DNMG: Deep molecular generative model by fusion of 3D information for de novo drug design.

Deep learning is improving and changing the process of de novo molecular design at a rapid pace. In recent years, great progress has been made in drug discovery and development by using deep generative models for de novo molecular design. However, most of the existing methods are string-based or graph-based and are limited by the lack of some very important properties, such as the three-dimensional information of molecules. We propose DNMG, a deep generative adversarial network (GAN) combined with transfer learning. Specifically, we use a Wasserstein-variant GAN based network architecture that considers the 3D grid spatial information of the ligand with atomic physicochemical properties to generate a representation of the molecule, which is then parsed into SMILES strings using an improved captioning network. Comprehensive in experiments demonstrate the ability of DNMG to generate valid and novel drug-like ligands. The DNMG model is used to design inhibitors for three targets, MK14, FNTA, and CDK2. The computational results show that the molecules generated by DNMG have better binding ability to the target proteins and better physicochemical properties. Overall, our deep generative model has excellent potential to generate molecules with high binding affinity for targets and explore the space of drug-like chemistry.

BioBlocksLab: A portable DIY Bio Lab using BioBlocks language.

Standard molecular biology laboratories are usually made with complex, sophisticated, and expensive equipment. Unfortunately, most of these labs are not affordable for everyone. In this paper, we show how we built a portable bio lab BioBlocksLab, made of four modules: a centrifuge, a thermocycler, electrophoresis, and an incubator. We also propose a new version of a blockly programming language to describe experimental lab protocols, called BioBlocks 2.0, which is based on the Microsoft MakeCode platform from the open-source project Microsoft Programming Experience Toolkit (PXT). We run BioBlocks programs of real lab protocols to control different hardware modules with biological reagents and get positive results. We offer an easy, affordable, and open-source way for everyone to do experiments with Do-It-Yourself (DIY) portable bio-labs.

PETrans: De Novo Drug Design with Protein-Specific Encoding Based on Transfer Learning.

Recent years have seen tremendous success in the design of novel drug molecules through deep generative models. Nevertheless, existing methods only generate drug-like molecules, which require additional structural optimization to be developed into actual drugs. In this study, a deep learning method for generating target-specific ligands was proposed. This method is useful when the dataset for target-specific ligands is limited. Deep learning methods can extract and learn features (representations) in a data-driven way with little or no human participation. Generative pretraining (GPT) was used to extract the contextual features of the molecule. Three different protein-encoding methods were used to extract the physicochemical properties and amino acid information of the target protein. Protein-encoding and molecular sequence information are combined to guide molecule generation. Transfer learning was used to fine-tune the pretrained model to generate molecules with better binding ability to the target protein. The model was validated using three different targets. The docking results show that our model is capable of generating new molecules with higher docking scores for the target proteins.

MARPPI: boosting prediction of protein-protein interactions with multi-scale architecture residual network.

Protein-protein interactions (PPIs) are a major component of the cellular biochemical reaction network. Rich sequence information and machine learning techniques reduce the dependence of exploring PPIs on wet experiments, which are costly and time-consuming. This paper proposes a PPI prediction model, multi-scale architecture residual network for PPIs (MARPPI), based on dual-channel and multi-feature. Multi-feature leverages Res2vec to obtain the association information between residues, and utilizes pseudo amino acid composition, autocorrelation descriptors and multivariate mutual information to achieve the amino acid composition and order information, physicochemical properties and information entropy, respectively. Dual channel utilizes multi-scale architecture improved ResNet network which extracts protein sequence features to reduce protein feature loss. Compared with other advanced methods, MARPPI achieves 96.03%, 99.01% and 91.80% accuracy in the intraspecific datasets of Saccharomyces cerevisiae, Human and Helicobacter pylori, respectively. The accuracy on the two interspecific datasets of Human-Bacillus anthracis and Human-Yersinia pestis is 97.29%, and 95.30%, respectively. In addition, results on specific datasets of disease (neurodegenerative and metabolic disorders) demonstrate the ability to detect hidden interactions. To better illustrate the performance of MARPPI, evaluations on independent datasets and PPIs network suggest that MARPPI can be used to predict cross-species interactions. The above shows that MARPPI can be regarded as a concise, efficient and accurate tool for PPI datasets.

Molormer: a lightweight self-attention-based method focused on spatial structure of molecular graph for drug-drug interactions prediction.

Multi-drug combinations for the treatment of complex diseases are gradually becoming an important treatment, and this type of treatment can take advantage of the synergistic effects among drugs. However, drug-drug interactions (DDIs) are not just all beneficial. Accurate and rapid identifications of the DDIs are essential to enhance the effectiveness of combination therapy and avoid unintended side effects. Traditional DDIs prediction methods use only drug sequence information or drug graph information, which ignores information about the position of atoms and edges in the spatial structure. In this paper, we propose Molormer, a method based on a lightweight attention mechanism for DDIs prediction. Molormer takes the two-dimension (2D) structures of drugs as input and encodes the molecular graph with spatial information. Besides, Molormer uses lightweight-based attention mechanism and self-attention distilling to process spatially the encoded molecular graph, which not only retains the multi-headed attention mechanism but also reduces the computational and storage costs. Finally, we use the Siamese network architecture to serve as the architecture of Molormer, which can make full use of the limited data to train the model for better performance and also limit the differences to some extent between networks dealing with drug features. Experiments show that our proposed method outperforms state-of-the-art methods in Accuracy, Precision, Recall and F1 on multi-label DDIs dataset. In the case study section, we used Molormer to make predictions of new interactions for the drugs Aliskiren, Selexipag and Vorapaxar and validated parts of the predictions. Code and models are available at https://github.com/IsXudongZhang/Molormer.

Multi-TransDTI: Transformer for Drug-Target Interaction Prediction Based on Simple Universal Dictionaries with Multi-View Strategy.

Prediction on drug-target interaction has always been a crucial link for drug discovery and repositioning, which have witnessed tremendous progress in recent years. Despite many efforts made, the existing representation learning or feature generation approaches of both drugs and proteins remain complicated as well as in high dimension. In addition, it is difficult for current methods to extract local important residues from sequence information while remaining focused on global structure. At the same time, massive data is not always easily accessible, which makes model learning from small datasets imminent. As a result, we propose an end-to-end learning model with SUPD and SUDD methods to encode drugs and proteins, which not only leave out the complicated feature extraction process but also greatly reduce the dimension of the embedding matrix. Meanwhile, we use a multi-view strategy with a transformer to extract local important residues of proteins for better representation learning. Finally, we evaluate our model on the BindingDB dataset in comparisons with different state-of-the-art models from comprehensive indicators. In results of 100% BindingDB, our AUC, AUPR, ACC, and F1-score reached 90.9%, 89.8%, 84.2%, and 84.3% respectively, which successively exceed the average values of other models by 2.2%, 2.3%, 2.6%, and 2.6%. Moreover, our model also generally surpasses their performance on 30% and 50% BindingDB datasets.

DeepFusion: A deep learning based multi-scale feature fusion method for predicting drug-target interactions.

Predicting drug-target interactions (DTIs) is essential for both drug discovery and drug repositioning. Recently, deep learning methods have achieved relatively significant performance in predicting DTIs. Generally, it needs a large amount of approved data of DTIs to train the model, which is actually tedious to obtain. In this work, we propose DeepFusion, a deep learning based multi-scale feature fusion method for predicting DTIs. To be specific, we generate global structural similarity feature based on similarity theory, convolutional neural network and generate local chemical sub-structure semantic feature using transformer network respectively for both drug and protein. Data experiments are conducted on four sub-datasets of BIOSNAP, which are 100%, 70%, 50% and 30% of BIOSNAP dataset. Particularly, using 70% sub-dataset, DeepFusion achieves ROC-AUC and PR-AUC by 0.877 and 0.888, which is close to the performance of some baseline methods trained by the whole dataset. In case study, DeepFusion achieves promising prediction results on predicting potential DTIs in case study.

AMDE: a novel attention-mechanism-based multidimensional feature encoder for drug-drug interaction prediction.

The properties of the drug may be altered by the combination, which may cause unexpected drug-drug interactions (DDIs). Prediction of DDIs provides combination strategies of drugs for systematic and effective treatment. In most of deep learning-based methods for predicting DDI, encoded information about the drugs is insufficient in some extent, which limits the performances of DDIs prediction. In this work, we propose a novel attention-mechanism-based multidimensional feature encoder for DDIs prediction, namely attention-based multidimensional feature encoder (AMDE). Specifically, in AMDE, we encode drug features from multiple dimensions, including information from both Simplified Molecular-Input Line-Entry System sequence and atomic graph of the drug. Data experiments are conducted on DDI data set selected from Drugbank, involving a total of 34 282 DDI relationships with 17 141 positive DDI samples and 17 141 negative samples. Experimental results show that our AMDE performs better than some state-of-the-art baseline methods, including Random Forest, One-Dimension Convolutional Neural Networks, DeepDrug, Long Short-Term Memory, Seq2seq, Deepconv, DeepDDI, Graph Attention Networks and Knowledge Graph Neural Networks. In practice, we select a set of 150 drugs with 3723 DDIs, which are never appeared in training, validation and test sets. AMDE performs well in DDIs prediction task, with AUROC and AUPRC 0.981 and 0.975. As well, we use Torasemide (DB00214) as an example and predict the most likely drug to interact with it. The top 15 scores all have been reported with clear interactions in literatures.

Network-Based Approaches for Drug Repositioning.

With deep learning creeping up into the ranks of big data, new models based on deep learning and massive data have made great leaps forward rapidly in the field of drug repositioning. However, there is no relevant review to summarize the transformations and development process of models and their data in the field of drug repositioning. Among all the computational methods, network-based methods play an extraordinary role. In view of these circumstances, understanding and comparing existing network-based computational methods applied in drug repositioning will help us recognize the cutting-edge technologies and offer valuable information for relevant researchers. Therefore, in this review, we present an interpretation of the series of important network-based methods applied in drug repositioning, together with their comparisons and development process.

CSConv2d: A 2-D Structural Convolution Neural Network with a Channel and Spatial Attention Mechanism for Protein-Ligand Binding Affinity Prediction.

The binding affinity of small molecules to receptor proteins is essential to drug discovery and drug repositioning. Chemical methods are often time-consuming and costly, and models for calculating the binding affinity are imperative. In this study, we propose a novel deep learning method, namely CSConv2d, for protein-ligand interactions' prediction. The proposed method is improved by a DEEPScreen model using 2-D structural representations of compounds as input. Furthermore, a channel and spatial attention mechanism (CS) is added in feature abstractions. Data experiments conducted on ChEMBLv23 datasets show that CSConv2d performs better than the original DEEPScreen model in predicting protein-ligand binding affinity, as well as some state-of-the-art DTIs (drug-target interactions) prediction methods including DeepConv-DTI, CPI-Prediction, CPI-Prediction+CS, DeepGS and DeepGS+CS. In practice, the docking results of protein (PDB ID: 5ceo) and ligand (Chemical ID: 50D) and a series of kinase inhibitors are operated to verify the robustness.

Type III secretion system effectors form robust and flexible intracellular virulence networks.

Infections with many Gram-negative pathogens, including Escherichia coli, Salmonella, Shigella, and Yersinia, rely on type III secretion system (T3SS) effectors. We hypothesized that while hijacking processes within mammalian cells, the effectors operate as a robust network that can tolerate substantial contractions. This was tested in vivo using the mouse pathogen Citrobacter rodentium (encoding 31 effectors). Sequential gene deletions showed that effector essentiality for infection was context dependent and that the network could tolerate 60% contraction while maintaining pathogenicity. Despite inducing very different colonic cytokine profiles (e.g., interleukin-22, interleukin-17, interferon-γ, or granulocyte-macrophage colony-stimulating factor), different networks induced protective immunity. Using data from >100 distinct mutant combinations, we built and trained a machine learning model able to predict colonization outcomes, which were confirmed experimentally. Furthermore, reproducing the human-restricted enteropathogenic E. coli effector repertoire in C. rodentium was not sufficient for efficient colonization, which implicates effector networks in host adaptation. These results unveil the extreme robustness of both T3SS effector networks and host responses.

An auxin-regulable oscillatory circuit drives the root clock in Arabidopsis.

In Arabidopsis, the root clock regulates the spacing of lateral organs along the primary root through oscillating gene expression. The core molecular mechanism that drives the root clock periodicity and how it is modified by exogenous cues such as auxin and gravity remain unknown. We identified the key elements of the oscillator (AUXIN RESPONSE FACTOR 7, its auxin-sensitive inhibitor IAA18/POTENT, and auxin) that form a negative regulatory loop circuit in the oscillation zone. Through multilevel computer modeling fitted to experimental data, we explain how gene expression oscillations coordinate with cell division and growth to create the periodic pattern of organ spacing. Furthermore, gravistimulation experiments based on the model predictions show that external auxin stimuli can lead to entrainment of the root clock. Our work demonstrates the mechanism underlying a robust biological clock and how it can respond to external stimuli.

Deep Collaborative Filtering for Prediction of Disease Genes.

Accurate prioritization of potential disease genes is a fundamental challenge in biomedical research. Various algorithms have been developed to solve such problems. Inductive Matrix Completion (IMC) is one of the most reliable models for its well-established framework and its superior performance in predicting gene-disease associations. However, the IMC method does not hierarchically extract deep features, which might limit the quality of recovery. In this case, the architecture of deep learning, which obtains high-level representations and handles noises and outliers presented in large-scale biological datasets, is introduced into the side information of genes in our Deep Collaborative Filtering (DCF) model. Further, for lack of negative examples, we also exploit Positive-Unlabeled (PU) learning formulation to low-rank matrix completion. Our approach achieves substantially improved performance over other state-of-the-art methods on diseases from the Online Mendelian Inheritance in Man (OMIM) database. Our approach is 10 percent more efficient than standard IMC in detecting a true association, and significantly outperforms other alternatives in terms of the precision-recall metric at the top-k predictions. Moreover, we also validate the disease with no previously known gene associations and newly reported OMIM associations. The experimental results show that DCF is still satisfactory for ranking novel disease phenotypes as well as mining unexplored relationships. The source code and the data are available at https://github.com/xzenglab/DCF.

Computational methods for identifying the critical nodes in biological networks.

A biological network is complex. A group of critical nodes determines the quality and state of such a network. Increasing studies have shown that diseases and biological networks are closely and mutually related and that certain diseases are often caused by errors occurring in certain nodes in biological networks. Thus, studying biological networks and identifying critical nodes can help determine the key targets in treating diseases. The problem is how to find the critical nodes in a network efficiently and with low cost. Existing experimental methods in identifying critical nodes generally require much time, manpower and money. Accordingly, many scientists are attempting to solve this problem by researching efficient and low-cost computing methods. To facilitate calculations, biological networks are often modeled as several common networks. In this review, we classify biological networks according to the network types used by several kinds of common computational methods and introduce the computational methods used by each type of network.

An artificial intelligent diagnostic system on mobile Android terminals for cholelithiasis by lightweight convolutional neural network.

Artificial intelligence (AI) tools have been applied to diagnose or predict disease risk from medical images with recent data disclosure actions, but few of them are designed for mobile terminals due to the limited computational power and storage capacity of mobile devices. In this work, a novel AI diagnostic system is proposed for cholelithiasis recognition on mobile devices with Android platform. To this aim, a data set of CT images of cholelithiasis is firstly collected from The Third Hospital of Shandong Province, China, and then we technically use histogram equalization to preprocess these CT images. As results, a lightweight convolutional neural network is obtained in a constructive way to extract cholelith features and recognize gallstones. In terms of implementation, we compile Java and C++ to adapt to the application of deep learning algorithm on mobile devices with Android platform. Noted that, the training task is completed offline on PC, but cholelithiasis recognition tasks are performed on mobile terminals. We evaluate and compare the performance of our MobileNetV2 with MobileNetV1, Single Shot Detector (SSD), YOLOv2 and original SSD (with VGG-16) as feature extractors for object detection. It is achieved that our MobileNetV2 achieve similar accuracy rate, about 91% with the other four methods, but the number of parameters used is reduced from 36.1M (SSD 300, SSD512), 50.7M (Yolov2) and 5.1M (MobileNetV1) to 4.3M (MobileNetV2). The complete process on testing mobile devices, including Virtual machine, Xiaomi 7 and Htc One M8 can be controlled within 4 seconds in recognizing cholelithiasis as well as the degree of the disease.

Engineered toxin-intein antimicrobials can selectively target and kill antibiotic-resistant bacteria in mixed populations.

Targeted killing of pathogenic bacteria without harming beneficial members of host microbiota holds promise as a strategy to cure disease and limit both antimicrobial-related dysbiosis and development of antimicrobial resistance. We engineer toxins that are split by inteins and deliver them by conjugation into a mixed population of bacteria. Our toxin-intein antimicrobial is only activated in bacteria that harbor specific transcription factors. We apply our antimicrobial to specifically target and kill antibiotic-resistant Vibrio cholerae present in mixed populations. We find that 100% of antibiotic-resistant V. cholerae receiving the plasmid are killed. Escape mutants were extremely rare (10-6-10-8). We show that conjugation and specific killing of targeted bacteria occurs in the microbiota of zebrafish and crustacean larvae, which are natural hosts for Vibrio spp. Toxins split with inteins could form the basis of precision antimicrobials to target pathogens that are antibiotic resistant.

Spiking Neural P Systems With Learning Functions.

Spiking neural P systems (SN P systems) are a class of distributed and parallel neural-like computing models, inspired from the way neurons communicate by means of spikes. In this paper, a new variant of the systems, called SN P systems with learning functions, is introduced. Such systems can dynamically strengthen and weaken connections among neurons during the computation. A class of specific SN P systems with simple Hebbian learning function is constructed to recognize English letters. The experimental results show that the SN P systems achieve average accuracy rate 98.76% in the test case without noise. In the test cases with low, medium, and high noises, the SN P systems outperform back propagation neural networks and probabilistic neural networks. Moreover, comparing with spiking neural networks, SN P systems perform a little better in recognizing letters with noise. The result of this paper is promising in terms of the fact that it is the first attempt to use SN P systems in pattern recognition after many theoretical advancements of SN P systems, and SN P systems exhibit the feasibility for tackling pattern recognition problems.

Dynamical Task Switching in Cellular Computers.

We present a scheme for implementing a version of task switching in engineered bacteria, based on the manipulation of plasmid copy numbers. Our method allows for the embedding of multiple computations in a cellular population, whilst minimising resource usage inefficiency. We describe the results of computational simulations of our model, and discuss the potential for future work in this area.

Meta-Path Methods for Prioritizing Candidate Disease miRNAs.

MicroRNAs (miRNAs) play critical roles in regulating gene expression at post-transcriptional levels. Numerous experimental studies indicate that alterations and dysregulations in miRNAs are associated with important complex diseases, especially cancers. Predicting potential miRNA-disease association is beneficial not only to explore the pathogenesis of diseases, but also to understand biological processes. In this work, we propose two methods that can effectively predict potential miRNA-disease associations using our reconstructed miRNA and disease similarity networks, which are based on the latest experimental data. We reconstruct a miRNA functional similarity network using the following biological information: the miRNA family information, miRNA cluster information, experimentally valid miRNA-target association and disease-miRNA information. We also reconstruct a disease similarity network using disease functional information and disease semantic information. We present Katz with specific weights and Katz with machine learning, on the comprehensive heterogeneous network. These methods, which achieve corresponding AUC values of 0.897 and 0.919, exhibit performance superior to the existing methods. Comprehensive data networks and reasonable considerations guarantee the high performance of our methods. Contrary to several methods, which cannot work in such situations, the proposed methods also predict associations for diseases without any known related miRNAs. A web service for the download and prediction of relationships between diseases and miRNAs is available at http://lab.malab.cn/soft/MDPredict/.

A Parallel Workflow Pattern Modeling Using Spiking Neural P Systems With Colored Spikes.

Spiking neural P systems, otherwise known as named SN P systems, are bio-inspired parallel and distributed neural-like computing models. Due to the spiking behavior, SN P systems fall into the category of spiking neural networks, and are considered to be an auspicious candidate of the 3G of neural networks. It has been reported that SN P systems with colored spikes are computationally capable, and perform well in describing behaviors of complex systems. Nonetheless, some practical issue is open to be investigate, such as workflow and traffic flow modeling. In this paper, a parallel workflow pattern modeling using SN P systems with colored spikes is proposed. As results, 20 designs are constructed using SN P systems for 20 classical workflow patterns. The functioning processes that operate both sequentially and simultaneously in the workflow pattern are able to be modeled and simulated. SN P systems with colored spikes have some similarity with Petri nets, hence can be used to model workflow patterns. This will provide a novel neural-like modeling method for modeling traffic flow.