Virtual Chemical Libraries Walters, W Patrick
Journal of medicinal chemistry,
02/2019, Letnik:
62, Številka:
3
Journal Article
Recenzirano
Advances in computer processing speed and storage capacity have enabled researchers to generate virtual chemical libraries containing billions of molecules. While these numbers appear large, they are ...only a small fraction of the number of organic molecules that could potentially be synthesized. This review provides an overview of recent advances in the generation and use of virtual chemical libraries in medicinal chemistry. We also consider the practical implications of these libraries in drug discovery programs and highlight a number of current and future challenges.
Conspectus Recent advances in computer hardware and software have led to a revolution in deep neural networks that has impacted fields ranging from language translation to computer vision. Deep ...learning has also impacted a number of areas in drug discovery, including the analysis of cellular images and the design of novel routes for the synthesis of organic molecules. While work in these areas has been impactful, a complete review of the applications of deep learning in drug discovery would be beyond the scope of a single Account. In this Account, we will focus on two key areas where deep learning has impacted molecular design: the prediction of molecular properties and the de novo generation of suggestions for new molecules. One of the most significant advances in the development of quantitative structure–activity relationships (QSARs) has come from the application of deep learning methods to the prediction of the biological activity and physical properties of molecules in drug discovery programs. Rather than employing the expert-derived chemical features typically used to build predictive models, researchers are now using deep learning to develop novel molecular representations. These representations, coupled with the ability of deep neural networks to uncover complex, nonlinear relationships, have led to state-of-the-art performance. While deep learning has changed the way that many researchers approach QSARs, it is not a panacea. As with any other machine learning task, the design of predictive models is dependent on the quality, quantity, and relevance of available data. Seemingly fundamental issues, such as optimal methods for creating a training set, are still open questions for the field. Another critical area that is still the subject of multiple research efforts is the development of methods for assessing the confidence in a model. Deep learning has also contributed to a renaissance in the application of de novo molecule generation. Rather than relying on manually defined heuristics, deep learning methods learn to generate new molecules based on sets of existing molecules. Techniques that were originally developed for areas such as image generation and language translation have been adapted to the generation of molecules. These deep learning methods have been coupled with the predictive models described above and are being used to generate new molecules with specific predicted biological activity profiles. While these generative algorithms appear promising, there have been only a few reports on the synthesis and testing of molecules based on designs proposed by generative models. The evaluation of the diversity, quality, and ultimate value of molecules produced by generative models is still an open question. While the field has produced a number of benchmarks, it has yet to agree on how one should ultimately assess molecules “invented” by an algorithm.
Code Sharing in the Open Science Era Walters, W. Patrick
Journal of chemical information and modeling,
10/2020, Letnik:
60, Številka:
10
Journal Article
Recenzirano
Odprti dostop
Many high-profile scientific journals have established policies mandating the release of code accompanying papers that describe computational methods. Unfortunately, the majority of journals that ...publish papers in Computational Chemistry and Cheminformatics have yet to define such guidelines. This Viewpoint reviews the current state of reproducibility for the field and makes a case for the inclusion of code with computational papers.
Introduction:
Lipinski's 1997 publication of the 'Rule of 5' (Ro5) was one of the most influential recent medicinal chemistry publications. In the almost 15 years since the publication of the ...original Ro5 paper, multiple groups have refined and expanded on the Ro5 and proposed additional heuristics to guide medicinal chemistry programs. While many variations on the Ro5 have been proposed, the majority of these remain close to the original guidelines proposed by Lipinski et al.
Areas covered:
This review provides an overview of heuristic methods for the design of drug-like molecules. The article also provides the reader with suggestions on future directions for the field.
Expert opinion:
While Lipinski's publication of the Ro5 and subsequent work by other authors has made medicinal chemists more aware of the relationships between physical properties and ADMET, it has hardly been a panacea. Pharmaceutical productivity continues to lag, and the industry is exploring new models to improve its output. If we are to progress, we need to move beyond simple models based on lipophilicity and gain a deeper understanding of molecular interactions.
While machine learning models have become a mainstay in Cheminformatics, the field has yet to agree on standards for model evaluation and comparison. In many cases, authors compare methods by ...performing multiple folds of cross-validation and reporting the mean value for an evaluation metric such as the area under the receiver operating characteristic. These comparisons of mean values often lack statistical rigor and can lead to inaccurate conclusions. In the interest of encouraging best practices, this tutorial provides an example of how multiple methods can be compared in a statistically rigorous fashion.
New Trends in Virtual Screening Walters, W. Patrick; Wang, Renxiao
Journal of chemical information and modeling,
09/2020, Letnik:
60, Številka:
9
Journal Article
Artificial intelligence (AI) tools are increasingly being applied in drug discovery. While some protagonists point to vast opportunities potentially offered by such tools, others remain sceptical, ...waiting for a clear impact to be shown in drug discovery projects. The reality is probably somewhere in-between these extremes, yet it is clear that AI is providing new challenges not only for the scientists involved but also for the biopharma industry and its established processes for discovering and developing new medicines. This article presents the views of a diverse group of international experts on the 'grand challenges' in small-molecule drug discovery with AI and the approaches to address them.
The acid/base properties of a molecule are among the most fundamental for drug action. However, they are often overlooked in a prospective design manner unless it has been established that a certain ...ionization state (e.g., quaternary base or presence of a carboxylic acid) appears to be required for activity. In medicinal chemistry optimization programs it is relatively common to attenuate basicity to circumvent undesired effects such as lack of biological selectivity or safety risks such as hERG or phospholipidosis. However, teams may not prospectively explore a range of carefully chosen compound pK a values as part of an overall chemistry strategy or design hypothesis. This review summarizes the potential advantages and disadvantages of both acidic and basic drugs and provides some new analyses based on recently available public data.
At the recent Artificial Intelligence Applications in Biopharma Summit in Boston, USA, a panel of scientists from industry who work at the interface of machine learning and pharma discussed the ...diverging opinions on the past, present and future role of AI for ADME/Tox in drug discovery and development.