| 1. |
- Cousins, David L., et al.
(author)
-
Pyrimidin-6-yl Trifluoroborate Salts as Versatile Templates for Heterocycle Synthesis
- 2021
-
In: Angewandte Chemie International Edition. - : Wiley. - 1433-7851 .- 1521-3773. ; 133:17, s. 9498-9501
-
Journal article (peer-reviewed)abstract
- We report a novel and general method to access a highly under‐studied privileged scaffold – pyrimidines bearing a trifluoroborate at C4, and highlight the broad utility of these intermediates in a rich array of downstream functionalization reactions. This chemistry is underpinned by the unique features of the trifluoroborate group; its robustness provides an opportunity to carry out chemoselective reactions at other positions on the pyrimidine while providing a pathway for elaboration at the C‐B bond when suitably activated.
|
|
| 2. |
- He, Jiazhen, et al.
(author)
-
Evaluation of reinforcement learning in transformer-based molecular design
- 2024
-
In: Journal of Cheminformatics. - 1758-2946 .- 1758-2946. ; 16:1
-
Journal article (peer-reviewed)abstract
- Designing compounds with a range of desirable properties is a fundamental challenge in drug discovery. In pre-clinical early drug discovery, novel compounds are often designed based on an already existing promising starting compound through structural modifications for further property optimization. Recently, transformer-based deep learning models have been explored for the task of molecular optimization by training on pairs of similar molecules. This provides a starting point for generating similar molecules to a given input molecule, but has limited flexibility regarding user-defined property profiles. Here, we evaluate the effect of reinforcement learning on transformer-based molecular generative models. The generative model can be considered as a pre-trained model with knowledge of the chemical space close to an input compound, while reinforcement learning can be viewed as a tuning phase, steering the model towards chemical space with user-specific desirable properties. The evaluation of two distinct tasks—molecular optimization and scaffold discovery—suggest that reinforcement learning could guide the transformer-based generative model towards the generation of more compounds of interest. Additionally, the impact of pre-trained models, learning steps and learning rates are investigated. Scientific contribution Our study investigates the effect of reinforcement learning on a transformer-based generative model initially trained for generating molecules similar to starting molecules. The reinforcement learning framework is applied to facilitate multiparameter optimisation of starting molecules. This approach allows for more flexibility for optimizing user-specific property profiles and helps finding more ideas of interest.
|
|
| 3. |
- He, Jiazhen, et al.
(author)
-
Molecular optimization by capturing chemist’s intuition using deep neural networks
- 2021
-
In: Journal of Cheminformatics. - : BioMed Central. - 1758-2946. ; 13:1
-
Journal article (peer-reviewed)abstract
- A main challenge in drug discovery is finding molecules with a desirable balance of multiple properties. Here, we focus on the task of molecular optimization, where the goal is to optimize a given starting molecule towards desirable properties. This task can be framed as a machine translation problem in natural language processing, where in our case, a molecule is translated into a molecule with optimized properties based on the SMILES representation. Typically, chemists would use their intuition to suggest chemical transformations for the starting molecule being optimized. A widely used strategy is the concept of matched molecular pairs where two molecules differ by a single transformation. We seek to capture the chemist’s intuition from matched molecular pairs using machine translation models. Specifically, the sequence-to-sequence model with attention mechanism, and the Transformer model are employed to generate molecules with desirable properties. As a proof of concept, three ADMET properties are optimized simultaneously: logD, solubility, and clearance, which are important properties of a drug. Since desirable properties often vary from project to project, the user-specified desirable property changes are incorporated into the input as an additional condition together with the starting molecules being optimized. Thus, the models can be guided to generate molecules satisfying the desirable properties. Additionally, we compare the two machine translation models based on the SMILES representation, with a graph-to-graph translation model HierG2G, which has shown the state-of-the-art performance in molecular optimization. Our results show that the Transformer can generate more molecules with desirable properties by making small modifications to the given starting molecules, which can be intuitive to chemists. A further enrichment of diverse molecules can be achieved by using an ensemble of models.
|
|
| 4. |
- He, Jiazhen, et al.
(author)
-
Transformer-based molecular optimization beyond matched molecular pairs
- 2022
-
In: Journal of Cheminformatics. - : Springer Science and Business Media LLC. - 1758-2946 .- 1758-2946. ; 14:1
-
Journal article (peer-reviewed)abstract
- Molecular optimization aims to improve the drug profile of a starting molecule. It is a fundamental problem in drug discovery but challenging due to (i) the requirement of simultaneous optimization of multiple properties and (ii) the large chemical space to explore. Recently, deep learning methods have been proposed to solve this task by mimicking the chemist's intuition in terms of matched molecular pairs (MMPs). Although MMPs is a widely used strategy by medicinal chemists, it offers limited capability in terms of exploring the space of structural modifications, therefore does not cover the complete space of solutions. Often more general transformations beyond the nature of MMPs are feasible and/or necessary, e.g. simultaneous modifications of the starting molecule at different places including the core scaffold. This study aims to provide a general methodology that offers more general structural modifications beyond MMPs. In particular, the same Transformer architecture is trained on different datasets. These datasets consist of a set of molecular pairs which reflect different types of transformations. Beyond MMP transformation, datasets reflecting general structural changes are constructed from ChEMBL based on two approaches: Tanimoto similarity (allows for multiple modifications) and scaffold matching (allows for multiple modifications but keep the scaffold constant) respectively. We investigate how the model behavior can be altered by tailoring the dataset while using the same model architecture. Our results show that the models trained on differently prepared datasets transform a given starting molecule in a way that it reflects the nature of the dataset used for training the model. These models could complement each other and unlock the capability for the chemists to pursue different options for improving a starting molecule.
|
|
| 5. |
- Lesko, Marek, et al.
(author)
-
Strategies for predictive modeling of overloaded oligonucleotide elution profiles in ion-pair chromatography
- 2023
-
In: Journal of Chromatography A. - : Elsevier. - 0021-9673 .- 1873-3778. ; 1711
-
Journal article (peer-reviewed)abstract
- Due to their potential for gene regulation, oligonucleotides have moved into focus as one of the preferred modalities modulating currently undruggable disease-associated targets. In the course of synthesis and storage of oligonucleotides a significant number of compound-related impurities can be generated. Purification protocols and analytical methods have become crucial for the therapeutic application of any oligonucleotides, be they antisense oligonucleotides (ASOs), small interfering ribonucleic acids (siRNAs) or conjugates. Ion-pair chromatography is currently the standard method for separating and analyzing therapeutic oligonucleotides. Although mathematical modeling can improve the accuracy and efficiency of ion-pair chromatography, its application remains challenging. Simple models may not be suitable to treat advanced single molecules, while complex models are still inefficient for industrial oligonucleotide optimization processes. Therefore, fundamental research to improve the accuracy and simplicity of mathematical models in ion-pair chromatography is still a necessity. In this study, we predict overloaded concentration profiles of oligonucleotides in ion-pair chromatography and compare relatively simple and more advanced predictive models. The experimental system consists of a traditional C18 column using (dibutyl)amine as the ion-pair reagent and acetonitrile as organic modifier. The models were built and tested based on three crude 16-mer oligonucleotides with varying degrees of phosphorothioation, as well as their respective n – 1 and (P = O)1 impurities. In short, the proposed models were suitable to predict the overloaded concentration profiles for different slopes of the organic modifier gradient and column load.
|
|
