The 2018 Nigerian Lassa fever season saw the largest ever recorded upsurge of cases, raising concerns over the emergence of a strain with increased transmission rate. To understand the molecular epidemiology of this upsurge we performed, for the first time at the epicenter of an unfolding outbreak, metagenomic nanopore sequencing directly from patient samples, an approach dictated by the highly variable genome of the target pathogen. Genomic data and phylogenetic reconstructions were communicated immediately to Nigerian authorities and the WHO to inform the public health response. Real-time analysis of 36 genomes, and subsequent confirmation using all 120 samples sequenced in-country, revealed extensive diversity and phylogenetic intermingling with strains from previous years, suggesting independent zoonotic transmission events; allaying concerns of an emergent strain or extensive human-to-human transmission.

BackgroundThe recent global emergence and re-emergence of arboviruses has caused significant human disease. Common vectors, symptoms and geographical distribution make differential diagnosis both important and challenging. AimTo investigate the feasibility of metagenomic sequencing for recovering whole genome sequences of chikungunya and dengue viruses from clinical samples.MethodsWe performed metagenomic sequencing using both the Illumina MiSeq and the portable Oxford Nanopore MinION on clinical samples which were real-time reverse transcription-PCR (qRT-PCR) positive for chikungunya (CHIKV) or dengue virus (DENV), two of the most important arboviruses. A total of 26 samples with a range of representative clinical Ct values were included in the study.ResultsDirect metagenomic sequencing of nucleic acid extracts from serum or plasma without viral enrichment allowed for virus identification, subtype determination and elucidated complete or near-complete genomes adequate for phylogenetic analysis. One PCR-positive CHIKV sample was also found to be coinfected with DENV. ConclusionsThis work demonstrates that metagenomic whole genome sequencing is feasible for the majority of CHIKV and DENV PCR-positive patient serum or plasma samples. Additionally, it explores the use of Nanopore metagenomic sequencing for DENV and CHIKV, which can likely be applied to other RNA viruses, highlighting the applicability of this approach to front-line public health and potential portable applications using the MinION.

Abstract-StarCraft: Broodwar (SC:BW) is a very popular commercial real strategy game (RTS) which has been extensively used in AI research. Despite being a popular test-bed reinforcement learning (RL) has not been evaluated extensively. A successful attempt was made to show the use of RL in a smallscale combat scenario involving an overpowered agent battling against multiple enemy units [1]. However, the chosen scenario was very small and not representative of the complexity of the game in its entirety. In order to build an RL agent that can manage the complexity of the full game, more efficient approaches must be used to tackle the state-space explosion. In this paper, we demonstrate how plan-based reward shaping can help an agent scale up to larger, more complex scenarios and significantly speed up the learning process as well as how high level planning can be combined with learning focusing on learning the Starcraft strategy, Battlecruiser Rush. We empirically show that the agent with plan-based reward shaping is significantly better both in terms of the learnt policy, as well as convergence speed when compared to baseline approaches which fail at reaching a good enough policy within a practical amount of time.

No abstract

Machine learning is a popular technique to predict the retention times of molecules based on descriptors. Descriptors and associated labels (e.g., retention times) of a set of molecules can be used to train a machine learning algorithm. However, descriptors are fixed molecular features which are not necessarily optimized for the given machine learning problem (e.g., to predict retention times). Recent advances in molecular machine learning make use of so-called graph convolutional networks (GCNs) to learn molecular representations from atoms and their bonds to adjacent atoms to optimize the molecular representation for the given problem. In this study, two GCNs were implemented to predict the retention times of molecules for three different chromatographic data sets and compared to seven benchmarks (including two state-of-the art machine learning models). Additionally, saliency maps were computed from trained GCNs to better interpret the importance of certain molecular sub-structures in the data sets. Based on the overall observations of this study, the GCNs performed better than all benchmarks, either significantly outperforming them (5–25% lower mean absolute error) or performing similar to them (<5% difference). Saliency maps revealed a significant difference in molecular sub-structures that are important for predictions of different chromatographic data sets (reversed-phase liquid chromatography vs hydrophilic interaction liquid chromatography).