Fig. 3: Deep learning model for the prediction and interpretation of kcat of mutated enzymes.
From: Deep learning-based kcat prediction enables improved enzyme-constrained model reconstruction
a,b, Prediction performance of kcat values for all wild-type (a) and mutated (b) enzymes. Colour brightness represents data density. c, Comparison between predicted and measured kcat values for several well-studied enzyme–substrate pairs with rich experimental mutagenesis data. Enzyme abbreviations: DHFR, dihydrofolate reductase; PGDH, d-3-phosphoglycerate dehydrogenase; AKIII, aspartokinase III; DAOCS, deacetoxycephalosporin C synthase; PNP, purine nucleoside phosphorylase; GGPPs, geranylgeranyl pyrophosphate synthase. Substrate abbreviations: G3P, glycerate 3-phosphate; L-Asp, l-aspartate; IPP, isopentenyl diphosphate. In a–c, the student’s t-test was used to calculate the P value for the Pearson’s correlation. d, Comparison of predicted kcat values on several mutated enzyme–substrate pairs between enzymes with wild-type-like kcat and decreased kcat. P < 0.05 (*), P < 0.01 (**) and P < 0.001 (***), two-sided Wilcoxon rank sum test. Detailed information and sample numbers can be found in Supplementary Table 2. e, Attention weight of residue position in the wild-type PNP enzyme, using inosine as substrate. The mutated residues in each of the mutated enzymes (with both wild-type-like kcat and decreased kcat) were marked on the curve according to their mutated residue. Dot size indicates the number of mutated enzymes with mutations of that residue. f, Overall attention weights for the PNP–inosine pair, comparing enzymes with wild-type-like kcat and decreased kcat by two-sided Wilcoxon rank sum test. n = 15 for wild-type-like kcat; n = 72 for decreased kcat. In each box plot (d and f), the central band represents the median value, the box represents the upper and lower quartiles and the whiskers extend up to 1.5 times the interquartile range beyond the box range.
