Structural insights into the molecular effects of the anthelmintics monepantel and betaine on the Caenorhabditis elegans acetylcholine receptor ACR-23.

Anthelmintics are drugs used for controlling pathogenic helminths in animals and plants. The natural compound betaine and the recently developed synthetic compound monepantel are both anthelmintics that target the acetylcholine receptor ACR-23 and its homologs in nematodes. Here, we present cryo-electron microscopy structures of ACR-23 in apo, betaine-bound, and betaine- and monepantel-bound states. We show that ACR-23 forms a homo-pentameric channel, similar to some other pentameric ligand-gated ion channels (pLGICs). While betaine molecules are bound to the classical neurotransmitter sites in the inter-subunit interfaces in the extracellular domain, monepantel molecules are bound to allosteric sites formed in the inter-subunit interfaces in the transmembrane domain of the receptor. Although the pore remains closed in betaine-bound state, monepantel binding results in an open channel by wedging into the cleft between the transmembrane domains of two neighboring subunits, which causes dilation of the ion conduction pore. By combining structural analyses with site-directed mutagenesis, electrophysiology and in vivo locomotion assays, we provide insights into the mechanism of action of the anthelmintics monepantel and betaine.

A gene regulatory network-aware graph learning method for cell identity annotation in single-cell RNA-seq data.

Cell identity annotation for single-cell transcriptome data is a crucial process for constructing cell atlases, unraveling pathogenesis, and inspiring therapeutic approaches. Currently, the efficacy of existing methodologies is contingent upon specific data sets. Nevertheless, such data are often sourced from various batches, sequencing technologies, tissues, and even species. Notably, the gene regulatory relationship remains unaffected by the aforementioned factors, highlighting the extensive gene interactions within organisms. Therefore, we propose scHGR, an automated annotation tool designed to leverage gene regulatory relationships in constructing gene-mediated cell communication graphs for single-cell transcriptome data. This strategy helps reduce noise from diverse data sources while establishing distant cellular connections, yielding valuable biological insights. Experiments involving 22 scenarios demonstrate that scHGR precisely and consistently annotates cell identities, benchmarked against state-of-the-art methods. Crucially, scHGR uncovers novel subtypes within peripheral blood mononuclear cells, specifically from CD4+ T cells and cytotoxic T cells. Furthermore, by characterizing a cell atlas comprising 56 cell types for COVID-19 patients, scHGR identifies vital factors like IL1 and calcium ions, offering insights for targeted therapeutic interventions.

Structural basis of ketamine action on human NMDA receptors.

Ketamine is a non-competitive channel blocker of N-methyl-D-aspartate (NMDA) receptors1. A single sub-anaesthetic dose of ketamine produces rapid (within hours) and long-lasting antidepressant effects in patients who are resistant to other antidepressants2,3. Ketamine is a racemic mixture of S- and R-ketamine enantiomers, with S-ketamine isomer being the more active antidepressant4. Here we describe the cryo-electron microscope structures of human GluN1-GluN2A and GluN1-GluN2B NMDA receptors in complex with S-ketamine, glycine and glutamate. Both electron density maps uncovered the binding pocket for S-ketamine in the central vestibule between the channel gate and selectivity filter. Molecular dynamics simulation showed that S-ketamine moves between two distinct locations within the binding pocket. Two amino acids-leucine 642 on GluN2A (homologous to leucine 643 on GluN2B) and asparagine 616 on GluN1-were identified as key residues that form hydrophobic and hydrogen-bond interactions with ketamine, and mutations at these residues reduced the potency of ketamine in blocking NMDA receptor channel activity. These findings show structurally how ketamine binds to and acts on human NMDA receptors, and pave the way for the future development of ketamine-based antidepressants.

The high-quality genome of Cryptotaenia japonica and comparative genomics analysis reveals anthocyanin biosynthesis in Apiaceae.

Cryptotaenia japonica, a traditional medicinal and edible vegetable crops, is well-known for its attractive flavors and health care functions. As a member of the Apiaceae family, the evolutionary trajectory and biological properties of C. japonica are not clearly understood. Here, we first reported a high-quality genome of C. japonica with a total length of 427 Mb and N50 length 50.76 Mb, was anchored into 10 chromosomes, which confirmed by chromosome (cytogenetic) analysis. Comparative genomic analysis revealed C. japonica exhibited low genetic redundancy, contained a higher percentage of single-cope gene families. The homoeologous blocks, Ks, and collinearity were analyzed among Apiaceae species contributed to the evidence that C. japonica lacked recent species-specific WGD. Through comparative genomic and transcriptomic analyses of Apiaceae species, we revealed the genetic basis of the production of anthocyanins. Several structural genes encoding enzymes and transcription factor genes of the anthocyanin biosynthesis pathway in different species were also identified. The CjANSa, CjDFRb, and CjF3H gene might be the target of Cjaponica_2.2062 (bHLH) and Cjaponica_1.3743 (MYB). Our findings provided a high-quality reference genome of C. japonica and offered new insights into Apiaceae evolution and biology.

Palmitoylation of SARS-CoV-2 Envelope protein is central to virus particle formation.

The Envelope (E) protein of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is an integral structural protein in the virus particles. However, its role in the assembly of virions and the underlying molecular mechanisms are yet to be elucidated, including whether the function of E protein is regulated by post-translational modifications. In the present study, we report that SARS-CoV-2 E protein is palmitoylated at C40, C43, and C44 by palmitoyltransferases zDHHC3, 6, 12, 15, and 20. Mutating these three cysteines to serines (C40/43/44S) reduced the stability of E protein, decreased the interaction of E with structural proteins Spike, Membrane, and Nucleocapsid, and thereby inhibited the production of virus-like particles (VLPs) and VLP-mediated luciferase transcriptional delivery. Specifically, the C40/43/44S mutation of E protein reduced the density of VLPs. Collectively, these results demonstrate that palmitoylation of E protein is vital for its function in the assembly of SARS-CoV-2 particles.IMPORTANCEIn this study, we systematically examined the biochemistry of palmitoylation of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) E protein and demonstrated that palmitoylation of SARS-CoV-2 E protein is required for virus-like particle (VLP) production and maintaining normal particle density. These results suggest that palmitoylated E protein is central for proper morphogenesis of SARS-CoV-2 VLPs in densities required for viral infectivity. This study presents a significant advancement in the understanding of how palmitoylation of viral proteins is vital for assembling SARS-CoV-2 particles and supports that palmitoyl acyltransferases can be potential therapeutic targets for the development of SARS-CoV-2 inhibitors.

Improved structure-related prediction for insufficient homologous proteins using MSA enhancement and pre-trained language model.

In recent years, protein structure problems have become a hotspot for understanding protein folding and function mechanisms. It has been observed that most of the protein structure works rely on and benefit from co-evolutionary information obtained by multiple sequence alignment (MSA). As an example, AlphaFold2 (AF2) is a typical MSA-based protein structure tool which is famous for its high accuracy. As a consequence, these MSA-based methods are limited by the quality of the MSAs. Especially for orphan proteins that have no homologous sequence, AlphaFold2 performs unsatisfactorily as MSA depth decreases, which may pose a barrier to its widespread application in protein mutation and design problems in which there are no rich homologous sequences and rapid prediction is needed. In this paper, we constructed two standard datasets for orphan and de novo proteins which have insufficient/none homology information, called Orphan62 and Design204, respectively, to fairly evaluate the performance of the various methods in this case. Then, depending on whether or not utilizing scarce MSA information, we summarized two approaches, MSA-enhanced and MSA-free methods, to effectively solve the issue without sufficient MSAs. MSA-enhanced model aims to improve poor MSA quality from the data source by knowledge distillation and generation models. MSA-free model directly learns the relationship between residues on enormous protein sequences from pre-trained models, bypassing the step of extracting the residue pair representation from MSA. Next, we evaluated the performance of four MSA-free methods (trRosettaX-Single, TRFold, ESMFold and ProtT5) and MSA-enhanced (Bagging MSA) method compared with a traditional MSA-based method AlphaFold2, in two protein structure-related prediction tasks, respectively. Comparison analyses show that trRosettaX-Single and ESMFold which belong to MSA-free method can achieve fast prediction ($\sim\! 40$s) and comparable performance compared with AF2 in tertiary structure prediction, especially for short peptides, $\alpha $-helical segments and targets with few homologous sequences. Bagging MSA utilizing MSA enhancement improves the accuracy of our trained base model which is an MSA-based method when poor homology information exists in secondary structure prediction. Our study provides biologists an insight of how to select rapid and appropriate prediction tools for enzyme engineering and peptide drug development. CONTACT: guofei@csu.edu.cn, jj.tang@siat.ac.cn.

GraphLncLoc: long non-coding RNA subcellular localization prediction using graph convolutional networks based on sequence to graph transformation.

The subcellular localization of long non-coding RNAs (lncRNAs) is crucial for understanding lncRNA functions. Most of existing lncRNA subcellular localization prediction methods use k-mer frequency features to encode lncRNA sequences. However, k-mer frequency features lose sequence order information and fail to capture sequence patterns and motifs of different lengths. In this paper, we proposed GraphLncLoc, a graph convolutional network-based deep learning model, for predicting lncRNA subcellular localization. Unlike previous studies encoding lncRNA sequences by using k-mer frequency features, GraphLncLoc transforms lncRNA sequences into de Bruijn graphs, which transforms the sequence classification problem into a graph classification problem. To extract the high-level features from the de Bruijn graph, GraphLncLoc employs graph convolutional networks to learn latent representations. Then, the high-level feature vectors derived from de Bruijn graph are fed into a fully connected layer to perform the prediction task. Extensive experiments show that GraphLncLoc achieves better performance than traditional machine learning models and existing predictors. In addition, our analyses show that transforming sequences into graphs has more distinguishable features and is more robust than k-mer frequency features. The case study shows that GraphLncLoc can uncover important motifs for nucleus subcellular localization. GraphLncLoc web server is available at http://csuligroup.com:8000/GraphLncLoc/.

IK-DDI: a novel framework based on instance position embedding and key external text for DDI extraction.

Determining drug-drug interactions (DDIs) is an important part of pharmacovigilance and has a vital impact on public health. Compared with drug trials, obtaining DDI information from scientific articles is a faster and lower cost but still a highly credible approach. However, current DDI text extraction methods consider the instances generated from articles to be independent and ignore the potential connections between different instances in the same article or sentence. Effective use of external text data could improve prediction accuracy, but existing methods cannot extract key information from external data accurately and reasonably, resulting in low utilization of external data. In this study, we propose a DDI extraction framework, instance position embedding and key external text for DDI (IK-DDI), which adopts instance position embedding and key external text to extract DDI information. The proposed framework integrates the article-level and sentence-level position information of the instances into the model to strengthen the connections between instances generated from the same article or sentence. Moreover, we introduce a comprehensive similarity-matching method that uses string and word sense similarity to improve the matching accuracy between the target drug and external text. Furthermore, the key sentence search method is used to obtain key information from external data. Therefore, IK-DDI can make full use of the connection between instances and the information contained in external text data to improve the efficiency of DDI extraction. Experimental results show that IK-DDI outperforms existing methods on both macro-averaged and micro-averaged metrics, which suggests our method provides complete framework that can be used to extract relationships between biomedical entities and process external text data.

MVML-MPI: Multi-View Multi-Label Learning for Metabolic Pathway Inference.

Development of robust and effective strategies for synthesizing new compounds, drug targeting and constructing GEnome-scale Metabolic models (GEMs) requires a deep understanding of the underlying biological processes. A critical step in achieving this goal is accurately identifying the categories of pathways in which a compound participated. However, current machine learning-based methods often overlook the multifaceted nature of compounds, resulting in inaccurate pathway predictions. Therefore, we present a novel framework on Multi-View Multi-Label Learning for Metabolic Pathway Inference, hereby named MVML-MPI. First, MVML-MPI learns the distinct compound representations in parallel with corresponding compound encoders to fully extract features. Subsequently, we propose an attention-based mechanism that offers a fusion module to complement these multi-view representations. As a result, MVML-MPI accurately represents and effectively captures the complex relationship between compounds and metabolic pathways and distinguishes itself from current machine learning-based methods. In experiments conducted on the Kyoto Encyclopedia of Genes and Genomes pathways dataset, MVML-MPI outperformed state-of-the-art methods, demonstrating the superiority of MVML-MPI and its potential to utilize the field of metabolic pathway design, which can aid in optimizing drug-like compounds and facilitating the development of GEMs. The code and data underlying this article are freely available at https://github.com/guofei-tju/MVML-MPI. Contact:  jtang@cse.sc.edu, guofei@csu.edu.com or wuxi_dyj@csj.uestc.edu.cn.

RetroCaptioner: beyond attention in end-to-end retrosynthesis transformer via contrastively captioned learnable graph representation.

MOTIVATION: Retrosynthesis identifies available precursor molecules for various and novel compounds. With the advancements and practicality of language models, Transformer-based models have increasingly been used to automate this process. However, many existing methods struggle to efficiently capture reaction transformation information, limiting the accuracy and applicability of their predictions. RESULTS: We introduce RetroCaptioner, an advanced end-to-end, Transformer-based framework featuring a Contrastive Reaction Center Captioner. This captioner guides the training of dual-view attention models using a contrastive learning approach. It leverages learned molecular graph representations to capture chemically plausible constraints within a single-step learning process. We integrate the single-encoder, dual-encoder, and encoder-decoder paradigms to effectively fuse information from the sequence and graph representations of molecules. This involves modifying the Transformer encoder into a uni-view sequence encoder and a dual-view module. Furthermore, we enhance the captioning of atomic correspondence between SMILES and graphs. Our proposed method, RetroCaptioner, achieved outstanding performance with 67.2% in top-1 and 93.4% in top-10 exact matched accuracy on the USPTO-50k dataset, alongside an exceptional SMILES validity score of 99.4%. In addition, RetroCaptioner has demonstrated its reliability in generating synthetic routes for the drug protokylol. AVAILABILITY AND IMPLEMENTATION: The code and data are available at https://github.com/guofei-tju/RetroCaptioner.

MTMol-GPT: De novo multi-target molecular generation with transformer-based generative adversarial imitation learning.

De novo drug design is crucial in advancing drug discovery, which aims to generate new drugs with specific pharmacological properties. Recently, deep generative models have achieved inspiring progress in generating drug-like compounds. However, the models prioritize a single target drug generation for pharmacological intervention, neglecting the complicated inherent mechanisms of diseases, and influenced by multiple factors. Consequently, developing novel multi-target drugs that simultaneously target specific targets can enhance anti-tumor efficacy and address issues related to resistance mechanisms. To address this issue and inspired by Generative Pre-trained Transformers (GPT) models, we propose an upgraded GPT model with generative adversarial imitation learning for multi-target molecular generation called MTMol-GPT. The multi-target molecular generator employs a dual discriminator model using the Inverse Reinforcement Learning (IRL) method for a concurrently multi-target molecular generation. Extensive results show that MTMol-GPT generates various valid, novel, and effective multi-target molecules for various complex diseases, demonstrating robustness and generalization capability. In addition, molecular docking and pharmacophore mapping experiments demonstrate the drug-likeness properties and effectiveness of generated molecules potentially improve neuropsychiatric interventions. Furthermore, our model's generalizability is exemplified by a case study focusing on the multi-targeted drug design for breast cancer. As a broadly applicable solution for multiple targets, MTMol-GPT provides new insight into future directions to enhance potential complex disease therapeutics by generating high-quality multi-target molecules in drug discovery.

scRNMF: An imputation method for single-cell RNA-seq data by robust and non-negative matrix factorization.

Single-cell RNA sequencing (scRNA-seq) has emerged as a powerful tool in genomics research, enabling the analysis of gene expression at the individual cell level. However, scRNA-seq data often suffer from a high rate of dropouts, where certain genes fail to be detected in specific cells due to technical limitations. This missing data can introduce biases and hinder downstream analysis. To overcome this challenge, the development of effective imputation methods has become crucial in the field of scRNA-seq data analysis. Here, we propose an imputation method based on robust and non-negative matrix factorization (scRNMF). Instead of other matrix factorization algorithms, scRNMF integrates two loss functions: L2 loss and C-loss. The L2 loss function is highly sensitive to outliers, which can introduce substantial errors. We utilize the C-loss function when dealing with zero values in the raw data. The primary advantage of the C-loss function is that it imposes a smaller punishment for larger errors, which results in more robust factorization when handling outliers. Various datasets of different sizes and zero rates are used to evaluate the performance of scRNMF against other state-of-the-art methods. Our method demonstrates its power and stability as a tool for imputation of scRNA-seq data.

MOV10 recruits DCP2 to decap human LINE-1 RNA by forming large cytoplasmic granules with phase separation properties.

Long interspersed element 1 (LINE-1) is the only active autonomous mobile element in the human genome. Its transposition can exert deleterious effects on the structure and function of the host genome and cause sporadic genetic diseases. Tight control of LINE-1 mobilization by the host is crucial for genetic stability. In this study, we report that MOV10 recruits the main decapping enzyme DCP2 to LINE-1 RNA and forms a complex of MOV10, DCP2, and LINE-1 RNP, exhibiting liquid-liquid phase separation (LLPS) properties. DCP2 cooperates with MOV10 to decap LINE-1 RNA, which causes degradation of LINE-1 RNA and thus reduces LINE-1 retrotransposition. We here identify DCP2 as one of the key effector proteins determining LINE-1 replication, and elucidate an LLPS mechanism that facilitates the anti-LINE-1 action of MOV10 and DCP2.

MxB inhibits long interspersed element type 1 retrotransposition.

Long interspersed element type 1 (LINE-1, also L1 for short) is the only autonomously transposable element in the human genome. Its insertion into a new genomic site may disrupt the function of genes, potentially causing genetic diseases. Cells have thus evolved a battery of mechanisms to tightly control LINE-1 activity. Here, we report that a cellular antiviral protein, myxovirus resistance protein B (MxB), restricts the mobilization of LINE-1. This function of MxB requires the nuclear localization signal located at its N-terminus, its GTPase activity and its ability to form oligomers. We further found that MxB associates with LINE-1 protein ORF1p and promotes sequestration of ORF1p to G3BP1-containing cytoplasmic granules. Since knockdown of stress granule marker proteins G3BP1 or TIA1 abolishes MxB inhibition of LINE-1, we conclude that MxB engages stress granule components to effectively sequester LINE-1 proteins within the cytoplasmic granules, thus hindering LINE-1 from accessing the nucleus to complete retrotransposition. Thus, MxB protein provides one mechanism for cells to control the mobility of retroelements.

Polycystic Ovary Syndrome Fuels Cardiovascular Inflammation and Aggravates Ischemic Cardiac Injury.

BACKGROUND: Reducing cardiovascular disease burden among women remains challenging. Epidemiologic studies have indicated that polycystic ovary syndrome (PCOS), the most common endocrine disease in women of reproductive age, is associated with an increased prevalence and extent of coronary artery disease. However, the mechanism through which PCOS affects cardiac health in women remains unclear. METHODS: Prenatal anti-Müllerian hormone treatment or peripubertal letrozole infusion was used to establish mouse models of PCOS. RNA sequencing was performed to determine global transcriptomic changes in the hearts of PCOS mice. Flow cytometry and immunofluorescence staining were performed to detect myocardial macrophage accumulation in multiple PCOS models. Parabiosis models, cell-tracking experiments, and in vivo gene silencing approaches were used to explore the mechanisms underlying increased macrophage infiltration in PCOS mouse hearts. Permanent coronary ligation was performed to establish myocardial infarction (MI). Histologic analysis and small-animal imaging modalities (eg, magnetic resonance imaging and echocardiography) were performed to evaluate the effects of PCOS on injury after MI. Women with PCOS and control participants (n=200) were recruited to confirm findings observed in animal models. RESULTS: Transcriptomic profiling and immunostaining revealed that hearts from PCOS mice were characterized by increased macrophage accumulation. Parabiosis studies revealed that monocyte-derived macrophages were significantly increased in the hearts of PCOS mice because of enhanced circulating Ly6C+ monocyte supply. Compared with control mice, PCOS mice showed a significant increase in splenic Ly6C+ monocyte output, associated with elevated hematopoietic progenitors in the spleen and sympathetic tone. Plasma norepinephrine (a sympathetic neurotransmitter) levels and spleen size were consistently increased in women with PCOS when compared with those in control participants, and norepinephrine levels were significantly correlated with circulating CD14++CD16- monocyte counts. Compared with animals without PCOS, PCOS animals showed significantly exacerbated atherosclerotic plaque development and post-MI cardiac remodeling. Conditional Vcam1 silencing in PCOS mice significantly suppressed cardiac inflammation and improved cardiac injury after MI. CONCLUSIONS: Our data documented previously unrecognized mechanisms through which PCOS could affect cardiovascular health in women. PCOS may promote myocardial macrophage accumulation and post-MI cardiac remodeling because of augmented splenic myelopoiesis.

Residual Immunity from Smallpox Vaccination and Possible Protection from Mpox, China.

Among persons born in China before 1980 and tested for vaccinia virus Tiantan strain (VVT), 28.7% (137/478) had neutralizing antibodies, 71.4% (25/35) had memory B-cell responses, and 65.7% (23/35) had memory T-cell responses to VVT. Because of cross-immunity between the viruses, these findings can help guide mpox vaccination strategies in China.

Causal associations of immune cell phenotypes with migraine: A mendelian randomization study.

The interaction between the immune system and the brain, crucial for blood-brain barrier integrity, is a potential factor in migraine development. Although there's evidence of a connection between immune dysregulation and migraine, a clear causal link has been lacking. To bridge this knowledge gap, we performed a two-sample Mendelian randomization (MR) analysis of 731 immune cell phenotypes to determine their causality with migraine, of which parameters included fluorescence, cell abundance, count, and morphology. Sensitivity and pleiotropy checks validated our findings. After applying a false discovery rate correction, our MR study identified 35 of 731 immune phenotypes with a significant causal link to migraine (p < 0.05). Of these, 24 showed a protective effect (inverse variance weighting : p < 0.05, odds ratio <1), and 11 were risk factors (inverse variance weighting : p < 0.05, odds ratio >1). Although limited by population sample size and potential population-specific genetic variations, our study uncovers a significant genetic link between certain immune cell markers and migraine, providing new insights into the disorder's pathophysiology. These discoveries are crucial for developing targeted biomarkers and personalized treatments. The research enhances our understanding of immune cells' role in migraine and may substantially improve patient outcomes and lessen its socio-economic impact.

Directed Dual Charge Pumping Tunes the d-Orbital Configuration of Pt Cluster Boosting Hydrogen Evolution Kinetic.

Achieving high catalytic activity with a minimum amount of platinum (Pt) is crucial for accelerating the cathodic hydrogen evolution reaction (HER) in proton exchange membrane (PEM) water electrolysis, yet it remains a significant challenge. Herein, a directed dual-charge pumping strategy to tune the d-orbital electronic distribution of Pt nanoclusters for efficient HER catalysis is proposed. Theoretical analysis reveals that the ligand effect and electronic metal-support interactions (EMSI) create an effective directional electron transfer channel for the d-orbital electrons of Pt, which in turn optimizes the binding strength to H*, thereby significantly enhancing HER efficiency of the Pt site. Experimentally, this directed dual-charge pumping strategy is validated by elaborating Sb-doped SnO2 (ATO) supported Fe-doped PtSn heterostructure catalysts (Fe-PtSn/ATO). The synthesized 3%Fe-PtSn/ATO catalysts exhibit lower overpotential (requiring only 10.5 mV to reach a current density of 10 mA cm- 2), higher mass activity (28.6 times higher than commercial 20 wt.% Pt/C), and stability in the HER process in acidic media. This innovative strategy presents a promising pathway for the development of highly efficient HER catalysts with low Pt loading.

Strain Effects in Ru-Au Bimetallic Aerogels Boost Electrocatalytic Hydrogen Evolution.

To improve the sluggish kinetics of the hydrogen evolution reaction (HER), a key component in water-splitting applications, there is an urgent desire to develop efficient, cost-effective, and stable electrocatalysts. Strain engineering is proving an efficient strategy for increasing the catalytic activity of electrocatalysts. This work presents the development of Ru-Au bimetallic aerogels by a simple one-step in situ reduction-gelation approach, which exhibits strain effects and electron transfer to create a remarkable HER activity and stability in an alkaline environment. The surface strain induced by the bimetallic segregated structure shifts the d-band center downward, enhancing catalysis by balancing the processes of water dissociation, OH* adsorption, and H* adsorption. Specifically, the optimized catalyst shows low overpotentials of only 24.1 mV at a current density of 10 mA cm-2 in alkaline electrolytes, surpassing commercial Pt/C. This study can contribute to the understanding of strain engineering in bimetallic electrocatalysts for HER at the atomic scale.

Identification of drug-side effect association via restricted Boltzmann machines with penalized term.

In the entire life cycle of drug development, the side effect is one of the major failure factors. Severe side effects of drugs that go undetected until the post-marketing stage leads to around two million patient morbidities every year in the United States. Therefore, there is an urgent need for a method to predict side effects of approved drugs and new drugs. Following this need, we present a new predictor for finding side effects of drugs. Firstly, multiple similarity matrices are constructed based on the association profile feature and drug chemical structure information. Secondly, these similarity matrices are integrated by Centered Kernel Alignment-based Multiple Kernel Learning algorithm. Then, Weighted K nearest known neighbors is utilized to complement the adjacency matrix. Next, we construct Restricted Boltzmann machines (RBM) in drug space and side effect space, respectively, and apply a penalized maximum likelihood approach to train model. At last, the average decision rule was adopted to integrate predictions from RBMs. Comparison results and case studies demonstrate, with four benchmark datasets, that our method can give a more accurate and reliable prediction result.