AI Science Tracker

Automated design and optimization of multitarget schizophrenia drug candidates by deep learning

Shanghai Institute of Materia Medica, Chinese Academy of Sciences · 20 Mar 2020 · medicine

Discovery

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.

Open in the full catalog for filters, charts and related discoveries. Browse medicine discoveries.

Related catalog entries

Links use documented relationships where available, plus shared catalog context. A shared topic or model family does not establish a scientific dependency.