Predicting the Hallucinogenic Potential of Molecules Using Artificial Intelligence.

The development of new drugs addressing serious mental health and other disorders should avoid the psychedelic experience. Analogs of psychedelic drugs can have clinical utility and are termed "psychoplastogens". These represent promising candidates for treating opioid use disorder to reduce drug dependence, with rarely reported serious adverse effects. This drug abuse cessation is linked to the induction of neuritogenesis and increased neuroplasticity, a hallmark of psychedelic molecules, such as lysergic acid diethylamine. Some, but not all psychoplastogens may act through the G-protein coupled receptor (GPCR) 5HT2A whereas others may display very different polypharmacology making prediction of hallucinogenic potential challenging. In the process of developing tools to help design new psychoplastogens, we have used artificial intelligence in the form of machine learning classification models for predicting psychedelic effects using a published in vitro data set from PsychLight (support vector classification (SVC), area under the curve (AUC) 0.74) and in vivo human data derived from books from Shulgin and Shulgin (SVC, AUC, 0.72) with nested five-fold cross validation. We have also explored conformal predictors with ECFP6 and electrostatic descriptors in an effort to optimize them. These models have been used to predict known 5HT2A agonists to assess their potential to act as psychedelics and induce hallucinations for PsychLight (SVC, AUC 0.97) and Shulgin and Shulgin (random forest, AUC 0.71). We have tested these models with head twitch data from the mouse. This predictive capability is desirable to reliably design new psychoplastogens that lack in vivo hallucinogenic potential and help assess existing and future molecules for this potential. These efforts also provide useful insights into understanding the psychedelic structure activity relationship.

The Goldilocks paradigm: comparing classical machine learning, large language models, and few-shot learning for drug discovery applications.

Recent advances in machine learning (ML) have led to newer model architectures including transformers (large language models, LLMs) showing state of the art results in text generation and image analysis as well as few-shot learning (FSLC) models which offer predictive power with extremely small datasets. These new architectures may offer promise, yet the 'no-free lunch' theorem suggests that no single model algorithm can outperform at all possible tasks. Here, we explore the capabilities of classical (SVR), FSLC, and transformer models (MolBART) over a range of dataset tasks and show a 'goldilocks zone' for each model type, in which dataset size and feature distribution (i.e. dataset "diversity") determines the optimal algorithm strategy. When datasets are small ( < 50 molecules), FSLC tend to outperform both classical ML and transformers. When datasets are small-to-medium sized (50-240 molecules) and diverse, transformers outperform both classical models and few-shot learning. Finally, when datasets are of larger and of sufficient size, classical models then perform the best, suggesting that the optimal model to choose likely depends on the dataset available, its size and diversity. These findings may help to answer the perennial question of which ML algorithm is to be used when faced with a new dataset.

Validation of Acetylcholinesterase Inhibition Machine Learning Models for Multiple Species.

Acetylcholinesterase (AChE) is an important enzyme and target for human therapeutics, environmental safety, and global food supply. Inhibitors of this enzyme are also used for pest elimination and can be misused for suicide or chemical warfare. Adverse effects of AChE pesticides on nontarget organisms, such as fish, amphibians, and humans, have also occurred as a result of biomagnifications of these toxic compounds. We have exhaustively curated the public data for AChE inhibition data and developed machine learning classification models for seven different species. Each set of models were built using up to nine different algorithms for each species and Morgan fingerprints (ECFP6) with an activity cutoff of 1 µM. The human (4075 compounds) and eel (5459 compounds) consensus models predicted AChE inhibition activity using external test sets from literature data with 81% and 82% accuracy, respectively, while the reciprocal cross (76% and 82% percent accuracy) was not species-specific. In addition, we also created machine learning regression models for human and eel AChE inhibition to return a predicted IC50 value for a queried molecule. We did observe an improved species specificity in the regression models, where a human support vector regression model of human AChE inhibition (3652 compounds) predicted the IC50s of the human test set to a better extent than the eel regression model (4930 compounds) on the same test set, based on mean absolute percentage error (MAPE = 9.73% vs 13.4%). The predictive power of these models certainly benefits from increasing the chemical diversity of the training set, as evidenced by expanding our human classification model by incorporating data from the Tox21 library of compounds. Of the 10 compounds we tested that were predicted active by this expanded model, two showed >80% inhibition at 100 µM. This machine learning approach therefore offers the ability to rapidly score massive libraries of molecules against the models for AChE inhibition that can then be selected for future in vitro testing to identify potential toxins. It also enabled us to create a public website, MegaAChE, for single-molecule predictions of AChE inhibition using these models at megaache.collaborationspharma.com.

Kidney Function Modifies the Effect of Intraoperative Opioid Dosage on Postoperative Delirium.

BACKGROUND: There are few studies demonstrating how kidney function affects the risk of developing delirium in older adult surgical patients administered opioids. This study determined whether baseline kidney function influences the relationship between morphine equivalent dose and the development of delirium on postoperative day (POD) 2 in patients with hip fracture. METHODS: This retrospective study analyzed emergency department (ED) estimated glomerular filtration rate (eGFR), perioperative serum creatinine, intravenous morphine equivalents, and POD2 delirium assessment by the Confusion Assessment Method in 652 patients aged 65 years or older without preoperative delirium. ED eGFR was used to divide subjects into groups by presence or absence of chronic kidney disease (CKD), and associations of opioid dose with POD2 delirium were compared using multivariable logistic regression. RESULTS: POD2 delirium incidence was 29.8% (N = 194). Intraoperative and postanesthesia care unit (PACU) morphine equivalent dosage as well as ED eGFR were similar comparing patients with and without POD2 delirium. Age, American Society of Anesthesiologists status, and dementia were associated with delirium on POD2. The odds of POD2 delirium increased significantly with increase of intraoperative opioid in patients with CKD (odds ratio = 1.6; 95% confidence interval = 1.2-2.2), but not in patients without CKD (P-interaction = .04). PACU or POD1 opioid doses were not associated with POD2 delirium after covariate adjustment. CONCLUSION: This study suggests that incremental increases in intraoperative opioids combined with CKD increase odds of POD2 delirium after hip fracture repair, compared with patients without CKD.

Before Hospice: Symptom Burden, Dementia, and Social Participation in the Last Year of Life.

Background: Little is known about clinical symptom burden, dementia, and social isolation in the last year of life among older adults. Objective: To describe and contrast the type and severity of symptom burden for older decedents with and without dementia, and whether specific symptoms and presence of dementia are associated with limitations in social participation in the last year of life. Design: Cross-sectional logistic regression analysis of a population-based study. Setting/Subjects: A total of 1270 community-dwelling adults of age ≥65 years in the United States participated in the 2011 National Health and Aging Trends Study and died by 2015. Measurements: Dementia status, 13 clinical symptoms, and limitations in 6 social activities were drawn from the interview preceding death. Severity of sensory, physical, and psychiatric symptom burden was examined in tertiles. Results: Decedents with dementia (37.3%) had higher prevalence of all symptoms (p's < 0.05), except insomnia and breathing problems. Dementia was associated with greater likelihood of high versus low burden of sensory (odds ratio [OR] 4.52 [95% confidence interval {CI} 3.08-6.63]), physical (OR 3.49 [95% CI 2.48-4.91]), and psychiatric (OR 2.80 [95% CI 1.98-3.95]) symptoms. Dementia and physical symptoms (problems with speaking, leg strength/movement, and balance) were independently associated with limitations in at least three social activities (p's < 0.05 for adjusted ORs). Conclusion: Symptom burden is higher in patients with dementia. Dementia and physical symptoms are associated with social activity limitations. Older patients with dementia or physical symptoms may benefit from earlier emphasis on palliative care and quality of life.