New Scalable and Efficient Online Pairwise Learning Algorithm.

Pairwise learning is an important machine-learning topic with many practical applications. An online algorithm is the first choice for processing streaming data and is preferred for handling large-scale pairwise learning problems. However, existing online pairwise learning algorithms are not scalable and efficient enough for large-scale high-dimensional data, because they were designed based on singly stochastic gradients. To address this challenging problem, in this article, we propose a dynamic doubly stochastic gradient algorithm (D2SG) for online pairwise learning. Especially, only the time and space complexities of O (d) are needed for incorporating a new sample, where d is the dimensionality of data. This means that our D2SG is much faster and more scalable than the existing online pairwise learning algorithms while the statistical accuracy can be guaranteed through our rigorous theoretical analysis under standard assumptions. The experimental results on a variety of real-world datasets not only confirm the theoretical result of our new D2SG algorithm, but also show that D2SG has better efficiency and scalability than the existing online pairwise learning algorithms.

Comparative Insights Into the Complete Genome Sequence of Highly Metal Resistant Cupriavidus metallidurans Strain BS1 Isolated From a Gold-Copper Mine.

The highly heavy metal resistant strain Cupriavidus metallidurans BS1 was isolated from the Zijin gold-copper mine in China. This was of particular interest since the extensively studied, closely related strain, C. metallidurans CH34 was shown to not be only highly heavy metal resistant but also able to reduce metal complexes and biomineralizing them into metallic nanoparticles including gold nanoparticles. After isolation, C. metallidurans BS1 was characterized and complete genome sequenced using PacBio and compared to CH34. Many heavy metal resistance determinants were identified and shown to have wide-ranging similarities to those of CH34. However, both BS1 and CH34 displayed extensive genome plasticity, probably responsible for significant differences between those strains. BS1 was shown to contain three prophages, not present in CH34, that appear intact and might be responsible for shifting major heavy metal resistance determinants from plasmid to chromid (CHR2) in C. metallidurans BS1. Surprisingly, the single plasmid - pBS1 (364.4 kbp) of BS1 contains only a single heavy metal resistance determinant, the czc determinant representing RND-type efflux system conferring resistance to cobalt, zinc and cadmium, shown here to be highly similar to that determinant located on pMOL30 in C. metallidurans CH34. However, in BS1 another homologous czc determinant was identified on the chromid, most similar to the czc determinant from pMOL30 in CH34. Other heavy metal resistance determinants such as cnr and chr determinants, located on megaplasmid pMOL28 in CH34, were shown to be adjacent to the czc determinant on chromid (CHR2) in BS1. Additionally, other heavy metal resistance determinants such as pbr, cop, sil, and ars were located on the chromid (CHR2) and not on pBS1 in BS1. A diverse range of genomic rearrangements occurred in this strain, isolated from a habitat of constant exposure to high concentrations of copper, gold and other heavy metals. In contrast, the megaplasmid in BS1 contains mostly genes encoding unknown functions, thus might be more of an evolutionary playground where useful genes could be acquired by horizontal gene transfer and possibly reshuffled to help C. metallidurans BS1 withstand the intense pressure of extreme concentrations of heavy metals in its environment.