Theoretical and Computational Chemistry

Automated Extraction of Chemical Synthesis Actions from Experimental Procedures

Abstract

Experimental procedures for chemical synthesis are commonly reported in prose in patents or in the scientific literature. The automatic extraction of the details necessary to reproduce and validate a synthesis in a chemical laboratory is quite often a tedious task, requiring extensive human intervention. 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. To achieve this, we design a set of synthesis actions with predefined properties and a deep-learning sequence to sequence model based on the transformer architecture to convert experimental procedures to action sequences. The model is pretrained on vast amounts of data generated automatically with a custom rule-based natural language processing approach and refined on a smaller set of manually annotated samples. Predictions on our test set resulted in a perfect (100%) match of the action sequence for 60.8% of sentences, a 90% match for 71.3% of sentences, and a 75% match for 82.4% of sentences.

Content

Thumbnail image of manuscript.pdf

Supplementary material

Thumbnail image of si.pdf
si
Thumbnail image of supplementary_data_1_actions_for_test_set.txt
supplementary data 1 actions for test set
Thumbnail image of supplementary_data_2_top_5_sequences.txt
supplementary data 2 top 5 sequences
Thumbnail image of supplementary_data_3_annotation_guideline.md
supplementary data 3 annotation guideline
Thumbnail image of supplementary_data_4_onmt_config.txt
supplementary data 4 onmt config