Molecule Edit Graph Attention Network: Modeling Chemical Reactions as Sequences of Graph Edits

Sacha, Mikołaj; Błaż, Mikołaj; Byrski, Piotr; Dąbrowski-Tumański, Paweł; Chromiński, Mikołaj; Loska, Rafał; Włodarczyk-Pruszyński, Paweł; Jastrzębski, Stanisław

doi:10.1021/acs.jcim.1c00537

Cited by 91 publications

(108 citation statements)

References 72 publications

Supporting

Mentioning

108

Contrasting

Order By: Relevance

“…[see e.g. 4,5,6,7,8,9,10,11,12,13,14]. For the practitioner that wants to use a method for predictions, or for a researcher developing a novel method, there are several comparisons for a subset of the available methods.…”

Section: Introductionmentioning

confidence: 99%

PaRoutes: a framework for benchmarking retrosynthesis route predictions

Genheden

Bjerrum

2022

Preprint

View full text Add to dashboard Cite

We introduce a framework for benchmarking multi-step retrosynthesis methods, i.e. route predictions, called PaRoutes. The framework consists of two sets of 10,000 synthetic routes extracted from the patent literature, a list of stock compounds, and a curated set of reactions on which one-step retrosynthesis models can be trained. PaRoutes also comes with scripts to compute route quality and route diversity quantities that are important for comparing methods. We use the PaRoute framework to compare three methods implemented in the AiZynthFinder software: Monte Carlo tree search (MCTS), Retro*, and a depth-first proof-number search (DFPN) algorithm, all using a template-based one-step retrosynthesis model. It is found that DFPN is inferior to both MCTS and Retro* and cannot be recommended in its current implementation. MCTS and Retro* are on a par with regard to search speed and the ability to find routes in which all starting material is in stock. However, MCTS outperforms Retro* when it comes to route quality and route diversity. MCTS more easily recovers the reference routes and tends to find a diverse set of solutions for a greater portion of the targets. We encourage practitioners and developers to benchmark their algorithms using PaRoutes and we envisage that the framework will become the community standard to compare retrosynthesis route predictions. It is available at https://github.com/MolecularAI/PaRoutes

show abstract

Section: Introductionmentioning

confidence: 99%

PaRoutes: a framework for benchmarking retrosynthesis route predictions

Genheden

Bjerrum

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…As baseline models, we compared our prediction results with five state-of-the-art retrosynthesis models: GLN (conditional graph logic network), 14 G2G (graph to graph), 15 GraphRetro , 16 MEGAN (molecule edit graph attention network), 17 and Augmented Transformer . 25 We denote our method by LocalRetro to emphasize the core idea, local reactivity prediction.…”

Section: Methods and Datasetsmentioning

confidence: 99%

Deep Retrosynthetic Reaction Prediction using Local Reactivity and Global Attention

Chen

Jung

2021

JACS Au

115

View full text Add to dashboard Cite

As a fundamental problem in chemistry, retrosynthesis aims at designing reaction pathways and intermediates for a target compound. The goal of artificial intelligence (AI)-aided retrosynthesis is to automate this process by learning from the previous chemical reactions to make new predictions. Although several models have demonstrated their potentials for automated retrosynthesis, there is still a significant need to further enhance the prediction accuracy to a more practical level. Here we propose a local retrosynthesis framework called LocalRetro , motivated by the chemical intuition that the molecular changes occur mostly locally during the chemical reactions. This differs from nearly all existing retrosynthesis methods that suggest reactants based on the global structures of the molecules, often containing fine details not directly relevant to the reactions. This local concept yields local reaction templates involving the atom and bond edits. Because the remote functional groups can also affect the overall reaction path as a secondary aspect, the proposed locally encoded retrosynthesis model is then further refined to account for the nonlocal effects of chemical reaction through a global attention mechanism. Our model shows a promising 89.5 and 99.2% round-trip accuracy at top-1 and top-5 predictions for the USPTO-50K dataset containing 50 016 reactions. We further demonstrate the validity of LocalRetro on a large dataset containing 479 035 reactions (UTPTO-MIT) with comparable round-trip top-1 and top-5 accuracy of 87.0 and 97.4%, respectively. The practical application of the model is also demonstrated by correctly predicting the synthesis pathways of five drug candidate molecules from various literature.

show abstract

“…Baselines Template-based GLN (Dai et al, 2019), templatefree G2G (Shi et al, 2020) and RetroXpert (Yan et al, 2020) are primary baselines, which not only achieve state-of-theart performance, but also provide open-source PyTorch code that allows us to verify their effectiveness. To show broad superiority, we also comapre SemiRetro with other baselines, incuding RetroSim (Coley et al, 2017b), NeuralSym (Segler & Waller, 2017), SCROP (Zheng et al, 2019), LV-Transformer (Chen et al, 2019), GraphRetro (Somnath et al, 2021), MEGAN (Sacha et al, 2021), MHNreact (Seidl et al, 2021), and Dual model (Sun et al, 2020). As the retrosynthesis task is quite complex, subtle implementation differences or mistakes may cause critical performance fluctuations.…”

Section: Basic Settingmentioning

confidence: 99%

“…For example, the top-50 semi-templates cover the case of 92.6%, while the full-templates only cover 26.8%. (Shi et al, 2020) 61.0 81.3 86.0 88.7 48.9 67.6 72.5 75.5 RetroXpert (Yan et al, 2020) 62.1 75.8 78.5 80.9 50.4 61.1 62.3 63.4 GraphRetro (Somnath et al, 2021) 63.9 81.5 85.2 88.1 53.7 68.3 72.2 75.5 MEGAN (Sacha et al, 2021) 60.7 82.0 87.5 91.6 48.1 70.7 78.4 86.1 MHNreact (Seidl et al, 2021) ----50.5 73.9 81.0 87.9 Dual (Sun et al, 2020) 65 scalable and efficient Although the reported accuracy is not optimum, SemiRetro is more scalable. The semi-template allows encoding property changes of existing atoms and bonds.…”

Section: Synthon Completion (Q2)mentioning

confidence: 99%

“…Common deep-learning-based retrosynthesis works can be divided into template-based (TB) (Coley et al, 2017b;Segler & Waller, 2017;Dai et al, 2019;Chen & Jung, 2021) and template-free (TF) (Liu et al, 2017;Karpov et al, 2019;Sacha et al, 2021) methods. Generally, TB methods achieve high accuracy by leveraging reaction templates, which encode the molecular changes during the reaction.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

SemiRetro: Semi-template framework boosts deep retrosynthesis prediction

Gao¹,

Tan²,

Wu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Recently, template-based (TB) and templatefree (TF) molecule graph learning methods have shown promising results to retrosynthesis. TB methods are more accurate using pre-encoded reaction templates, and TF methods are more scalable by decomposing retrosynthesis into subproblems, i.e., center identification and synthon completion. To combine both advantages of TB and TF, we suggest breaking a full-template into several semi-templates and embedding them into the two-step TF framework. Since many semi-templates are reduplicative, the template redundancy can be reduced while the essential chemical knowledge is still preserved to facilitate synthon completion. We call our method SemiRetro, introduce a new GNN layer (DR-GAT) to enhance center identification, and propose a novel self-correcting module to improve semi-template classification. Experimental results show that SemiRetro significantly outperforms both existing TB and TF methods. In scalability, SemiRetro covers 98.9% data using 150 semitemplates, while previous template-based GLN requires 11,647 templates to cover 93.3% data. In top-1 accuracy, SemiRetro exceeds templatefree G2G 4.8% (class known) and 6.0% (class unknown). Besides, SemiRetro has better training efficiency than existing methods.

show abstract

Molecule Edit Graph Attention Network: Modeling Chemical Reactions as Sequences of Graph Edits

Cited by 91 publications

References 72 publications

PaRoutes: a framework for benchmarking retrosynthesis route predictions

PaRoutes: a framework for benchmarking retrosynthesis route predictions

Deep Retrosynthetic Reaction Prediction using Local Reactivity and Global Attention

SemiRetro: Semi-template framework boosts deep retrosynthesis prediction

Contact Info

Product

Resources

About