A novel lipase, Lip486, which has no obvious homology with known lipases, was discovered using functional metagenomics technology. Phylogenetic tree analysis suggested that the enzyme belongs to a new subfamily called lipolytic enzyme family II. To explore the enzymatic properties, lip486 was expressed heterologously and e ciently in Escherichia coli. The recombinant enzyme displayed the highest activity on the substrate p-nitrophenyl caprate with a carbon chain length of 10, and its optimum temperature and pH were 53 °C and 8.0, respectively. The recombinant Lip486 showed good activity and stability in strong alkaline and medium-low -temperature environments. The results of compatibility and soaking tests showed that the enzyme had good compatibility with 4 kinds of commercial detergents, and an appropriate soaking time could further improve the enzyme activity. Oil stain removal test results for a cotton cloth indicated that the washing performance of commercial laundry detergent supplemented with Lip486 was further improved. In addition, as one of the smallest lipases found to date, Lip486 also has the advantages of high yield, good stability and easy molecular modi cation. These characteristics re ect the good application prospects for Lip486 in the detergent and other industries in the future.

No abstract

In unconstrained scenarios, face recognition remains challenging, particularly when faces are occluded. Existing methods generalize poorly due to the distribution distortion induced by unpredictable occlusions. To tackle this problem, we propose a hierarchical segmentation-based mask learning strategy for face recognition, enhancing occlusion-robustness by integrating segmentation representations of occlusion into face recognition in the latent space. We present a novel multi-scale segmentation-based mask learning (MSML) network, which consists of a face recognition branch (FRB), an occlusion segmentation branch (OSB), and hierarchical elaborate feature masking (FM) operators. With the guidance of hierarchical segmentation representations of occlusion learned by the OSB, the FM operators can generate multi-scale latent masks to eliminate mistaken responses introduced by occlusions and purify the contaminated facial features at multiple layers. In this way, the proposed MSML network can effectively identify and remove the occlusions from feature representations at multiple levels and aggregate features from visible facial areas. Experiments on face verification and recognition under synthetic or realistic occlusions demonstrate the effectiveness of our method compared to state-of-the-art methods.

A novel lipase, Lip486, which has no obvious homology with known lipases, was discovered using functional metagenomics technology. Phylogenetic tree analysis suggested that the enzyme belongs to a new subfamily called lipolytic enzyme family II. To explore the enzymatic properties, lip486 was expressed heterologously and efficiently in Escherichia coli. The recombinant enzyme displayed the highest activity on the substrate p-nitrophenyl caprate with a carbon chain length of 10, and its optimum temperature and pH were 53 °C and 8.0, respectively. The recombinant Lip486 showed good activity and stability in strong alkaline and medium-low -temperature environments. The results of compatibility and soaking tests showed that the enzyme had good compatibility with 4 kinds of commercial detergents, and an appropriate soaking time could further improve the enzyme activity. Oil stain removal test results for a cotton cloth indicated that the washing performance of commercial laundry detergent supplemented with Lip486 was further improved. In addition, as one of the smallest lipases found to date, Lip486 also has the advantages of high yield, good stability and easy molecular modification. These characteristics reflect the good application prospects for Lip486 in the detergent and other industries in the future.