Translating the InChI: adapting neural machine translation to predict IUPAC names from a chemical identifier.

Translating the InChI: adapting neural machine translation to predict IUPAC names from a chemical identifier.
复制标题

翻译InChI:调整神经机器翻译以根据化学标识符预测IUPAC名称。

DOI:
10.1186/s13321-021-00535-x
复制
发表时间:
2021-10-07
影响因子:
8.6
通讯作者:
Coles SJ
Coles SJ
中科院分区:
化学2区
文献类型:
--
作者:
Handsel J;Matthews B;Knight NJ;Coles SJ

文献摘要

参考文献

被引文献

相似文献

我们提出了一个序列到序列的机器学习模型,用于从其标准国际化学品标识符(InChI)中预测化学品的IUPAC名称。该模型在编码器-解码器架构中使用了两组变压器,这种设置类似于最先进的机器翻译中使用的神经网络。与神经机器翻译不同,神经机器翻译通常将输入和输出标记为单词或子单词,我们的模型处理InChI并逐字符预测IUPAC名称。该模型在从美国国家医学图书馆在线PubChem服务免费下载的1000万个InChI/IUPAC名称对的数据集上进行训练。在Tesla K80 GPU上进行了7天的训练,该模型的测试集准确率达到了91%。该模型在有机物上的表现特别好,大环化合物除外,与商业IUPAC名称生成软件相当。无机和有机金属化合物的预测不太准确。这可以解释为代表无机物的标准InChI的固有局限性,以及训练数据的低覆盖率。在线版本包含补充材料,可通过10.1186/s13321-021-00535-x获得。
We present a sequence-to-sequence machine learning model for predicting the IUPAC name of a chemical from its standard International Chemical Identifier (InChI). The model uses two stacks of transformers in an encoder-decoder architecture, a setup similar to the neural networks used in state-of-the-art machine translation. Unlike neural machine translation, which usually tokenizes input and output into words or sub-words, our model processes the InChI and predicts the IUPAC name character by character. The model was trained on a dataset of 10 million InChI/IUPAC name pairs freely downloaded from the National Library of Medicine’s online PubChem service. Training took seven days on a Tesla K80 GPU, and the model achieved a test set accuracy of 91%. The model performed particularly well on organics, with the exception of macrocycles, and was comparable to commercial IUPAC name generation software. The predictions were less accurate for inorganic and organometallic compounds. This can be explained by inherent limitations of standard InChI for representing inorganics, as well as low coverage in the training data. The online version contains supplementary material available at 10.1186/s13321-021-00535-x.
DOI: 10.1186/s13321-015-0068-4
发表时间: 2015
影响因子: 8.6
作者:
Heller SR;McNaught A;Pletnev I;Stein S;Tchekhovskoi D
通讯作者: Tchekhovskoi D
DOI: 10.1021/acscentsci.7b00572
发表时间: 2018-02-28
影响因子: 18.2
作者:
Gómez-Bombarelli R;Wei JN;Duvenaud D;Hernández-Lobato JM;Sánchez-Lengeling B;Sheberla D;Aguilera-Iparraguirre J;Hirzel TD;Adams RP;Aspuru-Guzik A
通讯作者: Aspuru-Guzik A
DOI: 10.1186/1758-2946-4-22
发表时间: 2012-09-18
影响因子: 8.6
作者:
O'Boyle NM
通讯作者: O'Boyle NM
RNase H类超级家族:新成员,比较结构分析和进化分类。
DOI: 10.1093/nar/gkt1414
发表时间: 2014-04
影响因子: 14.9
作者:
Majorek KA;Dunin-Horkawicz S;Steczkiewicz K;Muszewska A;Nowotny M;Ginalski K;Bujnicki JM
通讯作者: Bujnicki JM
DOI: 10.1186/s13321-021-00517-z
发表时间: 2021-05-24
影响因子: 8.6
作者:
Goodman JM;Pletnev I;Thiessen P;Bolton E;Heller SR
通讯作者: Heller SR