LibINVENT: Reaction-based Generative Scaffold Decoration for <i>in Silico</i> Library Design

Fialková, Vendy; Zhao, Jiaxi; Papadopoulos, Kostas; Engkvist, Ola; Bjerrum, Esben Jannik; Kogej, Thierry; Patronov, Atanas

doi:10.1021/acs.jcim.1c00469

Cited by 53 publications

(90 citation statements)

References 52 publications

(142 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1). 15 The model is adapted from Lib-INVENT, our previously reported generative model for library design by Fialková et al which in turn is based on work by Arús-Pous et al 38,39 Specifically, Link-INVENT features an encoder-decoder architecture consisting of identical RNNs with embedding size 256 and three hidden layers of 512 long short-term memory cells (LSTM). 40 Data Preparation.…”

Section: Methodsmentioning

confidence: 99%

“…Reaction-based Slicing: Slice the filtered ChEMBL compounds following the protocol from our Lib-INVENT work using reaction SMIRKS. 38 The result is a dataset of tuples with the structure:…”

Section: Methodsmentioning

confidence: 99%

“…Thus, 128 linked molecules were generated at each epoch. 38 Correspondingly, the same loss function was used in this work and is constructed by first defining the augmented log likelihood:…”

Section: Generate Training and Validation Setsmentioning

confidence: 99%

“…In contrast, Link-INVENT is trained based on the conditional probabilities of observing a linker given both molecular subunits, similar to the SyntaLinker model reported by Yang et al 17 Secondly, the data preparation to train the Link-INVENT prior was based on reaction-splicing of the ChEMBL compounds similar to the Lib-INVENT library design model we reported previously. 37,38 Our training set contains linkers that join molecular subunits ranging from a few atoms in size to larger moieties with rings. As a result, a single Link-INVENT prior is suited for diverse linker generation tasks.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Link-INVENT: Generative Linker Design with Reinforcement Learning

Guo

Knuth

Margreitter

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

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 linking, scaffold hopping, and PROTACs design case studies where the desirable molecules should satisfy a combination of different criteria. With the help of Reinforcement Learning, the agent used by Link-INVENT learns to generate favourable linkers connecting molecular subunits that satisfy diverse objectives, facilitating practical application of the model for real-world drug discovery projects. We also introduce a range of linker-specific objectives in the scoring function of REINVENT. The code is freely available at https://github.com/MolecularAI/Reinvent.

show abstract

Section: Methodsmentioning

confidence: 99%

“…Reaction-based Slicing: Slice the filtered ChEMBL compounds following the protocol from our Lib-INVENT work using reaction SMIRKS. 38 The result is a dataset of tuples with the structure:…”

Section: Methodsmentioning

confidence: 99%

Section: Generate Training and Validation Setsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Link-INVENT: Generative Linker Design with Reinforcement Learning

Guo

Knuth

Margreitter

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…DEVELOP allows the specification of pharmacophoric constraints and linker/elaboration length, providing a greater degree of control over the resulting molecules. In concurrent work to DEVELOP, Fialková et al 12 proposed LibINVENT, an extension to Scaffold-Decorator 8 which can be used to design core-sharing chemical libraries using only specific chemical reactions. LibIN-VENT also allows users to generate molecules with high 3D similarity to an existing active molecule via reinforcement learning.…”

Section: Introductionmentioning

confidence: 99%

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

Hadfield

Imrie

Merritt

et al. 2021

Preprint

View full text Add to dashboard Cite

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.

show abstract