Prediction of Compound Bioactivities Using Heat-Diffusion Equation

Tadashi Hidaka, Keiko Imamura, Takeshi Hioki, Terufumi Takagi, Yoshikazu Giga, Mi Ho Giga, Yoshiteru Nishimura, Yoshinobu Kawahara, Satoru Hayashi, Takeshi Niki, Makoto Fushimi, Haruhisa Inoue

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)


Machine learning is expected to improve low throughput and high assay cost in cell-based phenotypic screening. However, it is still a challenge to apply machine learning to achieving sufficiently complex phenotypic screening due to imbalanced datasets, non-linear prediction, and unpredictability of new chemotypes. Here, we developed a prediction model based on the heat-diffusion equation (PM-HDE) to address this issue. The algorithm was verified as feasible for virtual compound screening using biotest data of 946 assay systems registered with PubChem. PM-HDE was then applied to actual screening. Based on supervised learning of the data of about 50,000 compounds from biological phenotypic screening with motor neurons derived from ALS-patient-induced pluripotent stem cells, virtual screening of >1.6 million compounds was implemented. We confirmed that PM-HDE enriched the hit compounds and identified new chemotypes. This prediction model could overcome the inflexibility in machine learning, and our approach could provide a novel platform for drug discovery.

Original languageEnglish
Article number100140
Issue number9
Publication statusPublished - Dec 11 2020

All Science Journal Classification (ASJC) codes

  • General Decision Sciences


Dive into the research topics of 'Prediction of Compound Bioactivities Using Heat-Diffusion Equation'. Together they form a unique fingerprint.

Cite this