The data model developed to achieve these goals is described in Figure 4.
For example, Zhu et al. [10] developed five QSAR models for 7385 compounds with rat oral acute toxicity data, and the two models developed by kNN and RF achieved comparable performance for the test set (r 2 = 0.66 and 0.70, respectively) to TOPKAT.
Similarly, SVM models developed with dipeptide composition profile achieved MCC of 0.44, 0.70 and 0.45 for IgG, IgE and IgA respectively.
However, the models developed using 159 MACCS keys, achieve maximum MCC 0.77 with accuracy 89.96% [Table 3, Figure 4].
The improved prediction abilities of EJF over JF indicated that the genetic architecture can be better depicted by averaging multiple independent QTL models developed from disjoint subset maps as achieved by TAGGING.
The polynomial secondary models, developed to estimate the time to achieve a 3-log and a 5-log reduction, enabled the estimation of critical pH, NaCl and SPP concentrations, which are values at which the thermo-tolerance of E. coli O157 H7 reaches it maximum.
There are models developed by behavioural scientists based on achieving consensus; by epidemiologists/clinicians based on needs assessment; by philosophers based on notions of social justice; and by economists based on achieving efficiency.
The models developed using top-20 fingerprints [Figure 1], achieved maximum MCC 0.72 with a marginal decrease in the value of ROC to 0.94.
Initially, models developed and evaluated on EGFR100 train set using 881 fingerprints achieved maximum MCC 0.58 (Table 4).
Three DFA models were developed that achieved excellent discrimination between the subpopulations: (i) GC vs benign gastric conditions, among all the patients (89% sensitivity; 90% specificity); (ii) early stage GC (I and II) vs late stage (III and IV), among GC patients (89% sensitivity; 94% specificity); and (iii) ulcer vs less severe, among benign conditions (84% sensitivity; 87% specificity).
