Diverse Hits in De Novo Molecule Design: Diversity-Based Comparison of Goal-Directed Generators.

Since the rise of generative AI models, many goal-directed molecule generators have been proposed as tools for discovering novel drug candidates. However, molecule generators often produce highly similar molecules and tend to overemphasize conformity to an imperfect scoring function rather than capturing the true underlying properties sought. We rectify these two shortcomings by offering diversity-based evaluations using the #Circles metric and considering constraints on scoring function calls or computation time. Our findings highlight the superior performance of SMILES-based autoregressive models in generating diverse sets of desired molecules compared to graph-based models or genetic algorithms.

Improving Few- and Zero-Shot Reaction Template Prediction Using Modern Hopfield Networks.

Finding synthesis routes for molecules of interest is essential in the discovery of new drugs and materials. To find such routes, computer-assisted synthesis planning (CASP) methods are employed, which rely on a single-step model of chemical reactivity. In this study, we introduce a template-based single-step retrosynthesis model based on Modern Hopfield Networks, which learn an encoding of both molecules and reaction templates in order to predict the relevance of templates for a given molecule. The template representation allows generalization across different reactions and significantly improves the performance of template relevance prediction, especially for templates with few or zero training examples. With inference speed up to orders of magnitude faster than baseline methods, we improve or match the state-of-the-art performance for top-k exact match accuracy for k ≥ 3 in the retrosynthesis benchmark USPTO-50k. Code to reproduce the results is available at github.com/ml-jku/mhn-react.

On failure modes in molecule generation and optimization.

There has been a wave of generative models for molecules triggered by advances in the field of Deep Learning. These generative models are often used to optimize chemical compounds towards particular properties or a desired biological activity. The evaluation of generative models remains challenging and suggested performance metrics or scoring functions often do not cover all relevant aspects of drug design projects. In this work, we highlight some unintended failure modes in molecular generation and optimization and how these evade detection by current performance metrics.

Fréchet ChemNet Distance: A Metric for Generative Models for Molecules in Drug Discovery.

The new wave of successful generative models in machine learning has increased the interest in deep learning driven de novo drug design. However, method comparison is difficult because of various flaws of the currently employed evaluation metrics. We propose an evaluation metric for generative models called Fréchet ChemNet distance (FCD). The advantage of the FCD over previous metrics is that it can detect whether generated molecules are diverse and have similar chemical and biological properties as real molecules.

Effects of clonidine and midazolam premedication on bispectral index and recovery after elective surgery.

BACKGROUND AND OBJECTIVES: Alpha-2 agonists offer useful effects that make these drugs an interesting alternative for pharmacological premedication. METHODS: In a randomized, double-blind study, effects of clonidine (150 microg orally), midazolam (7.5 mg orally) and placebo administered 60-90 min prior to estimated anaesthesia induction time were investigated in 60 healthy ASA I or II patients. All patients received dipotassiumchlorazepate the evening before surgery. At predefined time points, effects of premedication on bispectral index, sedation score and visual analogue scales for anxiety and pain, cognitive function and stress hormones were determined. RESULTS: Administration of low-dose clonidine was associated with slightly lower bispectral index scores than a standard dose of midazolam or placebo. There were no significant differences in sedation score, visual analogue scale for anxiety and pain and cognitive function between treatment regimens. Clonidine, but not midazolam, reduced anaesthetic requirements for induction of anaesthesia and prevented an increase in heart rate as well as an increase in adrenocorticotropic hormone plasma levels during the preoperative period (P < 0.05 vs. placebo). Clonidine administration did not delay postoperative recovery. CONCLUSION: Clonidine augmented haemodynamic stability and partially blunted stress responses as determined by adrenocorticotropic hormone plasma levels. In addition, clonidine did not delay postoperative recovery. Therefore, surrogate parameters indicate that preanaesthetic medication with clonidine may be superior to midazolam in healthy individuals. Further studies have to confirm these results with regard to outcome parameters.