Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1016/j.patter.2020.100140 | PATTERNS |
Keywords | DocType | Volume |
AI,ALS,chemotype,compound screening,drug discovery,heat-diffusion equation,iPSC panel,machine learning,phenotypic screening,prediction | Journal | 1 |
Issue | ISSN | Citations |
9 | 2666-3899 | 0 |
PageRank | References | Authors |
0.34 | 0 | 12 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tadashi Hidaka | 1 | 0 | 0.34 |
Keiko Imamura | 2 | 0 | 0.34 |
Takeshi Hioki | 3 | 0 | 0.34 |
Terufumi Takagi | 4 | 0 | 0.34 |
Yoshikazu Giga | 5 | 11 | 6.05 |
Mi-Ho Giga | 6 | 5 | 2.75 |
Yoshiteru Nishimura | 7 | 0 | 0.34 |
Kawahara, Yoshinobu | 8 | 317 | 31.30 |
Satoru Hayashi | 9 | 0 | 0.34 |
Takeshi Niki | 10 | 0 | 0.34 |
Makoto Fushimi | 11 | 0 | 0.34 |
Haruhisa Inoue | 12 | 0 | 0.34 |