Writing the American story, 1945–1952

Lowe, John

doi:10.1017/chol9780521872171.018

Cited by 1 publication

(2 citation statements)

References 149 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The United States Patent Office extracts comprised of the Pistachio data set (2022Q1) from NextMove software, the publicly available subset USPTO extracted by Lowe, , and the USPTO50k subset from Schneider et al were used in this study . An extension of the method to ECReact containing enzyme data as curated by Probst et al was used for the enzymatic model .…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Unbiasing Retrosynthesis Language Models with Disconnection Prompts

et al. 2023

View full text Add to dashboard Cite

Data-driven approaches to retrosynthesis are limited in user interaction, diversity of their predictions, and recommendation of unintuitive disconnection strategies. Herein, we extend the notions of prompt-based inference in natural language processing to the task of chemical language modeling. We show that by using a prompt describing the disconnection site in a molecule we can steer the model to propose a broader set of precursors, thereby overcoming training data biases in retrosynthetic recommendations and achieving a 39% performance improvement over the baseline. For the first time, the use of a disconnection prompt empowers chemists by giving them greater control over the disconnection predictions, which results in more diverse and creative recommendations. In addition, in place of a human-in-the-loop strategy, we propose a two-stage schema consisting of automatic identification of disconnection sites, followed by prediction of reactant sets, thereby achieving a considerable improvement in class diversity compared with the baseline. The approach is effective in mitigating prediction biases derived from training data. This provides a wider variety of usable building blocks and improves the end user's digital experience. We demonstrate its application to different chemistry domains, from traditional to enzymatic reactions, in which substrate specificity is critical.

show abstract

Section: Methodsmentioning

confidence: 99%

“…The disconnection aware model can be used for multistep retrosynthesis on: . The US patent extract text mined by Lowe is publicly available and can be processed using code on our GitHub repository. , We additionally provide a preprocessed and labeled set of data obtained from the US patent extracts text mined by Lowe: .…”

mentioning

confidence: 99%