...
However, as the tables above demonstrate, many of the new parameters have higher average errors than their parents. For example, t122 is applied 9572 times with Sage 2.1.0 and has an average error of 0.16 kcal/mol. Its child parameters in the TM force field, t122b, c, and f, are applied a total of 9572 times and have average errors of 0.21, 0.17, and 0.10 kcal/mol, respectively. Only the last of these is lower than the original t122 value, and it represents the lowest count anyway, so a weighted average gives a higher overall error of 0.20 kcal/mol. The trends are less clear for the Sage vs Sage-TM comparison. Table 3 shows that the addition of the TM training data leads to a decrease in the average error for t122, t130, and t143, but an increase for t164 and t142.
Another factor demonstrated by these tables is that many of the new child parameters are not covered by the benchmarking data set in this case. t143, for example, has a, b, c, d, e, and f variants in the TM force field, but only a, b, and e appear in this data. In contrast, only t143c was not covered by the training set.
...