Identification of All-to-All Protein-Protein Interactions Based on Deep Hash Learning

Background: Protein-protein interaction (PPI) is vital for life processes, diseases treatment and new drugs discovery. The computational prediction of PPI is well accepted for its inexpensive and efficient nature comparing to the wet-lab experiment. When a new protein comes, one try to find whether there is any PPI relationship between this new protein and existing proteins, the current computational prediction methods usually compare this new protein to existing proteins one by one in pairwise. This is time comsuming. Results: We proposed an more efficient model, Deep Hash Learning Protein-and-Protein Interaction (DHL-PPI) model, to predict all-to-all PPI relationship on a database. First, DHL-PPI encodes a protein sequence into a binary Hash code based on the features extracted from sequences by using deep learning technique. This encoding scheme enables the PPI discrimination problem to be a much simpler searching problem. A protein with a binary code can be regarded as a number. In the prescreen of PPI prediction stage, the string match problem of searching a string against a database with M proteins can be turned into a much more simpler problem: to find a number inside an sorted array with length M. This prescreen process narrows down proteins inside the whole database into a much smaller candidate set for further confirmation. At last, DHL-PPI uses the Hamming distance to determine the final PPI relationship. Conclusions: The experimental results confirmed that DHL-PPI is feasible and effective. Using a dataset with strictly negative PPI examples of four species, DHL-PPI is superior or competitive to the other state-of-the-art methods in terms of precision, recall or F1 score. Furthermore, in the prediction stage, the proposed DHL-PPI decrease the usual time compexity of O(M2 ) to O(MlogM) for predicting all-to-all PPI interactons between any pairs in M proteins on a database. A protein database can be stored in the proposed encoding scheme and waited to be searched, which is a potential novel encoding scheme to cope with current searching problem for a large volume of database.

Boyer Moore string-match framework for a hybrid short message service spam filtering technique

Advances in technology and the proliferation of mobile device have continued to advance the ubiquitous nature of computing alongside their many prowess and improved features it brings as a disruptive technology to aid information sharing amongst many online users. This popularity, usage and adoption ease, mobility, and portability of the mobile smartphone devices have allowed for its acceptability and popularity. Mobile smartphones continue to adopt the use of short messages services accompanied with a scenario for spamming to thrive. Spams are unsolicited message or inappropriate contents. An effective spam filter studies are limited as short-text message service (SMS) are 140bytes, 160-characters, and rippled with abbreviation and slangs that further inhibits the effective training of models. The study proposes a string match algorithm used as deep learning ensemble on a hybrid spam filtering technique to normalize noisy features, expand text and use semantic dictionaries of disambiguation to train underlying learning heuristics and effectively classify SMS into legitimate and spam classes. Study uses a profile hidden Markov network to select and train the network structure and employs the deep neural network as a classifier network structure. Model achieves an accuracy of 97% with an error rate of 1.2%.

A Re-Ranking Method of Search Results Based on Keyword and User Interest

It is a pivotal task for a forensic investigator to search a hard disk to find interesting evidences. Currently, most search tools in digital forensic field, which utilize text string match and index technology, produce high recall (100%) and low precision. Therefore, the investigators often waste vast time on huge irrelevant search hits. In this chapter, an improved method for ranking of search results was proposed to reduce human efforts on locating interesting hits. The K-UIH (the keyword and user interest hierarchies) was constructed by both investigator-defined keywords and user interest learnt from electronic evidence adaptive, and then the K-UIH was used to re-rank the search results. The experimental results indicated that the proposed method is feasible and valuable in digital forensic search process.