Deep phenotypic profiling of neuroactive drugs in larval zebrafish
Abstract Behavioral larval zebrafish screens leverage a high-throughput small molecule discovery format to find neuroactive molecules relevant to mammalian physiology. We screen a library of 650 central nervous system active compounds in high replicate to train deep metric learning models on zebrafi...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-11-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-024-54375-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846165124121886720 |
|---|---|
| author | Leo Gendelev Jack Taylor Douglas Myers-Turnbull Steven Chen Matthew N. McCarroll Michelle R. Arkin David Kokel Michael J. Keiser |
| author_facet | Leo Gendelev Jack Taylor Douglas Myers-Turnbull Steven Chen Matthew N. McCarroll Michelle R. Arkin David Kokel Michael J. Keiser |
| author_sort | Leo Gendelev |
| collection | DOAJ |
| description | Abstract Behavioral larval zebrafish screens leverage a high-throughput small molecule discovery format to find neuroactive molecules relevant to mammalian physiology. We screen a library of 650 central nervous system active compounds in high replicate to train deep metric learning models on zebrafish behavioral profiles. The machine learning initially exploited subtle artifacts in the phenotypic screen, necessitating a complete experimental re-run with rigorous physical well-wise randomization. These large matched phenotypic screening datasets (initial and well-randomized) provide a unique opportunity to quantify and understand shortcut learning in a full-scale, real-world drug discovery dataset. The final deep metric learning model substantially outperforms correlation distance–the canonical way of computing distances between profiles–and generalizes to an orthogonal dataset of diverse drug-like compounds. We validate predictions by prospective in vitro radio-ligand binding assays against human protein targets, achieving a hit rate of 58% despite crossing species and chemical scaffold boundaries. These neuroactive compounds exhibit diverse chemical scaffolds, demonstrating that zebrafish phenotypic screens combined with metric learning achieve robust scaffold hopping capabilities. |
| format | Article |
| id | doaj-art-6e4a4b22ec8c46e2bccdf19be726c086 |
| institution | Kabale University |
| issn | 2041-1723 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj-art-6e4a4b22ec8c46e2bccdf19be726c0862024-11-17T12:35:39ZengNature PortfolioNature Communications2041-17232024-11-0115111610.1038/s41467-024-54375-yDeep phenotypic profiling of neuroactive drugs in larval zebrafishLeo Gendelev0Jack Taylor1Douglas Myers-Turnbull2Steven Chen3Matthew N. McCarroll4Michelle R. Arkin5David Kokel6Michael J. Keiser7Institute for Neurodegenerative Diseases, University of California, San FranciscoInstitute for Neurodegenerative Diseases, University of California, San FranciscoInstitute for Neurodegenerative Diseases, University of California, San FranciscoDepartment of Pharmaceutical Chemistry, University of California, San FranciscoInstitute for Neurodegenerative Diseases, University of California, San FranciscoDepartment of Pharmaceutical Chemistry, University of California, San FranciscoInstitute for Neurodegenerative Diseases, University of California, San FranciscoInstitute for Neurodegenerative Diseases, University of California, San FranciscoAbstract Behavioral larval zebrafish screens leverage a high-throughput small molecule discovery format to find neuroactive molecules relevant to mammalian physiology. We screen a library of 650 central nervous system active compounds in high replicate to train deep metric learning models on zebrafish behavioral profiles. The machine learning initially exploited subtle artifacts in the phenotypic screen, necessitating a complete experimental re-run with rigorous physical well-wise randomization. These large matched phenotypic screening datasets (initial and well-randomized) provide a unique opportunity to quantify and understand shortcut learning in a full-scale, real-world drug discovery dataset. The final deep metric learning model substantially outperforms correlation distance–the canonical way of computing distances between profiles–and generalizes to an orthogonal dataset of diverse drug-like compounds. We validate predictions by prospective in vitro radio-ligand binding assays against human protein targets, achieving a hit rate of 58% despite crossing species and chemical scaffold boundaries. These neuroactive compounds exhibit diverse chemical scaffolds, demonstrating that zebrafish phenotypic screens combined with metric learning achieve robust scaffold hopping capabilities.https://doi.org/10.1038/s41467-024-54375-y |
| spellingShingle | Leo Gendelev Jack Taylor Douglas Myers-Turnbull Steven Chen Matthew N. McCarroll Michelle R. Arkin David Kokel Michael J. Keiser Deep phenotypic profiling of neuroactive drugs in larval zebrafish Nature Communications |
| title | Deep phenotypic profiling of neuroactive drugs in larval zebrafish |
| title_full | Deep phenotypic profiling of neuroactive drugs in larval zebrafish |
| title_fullStr | Deep phenotypic profiling of neuroactive drugs in larval zebrafish |
| title_full_unstemmed | Deep phenotypic profiling of neuroactive drugs in larval zebrafish |
| title_short | Deep phenotypic profiling of neuroactive drugs in larval zebrafish |
| title_sort | deep phenotypic profiling of neuroactive drugs in larval zebrafish |
| url | https://doi.org/10.1038/s41467-024-54375-y |
| work_keys_str_mv | AT leogendelev deepphenotypicprofilingofneuroactivedrugsinlarvalzebrafish AT jacktaylor deepphenotypicprofilingofneuroactivedrugsinlarvalzebrafish AT douglasmyersturnbull deepphenotypicprofilingofneuroactivedrugsinlarvalzebrafish AT stevenchen deepphenotypicprofilingofneuroactivedrugsinlarvalzebrafish AT matthewnmccarroll deepphenotypicprofilingofneuroactivedrugsinlarvalzebrafish AT michellerarkin deepphenotypicprofilingofneuroactivedrugsinlarvalzebrafish AT davidkokel deepphenotypicprofilingofneuroactivedrugsinlarvalzebrafish AT michaeljkeiser deepphenotypicprofilingofneuroactivedrugsinlarvalzebrafish |