Fig. 3: Performance gain by LC-MS2Struct across molecular classes. | Nature Machine Intelligence

Fig. 3: Performance gain by LC-MS2Struct across molecular classes.

From: Joint structural annotation of small molecules using liquid chromatography retention order and tandem mass spectrometry data

Fig. 3

The ranking performance (top-k) improvement of LC-MS2Struct compared with only-MS2 (baseline). The data are presented as mean values (50 samples) and the error bars show the 95% confidence interval of the mean estimate (1,000 bootstrapping samples). The top-k accuracies (%) under the bars show the only-MS2 performance. For each molecular class, the number of unique molecular structures in the class is denoted in the x-axis label (n). a, Molecular classification using the ClassyFire51 framework (class level). b, PubChemLite40 annotation classification system. Molecules not present in PubChemLite are summarized under the ‘noClassification’ category. Note that in PubChemLite, a molecule can belong to multiple categories.

Source data

Back to article page