Protein–deoxyribonucleic acid (DNA) interactions are important in a variety of biological processes. Accurately predicting protein-DNA binding affinity has been one of the most attractive and challenging issues in computational biology. However, the existing approaches still have much room for improvement. In this work, we propose an ensemble model for Protein-DNA Binding Affinity prediction (emPDBA), which combines six base models with one meta-model. The complexes are classified into four types based on the DNA structure (double-stranded or other forms) and the percentage of interface residues. For each type, emPDBA is trained with the sequence-based, structure-based and energy features from binding partners and complex structures. Through feature selection by the sequential forward selection method, it is found that there do exist considerable differences in the key factors contributing to intermolecular binding affinity. The complex classification is beneficial for the important feature extraction for binding affinity prediction. The performance comparison of our method with other peer ones on the independent testing dataset shows that emPDBA outperforms the state-of-the-art methods with the Pearson correlation coefficient of 0.53 and the mean absolute error of 1.11 kcal/mol. The comprehensive results demonstrate that our method has a good performance for protein-DNA binding affinity prediction. Availability and implementation: The source code is available at https://github.com/ChunhuaLiLab/emPDBA/.

: Meeting foxtail millet (Setaria italica L.) (FM) production targets of high grain yield requires appropriate genotype selection and nitrogen (N) fertilization. However, high input costs and low crop yields are the major concerns for FM production systems, particularly in dry regions. To reduce the production costs without sacrificing yield, we assumed that N fertilization would increase the grain yield of FM varieties by improving reproductive organ biomass accumulation. To test this hypothesis, a two-year (2017 and 2018) field investigation in a randomized complete block design with split plot arrangement and three replicates was carried out on FM varieties, namely, V1 (Zhangzagu 8; hybrid) and V2 (Bagu 214; common) to ascertain the effects of five N levels (N1—15; N2—61; N3—108; N4—155; N5—201 kg N ha−1) on biomass accumulation and grain yield at different growth stages. Results showed that the V1 variety had a 34.8% and 28.5% higher grain yield compared to V2 treatment in both years, respectively. The interaction between variety and nitrogen was also significant. The combination of V1 and N4 produced a higher grain yield in both years. This increase in V1 grain yield was supported by the evidence of greater reproductive organ biomass formation, with a 113 and 120 kg ha−1 higher-than-average rate of biomass accumulation in both years, respectively. Among N rates, the N4 level resulted in a higher grain yield (3226 kg ha−1) and (3437 kg ha−1) compared with other N rates in the 2017 and 2018 growing seasons. This higher yield under N4 treatment was confirmed by a higher reproductive organ biomass accumulation at various growth phases, with 138 kg ha−1 and 124 kg ha−1 in 2017 and 2018, respectively. We also noticed that further increases in nitrogen levels did not increase FM grain yield. Conclusively, these data display the significance of proper FM production management techniques. Growing the varieties Zhangzagu 8 at 155 kg N ha-1 fertilization and Bagu 214 at 108 kg N ha−1 fertilization could be promising options to achieve higher grain yield.

No abstract