STOUT: SMILES to IUPAC names using neural machine translation

Abstract

Chemical compounds can be identified through a graphical depiction, a suitable string representation, or a chemical name. A universally accepted naming scheme for chemistry was established by the International Union of Pure and Applied Chemistry (IUPAC) based on a set of rules. Due to the complexity of this ruleset a correct chemical name assignment remains challenging for human beings and there are only a few rule-based cheminformatics toolkits available that support this task in an automated manner. Here we present STOUT (SMILES-TO-IUPAC-name translator), a deep-learning neural machine translation approach to generate the IUPAC name for a given molecule from its SMILES string as well as the reverse translation, i.e. predicting the SMILES string from the IUPAC name. In both cases, the system is able to predict with an average BLEU score of about 90% and a Tanimoto similarity index of more than 0.9. Also incorrect predictions show a remarkable similarity between true and predicted compounds.

Improved decision making with similarity based machine learning

“…More specifically, we consider the caged ether-bridged C 6 H 8 O 2 compound, 3,8-dioxatricyclo[4.2.1.0 2,5 ]nonane 37,38 , and the fused C 7 H 10 O aldehyde, 4-methylbicyclo[2.1.0]pentane-2carbaldehyde 37,38 , encoding motifs that are respectively rather rare or frequent within the chemical space spanned by QM9 29 . SML learning curves (Fig.…”

“…Note that this is not an unusual 'academic' situation as the latter can nowadays be performed commercially through synthesis service companies such as Enamine Ltd. While such services have reached considerable reliability, reporting success rates of 60-80% and higher, challenging boutique target compounds, for example cyclopropylmethyl2-(2oxo-3,4-dihydro-2H-1,3-benzoxazin-3-yl)acetate 37,38 on display in Fig. 4A can impose substantial time delays until the compound has been made, characterized, and shipped, increasing lead times to several weeks or more.…”

Image2SMILES: Transformer‐Based Molecular Optical Recognition Engine**

“…Weir et al [11] extended the CNN + RNN approach for recognition of hand-drawn hydrocarbon chemical structures. Sundaramoorthy et al, [12] and Rajan et al [13] proposed Vision Transformer and CNN + Transformer approaches as an alternative to the CNN + RNN approach. In contrast to end-to-end approaches, Oldenhof et al [14] proposed a hybrid approach where chemical primitives are located and recognized by several deep-learning models combining together into a chemical graph by a defined algorithm.…”

“…extended the CNN+RNN approach for recognition of hand‐drawn hydrocarbon chemical structures. Sundaramoorthy et al., [12] and Rajan et al [13] . proposed Vision Transformer and CNN+Transformer approaches as an alternative to the CNN+RNN approach.…”

Molecular Identification from AFM images using the IUPAC Nomenclature and Attribute Multimodal Recurrent Neural Networks

“…Automatic image captioning has been a field of intensive research for deep learning techniques over the last years (41,42,43,44). It has been recently and successfully used (45,46) for optical chemical structure recognition (47), the translation of graphical molecular depictions into machinereadable formats. These works are able to predict the SMILES textual representation (48) of a molecule from an image with its chemical structure depiction by using standard encoderdecoder (46) or transformer (45) models.…”