Predicting Pharmacokinetics in Rats Using Machine Learning: A Comparative Study Between Empirical, Compartmental, and PBPK-Based Approaches.

A successful drug needs to combine several properties including high potency and good pharmacokinetic (PK) properties to sustain efficacious plasma concentration over time. To estimate required doses for preclinical animal efficacy models or for the clinics, in vivo PK studies need to be conducted. Although the prediction of ADME properties of compounds using machine learning (ML) models based on chemical structures is well established in drug discovery, the prediction of complete plasma concentration-time profiles has only recently gained attention.

Multi-Task ADME/PK prediction at industrial scale: leveraging large and diverse experimental datasets.

ADME (Absorption, Distribution, Metabolism, Excretion) properties are key parameters to judge whether a drug candidate exhibits a desired pharmacokinetic (PK) profile. In this study, we tested multi-task machine learning (ML) models to predict ADME and animal PK endpoints trained on in-house data generated at Boehringer Ingelheim. Models were evaluated both at the design stage of a compound (i.

Interpreting Neural Network Models for Toxicity Prediction by Extracting Learned Chemical Features.

Neural network models have become a popular machine-learning technique for the toxicity prediction of chemicals. However, due to their complex structure, it is difficult to understand predictions made by these models which limits confidence. Current techniques to tackle this problem such as SHAP or integrated gradients provide insights by attributing importance to the input features of individual compounds.

Analysis of the benefits of imputation models over traditional QSAR models for toxicity prediction.

Recently, imputation techniques have been adapted to predict activity values among sparse bioactivity matrices, showing improvements in predictive performance over traditional QSAR models. These models are able to use experimental activity values for auxiliary assays when predicting the activity of a test compound on a specific assay. In this study, we tested three different multi-task imputation techniques on three classification-based toxicity datasets: two of small scale (12 assays each) and one large scale with 417 assays.

Psychobiological Correlates of Aggression in Female Adolescents with Borderline Personality Disorder.

Introduction: Aggressive behavior in reaction to threats, frustration, or provocation is prevalent in borderline personality disorder (BPD). This study investigated aggressive behavior and its biological correlates in adolescents with BPD.

Methods: Twenty-one female adolescents with a DSM-IV BPD diagnosis and 25 sex- and age-matched healthy controls participated in the Taylor Aggression Paradigm (TAP), a laboratory-based experiment measuring aggressive behavior in the interpersonal context.

Prediction and mechanistic analysis of drug-induced liver injury (DILI) based on chemical structure.

Background: Drug-induced liver injury (DILI) is a major safety concern characterized by a complex and diverse pathogenesis. In order to identify DILI early in drug development, a better understanding of the injury and models with better predictivity are urgently needed. One approach in this regard are in silico models which aim at predicting the risk of DILI based on the compound structure.

Carbon monoxide releasing molecule 401 (CORM-401) modulates phase I metabolism of xenobiotics.

Next to its well-studied toxicity, carbon monoxide (CO) is recognized as a signalling molecule in various cellular processes. Thus, CO-releasing molecules (CORMs) are of considerable interest for basic research and drug development. Aim of the present study was to investigate if CO, released from CORMs, inhibits cytochrome P450-dependent monooxygenase (CYP) activity and modulates xenobiotic metabolism.

Reduced sound-evoked and resting-state BOLD fMRI connectivity in tinnitus.

Unlabelled: The exact neurophysiological basis of chronic tinnitus, which affects 10-15% of the population, remains unknown and is controversial at many levels. It is an open question whether phantom sound perception results from increased central neural gain or not, a crucial question for any future therapeutic intervention strategies for tinnitus. We performed a comprehensive study of mild hearing-impaired participants with and without tinnitus, excluding participants with co-occurrences of hyperacusis.