Machine learning accelerates pharmacophore-based virtual screening of MAO inhibitors.

Nowadays, an efficient and robust virtual screening procedure is crucial in the drug discovery process, especially when performed on large and chemically diverse databases. Virtual screening methods, like molecular docking and classic QSAR models, are limited in their ability to handle vast numbers of compounds and to learn from scarce data, respectively. In this study, we introduce a universal methodology that uses a machine learning-based approach to predict docking scores without the need for time-consuming molecular docking procedures.

Relative molecule self-attention transformer.

The prediction of molecular properties is a crucial aspect in drug discovery that can save a lot of money and time during the drug design process. The use of machine learning methods to predict molecular properties has become increasingly popular in recent years. Despite advancements in the field, several challenges remain that need to be addressed, like finding an optimal pre-training procedure to improve performance on small datasets, which are common in drug discovery.

Deep Learning Models Capture Histological Disease Activity in Crohn's Disease and Ulcerative Colitis with High Fidelity.

Background And Aims: Histological disease activity in inflammatory bowel disease [IBD] is associated with clinical outcomes and is an important endpoint in drug development. We developed deep learning models for automating histological assessments in IBD.

Methods: Histology images of intestinal mucosa from phase 2 and phase 3 clinical trials in Crohn's disease [CD] and ulcerative colitis [UC] were used to train artificial intelligence [AI] models to predict the Global Histology Activity Score [GHAS] for CD and Geboes histopathology score for UC.

Extended study on atomic featurization in graph neural networks for molecular property prediction.

Graph neural networks have recently become a standard method for analyzing chemical compounds. In the field of molecular property prediction, the emphasis is now on designing new model architectures, and the importance of atom featurization is oftentimes belittled. When contrasting two graph neural networks, the use of different representations possibly leads to incorrect attribution of the results solely to the network architecture.

Generative Models Should at Least Be Able to Design Molecules That Dock Well: A New Benchmark.

Designing compounds with desired properties is a key element of the drug discovery process. However, measuring progress in the field has been challenging due to the lack of realistic retrospective benchmarks, and the large cost of prospective validation. To close this gap, we propose a benchmark based on docking, a widely used computational method for assessing molecule binding to a protein.

Feature-Based Interpolation and Geodesics in the Latent Spaces of Generative Models.

Interpolating between points is a problem connected simultaneously with finding geodesics and study of generative models. In the case of geodesics, we search for the curves with the shortest length, while in the case of generative models, we typically apply linear interpolation in the latent space. However, this interpolation uses implicitly the fact that Gaussian is unimodal.

Docking-based generative approaches in the search for new drug candidates.

Despite the popularity of virtual screening (VS) of existing compound libraries, the search for new potential drug candidates also takes advantage of generative protocols, where new compound suggestions are enumerated using various algorithms. To increase the activity potency of generative approaches, they have recently been coupled with molecular docking, a leading methodology of structure-based drug design (SBDD). In this review, we summarize progress since docking-based generative models emerged.

Generation of new inhibitors of selected cytochrome P450 subtypes- study.

Physicochemical and pharmacokinetic compound profile has crucial impact on compound potency to become a future drug. Ligands with desired activity profile cannot be used for treatment if they are characterized by unfavourable physicochemical or ADMET properties. In the study, we consider metabolic stability and focus on selected subtypes of cytochrome P450 - proteins, which take part in the first phase of compound transformations in the organism.

Mol-CycleGAN: a generative model for molecular optimization.

Designing a molecule with desired properties is one of the biggest challenges in drug development, as it requires optimization of chemical compound structures with respect to many complex properties. To improve the compound design process, we introduce Mol-CycleGAN-a CycleGAN-based model that generates optimized compounds with high structural similarity to the original ones. Namely, given a molecule our model generates a structurally similar one with an optimized value of the considered property.

[Risk of incarceration of persons undergoing psychiatric care. A retrospective longitudinal study on the French department of Oise using information from a psychiatric hospital discharge database].

Introduction: Compared to the general population, persons with mental disorders are overrepresented in prison. In a study carried out in Picardy (northern France) in 2017, a quarter of those entering prison had had contact with a psychiatric service prior to their incarceration. Since to our knowledge no work on this subject has been published in France, we conducted a retrospective study, the main objective of which was to propose an estimate measure of incarceration likelihood in people with mental disorders.

Mental disorders on admission to jail: A study of prevalence and a comparison with a community sample in the north of France.

Background: The aim of the present study was to estimate prevalence rates of psychiatric and substance use disorders in male and female prisoners on admission to prison in the north of France and compare the frequency of these disorders to the general population.

Methods: This cross-sectional survey on Mental Health in the Prison Population (MHPP), conducted between March 2014 and April 2017, interviewed 653 randomly selected men and women who had recently been committed to the French general population prison system in the Nord and Pas-de-Calais departments. For each subject, the Mini International Neuropsychiatric Interview (MINI), a standardized psychiatric interview, was used to screen for psychiatric and substance use disorders.

[Supervised off-label prescribing of methylphenidate in adult ADHD].

Objective: Off-label prescription is a common practice in psychiatry, raising health and economic concerns. Collegial consultation could allow a framed prescription of treatments that are not authorized in specific indications. Attention Deficit Hyperactivity in adult populations (ADHD) is a striking example of a pathology where off-label prescription is frequent.

Heart rate variability changes and emotion regulation abilities in short- and long-term abstinent alcoholic individuals.

Introduction: Difficulties in identifying and regulating emotion are recognized as major factors of relapse in alcohol use disorders (AUD). This study aimed to evaluate the differences of emotion regulation processes in AUD patients with short-term (STA, less than one month) and long-term abstinence (LTA, at least six months) by recording the high frequency of Heart Rate Variability (HF-HRV) in response to emotional and neutral stimuli.

Method: Emotional induction constituted the presentation of highly emotional and neutral pictures (IAPS data base) presenting human interactions.

Autobiographical Memory Deficits in Alcohol-Dependent Patients with Short- and Long-Term Abstinence.

Background: Autobiographical memory (AM) enables the storage and retrieval of life experiences that allow individuals to build their sense of identity. Several AM impairments have been described in patients with alcohol abuse disorders without assessing whether such deficits can be recovered. This cross-sectional study aimed to identify whether the semantic (SAM) and episodic (EAM) dimensions of AM are affected in individuals with alcohol dependence after short-term abstinence (STA) or long-term abstinence (LTA).

[Continued use of hypnotic initiated as part of antidepressant treatment].

Introduction: Chronic hypnotic prescription is common, but not recommended. This study analysed whether hypnotic use at the beginning of antidepressant treatment could be the starting point for future hypnotic use.

Methods: Concomitant hypnotic and antidepressant prescriptions were retrieved from the National Health Insurance Fund for employees of the Nord-Pas-de-Calais database.

[Outpatient cannabis withdrawal programme].

Cannabis is the most consumed illicit substance in France, and its use can lead to dependency. Lille university hospital, le Pari association, offers patients wanting to stop using cannabis a support therapy based on positive feedback led by nurses, as well as symptomatic treatment of anxiety and sleep disorders.

[Temporary recommendation for use on off-label baclofen: viewpoint of Prescribers of the CAMTEA system].

The use of high dose baclofen for alcohol-dependence emerged in France from 2008 based on empirical findings, and is still off-label. However, due to the rapid increase in this prescribing practice, the French health authorities have decided to frame it using an extraordinary regulatory measure named "temporary recommendation for use" (TRU). Baclofen prescribers from CAMTEA, a regional team-based off-label system for supervising baclofen prescribing, which was developed much prior to the TRU, discuss herein the pros and cons of this measure and the applicability of its different aspects in the daily clinical practice.

Safety and drinking outcomes among patients with comorbid alcohol dependence and borderline personality disorder treated with high-dose baclofen: a comparative cohort study.

In France, the off-label use of high-dose baclofen (HDB) for alcohol dependence is spreading. HDB induces frequent neuropsychiatric adverse events (AEs). Borderline personality disorder (BPD) is a major axis-two psychiatric disorder that exposes to frequent comorbid alcohol dependence and increased risky behaviors.