A machine learning approach for understanding the metabolomics response of children with autism spectrum disorder to medical cannabis treatment
Abstract Autism spectrum disorder (ASD) is a neurodevelopmental condition impacting behavior, communication, social interaction and learning abilities. Medical cannabis (MC) treatment can reduce clinical symptoms in individuals with ASD. Cannabis-responsive biomarkers are metabolites found in saliva...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-08-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-40073-0 |
| _version_ | 1827634233589366784 |
|---|---|
| author | Jean-Christophe Quillet Michael Siani-Rose Robert McKee Bonni Goldstein Myiesha Taylor Itzhak Kurek |
| author_facet | Jean-Christophe Quillet Michael Siani-Rose Robert McKee Bonni Goldstein Myiesha Taylor Itzhak Kurek |
| author_sort | Jean-Christophe Quillet |
| collection | DOAJ |
| description | Abstract Autism spectrum disorder (ASD) is a neurodevelopmental condition impacting behavior, communication, social interaction and learning abilities. Medical cannabis (MC) treatment can reduce clinical symptoms in individuals with ASD. Cannabis-responsive biomarkers are metabolites found in saliva that change in response to MC treatment. Previously we showed levels of these biomarkers in children with ASD successfully treated with MC shift towards the physiological levels detected in typically developing (TD) children, and potentially can quantify the impact. Here, we tested for the first time the capabilities of machine learning techniques applied to our dynamic, high-resolution and rich feature dataset of cannabis-responsive biomarkers from a limited number of children with ASD before and after MC treatment and a TD group to identify: (1) biomarkers distinguishing ASD and TD groups; (2) non-cannabinoid plant molecules with synergistic effects; and (3) biomarkers associated with specific cannabinoids. We found: (1) lysophosphatidylethanolamine can distinguish between ASD and TD groups; (2) novel phytochemicals contribute to the therapeutic effects of MC treatment by inhibition of acetylcholinesterase; and (3) THC- and CBD-associated cannabis-responsive biomarkers are two distinct groups, while CBG is associated with some biomarkers from both groups. |
| first_indexed | 2024-03-09T15:11:30Z |
| format | Article |
| id | doaj.art-26f26e337e65469099a1eb0fde74671e |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-09T15:11:30Z |
| publishDate | 2023-08-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-26f26e337e65469099a1eb0fde74671e2023-11-26T13:20:30ZengNature PortfolioScientific Reports2045-23222023-08-0113111310.1038/s41598-023-40073-0A machine learning approach for understanding the metabolomics response of children with autism spectrum disorder to medical cannabis treatmentJean-Christophe Quillet0Michael Siani-Rose1Robert McKee2Bonni Goldstein3Myiesha Taylor4Itzhak Kurek5Cannformatics, Inc.Cannformatics, Inc.Cannformatics, Inc.Cannformatics, Inc.Cannformatics, Inc.Cannformatics, Inc.Abstract Autism spectrum disorder (ASD) is a neurodevelopmental condition impacting behavior, communication, social interaction and learning abilities. Medical cannabis (MC) treatment can reduce clinical symptoms in individuals with ASD. Cannabis-responsive biomarkers are metabolites found in saliva that change in response to MC treatment. Previously we showed levels of these biomarkers in children with ASD successfully treated with MC shift towards the physiological levels detected in typically developing (TD) children, and potentially can quantify the impact. Here, we tested for the first time the capabilities of machine learning techniques applied to our dynamic, high-resolution and rich feature dataset of cannabis-responsive biomarkers from a limited number of children with ASD before and after MC treatment and a TD group to identify: (1) biomarkers distinguishing ASD and TD groups; (2) non-cannabinoid plant molecules with synergistic effects; and (3) biomarkers associated with specific cannabinoids. We found: (1) lysophosphatidylethanolamine can distinguish between ASD and TD groups; (2) novel phytochemicals contribute to the therapeutic effects of MC treatment by inhibition of acetylcholinesterase; and (3) THC- and CBD-associated cannabis-responsive biomarkers are two distinct groups, while CBG is associated with some biomarkers from both groups.https://doi.org/10.1038/s41598-023-40073-0 |
| spellingShingle | Jean-Christophe Quillet Michael Siani-Rose Robert McKee Bonni Goldstein Myiesha Taylor Itzhak Kurek A machine learning approach for understanding the metabolomics response of children with autism spectrum disorder to medical cannabis treatment Scientific Reports |
| title | A machine learning approach for understanding the metabolomics response of children with autism spectrum disorder to medical cannabis treatment |
| title_full | A machine learning approach for understanding the metabolomics response of children with autism spectrum disorder to medical cannabis treatment |
| title_fullStr | A machine learning approach for understanding the metabolomics response of children with autism spectrum disorder to medical cannabis treatment |
| title_full_unstemmed | A machine learning approach for understanding the metabolomics response of children with autism spectrum disorder to medical cannabis treatment |
| title_short | A machine learning approach for understanding the metabolomics response of children with autism spectrum disorder to medical cannabis treatment |
| title_sort | machine learning approach for understanding the metabolomics response of children with autism spectrum disorder to medical cannabis treatment |
| url | https://doi.org/10.1038/s41598-023-40073-0 |
| work_keys_str_mv | AT jeanchristophequillet amachinelearningapproachforunderstandingthemetabolomicsresponseofchildrenwithautismspectrumdisordertomedicalcannabistreatment AT michaelsianirose amachinelearningapproachforunderstandingthemetabolomicsresponseofchildrenwithautismspectrumdisordertomedicalcannabistreatment AT robertmckee amachinelearningapproachforunderstandingthemetabolomicsresponseofchildrenwithautismspectrumdisordertomedicalcannabistreatment AT bonnigoldstein amachinelearningapproachforunderstandingthemetabolomicsresponseofchildrenwithautismspectrumdisordertomedicalcannabistreatment AT myieshataylor amachinelearningapproachforunderstandingthemetabolomicsresponseofchildrenwithautismspectrumdisordertomedicalcannabistreatment AT itzhakkurek amachinelearningapproachforunderstandingthemetabolomicsresponseofchildrenwithautismspectrumdisordertomedicalcannabistreatment AT jeanchristophequillet machinelearningapproachforunderstandingthemetabolomicsresponseofchildrenwithautismspectrumdisordertomedicalcannabistreatment AT michaelsianirose machinelearningapproachforunderstandingthemetabolomicsresponseofchildrenwithautismspectrumdisordertomedicalcannabistreatment AT robertmckee machinelearningapproachforunderstandingthemetabolomicsresponseofchildrenwithautismspectrumdisordertomedicalcannabistreatment AT bonnigoldstein machinelearningapproachforunderstandingthemetabolomicsresponseofchildrenwithautismspectrumdisordertomedicalcannabistreatment AT myieshataylor machinelearningapproachforunderstandingthemetabolomicsresponseofchildrenwithautismspectrumdisordertomedicalcannabistreatment AT itzhakkurek machinelearningapproachforunderstandingthemetabolomicsresponseofchildrenwithautismspectrumdisordertomedicalcannabistreatment |