**5. Conclusions**

The reliability of statistical optimization of the external parameter in enhancing keratinase production *Bacillus* sp. UPM-AAG1 I was demonstrated in this work. The significant parameter required for the optimum keratinase production was screened using Plackett-Burman design. Optimization of keratinase by RSM allowed us to evaluate the effect of various parameter at different levels. The CCD design applied results 1.7-fold in keratinase yield. The acceptable degree of similarity between the predicted model and actual activity signifies the reliability of the statistical model in optimization of keratinase. The optimized parameters and characteristics of the bacterium include optimal growth at near neutrality, ambient temperature, and able to support growth and keratinase production without external supplementary requirements. Moreover, the hydrolysate of *Bacillus* sp. UPM-AAG1 obtained through statistical optimization is rich in amino acids. These properties make the bacterium an excellent choice for local commercial application where keratinase production should be optimum at ambient temperature and no additional C or N sources should be added to minimize cost. In the future, cheaper, or even waste, materials from the local agricultural industries, such as waste bagasse or Palm Mill Oil Effluent or POME, may be tested to improve keratinase production and feather degradation in general.

**Supplementary Materials:** The following are available online at http://www.mdpi.com/2073-4344/10/8/848/s1, Figure S1: Azokeratin formation from feather keratin treated with the azotization of sulfanilic acid. Figure S2: Model diagnostic plots; (a) predicted versus actual, (b) studentized residue versus predicted, (c) normal plots of residue and (d) outlier T versus run.

**Author Contributions:** Conceptualization, M.Y.S. and N.A.Y.; methodology, M.Y.S.; software, S.A.A.; validation, M.E.K., M.Y.S. and N.A.Y.; formal analysis, A.A.G. and S.A.A.; investigation, A.A.G.; resources, M.Y.S.; data curation, M.Y.S.; writing—original draft preparation, A.A.A.; writing—review and editing, M.Y.S.; visualization, S.A.A.; supervision, M.E.K., M.Y.S. and N.A.Y.; project administration, M.Y.S.; funding acquisition, M.Y.S. All authors have read and agreed to the published version of the manuscript.

**Funding:** The authors would like to thank the support of the Graduate Research Fellowship University Putra Malaysia (GRF-UPM) given to Aa'ishah Abd Gafar.

**Conflicts of Interest:** The authors declare the results obtained in this study will be used in discussion for a possible transfer of technology to a local small and medium enterprise (SME) company, of which the company did not sponsor the works carried out in this study.
