Journal of Cheminformatics最新文献

This study describes the development and evaluation of six new models for predicting physical–chemical (PC) properties that are highly relevant for chemical hazard, exposure, and risk estimation: solubility (in water S_W and octanol S_O), vapor pressure (VP), and the octanol–water (K_OW), octanol–air (K_OA), and air–water (K_AW) partition ratios. The models are implemented in the Iterative Fragment Selection Quantitative Structure–Activity Relationship (IFSQSAR) python package, Version 1.1.0. These models are implemented as Poly-Parameter Linear Free Energy Relationship (PPLFER) equations which combine experimentally calibrated system parameters and solute descriptors predicted with QSPRs. Two other ancillary models have been developed and implemented, a QSPR for Molar Volume (MV) and a classifier for the physical state of chemicals at room temperature. The IFSQSAR methods for characterizing applicability domain (AD) and calculating uncertainty estimates expressed as 95% prediction intervals (PI) for predicted properties are described and tested on 9,000 measured partition ratios and 4,000 VP and S_W values. The measured data are external to IFSQSAR training and validation datasets and are used to assess the predictivity of the models for “novel chemicals” in an unbiased manner. The 95% PI intervals calculated from validation datasets for partition ratios needed to be scaled by a factor of 1.25 to capture 95% of the external data. Predictions for VP and S_W are more uncertain, primarily due to the challenges in differentiating their physical state (i.e., liquids or solids) at room temperature. The prediction accuracy of the models for log K_OW, log K_AW and log K_OA of novel, data-poor chemicals is estimated to be in the range of 0.7 to 1.4 root mean squared error of prediction (RMSEP), with RMSEP in the range 1.7–1.8 for log VP and log S_W.

Scientific contribution

New partitioning models integrate empirical PPLFER equations and QSARs, allowing for seamless integration of experimental data and model predictions. This work tests the real predictivity of the models for novel chemicals which are not in the model training or external validation datasets.

Graphical Abstract

Generative models are undergoing rapid research and application to de novo drug design. To facilitate their application and evaluation, we present MolScore. MolScore already contains many drug-design-relevant scoring functions commonly used in benchmarks such as, molecular similarity, molecular docking, predictive models, synthesizability, and more. In addition, providing performance metrics to evaluate generative model performance based on the chemistry generated. With this unification of functionality, MolScore re-implements commonly used benchmarks in the field (such as GuacaMol, MOSES, and MolOpt). Moreover, new benchmarks can be created trivially. We demonstrate this by testing a chemical language model with reinforcement learning on three new tasks of increasing complexity related to the design of 5-HT_2a ligands that utilise either molecular descriptors, 266 pre-trained QSAR models, or dual molecular docking. Lastly, MolScore can be integrated into an existing Python script with just three lines of code. This framework is a step towards unifying generative model application and evaluation as applied to drug design for both practitioners and researchers. The framework can be found on GitHub and downloaded directly from the Python Package Index.

Scientific Contribution

MolScore is an open-source platform to facilitate generative molecular design and evaluation thereof for application in drug design. This platform takes important steps towards unifying existing benchmarks, providing a platform to share new benchmarks, and improves customisation, flexibility and usability for practitioners over existing solutions.

Graphical Abstract

In drug discovery, virtual screening is crucial for identifying potential hit compounds. This study aims to present a novel pipeline that employs machine learning models that amalgamates various conventional screening methods. A diverse array of protein targets was selected, and their corresponding datasets were subjected to active/decoy distribution analysis prior to scoring using four distinct methods: QSAR, Pharmacophore, docking, and 2D shape similarity, which were ultimately integrated into a single consensus score. The fine-tuned machine learning models were ranked using the novel formula “w_new”, consensus scores were calculated, and an enrichment study was performed for each target. Distinctively, consensus scoring outperformed other methods in specific protein targets such as PPARG and DPP4, achieving AUC values of 0.90 and 0.84, respectively. Remarkably, this approach consistently prioritized compounds with higher experimental PIC₅₀ values compared to all other screening methodologies. Moreover, the models demonstrated a range of moderate to high performance in terms of R² values during external validation. In conclusion, this novel workflow consistently delivered superior results, emphasizing the significance of a holistic approach in drug discovery, where both quantitative metrics and active enrichment play pivotal roles in identifying the best virtual screening methodology.

Scientific contribution

We presented a novel consensus scoring workflow in virtual screening, merging diverse methods for enhanced compound selection. We also introduced ‘w_new’, a groundbreaking metric that intricately refines machine learning model rankings by weighing various model-specific parameters, revolutionizing their efficacy in drug discovery in addition to other domains.

Graphical Abstract

Effective visualization of small molecules is paramount in conveying concepts and results in cheminformatics. Scalable vector graphics (SVG) are preferred for creating such visualizations, as SVGs can be easily altered in post-production and exported to other formats. A wide spectrum of software applications already exist that can visualize molecules, and customize these visualizations, in many ways. However, software packages that can output projected 3D models onto a 2D canvas directly as SVG, while being programmatically accessible from Python, are lacking. Here, we introduce CineMol, which can draw vectorized approximations of three-dimensional small molecule models in seconds, without triangulation or ray tracing, resulting in files of around 50–300 kilobytes per molecule model for compounds with up to 45 heavy atoms. The SVGs outputted by CineMol can be readily modified in popular vector graphics editing software applications. CineMol is written in Python and can be incorporated into any existing Python cheminformatics workflow, as it only depends on native Python libraries. CineMol also provides programmatic access to all its internal states, allowing for per-atom and per-bond-based customization. CineMol’s capacity to programmatically create molecular visualizations suitable for post-production offers researchers and scientists a powerful tool for enhancing the clarity and visual impact of their scientific presentations and publications in cheminformatics, metabolomics, and related scientific disciplines.

Scientific contribution

We introduce CineMol, a Python-based tool that provides a valuable solution for cheminformatics researchers by enabling the direct generation of high-quality approximations of two-dimensional SVG visualizations from three-dimensional small molecule models, all within a programmable Python framework. CineMol offers a unique combination of speed, efficiency, and accessibility, making it an indispensable tool for researchers in cheminformatics, especially when working with SVG visualizations.

We present an updated overview of the AiZynthFinder package for retrosynthesis planning. Since the first version was released in 2020, we have added a substantial number of new features based on user feedback. Feature enhancements include policies for filter reactions, support for any one-step retrosynthesis model, a scoring framework and several additional search algorithms. To exemplify the typical use-cases of the software and highlight some learnings, we perform a large-scale analysis on several hundred thousand target molecules from diverse sources. This analysis looks at for instance route shape, stock usage and exploitation of reaction space, and points out strengths and weaknesses of our retrosynthesis approach. The software is released as open-source for educational purposes as well as to provide a reference implementation of the core algorithms for synthesis prediction. We hope that releasing the software as open-source will further facilitate innovation in developing novel methods for synthetic route prediction. AiZynthFinder is a fast, robust and extensible open-source software and can be downloaded from https://github.com/MolecularAI/aizynthfinder.