Estimating the pose of multiple animals is a challenging computer vision problem: frequent interactions cause occlusions and complicate the association of detected keypoints to the correct individuals, as well as having highly similar looking animals that interact more closely than in typical multi-human scenarios. To take up this challenge, we build on DeepLabCut, an open-source pose estimation toolbox, and provide high-performance animal assembly and tracking—features required for multi-animal scenarios. Furthermore, we integrate the ability to predict an animal’s identity to assist tracking (in case of occlusions). We illustrate the power of this framework with four datasets varying in complexity, which we release to serve as a benchmark for future algorithm development.

Motivation Accurate prediction of cancer drug response (CDR) is challenging due to the uncertainty of drug efficacy and heterogeneity of cancer patients. Strong evidences have implicated the high dependence of CDR on tumor genomic and transcriptomic profiles of individual patients. Precise identification of CDR is crucial in both guiding anti-cancer drug design and understanding cancer biology. Results In this study, we present DeepCDR which integrates multi-omics profiles of cancer cells and explores intrinsic chemical structures of drugs for predicting CDR. Specifically, DeepCDR is a hybrid graph convolutional network consisting of a uniform graph convolutional network and multiple subnetworks. Unlike prior studies modeling hand-crafted features of drugs, DeepCDR automatically learns the latent representation of topological structures among atoms and bonds of drugs. Extensive experiments showed that DeepCDR outperformed state-of-the-art methods in both classification and regression settings under various data settings. We also evaluated the contribution of different types of omics profiles for assessing drug response. Furthermore, we provided an exploratory strategy for identifying potential cancer-associated genes concerning specific cancer types. Our results highlighted the predictive power of DeepCDR and its potential translational value in guiding disease-specific drug design. Availability and implementation DeepCDR is freely available at https://github.com/kimmo1019/DeepCDR. Supplementary information Supplementary data are available at Bioinformatics online.

Background Candidemia is the most common, serious fungal infection and Candida antifungal resistance is a challenge. We report recent surveillance of candidemia in China. Methods The study encompassed 77 Chinese hospitals over 3 years. Identification of Candida species was by mass spectrometry and DNA sequencing. Antifungal susceptibility was determined using the Clinical and Laboratory Standards Institute broth microdilution method. Results In total, 4010 isolates were collected from candidemia patients. Although C. albicans was the most common species, non-albicans Candida species accounted for over two-thirds of isolates, predominated C. parapsilosis complex (27.1%), C. tropicalis (18.7%), and C. glabrata complex (12.0%). Most C. albicans and C. parapsilosis complex isolates were susceptible to all antifungal agents (resistance rate <5%). However, there was a decrease in voriconazole susceptibility to C. glabrata sensu stricto over the 3 years and fluconazole resistance rate in C. tropicalis tripled. Amongst less common Candida species, over one-third of C. pelliculosa isolates were coresistant to fluconazole and 5-flucytocine, and >56% of C. haemulonii isolates were multidrug resistance. Conclusions Non-albicans Candida species are the predominant cause of candidemia in China. Azole resistance is notable amongst C. tropicalis and C. glabrata. Coresistance and multidrug resistance has emerged in less common Candida species.

Background: Multidrug-resistant bacteria, especially those with high virulence, are an emerging problem in clinical settings. Methods: We conducted a multicentre epidemiological and comparative genomic analysis on the evolution, virulence and antimicrobial resistance of carbapenem-resistant Enterobacteriaceae in patients with bacterial liver abscesses from 2012 to 2016. Results: A total of 477 bacterial isolates were collected. Enterobacteriaceae were the main pathogen (89.3%) with K. pneumoniae (52.4%) predominating followed by Escherichia coli (26.8%). All CRKps (3.2%) were of sequence type (ST) 11 and serotypes K47 or K64, and simultaneously possessed acquired bla KPC-2 /bla KPC-5 and bla CTX-M-65 together with the multidrug transporter EmrE. Seven Hv-CRKps (five ST11-K47, two ST11-K64) were confirmed by bacteriological test, neutrophil killing assay and Galleria mellonella infection model. Genomic analysis indicated that the emergence of one ST11-K64 Hv-CRKp strain was related to the acquisition of rmpA/rmpA2 genes and siderophore gene clusters, while ST11-K47 Hv-CRKp lacked these traditional virulence genes. Further complete genome analysis of one ST11-K47 Hv-CRKp strain, R16, showed that it acquired a rare plasmid (pR16-Hv-CRKp1) carrying bla KPC-2 , bla SHV-12 , bla TEM-1 , bla CTX-M-65 , rmtB and a predicted virulence gene R16_5486 simultaneously. Conclusion:The emergence of the ST11-K47/K64 Hv-CRKps, which are simultaneously multidrug-resistant and hypervirulent, requires urgent control measures to be implemented.