Novel Psychoactive Substances: Slaying the Dragon With Artificial Intelligence

人工智能 人工智能应用 计算机科学 心理学 化学 法医毒理学 认知科学 工程类 数据科学 工程伦理学
作者
David S. Wishart,K. Prashanthi,Yamilé López‐Hernández
出处
期刊:Therapeutic Drug Monitoring [Lippincott Williams & Wilkins]
卷期号:48 (2): 149-159
标识
DOI:10.1097/ftd.0000000000001429
摘要

BACKGROUND: The emergence of novel psychoactive substances (NPSs) has overwhelmed forensic, health care, and regulatory systems. Conventional analytical techniques are ineffective for identifying known compounds but fail against newly synthesized NPSs lacking reference standards. This review explores the roles of artificial intelligence (AI) and machine learning in addressing growing challenges in NPS identification and characterization. METHODS: The authors reviewed the current forensic workflows and the integration of AI-based approaches, including deep learning models, chemical language models, and spectral prediction tools. Particular emphasis was placed on the DarkNPS framework, which uses Long Short-Term Memory networks and SMILES-based data augmentation to generate millions of plausible NPS structures, and on spectral prediction tools, such as Competitive Fragmentation Modeling for Metabolite Identification (CFM-ID) and novel psychoactive substances-mass spectrometry, for in silico MS/MS spectra generation. Additional emerging AI technologies, such as transformers, graph neural networks, and multimodal frameworks, were also examined. RESULTS: AI-based systems significantly reduced the time and resources required for NPS identification by enabling structure generation, spectral prediction, and prioritization without physical standards. The DarkNPS model successfully predicted structures for >8.9 million plausible NPS compounds, with over 90% of the future market NPS accurately anticipated. In silico MS/MS spectral libraries built using AI tools demonstrated high cosine similarity scores (>0.7) with the experimental spectra, allowing top-hit identification in 75%-90% of the cases. This improved efficiency can facilitate more accurate diagnoses, guide timely treatment decisions, and support public health responses to emerging NPS threats. CONCLUSIONS: Integrating AI with traditional analytical chemistry significantly enhanced the speed, scope, precision, and utility of NPS identification, marking a promising shift in forensic toxicology and chemical surveillance.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
科研通AI6.3的应助被巧克力采纳,获得10
刚刚
刚刚
回望发布了新的文献求助10
1秒前
1秒前
nmd323发布了新的文献求助10
2秒前
爱吃香菜完成签到,获得积分10
2秒前
骞骞完成签到,获得积分10
3秒前
3秒前
今后的应助被帅气的白风采纳,获得10
4秒前
5秒前
李健的小迷弟的应助被兮尔采纳,获得10
5秒前
欧耶发布了新的文献求助10
5秒前
香蕉觅云的应助被雨花石采纳,获得10
6秒前
6秒前
7秒前
Layman发布了新的文献求助10
7秒前
星遨关注了科研通微信公众号
9秒前
一号发布了新的文献求助10
9秒前
www完成签到,获得积分10
10秒前
10秒前
充电宝的应助被额特别采纳,获得10
11秒前
11秒前
柔弱傲丝完成签到,获得积分10
11秒前
12秒前
挚友发布了新的文献求助10
13秒前
初景发布了新的文献求助100
14秒前
如懿发布了新的文献求助10
14秒前
JohnRyan发布了新的文献求助10
15秒前
一号完成签到,获得积分10
16秒前
优美的易真完成签到 ,获得积分10
16秒前
爱听歌的雁开完成签到 ,获得积分10
17秒前
18秒前
永刚发布了新的文献求助10
19秒前
Aikesi完成签到,获得积分10
19秒前
科研通AI2S的应助被欧耶采纳,获得10
20秒前
Maestro_S的应助被tide采纳,获得30
20秒前
bkagyin的应助被金光闪闪采纳,获得10
21秒前
科研通AI65的应助被1900采纳,获得10
21秒前
DW的应助被Chris采纳,获得10
22秒前
23秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
plantTFDB 508
高分子基功能界面水蒸发材料与应用研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8177802
求助须知:如何正确求助?哪些是违规求助? 9568632
关于积分的说明 21799933
捐赠科研通 7772424
什么是DOI,文献DOI怎么找? 3432505
关于科研通互助平台的介绍 2556698
邀请新用户注册赠送积分活动 2478055