Despite recent interest in deep generative models for scaffold elaboration, their applicability to fragment-to-lead campaigns has so far been limited. This is primarily due to their inability to account for local protein structure or a user9s design hypothesis. We propose a novel method for fragment elaboration, STRIFE that overcomes these issues. STRIFE takes as input Fragment Hotspot Maps (FHMs) extracted from a protein target, and processes them to provide meaningful and interpretable structural information to its generative model, which in turn is able to rapidly generate elaborations with complementary pharmacophores to the protein. In a large-scale evaluation, STRIFE outperforms existing, structure-unaware, fragment elaboration methods in proposing highly ligand efficient elaborations. In addition to automatically extracting pharmacophoric information from a protein target9s FHM, STRIFE optionally allows the user to specify their own design hypotheses.

https://biorxiv.org/content/10.1101/2021.10.21.465268v1.full.pdf

Incorporating Target-Specific Pharmacophoric Information Into Deep Generative Models For Fragment Elaboration

The construction of a virtual library (VL) consisting of novel molecules based on structure-activity relationships is crucial for lead optimization in rational drug design. In this study, we propose a novel scaffold-retained structure generator, EMPIRE (Exhaustive Molecular library Production In a scaffold-REtained manner), to create novel molecules in an arbitrary chemical space. By combining a deep learning model-based generator and a building block-based generator, the proposed method efficiently provides a VL consisting of molecules that retain the input scaffold and contain unique arbitrary substructures. The proposed method enables us to construct rational VLs located in unexplored chemical spaces containing molecules with unique skeletons (e.g., bicyclo[1.1.1]pentane and cubane) or elements (e.g., boron and silicon). We expect EMPIRE to contribute to efficient drug design with unique substructures by virtual screening.

Scaffold-Retained Structure Generator to Exhaustively Create Molecules in an Arbitrary Chemical Space

Despite recent interest in deep generative models for scaffold elaboration, their applicability to fragment-to-lead campaigns has so far been limited. This is primarily due to their inability to account for local protein structure or a user's design hypothesis. We propose a novel method for fragment elaboration, STRIFE, that overcomes these issues. STRIFE takes as input fragment hotspot maps (FHMs) extracted from a protein target and processes them to provide meaningful and interpretable structural information to its generative model, which in turn is able to rapidly generate elaborations with complementary pharmacophores to the protein. In a large-scale evaluation, STRIFE outperforms existing, structure-unaware, fragment elaboration methods in proposing highly ligand-efficient elaborations. In addition to automatically extracting pharmacophoric information from a protein target's FHM, STRIFE optionally allows the user to specify their own design hypotheses. 

Incorporating Target-Specific Pharmacophoric Information into Deep Generative Models for Fragment Elaboration

In this work, we present Link-INVENT as an extension to the existing de novo molecular design platform REINVENT. We provide illustrative examples on how Link-INVENT can be applied on fragment...

Link-INVENT: Generative Linker Design with Reinforcement Learning

A plethora of AI-based techniques now exists to conduct de novo molecule generation that can devise molecules conditioned towards a particular endpoint in the context of drug design. One popular approach is using reinforcement learning to update a recurrent neural network or language-based de novo molecule generator. However, reinforcement learning can be inefficient, sometimes requiring up to 105 molecules to be sampled to optimize more complex objectives, which poses a limitation when using computationally expensive scoring functions like docking or computer-aided synthesis planning models. In this work, we propose a reinforcement learning strategy called Augmented Hill-Climb based on a simple, hypothesis-driven hybrid between REINVENT and Hill-Climb that improves sample-efficiency by addressing the limitations of both currently used strategies. We compare its ability to optimize several docking tasks with REINVENT and benchmark this strategy against other commonly used reinforcement learning strategies including REINFORCE, REINVENT (version 1 and 2), Hill-Climb and best agent reminder. We find that optimization ability is improved ~ 1.5-fold and sample-efficiency is improved ~ 45-fold compared to REINVENT while still delivering appealing chemistry as output. Diversity filters were used, and their parameters were tuned to overcome observed failure modes that take advantage of certain diversity filter configurations. We find that Augmented Hill-Climb outperforms the other reinforcement learning strategies used on six tasks, especially in the early stages of training or for more difficult objectives. Lastly, we show improved performance not only on recurrent neural networks but also on a reinforcement learning stabilized transformer architecture. Overall, we show that Augmented Hill-Climb improves sample-efficiency for language-based de novo molecule generation conditioning via reinforcement learning, compared to the current state-of-the-art. This makes more computationally expensive scoring functions, such as docking, more accessible on a relevant timescale. 

/pdf/augmented-hill-climb-increases-reinforcement-learning-1iipksnn.pdf

Augmented Hill-Climb increases reinforcement learning efficiency for language-based de novo molecule generation

Because of the strong relationship between the desired molecular activity and its structural core, the screening of focused, core-sharing chemical libraries is a key step in lead optimization. Despite the plethora of current research focused on in silico methods for molecule generation, to our knowledge, no tool capable of designing such libraries has been proposed. In this work, we present a novel tool for de novo drug design called LibINVENT. It is capable of rapidly proposing chemical libraries of compounds sharing the same core while maximizing a range of desirable properties. To further help the process of designing focused libraries, the user can list specific chemical reactions that can be used for the library creation. LibINVENT is therefore a flexible tool for generating virtual chemical libraries for lead optimization in a broad range of scenarios. Additionally, the shared core ensures that the compounds in the library are similar, possess desirable properties, and can also be synthesized under the same or similar conditions. The LibINVENT code is freely available in our public repository at https://github.com/MolecularAI/Lib-INVENT. The code necessary for data preprocessing is further available at: https://github.com/MolecularAI/Lib-INVENT-dataset.

/pdf/libinvent-reaction-based-generative-scaffold-decoration-for-4c5iy1phot.pdf

LibINVENT: Reaction-based Generative Scaffold Decoration for in Silico Library Design

Author Correction: Improving de novo molecular design with curriculum learning

Reinforcement learning (RL) is a powerful paradigm that has gained popularity across multiple domains. However, applying RL may come at a cost of multiple interactions between the agent and the environment. This cost can be especially pronounced when the single feedback from the environment is slow or computationally expensive, causing extensive periods of nonproductivity. Curriculum learning (CL) provides a suitable alternative by arranging a sequence of tasks of increasing complexity with the aim of reducing the overall cost of learning. Here, we demonstrate the application of CL for drug discovery. We implement CL in the de novo design platform, REINVENT, and apply it on illustrative de novo molecular design problems of different complexity. The results show both accelerated learning and a positive impact on the quality of the output when compared to standard policy based RL. To our knowledge, this is the first application of CL for the purposes of de novo molecular design. The code is freely available at https://github.com/MolecularAI/Reinvent.

/pdf/improving-de-novo-molecular-design-with-curriculum-learning-4ijfuia2xf.pdf

Vendy Fialková

Papers

LibINVENT: Reaction-based Generative Scaffold Decoration for in Silico Library Design

Author Correction: Improving de novo molecular design with curriculum learning

Improving De Novo Molecular Design with Curriculum Learning