As key oncogenic drivers in non-small-cell lung cancer (NSCLC), various mutations in the epidermal growth factor receptor (EGFR) with variable drug sensitivities have been a major obstacle for precision medicine. To achieve clinical-level drug recommendations, a platform for clinical patient case retrieval and reliable drug sensitivity prediction is highly expected. Therefore, we built a database, D3EGFRdb, with the clinicopathologic characteristics and drug responses of 1339 patients with EGFR mutations via literature mining. On the basis of D3EGFRdb, we developed a deep learning-based prediction model, D3EGFRAI, for drug sensitivity prediction of new EGFR mutation-driven NSCLC. Model validations of D3EGFRAI showed a prediction accuracy of 0.81 and 0.85 for patients from D3EGFRdb and our hospitals, respectively. Furthermore, mutation scanning of the crucial residues inside drug-binding pockets, which may occur in the future, was performed to explore their drug sensitivity changes. D3EGFR is the first platform to achieve clinical-level drug response prediction of all approved small molecule drugs for EGFR mutation-driven lung cancer and is freely accessible at https://www.d3pharma.com/D3EGFR/index.php.

Multi-Gbps 60 GHz millimeter wave (mmWave) networks, are considered as the enabling technology for emerging applications such as untethered VR and 4K/8K Miracast. However, user motion, and even orientation change, can cause mis-alignment between mmWave transceivers’ directional beams and thus severe link outage. Within the practical 3D spaces, the combination of location and orientation dynamics leads to the exponential growth of beam searching complexity, which substantially exacerbates the outage. In this paper, we first measure the impact of 3D motion on 60 GHz link performance in the context of VR and Miracast applications. We find that 3D motion exhibits inherent non-predictability, so conventional beam steering solutions are no longer effective. Therefore, we propose a model-driven 3D beam-steering mechanism called Parallel Scanner (PSCAN), which can maintain high performance for mobile 60 GHz links. To enable PSCAN, we first discover and prove a hidden interaction between 3D beams and the spatial channel profile of 60 GHz radios. Leveraging on which, PSCAN strategically scans the 3D space to reduce the search latency by more than one order of magnitude. Experiment results based on a custom-built 60 GHz platform demonstrate PSCAN’s remarkable throughput gain, up to$5\times $, compared with the state-of-the-art.

Maximizing the quality of experience (QoE) for real-time video is a long-standing challenge. Traditional video transport protocols, represented by a few deterministic rules, can hardly adapt to the heterogeneous and highly dynamic modern Internet. Emerging learning-based algorithms have demonstrated potential to meet the challenge. However, our measurement study reveals an alarming long tail performance issue: these algorithms tend to be bottle-necked by occasional catastrophic events due to the built-in exploration mechanisms. In this work, we propose Loki, which improves the robustness of learning-based model by coherently integrating it with a rule-based algorithm. To enable integration at feature level, we first reverse-engineer the rule-based algorithm into an equivalent "black-box" neural network. Then, we design a dual-attention feature fusion mechanism to fuse it with a reinforcement learning model. We train Loki in a commercial real-time video system through online learning, and evaluate it over 101 million video sessions, in comparison to state-of-the-art rule-based and learning-based solutions. The results show that Loki improves not only the average but also the tail performance substantially (26.30% to 44.24% reduction of stall rate and 1.76% to 2.17% increase in video throughput at 95-percentile).

BACKGROUND: Hybrid capture-based next-generation sequencing of DNA has been widely applied in the detection of circulating tumor DNA (ctDNA). Various methods have been proposed for ctDNA detection, but low-allelic-fraction (AF) variants are still a great challenge. In addition, no panel-wide calling algorithm is available, which hiders the full usage of ctDNA based 'liquid biopsy'. Thus, we developed the VBCALAVD (Virtual Barcode-based Calling Algorithm for Low Allelic Variant Detection) in silico to overcome these limitations. RESULTS: Based on the understanding of the nature of ctDNA fragmentation, a novel platform-independent virtual barcode strategy was established to eliminate random sequencing errors by clustering sequencing reads into virtual families. Stereotypical mutant-family-level background artifacts were polished by constructing AF distributions. Three additional robust fine-tuning filters were obtained to eliminate stochastic mutant-family-level noises. The performance of our algorithm was validated using cell-free DNA reference standard samples (cfDNA RSDs) and normal healthy cfDNA samples (cfDNA controls). For the RSDs with AFs of 0.1, 0.2, 0.5, 1 and 5%, the mean F1 scores were 0.43 (0.25~0.56), 0.77, 0.92, 0.926 (0.86~1.0) and 0.89 (0.75~1.0), respectively, which indicates that the proposed approach significantly outperforms the published algorithms. Among controls, no false positives were detected. Meanwhile, characteristics of mutant-family-level noise and quantitative determinants of divergence between mutant-family-level noises from controls and RSDs were clearly depicted. CONCLUSIONS: Due to its good performance in the detection of low-AF variants, our algorithm will greatly facilitate the noninvasive panel-wide detection of ctDNA in research and clinical settings. The whole pipeline is available at https://github.com/zhaodalv/VBCALAVD.

Google congestion control (GCC) is the de-facto standard for web real-time communications (WebRTC) applications and has been implemented in mainstream browsers including Chrome and Firefox. While GCC is designed to achieve high video bit-rate and low latency simultaneously, we find that GCC's performance is far from satisfactory particularly under good network conditions. In particular, we collect a GCC trace dataset with over 1.18 million sessions from a major crowd-sourced live video streaming service provider. We perform in-depth analytics using the dataset, which shows that the sending video bit-rate unnecessarily experiences frequent rollbacks caused by minor fluctuation of transmission delay. To address the issue, we propose a mechanism called GCC-β, which can distinguish normal network fluctuation from real network congestion, and then adaptively sends appropriate bitrates. We implement GCC-β in the WebRTC framework and evaluate its performance using test-bed experiments. The results show that GCC-β is able to avoid up to 90% unnecessary bitrate rollbacks.

Despite the pervasive use of real-time video telephony services, the users' quality of experience (QoE) remains unsatisfactory, especially over the mobile Internet. Previous work studied the problem via controlled experiments, while a systematic and in-depth investigation in the wild is still missing. To bridge the gap, we conduct a large-scale measurement campaign on \appname, an operational mobile video telephony service. Our measurement logs fine-grained performance metrics over 1 million video call sessions. Our analysis shows that the application-layer video codec and transport-layer protocols remain highly uncoordinated, which represents one major reason for the low QoE. We thus propose \name, a machine learning based framework to resolve the issue. Instead of blindly following the transport layer's estimation of network capacity, \name reviews historical logs of both layers, and extracts high-level features of codec/network dynamics, based on which it determines the highest bitrates for forthcoming video frames without incurring congestion. To attain the ability, we train \name with the aforementioned massive data traces using a custom-designed imitation learning algorithm, which enables \name to learn from past experience. We have implemented and incorporated \name into \appname. Our experiments show that \name outperforms state-of-the-art solutions, improving video quality while reducing stalling time by multi-folds under various practical scenarios.

Despite the pervasive use of real-time video telephony services, their quality of experience (QoE) remains unsatisfactory, especially over the mobile Internet. We conduct a large-scale measurement campaign on \appname, an operational mobile video telephony service. Our analysis shows that the application-layer video codec and transport-layer protocols remain highly uncoordinated, which represents one major reason for the low QoE. We thus propose \name, a machine learning based framework to resolve the issue. We train \name with the massive data traces from the measurement campaign using a custom-designed imitation learning algorithm, which enables \name to learn from past experience following an expert's iterative demonstration/supervision. We have implemented and incorporated \name into the \appname. Our experiments show that \name outperforms state-of-the-art solutions, improving video quality while reducing stalling time by multi-folds under various practical scenarios.

60 GHz networks, with multi-Gbps bitrate, are considered as the enabling technology for emerging applications such as wireless Virtual Reality (VR) and 4K/8K real-time Miracast. However, user motion, and even orientation change, can cause mis-alignment between 60 GHz transceivers' directional beams, thus causing severe link outage. Within the practical 3D spaces, the combination of location and orientation dynamics leads to exponential growth of beam searching complexity, which substantially exacerbates the outage and hinders fast recovery. In this paper, we first conduct an extensive measurement to analyze the impact of 3D motion on 60 GHz link performance, in the context of VR and Miracast applications. We find that 3D motion exhibits inherent non-predictability, so conventional beam steering solutions, which targets 2D scenarios with lower search space and short-term motion coherence, fail in practical 3D setup. Motivated by these observations, we propose a model-driven 3D beam-steering mechanism called Orthogonal Scanner (OScan), which can maintain high performance for mobile 60 GHz links in 3D space. OScan discovers and leverages a hidden interaction between 3D beams and the spatial channel profile of 60 GHz radios, and strategically scans the 3D space so as to reduce the search latency by more than one order of magnitude. Experiment results based on a custom-built 60 GHz platform along with a trace-driven emulator demonstrate OScan's remarkable throughput gain, up to 5×, compared with the state-of-the-art.

Recommender systems, inferring users' preferences from their historical activities and personal profiles, have been an enormous success in the last several years. Most of the existing works are based on the similarities of users, objects or both that derived from their purchases records in the online shopping platforms. Such approaches, however, are facing bottlenecks when the known information is limited. The extreme case is how to recommend products to new users, namely the so-called cold-start problem. The rise of the online social networks gives us a chance to break the glass ceiling. Birds of a feather flock together. Close friends may have similar hidden pattern of selecting products and the advices from friends are more trustworthy. In this paper, we integrate the individual's social relationships into recommender systems and propose a new method, called Social Mass Diffusion (SMD), based on a mass diffusion process in the combined network of users' social network and user-item bipartite network. The results show that the SMD algorithm can achieve higher recommendation accuracy than the Mass Diffusion (MD) purely on the bipartite network. Especially, the improvement is striking for small degree users. Moreover, SMD provides a good solution to the cold-start problem. The recommendation accuracy for new users significantly higher than that of the conventional popularity-based algorithm. These results may shed some light on the new designs of better personalized recommender systems and information services.

This paper investigates the production tolerances and variations of the lamination and permanent magnet on the cogging torque of the surface permanent magnet (SPM) machine with mass production. The finite element analysis (FEA) and experiment contrasted analysis method is adopted to deal with the additional component cogging torque, of the 12 slots 10 poles combination SPM machine, caused by production variation of the magnet, stator and rotor lamination. Its reveal that the eccentricity has small effect on the cogging torque, however, the manufacturing tolerances of lamination and inconsistency of permanent magnet have more significant influence on the cogging torque. This paper also propose the method by successively rotating each lamination of stator and rotor to suppress the additional components of the cogging torque.

Multiple-input multiple-output (MIMO) technologies have the advantage of improving system throughput and error performance by exploiting the spatial diversity, owing to the multiple independent transmit-receive paths. A lot of efforts have been put into MIMO broadcast channels research and it is expected to be a core technology for 3G and 4G wireless systems. Generally, channel state information (CSI) is required at the transmitter, to fully exploit the diversity. In the case that channel reciprocity does not apply, limited feedback is one effective solution to get CSI at the transmitter but it increases system complexity and degrades the performance. In this paper, we propose a low complexity limited feedback scheme for MIMO broadcast channels. Non-cooperative receivers without full CSI and a feedback link with a limited rate are considered. The proposed scheme is based on a novel Grassmannian-based two-layer codebook, each layer having a small dimension, and a vector selection algorithm, to maximize the effective channel gain. A simulation is presented for the proposed scheme, showing that the performance is very close to the best known conventional high dimensional codebook, while the search complexity and memory requirement are reduced by several orders of magnitude.

We consider relay broadcast channels (RBCs) with multiple antennas at all nodes. A practical precoding, relaying and combining scheme is proposed. Under an overall power constraint, we derive the optimal power allocation solution in a closed form. The conditions for an effective RBC scheme are identified with a qualitative analysis to the relationship between the relay gain and the relative strengths of the direct and relay links. Simulation results are shown for various channel configurations, which verify the analysis and conclude that the first hop in the relay chain is a determining factor to the overall performance of the RBC.