Fusion of Hash-Based Hard and Soft Biometrics for Enhancing Face Image Database Search and Retrieval

The utilization of digital picture search and retrieval has grown substantially in numerous fields for different purposes during the last decade,owing to the continuing advances in image processing and computer vision approaches.In multiple real-life applications,for example,social media,content-based face picture retrieval is a well-invested technique for large-scale databases,where there is a significant necessity for reliable retrieval capabilities enabling quick search in a vast number of pictures.Humans widely employ faces for recognizing and identifying people.Thus,face recognition through formal or personal pictures is increasingly used in various real-life applications,such as helping crime investigators retrieve matching images from face image databases to identify victims and criminals.However,such face image retrieval becomes more challenging in large-scale databases,where traditional vision-based face analysis requires ample additional storage space than the raw face images already occupied to store extracted lengthy feature vectors and takes much longer to process and match thousands of face images.This work mainly contributes to enhancing face image retrieval performance in large-scale databases using hash codes inferred by locality-sensitive hashing(LSH)for facial hard and soft biometrics as(Hard BioHash)and(Soft BioHash),respectively,to be used as a search input for retrieving the top-k matching faces.Moreover,we propose the multi-biometric score-level fusion of both face hard and soft BioHashes(Hard-Soft BioHash Fusion)for further augmented face image retrieval.The experimental outcomes applied on the Labeled Faces in the Wild(LFW)dataset and the related attributes dataset(LFW-attributes),demonstrate that the retrieval performance of the suggested fusion approach(Hard-Soft BioHash Fusion)significantly improved the retrieval performance compared to solely using Hard BioHash or Soft BioHash in isolation,where the suggested method provides an augmented accuracy of 87%when executed on 1000 specimens and 77%on 5743 samples.These results remarkably outperform the results of the Hard BioHash method by(50%on the 1000 samples and 30%on the 5743 samples),and the Soft BioHash method by(78%on the 1000 samples and 63%on the 5743 samples).

Discovery of a Novel 5-HT_(2A) Inhibitor by Pharmacophore-based Virtual Screening

The serotonin 2A（5-HT2A） receptor has been implicated in several neurological conditions and potent 5-HT2A antagonists have therapeutic effects in the treatment of schizo phrenia and depression.In this study,a potent novel 5-HT2A inhibitor 05245768 with a Ki value of （593.89±34.10） nmol/L was discovered by integrating a set of computational approaches and experiments（protein structure prediction,pharmacophore-based virtual screening,automated molecular docking and pharmacological bioassay）.The 5-HT2A receptor showed a negatively charged bin-ding pocket.The binding mode of compound 05245768 with 5-HT2A was obtained by GOLD docking procedure,which revealed the conserved interaction between protonated nitrogen in compound 05245768 and carboxylate group of D3.32 at the active site of 5-HT2A.

pepgrep:A Tool for Peptide MS/MS Pattern Matching

Typically, detection of protein sequences in collision-induced dissociation （CID） tandem MS （MS2） dataset is performed by mapping identified peptide ions back to protein sequence by using the protein database search （PDS） engine. Finding a particular peptide sequence of interest in CID MS2 records very often requires manual evaluation of the spectrum, regardless of whether the peptide-associated MS2 scan is identified by PDS algorithm or not. We have developed a com- pact cross-platform database-free command-line utility, pepgrep, which helps to find an MS2 finger- print for a selected peptide sequence by pattern-matching of modelled MS2 data using Peptide-to- MS2 scoring algorithm, pepgrep can incorporate dozens of mass offsets corresponding to a variety of post-translational modifications （PTMs） into the algorithm. Decoy peptide sequences are used with the tested peptide sequence to reduce false-positive results. The engine is capable of screening an MS2 data file at a high rate when using a cluster computing environment. The matched MS2 spectrum can be displayed by using built-in graphical application programming interface （API） or optionally recorded to file. Using this algorithm, we were able to find extra peptide sequences in studied CID spectra that were missed by PDS identification. Also we found pepgrep especially useful for examining a CID of small fractions of peptides resulting from, for example, affinity puri- fication techniques. The peptide sequences in such samples are less likely to be positively identified by using routine protein-centric algorithm implemented in PDS. The software is freely available at http：//bsproteomics.essex.ac.uk：8080/data/download/pepgrep- 1.4.tgz.