MolProphet: A One-Stop, General Purpose, and AI-Based Platform for the Early Stages of Drug Discovery.

Artificial intelligence (AI) is an effective tool to accelerate drug discovery and cut costs in discovery processes. Many successful AI applications are reported in the early stages of small molecule drug discovery. However, most of those applications require a deep understanding of software and hardware, and focus on a single field that implies data normalization and transfer between those applications is still a challenge for normal users. It usually limits the application of AI in drug discovery. Here, based on a series of robust models, we formed a one-stop, general purpose, and AI-based drug discovery platform, MolProphet, to provide complete functionalities in the early stages of small molecule drug discovery, including AI-based target pocket prediction, hit discovery and lead optimization, and compound targeting, as well as abundant analyzing tools to check the results. MolProphet is an accessible and user-friendly web-based platform that is fully designed according to the practices in the drug discovery industry. The molecule screened, generated, or optimized by the MolProphet is purchasable and synthesizable at low cost but with good drug-likeness. More than 400 users from industry and academia have used MolProphet in their work. We hope this platform can provide a powerful solution to assist each normal researcher in drug design and related research areas. It is available for everyone at https://www.molprophet.com/.

Delayed sternal Mycobacterium tuberculosis infection after left ventricular assist device implantation: A case report.

The incidence of Mycobacterium tuberculosis (Mtb) infection in patients with mechanical circulatory support devices is extremely rare. We present a case involving a 38-year-old male who experienced a delayed sternal Mtb infection following left ventricular assist device (LVAD) implantation. More than 5 months post-surgery, the patient was readmitted to the hospital presenting a subxiphoid abscess. The incision site displayed an unsatisfactory healing process after the incision and drainage of the abscess. Despite engaging in a rigorous treatment protocol, which included anti-infective therapy, vacuum-assisted closure, and surgical debridement, the patient's wound remained unhealed. Ultimately, after pus gene sequencing confirmed the diagnosis, the patient was administered a regimen combining anti-tuberculosis and anti-infective therapy, which culminated in the successful healing of the wound. This singular case study not only reveals the clinical progression of an unexpected Mtb infection post-implantation but also emphasizes the challenges encountered in diagnosis and management.

A color extraction algorithm by segmentation.

The segmentation and extraction on color features can provide useful information for many different application domains. However, most of the existing image processing algorithms on feature extraction are gray image-based and consider only one-dimensional parameters. In order to carry out a fast and accurate color feature extraction, this paper proposes a color extraction algorithm by segmentation that is called a color extraction algorithm This algorithm is compared under different color distribution situations, and the extraction effect on color is also shown by the combination of the segmentation and feature extraction algorithms. Experimental results show that such segmentation algorithm has some advantages for color segmentation. In the fuzzy color image preprocessing, this paper gives the location method of region of interest. Moreover, compared with other existing extraction algorithms, the presented segmentation extraction algorithm in this paper not only has higher accuracy, shorter extraction time and stronger anti-interference ability, but also has better effect on more divergent color edge. Experimental evaluation of the proposed color extraction algorithm demonstrates dominance over existing algorithms for feature extraction. These researches in this paper provide a new way of thinking for color feature extraction by segmentation, which has an important theoretical references and practical significance.

Gradient adaptive sampling and multiple temporal scale 3D CNNs for tactile object recognition.

Tactile object recognition (TOR) is very important for the accurate perception of robots. Most of the TOR methods usually adopt uniform sampling strategy to randomly select tactile frames from a sequence of frames, which will lead to a dilemma problem, i.e., acquiring the tactile frames with high sampling rate will get lots of redundant data, while the low sampling rate will miss important information. In addition, the existing methods usually adopt single time scale to construct TOR model, which will induce that the generalization capability is not enough for processing the tactile data generated under different grasping speeds. To address the first problem, a novel gradient adaptive sampling (GAS) strategy is proposed, which can adaptively determine the sampling interval according to the importance of tactile data, therefore, the key information can be acquired as much as possible when the number of tactile frames is limited. To handle the second problem, a multiple temporal scale 3D convolutional neural networks (MTS-3DCNNs) model is proposed, which downsamples the input tactile frames with multiple temporal scales (MTSs) and extracts the MTS deep features, and the fused features have better generalization capability for recognizing the object grasped with different speed. Furthermore, the existing lightweight network ResNet3D-18 is modified to obtain a MR3D-18 network which can match the tactile data with smaller size and prevent the overfitting problem. The ablation studies show the effectiveness of GAS strategy, MTS-3DCNNs, and MR3D-18 networks. The comprehensive comparisons with advanced methods demonstrate that our method is SOTA on two benchmarks.

Peak Blood Lactate at 24 h after ECMO Can Predict 30-day Mortality in Infants after Complex Cardiac Surgery.

OBJECTIVE: Peak blood lactate at 24 h after extracorporeal membrane oxygenation (ECMO) can predict 30-day mortality in infants after complex cardiac surgery. METHODS: Twenty-eight infants with ECMO after complex congenital heart disease surgery were selected from March 2019 to March 2022 in our hospital. The infants were divided into survival group (n = 11) and non-survival group (n = 17) according to 30-day survival after discharge from hospital. The risk factors at 30-day mortality after discharge were analyzed by Cox regression analysis. RESULTS: When compared to the non-survival group, there were significant differences in peak blood lactate at 24 h after ECMO, liver dysfunction and multiple organ dysfunction syndrome (MODS) in the survival group (p < 0.05). Cox regression analysis showed that peak blood lactate at 24 h after ECMO (HR = 1.074, 95% CI: 1.005-1.149, p = 0.036) and MODS (HR = 4.120, 95% CI: 1.373-12.362, p = 0.012) were related risk factors affecting the prognosis of infants. The best cutoff value for the peak blood lactate at 24 h after ECMO was 10.2 mmol/L. The area under the curve (AUC) for predicting the 30-day survival rate of the ECMO assisted infants after discharge from hospital was 0.770 (95% CI: 0.592-0.948, p = 0.018), with a sensitivity of 94.1% and specificity of 54.5%. CONCLUSION: The peak blood lactate at 24 h after ECMO can predict the 30-day mortality after discharge of infants treated with ECMO after complex cardiac surgery. The best cut-off value for peak blood lactate at 24 h after ECMO was 10.2 mmol/L.

[Comparison of the efficacy of different venous intubation in venous-arterial extracorporeal membrane oxygenation assisted lung transplantation].

OBJECTIVE: To compare the curative effects of different venous cannulas and drainage to improve patient's whole body oxygenation during the auxiliary process of venous-arterial extracorporeal membrane oxygenation (VA-ECMO) in lung transplantation. METHODS: From December 2016 to December 2019, 12 patients who were assisted by VA-ECMO in one lung transplantation in People's Hospital of Henan Province were selected as the research objects. According to the number of side holes of venous cannulas, they were divided into two groups: one group with few side holes and other group with multiple side holes. The differences in blood gas indexes among the right radial artery, left radial artery, and right internal jugular vein before and after assistance were compared, and the assistance effect was evaluated. RESULTS: The arterial partial pressure of oxygen (PaO2) of blood gas indexes of the right and left radial arteries in both groups were significantly higher than that before assistance [mmHg (1 mmHg = 0.133 kPa): right and left radial artery in few side holes group: 79.5±4.2 vs. 48.3±3.8 and 88.1±3.5 vs. 48.3±3.8; right and left radial artery in multiple side holes group: 67.7±5.9 vs. 48.7±3.2 and 84.0±3.8 vs. 48.7±3.2, all P < 0.05]. The arterial partial pressure of carbon dioxide (PaCO2) of blood gas index was significantly lower than that before assistance (mmHg: 44.2±2.6 vs. 71.7±4.4 for the right radial artery and 44.7±1.4 vs. 71.7±4.4 for the left radial artery in the group with few side holes; 46.2±2.1 vs. 71.2±3.5 for the right radial artery and 44.1±1.9 vs. 71.2±3.5 for the left radial artery in the group with multiple side holes, all P < 0.05). The partial pressure of oxygen in venous blood (PvO2) of blood gas index of ECMO system in the group with few side holes was significantly lower than that of the multiport side holes group (mmHg: 56.4±3.2 vs. 88.7±1.5, P < 0.01), and the partial pressure of carbon dioxide in venous blood (PvCO2) was significantly higher than that of multiport side holes group (mmHg: 63.6±3.7 vs. 44.2±1.7, P < 0.01). CONCLUSIONS: When VA-ECMO is used in lung transplantation, the superior vena cava blood flow can be fully drained by using intravenous cannula with few side holes. It can effectively improve the oxygenation of the upper body of lung transplant patients, avoid the dilemma of hypoxemia in the upper body and hyperxemia in the lower body, provide more effective assistance to patients undergoing single lung transplantation, and is more meaningful for improving the oxygenation status of the whole body in patients undergoing single lung transplantation.

Anti-inflammatory cytokine IL10 loaded cRGD liposomes for the targeted treatment of atherosclerosis.

AIM: Atherosclerosis (AS) is one of the main causes of cardiovascular disease which might lead to myocardial infarction or stroke and further leads to fatality. METHOD: In this study, we have designed an anti-inflammatory cytokine interleukin-10 (IL10) delivery system to effectively alleviate the inflammation of atherosclerosis plaque. The targeted delivery of IL10 to the atherosclerotic plaques was achieved by cRGD conjugated liposomes (IL10-cRGD-Lip). RESULTS: The IL10-cRGD-Lip of size 179.4 ± 10.91 nm having PDI 0.14 ± 0.04 with a surface charge of +18.34 ± 1.36 mV was prepared. The in-vitro analysis clearly suggests that IL10-cRGD-Lip sustains the release of IL10 and could significantly reduce ROS and NO. The immuno-staining results revealed that IL-1ß and TNF-α were down-regulated after the treatment with IL10-cRGD-Lip in Lipopolysaccharide (LPS) stimulated RAW 264.7 cells. CONCLUSION: the in-vitro results clearly suggest that anti-inflammatory cytokine IL10 could be used for the cure of inflammatory maladies including atherosclerosis.

Micro-cracks detection of solar cells surface via combining short-term and long-term deep features.

The machine vision based methods for micro-cracks detection of solar cells surface have become one of the main research directions with its efficiency and convenience. The existed methods are roughly classified into two categories: current viewing information based methods, prior knowledge based methods, however, the former usually adopt hand-designed features with poor generality and lacks the guidance of prior knowledge, the latter are usually implemented through the machine learning, and the generalization ability is also limited since the large-scale annotation dataset is scarce. To resolve above problems, a novel micro-cracks detection method via combining short-term and long-term deep features is proposed in this paper. The short-term deep features which represent the current viewing information are learned from the input image itself through stacked denoising auto encoder (SDAE), the long-term deep features which represent the prior knowledge are learned from a large number of natural scene images that people often see through convolutional neural networks (CNNs). The subjective and objective evaluations demonstrate that: 1) the performance of combining the short-term and long-term deep features is better than any of them alone, 2) the performance of proposed method is superior to the shallow learning based methods, 3) the proposed method can effectively detect various kinds of micro-cracks.

Hardness Recognition of Robotic Forearm Based on Semi-supervised Generative Adversarial Networks.

The hardness recognition is of great significance to tactile sensing and robotic control. The hardness recognition methods based on deep learning have demonstrated a good performance, however, a huge amount of manually labeled samples which require lots of time and labor costs are necessary for the training of deep neural networks. In order to alleviate this problem, a semi-supervised generative adversarial network (GAN) which requires less manually labeled samples is proposed in this paper. First of all, a large number of unlabeled samples are made use of through the unsupervised training of GAN, which is used to provide a good initial state to the following model. Afterwards, the manually labeled samples corresponding to each hardness level are individually used to train the GAN, of which the architecture and initial parameter values are inherited from the unsupervised GAN, and augmented by the generator of trained GAN. Finally, the hardness recognition network (HRN), of which the main architecture and initial parameter values are inherited from the discriminator of unsupervised GAN, is pretrained by a large number of augmented labeled samples and fine-tuned by manually labeled samples. The hardness recognition result can be obtained online by importing the tactile data captured by the robotic forearm into the trained HRN. The experimental results demonstrate that the proposed method can significantly save the manual labeling work while providing an excellent recognition precision for hardness recognition.

DRUGS System Improving the Effects of Clinical Pathways: A Systematic Study.

The aim of the study is to assess the feasibility of Drugs Rational Usage Guideline System (DRUGS)-supported clinical pathway (CP) for breast carcinoma, cataract, inguinal hernia and 2-diabetes mellitus whether the application of such a system could improve work efficiency, medical safety, and decrease hospital cost. Four kinds of diseases which included 1773 cases (where 901 cases using paper-based clinical pathways and 872 cases using DRUGS-supported clinical pathways) were selected and their demographic and clinical data were collected. The evaluation criteria were length of stay, preoperative length of stay, hospital cost, antibiotics prescribed during hospitalization, unscheduled surgery, complications and prognosis. The median total LOS was 1 to 3 days shorter in the DRUGS-supported CP group as compared to the Paper-based CP group for all types (p < 0.05). Totel hospital cost decreased significantly in the DRUGS-supported CP group than that in Paper-based CP group. About antibiotics prescribed during hospitalization, there were no statistically differences in the time of initial dose of antibiotic and the duration of administration except the choice of antibiotic categories. The proportion of DRUGS-supported clinical pathway conditions where a broad-spectrum antibiotic was prescribed decreased from 63.6 to 34.5 % (p < 0.01) in the Paper-based group. While after the intervention, the differences were statistically not significant in unscheduled surgery, complications and prognosis. In this study, DRUGS-supported clinical pathway for breast carcinoma, cataract, inguinal hernia, 2-diabetes mellitus was smoothly shifted from a paper-based to an electronic system, and confer benefits at the hospital level.

Sequence-dependent solution structure and motions of 13 TATA/TBP (TATA-box binding protein) complexes.

The TATA element is a well-known example of a DNA promoter sequence recognized by the TATA box binding protein (TBP) through its intrinsic motion and deformability. Although TBP recognizes the TATA element octamer unusually (through the minor groove, which lacks the distinctive features of the major groove), single base-pair replacements alter transcriptional activity. Recent crystallographic experiments have suggested that TATA/TBP complexes differing by a single base pair retain substantial structural similarity despite their functional differences in activating transcription. To investigate the subtle role of sequence-dependent motion within the TATA element and certain aspects of its effect on assembly of the transcriptional complex, we examine 5-ns dynamics trajectories of 13 variant TATA/TBP complexes differing from each other by a single base pair. They include the wild-type (WT) adenovirus 2 major late promoter (AdMLP) TATA element, TATAAAAG (the octamer specifies positions -31 to -24 with respect to the transcription initiation site), and the variants A31 (i.e., AATAAAAG), T30, A29, C29, G28, T28, T27, G26, T26, C25, T25, and T24. Our simulated TATA/TBP complexes develop sequence-dependent structure and motion trends that may lead to favorable orientations for high-activity variants (with respect to binding TFIIA, TFIIB, and other transcription factors), while conversely, accelerate dissociation of low-activity TATA/TBP complexes. The motions that promote favorable geometries for preinitiation complexes include small rotations between TBP's N- and C-terminal domains, sense strand DNA backbone "slithering," and rotations in TBP's H2 and H2' helices. Low-activity variants tend to translate the H1 and H1' helices and withdraw the intercalating phenylalanines. These cumulative DNA and protein motions lead to a spatial spread of complex orientations up to 4 A; this is associated with an overall bend of the variant TATA/TBP complexes that spans 93 degrees to 110 degrees (107 degrees for the crystal reference). Taken together, our analyses imply larger differences when these local structural and bending changes are extended to longer DNA (upstream and downstream) and suggest that specific local TATA/TBP motions (e.g., shifts in TBP helices and TATA bases and backbone) play a role in modulating the formation and maintenance of the transcription initiation complex.

Inherent speedup limitations in multiple time step/particle mesh Ewald algorithms.

Multiple time step (MTS) algorithms present an effective integration approach to reduce the computational cost of dynamics simulations. By using force splitting to allow larger time steps for the more slowly varying force components, computational savings can be realized. The Particle-Mesh-Ewald (PME) method has been independently devised to provide an effective and efficient treatment of the long-range electrostatics interactions. Here we examine the performance of a combined MTS/PME algorithm previously developed for AMBER on a large polymerase beta/DNA complex containing 40,673 atoms. Our goal is to carefully combine the robust features of the Langevin/MTS (LN) methodology implemented in CHARMM-which uses position rather than velocity Verlet with stochasticity to make possible outer time steps of 150 fs-with the PME formulation. The developed MTS/PME integrator removes fast terms from the reciprocal-space Ewald component by using switch functions. We analyze the advantages and limitations of the resulting scheme by comparing performance to the single time step leapfrog Verlet integrator currently used in AMBER by evaluating different time-step protocols using three assessors for accuracy, speedup, and stability, all applied to long (i.e., nanosecond) simulations to ensure proper energy conservation. We also examine the performance of the algorithm on a parallel, distributed shared-memory computer (SGI Origin 2000 with 8 300-MHz R12000 processors). Good energy conservation and stability behavior can be demonstrated, for Newtonian protocols with outer time steps of up to 8 fs and Langevin protocols with outer time steps of up to 16 fs. Still, we emphasize the inherent limitations imposed by the incorporation of MTS methods into the PME formulation that may not be widely appreciated. Namely, the limiting factor on the largest outer time-step size, and hence speedup, is an intramolecular cancellation error inherent to PME. This error stems from the excluded-nonbonded correction term contained in the reciprocal-space component. This cancellation error varies in time and introduces artificial frequencies to the governing dynamics motion. Unfortunately, we find that this numerical PME error cannot be easily eliminated by refining the PME parameters (grid resolution and/or order of interpolating polynomial). We suggest that methods other than PME for fast electrostatics may allow users to reap the full advantages from MTS algorithms.

A new program for optimizing periodic boundary models of solvated biomolecules (PBCAID).

Simulations of solvated macromolecules often use periodic lattices to account for long-range electrostatics and to approximate the surface effects of bulk solvent. The large percentage of solvent molecules in such models (compared to macromolecular atoms) makes these procedures computationally expensive. The cost can be reduced by using periodic cells containing an optimized number of solvent molecules (subject to a minimal distance between the solute and the periodic images). We introduce an easy-to-use program "PBCAID" to initialize and optimize a periodic lattice specified as one of several known space-filling polyhedra. PBCAID reduces the volume of the periodic cell by finding the solute rotation that yields the smallest periodic cell dimensions. The algorithm examines rotations by using only a subset of surface atoms to measure solute/image distances, and by optimizing the distance between the solute and the periodic cell surface. Once the cell dimension is optimized, PBCAID incorporates a procedure for solvating the domain with water by filling the cell with a water lattice derived from an ice structure scaled to the bulk density of water. Results show that PBCAID can optimize system volumes by 20 to 70% and lead to computational savings in the nonbonded computations from reduced solvent sizes. Copyright 2001 John Wiley & Sons, Inc. J Comput Chem 22: 1843-1850, 2001