• Publications
  • Influence
“Found in Translation”: predicting outcomes of complex organic chemistry reactions using neural sequence-to-sequence models† †Electronic supplementary information (ESI) available: Time-split test set
TLDR
Using a text-based representation of molecules, chemical reactions are predicted with a neural machine translation model borrowed from language processing. Expand
Two-dimensional materials from high-throughput computational exfoliation of experimentally known compounds
Two-dimensional (2D) materials have emerged as promising candidates for next-generation electronic and optoelectronic applications. Yet, only a few dozen 2D materials have been successfullyExpand
Molecular Transformer: A Model for Uncertainty-Calibrated Chemical Reaction Prediction
TLDR
We show that a multihead attention Molecular Transformer model outperforms all algorithms in the literature, achieving a top-1 accuracy above 90% on a common benchmark data set. Expand
Transfer learning enables the molecular transformer to predict regio- and stereoselective reactions on carbohydrates
Organic synthesis methodology enables the synthesis of complex molecules and materials used in all fields of science and technology and represents a vast body of accumulated knowledge optimallyExpand
Molecular Transformer for Chemical Reaction Prediction and Uncertainty Estimation
TLDR
We show that a multi-head attention Molecular Transformer model outperforms all algorithms in the literature, achieving a top-1 accuracy above 90% on a common benchmark dataset. Expand
Predicting retrosynthetic pathways using transformer-based models and a hyper-graph exploration strategy†
TLDR
We present an extension of our Molecular Transformer model combined with a hyper-graph exploration strategy for automatic retrosynthesis route planning without human intervention. Expand
Exploring Chemical Space using Natural Language Processing Methodologies for Drug Discovery
TLDR
Text-based representations of chemicals and proteins can be thought of as unstructured languages codified by humans to describe domain-specific knowledge. Expand
Automated extraction of chemical synthesis actions from experimental procedures
TLDR
We present a method to convert unstructured experimental procedures written in English to structured synthetic steps (action sequences) reflecting all the operations needed to successfully conduct the corresponding chemical reactions. Expand
Dataset Bias in the Natural Sciences: A Case Study in Chemical Reaction Prediction and Synthesis Design
TLDR
In this paper, we identify three trends in the application of machine learning with respect to the design of synthetic pathways that may benefit from a change in direction. Expand
Predicting retrosynthetic pathways using a combined linguistic model and hyper-graph exploration strategy
TLDR
We present an extension of our Molecular Transformer architecture combined with a hyper-graph exploration strategy for automatic retrosynthesis route planning without human intervention. Expand
...
1
2
3
...