Automated design and optimization of multitarget schizophrenia drug candidates by deep learning
Source check: Needs source check. Not independent scientific confirmation.
Finding: The later journal abstract reports a deep recurrent generator and multitask activity network, receptor testing of compound 3 and six analogs, and animal-model antipsychotic effects for compound 8 with low reported sedation/catalepsy potential. These are preclinical results. Journal online publication was 2020-07-12; the original preprint’s posting date and version-specific results remain unchecked.
Technology: Deep recurrent generator and multitask deep neural network
Publication: Preprint · Test context: direct test. Catalog categories, not an evidence grade.
- AI contribution
- A deep recurrent neural network generated and iteratively refined candidate molecules; a multitask deep neural network predicted D2, 5-HT1A, and 5-HT2A activity to rank candidates and guide hit expansion.
- Test and result
- The journal abstract reports synthesis and receptor testing of compound 3, experimental evaluation of six analogs, and animal-model testing of compound 8. The accessible abstract does not provide animal species, sample sizes, dose, comparator, or behavioral endpoint details.
- Limitation / still unknown
- Animal model, group sizes, dose, comparator, and behavioral endpoints were not available in the reviewed abstract. No human safety or efficacy was established. The record's date refers to the preprint, while the journal version was online 2020-07-12 and assigned to the 2020-10-15 issue.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://doi.org/10.1101/2020.03.19.999615
Needs source check · editorial details
The source has not been fully checked or contains conflicting information. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review date: 18 Nov 2026. Review scope: Indexed primary PubMed journal abstract and online/issue dates; official bioRxiv v1 and full journal Methods not accessed..
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 2/5 · Validation 3/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.