellular organization in health and disease. These methods are generating large quantities of high-dimensional biological data in the form of tissue-specific and whole organism cell atlases. AI techniques, specifically foundation models, present an opportunity to integrate this immense and diverse data to provide valuable biological insights. I will provide a brief overview of the currently available single-cell machine-learning models that have been trained on data from millions of cells. These models have the ability to integrate new data, predict cell types, understand network dynamics and identify similar cell states. I will also discuss the sources of training data used by these models and how CellKb (https://www.cellkb.com), our knowledgebase of high-quality cell type gene signatures, helps improve the accuracy of training data labels. 

Speaker: Srinivas Padmanabhan, SRM Group, India
Title: Next-Gen Healthcare:  Revolutionizing AI development with ethical considerations from clinical research to patient care.

Abstract: This presentation examines the human need to integrate empathy and ethics into the design of AI systems that go beyond augmenting human in the loop but rather carries the responsibility of decision making to prioritise care quality in the healthcare ecosystem. SRM Group is at the global forefront of patient focused thought leadership across our University, Clinical trials, Patient care and IT service delivery that is enabled by the GenAI technology frameworks and responsible Data Science practices. By transitioning from data-centric approach to a framework that is truly intelligent, it transforms quantitative processes to a deeply humanistic exercise that improves the quality of healthcare service delivery.

Speaker: Dr. Manas Kala, Chief Executive Officer, Veritus AI, Japan and Assistant Professor, Osaka University, Japan

Title: Researchers Break Ground, AI Is Just the Shovel

Abstract: Great research doesn’t come from algorithms, it comes from researchers. But with two new papers published every minute, keeping up with relevant knowledge has become a challenge. As a result, researchers now spend over 500 hours a year on repetitive tasks – literature reviews, grant applications, manuscript revisions – just to keep up, often at the cost of innovation. At Veritus, we believe researchers break ground, AI is just the shovel. In this talk, Manas Kala, Founder & CEO of Veritus, shares how AI-powered research workflows are helping top university labs in Japan become 5X more productive, innovate faster, and refocus their time on high-impact science. Learn how researchers are cutting through the noise, accelerating discovery, and reclaiming the time to focus on what really matters: delivering breakthrough discoveries.

Speaker: Dr. Natalia Polouliakh, Researcher, Sony CSL, Japan

Title: Beyond the Trust: Evolution of Percellome data analysis with SHOE and AGCT on Garuda platform.

Abstract: The "Percellome" database provides a unique "per cell" readout of mRNA copy numbers across various mouse organs. It encompasses data from over 100 chemicals accumulated over decades at the National Institute of Health and Science of Japan (Prof. Jun Kanno's group). For the past decade, our team, has been participating in the Turing Challenge by developing an analytical pipeline for the automated and rapid discovery, annotation, and presentation of transcriptional regulation linked to the public toxicity effects of compounds such as dioxin, pentachlorophenol, indigo, and even coffee. Through this effort, we have created innovative tools for sequence-to-gene expression analysis and network inference, offering multiple perspectives on fundamental biological phenomena. Our Percellome suite aims to make this invaluable dataset widely accessible, empowering researchers and the public to explore and build upon decades of high-precision animal studies. By unlocking new insights, we strive to honor past research efforts and drive future human health and environmental safety advancements.

Speaker: Ryota Yamada, CEO, Fuku Inc.

Title: AI-Augmented Laboratory: Transforming Scientific Research Through Intelligent Information Extraction

Abstract: This flash talk introduces our company's vision of the "AI-Augmented Laboratory" - a next-generation research environment that embodies our mission to "Open science and expand human potential." We will outline this transformative concept and demonstrate two practical implementations that are making it a reality: (1) our automated system for extracting and structuring information from scientific papers using generative AI, and (2) our natural language interface that enables researchers to query databases conversationally without technical expertise. These examples showcase how AI augmentation streamlines knowledge acquisition and data access, allowing scientists to focus on discovery rather than information management.

Speaker: Dr Yosuke Ozawa, CEO, Epistra

Title: Autonomous Optimization of Life Science Experiments

Abstract: [Background] In recent years, life science experiments have become integral in several applied fields, such as regenerative medicine and bio-manufacturing, where they serve as methods for producing final products. However, with the advancement of life sciences, the complexity of experimental protocols has increased, presenting several challenges. These include: 1. Reproducibility: Difficulty in replicating the same conditions and results. 2. Tacit knowledge formalization: Complex procedures and the "know-how" are difficult to formalize into explicit knowledge. 3. Personalization of expertise: Expertise remains concentrated with specific individuals, leading to a lack of widespread knowledge sharing. When these experimental processes are used as manufacturing methods, it can lead to extended research and development timelines due to the lack of reproducibility. In the production stage, unstable results contribute to increased manufacturing costs. 

[Methods] To address these challenges, a technique was developed that uses AI to autonomously optimize life science experiments by selecting optimal exploratory points without prior assumptions. The method is based on Bayesian optimization, a type of black-box optimization technique. Bayesian optimization assumes that the prior distribution of functions in non-parametric Bayesian approaches follows a Gaussian process. This system combines automated state evaluation techniques using cellular measurements to gather evaluation data from microscope images. It then explores optimal combinations of parameters that constitute experimental protocols.

 [Results and Discussions] Several applied examples, including differentiation induction experiments of iPS cells into retinal pigment epithelial cells, are introduced. Additionally, a new method combining metabolomic data analysis with automated optimization technology is also presented.

Accommodation for Speakers

Speakers will be accommodated at JR-East Hotel Mets Premier Gotanda, located just a one-minute walk from JR Gotanda Station. This modern hotel offers a comfortable stay with convenient access to Shibuya, Shinagawa, and other key areas in Tokyo.

• Location: 1-minute walk from JR Gotanda Station

• Rooms: Equipped with separate bathrooms and wash areas

• Dining: Japanese and Western breakfast options, rice bowls, and a semi-buffet with fresh salads and beverages

• Facilities: Free Wi-Fi, laundry services, and business-friendly amenities

For more details, visit the official hotel website: Hotel Mets Gotanda.

Organizers

Dr Hiroaki Kitano, SBI Japan

Dr Samik Ghosh, SBI Japan

Dr Sucheendra Kumar Palaniappan, SBI Japan

Yoko Furugori, SBI Japan

Michiru Arai, SBI Japan