用互关联后继树模型实现一个局部相似性比对算法

对基因数据库的一种常见操作是找到与待查询序列相似的序列.目前常使用的是BLAST算法,但是这种启发式算法有时会漏解.如果使用精确匹配算法,例如Smith-Waterman(S-W)算法,计算代价又会太大.OASIS算法是一种高效并且精确的生物序列局部相似性比对算法,而且互关联后继树模型的空间效率很高,因此使用互关联后继树实现了OASIS,并命名为OASISirst算法,其比对结果和OASIS一样按照得分降序排列,并且当目标序列和查询序列均较长时,时间优势明显.

基于领域词典和Sentence-BERT的智能问答系统

主流的问答系统主要分为基于语义和基于文本匹配两种,而在基于文本匹配的问答模型中,通常是将问题对直接进行相似性比对进而得出最终的答案。然而,自然语言长问句一般比较冗余,如果直接进行计算,受冗余部分影响,正确率一般不高。为解决上述问题,文章提出了一种基于Sentence-Bert和领域词典的智能问答系统,旨在实现更高效、更准确地问答。系统采用领域词典来过滤问句中的冗余部分,再使用训练好的Sentence-Bert句向量模型对预处理后的问句进行向量化,并计算余弦相似度来找到最匹配的问题。实验结果表明,相比Sentence-BERT,提高了问句相似性比对的精度。

一种低复杂度的监控视频异物入侵检测算法

提出了一种应用于监控视频的异物入侵检测快速算法。算法分成两个部分,包括利用低层语义快速粗定位和利用高层语义精确检测。粗定位部分通过背景建模获得可疑目标区域,再用基于运动轨迹的快速粗过滤算法获得候选区域。其中,所提快速粗过滤算法以目标运动位移量与平均移动速率特征抑制噪声干扰。精确检测部分通过设计一个轻量级相似性比对神经网络进一步过滤误报以获取报警区域,然后利用分类器实现报警结果分类。实验结果表明,相比于darknet19二次分类过滤和YOLO目标检测等算法,所提算法性能更优,更具一般性,能够检测出非常见物,同时也能够在移动便携式计算机上实时运行。

Derivation of Optimal Global Equalization Function with Variable Size Block Based Local Contrast Enhancement

A conventional global contrast enhancement is difficult to apply in various images because image quality and contrast enhancement are dependent on image characteristics largely. And a local contrast enhancement not only causes a washed-out effect, but also blocks. To solve these drawbacks, this paper derives an optimal global equalization function with variable size block based local contrast enhancement. The optimal equalization function makes it possible to get a good quality image through the global contrast enhancement. The variable size block segmentation is firstly exeoated using intensity differences as a measure of similarity. In the second step, the optimal global equalization function is obtained from the enhanced contrast image having variable size blocks. Conformed experiments have showed that the proposed algorithm produces a visually comfortable result image.

The number of alignments between two DNA sequences

We consider two DNA sequences and compare both sequences. One of the crucial issues in bioinformatics is to measure the similarity of two DNA sequences. To this purpose one has to consider different alignments between both sequences. The number of alignments grows very rapidly with the length of the sequences. In this paper we give exact, explicit and computable formulas for the number of different possible alignments and for some classes of reduced alignments. We provide a new insight into the theory of DNA sequence alignment.

3D-QSAR and docking studies on 2-arylbenzoxazole and linker-Y transthyretin amyloidogenesis inhibitors

Transthyretin(TTR),a plasma protein with a tetramer structure,could form amyloid fibril associated with several human diseases through the dissociation of tetramer and the misfolding of monomer.These amyloidogenesis can be inhibited by small molecules which bind to the central channel of TTR.A number of small molecules like 2-arylbenzoxazoles(ABZ)analogues are proposed as promising therapeutic strategy to treat amyloidosis.In this work,comparative molecular field analysis(CoMFA)and comparative molecular similarity indices analysis(CoMSIA)three-dimensional quantitative structure-activity relationship(3D-QSAR)and docking studies were performed on series of 2-arylbenzoxazoles(ABZ)and linker-Y analogues to investigate the inhibitory activities of TTR amyloidogenesis at atomic level.Significant correlation coefficients for ABZ series(CoMFA,r2=0.877,q2=0.431;CoMSIA,r2=0.836,q2=0.447)and those for linker-Y series(CoMFA,r2=0.828,q2=0.522;CoMSIA,r2=0.800,q2=0.493)were obtained,and the generated models were validated using test sets.In addition,docking studies on 6 compounds binding to TTR were performed to analyze the forward or reverse binding mode and interactions between molecules and TTR.These results from 3D-QSAR and docking studies have great significance for designing novel TTR amyloidogenesis inhibitors in the future.