Vina-FPGA-Cluster: Multi-FPGA Based Molecular Docking Tool with High-Accuracy and Multi-Level Parallelism.

AutoDock Vina (Vina) stands out among numerous molecular docking tools due to its precision and comparatively high speed, playing a key role in the drug discovery process. Hardware acceleration of Vina on FPGA platforms offers a high energy-efficiency approach to speed up the docking process. However, previous FPGA-based Vina accelerators exhibit several shortcomings: 1) Simple uniform quantization results in inevitable accuracy drop; 2) Due to Vina's complex computing process, the evaluation and optimization phase for hardware design becomes extended; 3) The iterative computations in Vina constrain the potential for further parallelization. 4) The system's scalability is limited by its unwieldy architecture. To address the above challenges, we propose Vina-FPGA-cluster, a multi-FPGA-based molecular docking tool enabling high-accuracy and multi-level parallel Vina acceleration. Standing upon the shoulders of Vina-FPGA, we first adapt hybrid fixed-point quantization to minimize accuracy loss. We then propose a SystemC-based model, accelerating the hardware accelerator architecture design evaluation. Next, we propose a novel bidirectional AG module for data-level parallelism. Finally, we optimize the system architecture for scalable deployment on multiple Xilinx ZCU104 boards, achieving task-level parallelism. Vina-FPGA-cluster is tested on three representative molecular docking datasets. The experiment results indicate that in the context of RMSD (for successful docking outcomes with metrics below 2Å), Vina-FPGA-cluster shows a mere 0.2% lose. Relative to CPU and Vina-FPGA, Vina-FPGA-cluster achieves 27.33× and 7.26× speedup, respectively. Notably, Vina-FPGA-cluster is able to deliver the 1.38× speedup as GPU implementation (Vina-GPU), with just the 28.99% power consumption.

Accelerating AutoDock Vina with GPUs.

AutoDock Vina is one of the most popular molecular docking tools. In the latest benchmark CASF-2016 for comparative assessment of scoring functions, AutoDock Vina won the best docking power among all the docking tools. Modern drug discovery is facing a common scenario of large virtual screening of drug hits from huge compound databases. Due to the seriality characteristic of the AutoDock Vina algorithm, there is no successful report on its parallel acceleration with GPUs. Current acceleration of AutoDock Vina typically relies on the stack of computing power as well as the allocation of resource and tasks, such as the VirtualFlow platform. The vast resource expenditure and the high access threshold of users will greatly limit the popularity of AutoDock Vina and the flexibility of its usage in modern drug discovery. In this work, we proposed a new method, Vina-GPU, for accelerating AutoDock Vina with GPUs, which is greatly needed for reducing the investment for large virtual screens and also for wider application in large-scale virtual screening on personal computers, station servers or cloud computing, etc. Our proposed method is based on a modified Monte Carlo using simulating annealing AI algorithm. It greatly raises the number of initial random conformations and reduces the search depth of each thread. Moreover, a classic optimizer named BFGS is adopted to optimize the ligand conformations during the docking progress, before a heterogeneous OpenCL implementation was developed to realize its parallel acceleration leveraging thousands of GPU cores. Large benchmark tests show that Vina-GPU reaches an average of 21-fold and a maximum of 50-fold docking acceleration against the original AutoDock Vina while ensuring their comparable docking accuracy, indicating its potential for pushing the popularization of AutoDock Vina in large virtual screens.

Transfer learning with molecular graph convolutional networks for accurate modeling and representation of bioactivities of ligands targeting GPCRs without sufficient data.

There are many new or potential drug targets in G protein-coupled receptors (GPCRs) without sufficient ligand associations, and it is essential and urgent to implement drug discovery targeting these GPCRs. Precise modeling and representing ligand bioactivities are essential for screening and optimizing these GPCR targeted drugs, yet insufficient samples made it difficult to achieve. Transfer learning intends to solve this by introducing rich information from related source domains with sufficient ligand training samples. In addition, ligand molecules naturally constitute a graph structure, which can be utilized by molecular graph convolutional networks to form an end-to-end multiple-level representation learning. This study proposed a novel method, TL-MGCN, using transfer learning with molecular graph convolutional networks to precisely model and represent bioactivities of ligands targeting GPCRs without sufficient data. The study tested TL-MGCN on a series of 54 representative target domain datasets which cover most human subfamilies, and 44 out of them have less than 600 ligand associations. TL-MGCN obtained an average improvement of 28.74%, 17.28%, 10.05%, 77.83%, 43.65% and 14.65% on correlation coefficient (r2) and 11.90%, 7.43%, 14.86%, 41.46%, 31.02% and 22.94% on root-mean-square error (RMSE) compared with the WDL-RF, transfer learning version of WDL-RF (TR-WDL-RF), attentive FP, GIN, Weave and MPNN predictors, respectively. Users have free access to the web server of TL-MGCN, along with the source codes and datasets, at http://www.noveldelta.com/TL_MGCN for academic purposes.

Homologous G Protein-Coupled Receptors Boost the Modeling and Interpretation of Bioactivities of Ligand Molecules.

G protein-coupled receptors (GPCRs) are one of the most important drug targets, accounting for ∼34% of drugs on the market. For drug discovery, accurate modeling and explanation of bioactivities of ligands is critical for the screening and optimization of hit compounds. Homologous GPCRs are more likely to interact with chemically similar ligands, and they tend to share common binding modes with ligand molecules. The inclusion of homologous GPCRs in learning bioactivities of ligands potentially enhances the accuracy and interpretability of models due to utilizing increased training sample size and the existence of common ligand substructures that control bioactivities. Accurate modeling and interpretation of bioactivities of ligands by combining homologous GPCRs can be formulated as multitask learning with joint feature learning problem and naturally matched with the group lasso learning algorithm. Thus, we proposed a multitask regression learning with group lasso (MTR-GL) implemented by l2,1-norm regularization to model bioactivities of ligand molecules and then tested the algorithm on a series of thirty-five representative GPCRs datasets that cover nine subfamilies of human GPCRs. The results show that MTR-GL is overall superior to single-task learning methods and classic multitask learning with joint feature learning methods. Moreover, MTR-GL achieves better performance than state-of-the-art deep multitask learning based methods of predicting ligand bioactivities on most datasets (31/35), where MTR-GL obtained an average improvement of 38% on correlation coefficient (r2) and 29% on root-mean-square error over the DeepNeuralNet-QSAR predictors.

Wearable on-device deep learning system for hand gesture recognition based on FPGA accelerator.

Gesture recognition is critical in the field of Human-Computer Interaction, especially in healthcare, rehabilitation, sign language translation, etc. Conventionally, the gesture recognition data collected by the inertial measurement unit (IMU) sensors is relayed to the cloud or a remote device with higher computing power to train models. However, it is not convenient for remote follow-up treatment of movement rehabilitation training. In this paper, based on a field-programmable gate array (FPGA) accelerator and the Cortex-M0 IP core, we propose a wearable deep learning system that is capable of locally processing data on the end device. With a pre-stage processing module and serial-parallel hybrid method, the device is of low-power and low-latency at the micro control unit (MCU) level, however, it meets or exceeds the performance of single board computers (SBC). For example, its performance is more than twice as much of Cortex-A53 (which is usually used in Raspberry Pi). Moreover, a convolutional neural network (CNN) and a multilayer perceptron neural network (NN) is used in the recognition model to extract features and classify gestures, which helps achieve a high recognition accuracy at 97%. Finally, this paper offers a software-hardware co-design method that is worth referencing for the design of edge devices in other scenarios.

Analysis of implant loss risk factors especially in maxillary molar location: A retrospective study of 6977 implants in Chinese individuals.

BACKGROUND: The knowledge of the potential risk factors associated with implant loss is crucial for dental clinicians, but the opinions about the risk factors are still diverse and controversial. PURPOSE: This retrospective study assessed the risk factors associated with implant loss, especially that in the maxillary molar location. MATERIALS AND METHODS: From January 2015 to March 2017, 4338 Chinese patients received 6977 implants at Nanjing Stomatological Hospital. Information on patient age, gender, bone grafting procedure, implant location, length and diameter, and the records of lost implants were obtained. The Kaplan-Meier method and log-rank test were used to conduct a survival function analysis. Chi-square test and multivariate Cox regression analysis were used to identify risk factors related to implant loss. RESULTS: The cumulative survival rate (CSR) after 0-32 months of observation period for all implants was 97.76%, and the CSR for maxillary molar implants was 97.00%. Maxillary molar implants showed a significantly lower CSR than the other implants (P < .05). Male sex, short implants (<10 mm) were considered as risk factors for implant loss. However, male sex and bone grafting procedure were regarded as risk factors for maxillary molar implant loss, which was slightly different from the result of all implants. CONCLUSIONS: Male sex, short implants (<10 mm) and maxillary molar location were considered as potential risk factors for implant loss, whereas male sex and bone grafting procedure were significantly associated with implant loss in maxillary molar location.

SPIO Enhance the Cross-Presentation and Migration of DCs and Anionic SPIO Influence the Nanoadjuvant Effects Related to Interleukin-1ß.

Superparamagnetic iron oxide nanoparticles (SPIO) have been synthesized and explored for use as carriers of various nanoadjuvants via loading into dendritic cells (DCs). In our study, homogeneous and superparamagnetic nanoparticles are susceptible to internalization by DCs and SPIO-pulsed DCs showed excellent biocompatibility and capacity for ovalbumin (OVA) cross-presentation. Herein, we found that SPIO-loaded DCs can promote the maturation and migration of DCs in vitro. SPIO coated with 3-aminopropyltrimethoxysilane (APTS) and meso-2,3-dimercaptosuccinic acid (DMSA), which present positive and negative charges, respectively, were prepared. We aimed to investigate whether the surface charge of SPIO can affect the antigen cross-presentation of the DCs. Additionally, the formation of interleukin-1ß (IL-1ß) was examined after treatment with oppositely charged SPIO to identify the nanoadjuvants mechanism. In conclusion, our results suggest that SPIO are biocompatible and can induce the migration of DCs into secondary lymph nodes. SPIO coated with APTS (SPIO/A+) exhibited excellent adjuvant potentials for the promotion of antigen cross-presentation and T cell activation and surpassed that of DMSA-coated nanoparticles (SPIO/D-). This process may be related to the secretion of IL-1ß. Our study provides insights into the predictive modification of nanoadjuvants, which will be valuable in DC vaccine design and could lead to the creation of new adjuvants for applications in vaccines for humans.

Study on changes of partial pressure of brain tissue oxygen and brain temperature in acute phase of severe head injury during mild hypothermia therapy.

OBJECTIVE: To study the changes of partial pressure of brain tissue oxygen (PbtO2) and brain temperature in acute phase of severe head injury during mild hypothermia therapy and the clinical significance. METHODS: One hundred and sixteen patients with severe head injury were selected and divided into a mild hypothermia group (n=58), and a control group (n=58) according to odd and even numbers of hospitalization. While mild hypothermia therapy was performed PbtO2 and brain temperature were monitored for 1-7 days (mean=86 hours), simultaneously, the intracranial pressure, rectum temperature, cerebral perfusion pressure, PaO2 and PaCO2 were also monitored. The patients were followed up for 6 months and the prognosis was evaluated with GOS (Glasgow outcome scale). RESULTS: The mean value of PbtO2 within 24 hour monitoring in the 116 patients was 13.7 mm Hg +/- 4.94 mm Hg, lower than the normal value (16 mm Hg +/- 40 mm Hg ) The time of PbtO2 recovering to the normal value in the mild hypothermia group was shortened by 10 +/- 4.15 hours compared with the control group (P<0.05). The survival rate of the mild hypothermia group was 60.43%, higher than that of the control group (46.55%). After the recovery of the brain temperature, PbtO2 increased with the rise of the brain temperature. CONCLUSIONS: Mild hypothermia can improve the survival rate of severe head injury. The technique of monitoring PbtO2 and the brain temperature is safe and reliable, and has important clinical significance in judging disease condition and instructing clinical therapy.