Gunasekaran and Nussinov reported that the magnitude of the dihedral angle changes is minimal after ligand binding [ 19], which explains why our method has a performance similar to that of Ligsite-csc for both ligand-bound and ligand-free protein ligand-binding site prediction when only one potential pocket is predicted, as shown in Figure 6.
The concentrations of gases were predicted as shown in Fig. 6.
After the GA-improved BPNN training, the susceptibility of landslides was predicted, as shown in Fig. 19.
Based on the identified metabolites, namely, 1-hydroxy-2-naphthoic acid, salicylic acid, o-phthalic, catechol, gentisic acid and protocatechuic acid, and the pathways reported from PAH-degrading isolates, the phenanthrene metabolic pathway of CY-1 was predicted as shown in Fig. 3.
In this way, the phenotypes of 6 proteins were predicted, as shown in Table 5.
Five potential binding pockets were predicted as shown in Figure 2a.
This resulted in a minimum of 133 recombination events being predicted as shown in Supplementary Fig. S2.
With a total of 9731 training sequences, only 7158 training sequences were predicted, as shown in Table 3.
Based on the identified pheromone precursors, the putative sex pheromone biosynthetic pathway of E. cautella was predicted as shown in Fig. 3.
Based on the results of the present study, the possible signal network by which celastrol induced apoptosis was predicted (as shown in Figure 7).
