Tomoya Otabi
Machine Learning Engineer at 株式会社アットマーク/At mark Inc
Japan
Summary
🤩
Rockstar🎓
Top SchoolTomoya Otabi is a Machine Learning Engineer with nine years of experience bridging bioinformatics, chemoinformatics and full‑stack web development to deliver end‑to‑end AI products. He spent over four years applying deep learning to drug discovery—contributing to notable open‑source projects like Chainer Chemistry by adding evaluation metrics, time‑aware dataset splitters and PDBbind support—and then broadened into structured‑data ML and production web apps. Based in Japan, he brings 2+ years of full‑stack experience to scale data‑driven user experiences while maintaining rigorous model evaluation practices. Tomoya’s background in life sciences and interdisciplinary graduate training at the University of Tokyo give him an uncommon ability to translate complex experimental data into practical software solutions.
8 years of coding experience
6 years of employment as a software developer
修士, 学際情報学府, 修士, 学際情報学府 at 東京大学大学院農学部応用生命科学, 農学部応用生命科学 at 東京大学
Github Skills (8)
regression-models10
deep-learning10
python10
data-science10
chainer10
chemistry9
machine-learning8
biology8
Programming languages (14)
Github contributions (5)
chainer/chainer-chemistry
Jun 2018 - Mar 2019
Chainer Chemistry: A Library for Deep Learning in Biology and Chemistry
Role in this project:
Data Scientist
Data ScientistContributions:1 release, 78 commits, 20 PRs in 9 months
Contributions summary:Tomoya implemented an R2 score function, a common metric for evaluating regression models, and integrated it into the testing framework. Furthermore, they added a time order splitter, which is used for splitting the dataset based on time for validation and test sets, implying work on time-series or time-dependent data. These contributions suggest a focus on model evaluation and dataset preparation within the context of deep learning for chemistry and biology. The addition of PDBbind dataset support highlights a focus on a specific dataset for chemistry-related models.
chemistrygraph-convolutional-networkspythondeep-learningbiology
natsukium/otabi.net
Apr 2023 - Jan 2025
Contributions:47 PRs, 43 pushes, 48 branches in 1 year 9 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.