Create an Engine of
Scientific Discovery

Mission

Our ultimate goal is to develop an AI system that can make major scientific discoveries that would improve the state of the world and provide a meaningful impact on the lives of billions of people.

Towards enabling businesses and communities to realize the goal, we have built large-scale platforms for automation Garuda Platform, text-mining Taxila Platform, and learning Gandhara AI framework, as a basic infrastructure to empower the grand challenge.

Our platforms and custom solutions provide highly intelligent services to assist scientific activities in drug discovery, clinical trials, healthcare and in domains beyond biology.

Dive into the Vision

Recent Posts

New Publication on mutagenenicity prediction…

A new paper is now published by our researchers from our research collaboration project.

Acharya, S., Shinada, N.K., Koyama, N. et al. Asking the right questions for mutagenicity prediction from BioMedical text. npj Syst Biol Appl 9, 63 (2023). https://doi.org/10.1038/s41540-023-00324-2

We are excited to share our latest publication in Nature Systems Biology and Applications! This work is a part of the incredible journey we’ve been on for the past many years, striving to harness the power of AI for risk assessment in Toxicology.

Exploring the Frontiers of Generative AI Tools Part II— Tools for Empowering Research, Note Taking, and Beyond

Leo Jiang

To provide you with a visual representation of these innovative tools, we have created a quad chart that showcases their rankings in terms of their purpose. These tools take full advantage of generative AI models and combine them with other processes, such as GPT-4 and natural language processing, to produce various unique programs tailored to all types of people.

Exploring the Frontiers of Generative AI Tools Part I — Tools for Empowering Reading, Writing, and Beyond

Leo Jiang

As technology continues to advance at an unprecedented pace, we find ourselves on the brink of a new era where artificial intelligence (AI) seamlessly integrates into our daily lives, enhancing our experiences and productivity. From analyzing hundreds of pages to generating unique text, the world of generative AI is growing exponentially through the constant improvement of large language models (LLMs). In this article, we will explore this ever-expanding world of generative AI and LLMs through the use of some fascinating tools.

New Publication on Mutagenesis “Optimizing machine-learning models for mutagenicity prediction through better feature selection”

A new paper is now published by our researchers from our research collaboration project.

Nicolas K Shinada, Naoki Koyama, Megumi Ikemori, Tomoki Nishioka, Seiji Hitaoka, Atsushi Hakura, Shoji Asakura, Yukiko Matsuoka, Sucheendra K Palaniappan, Optimizing machine-learning models for mutagenicity prediction through better feature selection, Mutagenesis, 2022;, geac010, https://doi.org/10.1093/mutage/geac010

Abstract
Assessing a compound’s mutagenicity using machine learning is an important activity in the drug discovery and development process. Traditional methods of mutagenicity detection, such as Ames test, are expensive and time and labor intensive. In this context, in silico methods that predict a compound mutagenicity with high accuracy are important. Recently, machine-learning (ML) models are increasingly being proposed to improve the accuracy of mutagenicity prediction. While these models are used in practice, there is further scope to improve the accuracy of these models. We hypothesize that choosing the right features to train the model can further lead to better accuracy. We systematically consider and evaluate a combination of novel structural and molecular features which have the maximal impact on the accuracy of models. We rigorously evaluate these features against multiple classification models (from classical ML models to deep neural network models). The performance of the models was assessed using 5- and 10-fold cross-validation and we show that our approach using the molecule structure, molecular properties, and structural alerts as feature sets successfully outperform the state-of-the-art methods for mutagenicity prediction for the Hansen et al. benchmark dataset with an area under the receiver operating characteristic curve of 0.93. More importantly, our framework shows how combining features could benefit model accuracy improvements.

Building recsys workflows: From idea to production in days, instead of weeks

Ramanathan R

TL;DR: Technology blog on how we deployed a reciprocal recommender system using AWS Step Functions, Data Science SDK and other AWS infrastructure/services. Discusses the problem and our solution design and architecture with code snippets. Codebase can be extended to productionize custom scripts for similar MLOps pipelines.

JSOT 2021

Our collaboration work with Eisai was presented at JSOT 2021 (The 48th Annual Meeting of the Japanese Society of Toxicology) on 2021/07/08

Development of AI mutagenicity prediction system incorporating the knowledge of expert review
○ Naoki KOYAMA1 , Megumi IKEMORI2 , Tomoki NISHIOKA3 , Seiji HITAOKA3 , Atsushi HAKURA1 , Chihiro NAKAZAWA1 , Chakravarti K SUMAN4 , Saiakhov D ROUSTEM4 , Shinada K NICOLAS5 , Palaniappan K SUCHEENDRA5 , Yukiko MATSUOKA5 , Shoji ASAKURA1 11 Global Drug Safety, Eisai Co., Ltd., 2 Planning & Operation. hhc Data Creation Center, Eisai Co., Ltd., 3 5D Integration Unit, hhc Data Creation Center, Eisai Co., Ltd., 4 MultiCASE Inc., 5 SBX Corporation