Revolutionizing GPCR-ligand predictions: DeepGPCR with experimental validation for high-precision drug discovery.

G-protein coupled receptors (GPCRs), crucial in various diseases, are targeted of over 40% of approved drugs. However, the reliable acquisition of experimental GPCRs structures is hindered by their lipid-embedded conformations. Traditional protein-ligand interaction models falter in GPCR-drug interactions, caused by limited and low-quality structures. Generalized models, trained on soluble protein-ligand pairs, are also inadequate. To address these issues, we developed two models, DeepGPCR_BC for binary classification and DeepGPCR_RG for affinity prediction. These models use non-structural GPCR-ligand interaction data, leveraging graph convolutional networks and mol2vec techniques to represent binding pockets and ligands as graphs. This approach significantly speeds up predictions while preserving critical physical-chemical and spatial information. In independent tests, DeepGPCR_BC surpassed Autodock Vina and Schrödinger Dock with an area under the curve of 0.72, accuracy of 0.68 and true positive rate of 0.73, whereas DeepGPCR_RG demonstrated a Pearson correlation of 0.39 and root mean squared error of 1.34. We applied these models to screen drug candidates for GPR35 (Q9HC97), yielding promising results with three (F545-1970, K297-0698, S948-0241) out of eight candidates. Furthermore, we also successfully obtained six active inhibitors for GLP-1R. Our GPCR-specific models pave the way for efficient and accurate large-scale virtual screening, potentially revolutionizing drug discovery in the GPCR field.

A deep learning based multi-model approach for predicting drug-like chemical compound's toxicity.

Ensuring the safety and efficacy of chemical compounds is crucial in small-molecule drug development. In the later stages of drug development, toxic compounds pose a significant challenge, losing valuable resources and time. Early and accurate prediction of compound toxicity using deep learning models offers a promising solution to mitigate these risks during drug discovery. In this study, we present the development of several deep-learning models aimed at evaluating different types of compound toxicity, including acute toxicity, carcinogenicity, hERG_cardiotoxicity (the human ether-a-go-go related gene caused cardiotoxicity), hepatotoxicity, and mutagenicity. To address the inherent variations in data size, label type, and distribution across different types of toxicity, we employed diverse training strategies. Our first approach involved utilizing a graph convolutional network (GCN) regression model to predict acute toxicity, which achieved notable performance with Pearson R 0.76, 0.74, and 0.65 for intraperitoneal, intravenous, and oral administration routes, respectively. Furthermore, we trained multiple GCN binary classification models, each tailored to a specific type of toxicity. These models exhibited high area under the curve (AUC) scores, with an impressive AUC of 0.69, 0.77, 0.88, and 0.79 for predicting carcinogenicity, hERG_cardiotoxicity, mutagenicity, and hepatotoxicity, respectively. Additionally, we have used the approved drug dataset to determine the appropriate threshold value for the prediction score in model usage. We integrated these models into a virtual screening pipeline to assess their effectiveness in identifying potential low-toxicity drug candidates. Our findings indicate that this deep learning approach has the potential to significantly reduce the cost and risk associated with drug development by expediting the selection of compounds with low toxicity profiles. Therefore, the models developed in this study hold promise as critical tools for early drug candidate screening and selection.

Generating and screening de novo compounds against given targets using ultrafast deep learning models as core components.

Deep learning is an artificial intelligence technique in which models express geometric transformations over multiple levels. This method has shown great promise in various fields, including drug development. The availability of public structure databases prompted the researchers to use generative artificial intelligence models to narrow down their search of the chemical space, a novel approach to chemogenomics and de novo drug development. In this study, we developed a strategy that combined an accelerated LSTM_Chem (long short-term memory for de novo compounds generation), dense fully convolutional neural network (DFCNN), and docking to generate a large number of de novo small molecular chemical compounds for given targets. To demonstrate its efficacy and applicability, six important targets that account for various human disorders were used as test examples. Moreover, using the M protease as a proof-of-concept example, we find that iteratively training with previously selected candidates can significantly increase the chance of obtaining novel compounds with higher and higher predicted binding affinities. In addition, we also check the potential benefit of obtaining reliable final de novo compounds with the help of MD simulation and metadynamics simulation. The generation of de novo compounds and the discovery of binders against various targets proposed here would be a practical and effective approach. Assessing the efficacy of these top de novo compounds with biochemical studies is promising to promote related drug development.

Deep Learning-Based Bioactive Therapeutic Peptide Generation and Screening.

Many bioactive peptides demonstrated therapeutic effects over complicated diseases, such as antiviral, antibacterial, anticancer, etc. It is possible to generate a large number of potentially bioactive peptides using deep learning in a manner analogous to the generation of de novo chemical compounds using the acquired bioactive peptides as a training set. Such generative techniques would be significant for drug development since peptides are much easier and cheaper to synthesize than compounds. Despite the limited availability of deep learning-based peptide-generating models, we have built an LSTM model (called LSTM_Pep) to generate de novo peptides and fine-tuned the model to generate de novo peptides with specific prospective therapeutic benefits. Remarkably, the Antimicrobial Peptide Database has been effectively utilized to generate various kinds of potential active de novo peptides. We proposed a pipeline for screening those generated peptides for a given target and used the main protease of SARS-COV-2 as a proof-of-concept. Moreover, we have developed a deep learning-based protein-peptide prediction model (DeepPep) for rapid screening of the generated peptides for the given targets. Together with the generating model, we have demonstrated that iteratively fine-tuning training, generating, and screening peptides for higher-predicted binding affinity peptides can be achieved. Our work sheds light on developing deep learning-based methods and pipelines to effectively generate and obtain bioactive peptides with a specific therapeutic effect and showcases how artificial intelligence can help discover de novo bioactive peptides that can bind to a particular target.

DeepBindBC: A practical deep learning method for identifying native-like protein-ligand complexes in virtual screening.

Identifying native-like protein-ligand complexes (PLCs) from an abundance of docking decoys is critical for large-scale virtual drug screening in early-stage drug discovery lead searching efforts. Providing reliable prediction is still a challenge for most current affinity predicting models because of a lack of non-binding data during model training, lost critical physical-chemical features, and difficulties in learning abstract information with limited neural layers. In this work, we proposed a deep learning model, DeepBindBC, for classifying putative ligands as binding or non-binding. Our model incorporates information on non-binding interactions, making it more suitable for real applications. ResNet model architecture and more detailed atom type representation guarantee implicit features can be learned more accurately. Here, we show that DeepBindBC outperforms Autodock Vina, Pafnucy, and DLSCORE for three DUD.E testing sets. Moreover, DeepBindBC identified a novel human pancreatic α-amylase binder validated by a fluorescence spectral experiment (Ka = 1.0 × 105 M). Furthermore, DeepBindBC can be used as a core component of a hybrid virtual screening pipeline that incorporating many other complementary methods, such as DFCNN, Autodock Vina docking, and pocket molecular dynamics simulation. Additionally, an online web server based on the model is available at http://cbblab.siat.ac.cn/DeepBindBC/index.php for the user's convenience. Our model and the web server provide alternative tools in the early steps of drug discovery by providing accurate identification of native-like PLCs.

DeepBindGCN: Integrating Molecular Vector Representation with Graph Convolutional Neural Networks for Protein-Ligand Interaction Prediction.

The core of large-scale drug virtual screening is to select the binders accurately and efficiently with high affinity from large libraries of small molecules in which non-binders are usually dominant. The binding affinity is significantly influenced by the protein pocket, ligand spatial information, and residue types/atom types. Here, we used the pocket residues or ligand atoms as the nodes and constructed edges with the neighboring information to comprehensively represent the protein pocket or ligand information. Moreover, the model with pre-trained molecular vectors performed better than the one-hot representation. The main advantage of DeepBindGCN is that it is independent of docking conformation, and concisely keeps the spatial information and physical-chemical features. Using TIPE3 and PD-L1 dimer as proof-of-concept examples, we proposed a screening pipeline integrating DeepBindGCN and other methods to identify strong-binding-affinity compounds. It is the first time a non-complex-dependent model has achieved a root mean square error (RMSE) value of 1.4190 and Pearson r value of 0.7584 in the PDBbind v.2016 core set, respectively, thereby showing a comparable prediction power with the state-of-the-art affinity prediction models that rely upon the 3D complex. DeepBindGCN provides a powerful tool to predict the protein-ligand interaction and can be used in many important large-scale virtual screening application scenarios.

Evaluation of residue-residue contact prediction methods: From retrospective to prospective.

Sequence-based residue contact prediction plays a crucial role in protein structure reconstruction. In recent years, the combination of evolutionary coupling analysis (ECA) and deep learning (DL) techniques has made tremendous progress for residue contact prediction, thus a comprehensive assessment of current methods based on a large-scale benchmark data set is very needed. In this study, we evaluate 18 contact predictors on 610 non-redundant proteins and 32 CASP13 targets according to a wide range of perspectives. The results show that different methods have different application scenarios: (1) DL methods based on multi-categories of inputs and large training sets are the best choices for low-contact-density proteins such as the intrinsically disordered ones and proteins with shallow multi-sequence alignments (MSAs). (2) With at least 5L (L is sequence length) effective sequences in the MSA, all the methods show the best performance, and methods that rely only on MSA as input can reach comparable achievements as methods that adopt multi-source inputs. (3) For top L/5 and L/2 predictions, DL methods can predict more hydrophobic interactions while ECA methods predict more salt bridges and disulfide bonds. (4) ECA methods can detect more secondary structure interactions, while DL methods can accurately excavate more contact patterns and prune isolated false positives. In general, multi-input DL methods with large training sets dominate current approaches with the best overall performance. Despite the great success of current DL methods must be stated the fact that there is still much room left for further improvement: (1) With shallow MSAs, the performance will be greatly affected. (2) Current methods show lower precisions for inter-domain compared with intra-domain contact predictions, as well as very high imbalances in precisions between intra-domains. (3) Strong prediction similarities between DL methods indicating more feature types and diversified models need to be developed. (4) The runtime of most methods can be further optimized.

A novel virtual screening procedure identifies Pralatrexate as inhibitor of SARS-CoV-2 RdRp and it reduces viral replication in vitro.

The spread of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus poses serious threats to the global public health and leads to worldwide crisis. No effective drug or vaccine is readily available. The viral RNA-dependent RNA polymerase (RdRp) is a promising therapeutic target. A hybrid drug screening procedure was proposed and applied to identify potential drug candidates targeting RdRp from 1906 approved drugs. Among the four selected market available drug candidates, Pralatrexate and Azithromycin were confirmed to effectively inhibit SARS-CoV-2 replication in vitro with EC50 values of 0.008µM and 9.453 µM, respectively. For the first time, our study discovered that Pralatrexate is able to potently inhibit SARS-CoV-2 replication with a stronger inhibitory activity than Remdesivir within the same experimental conditions. The paper demonstrates the feasibility of fast and accurate anti-viral drug screening for inhibitors of SARS-CoV-2 and provides potential therapeutic agents against COVID-19.

A novel machine learning based approach for iPS progenitor cell identification.

Identification of induced pluripotent stem (iPS) progenitor cells, the iPS forming cells in early stage of reprogramming, could provide valuable information for studying the origin and underlying mechanism of iPS cells. However, it is very difficult to identify experimentally since there are no biomarkers known for early progenitor cells, and only about 6 days after reprogramming initiation, iPS cells can be experimentally determined via fluorescent probes. What is more, the ratio of progenitor cells during early reprograming period is below 5%, which is too low to capture experimentally in the early stage. In this paper, we propose a novel computational approach for the identification of iPS progenitor cells based on machine learning and microscopic image analysis. Firstly, we record the reprogramming process using a live cell imaging system after 48 hours of infection with retroviruses expressing Oct4, Sox2 and Klf4, later iPS progenitor cells and normal murine embryonic fibroblasts (MEFs) within 3 to 5 days after infection are labeled by retrospectively tracing the time-lapse microscopic image. We then calculate 11 types of cell morphological and motion features such as area, speed, etc., and select best time windows for modeling and perform feature selection. Finally, a prediction model using XGBoost is built based on the selected six types of features and best time windows. Our model allows several missing values/frames in the sample datasets, thus it is applicable to a wide range of scenarios. Cross-validation, holdout validation and independent test experiments show that the minimum precision is above 52%, that is, the ratio of predicted progenitor cells within 3 to 5 days after viral infection is above 52%. The results also confirm that the morphology and motion pattern of iPS progenitor cells is different from that of normal MEFs, which helps with the machine learning methods for iPS progenitor cell identification.

Sequence and structural analysis of fibronectin-binding protein reveals importance of multiple intrinsic disordered tandem repeats.

The location of certain amino acid sequences like repeats along the polypeptide chain is very important in the context of forming the overall shape of the protein molecule which in fact determines its function. In gram-positive bacteria, fibronectin-binding protein (FnBP) is one such repeat containing protein, and it is a cell wall-attached protein responsible for various acute infections in human. Several studies on sequence, structure, and function of fibronectin-binding regions of FnBPs were reported; however, no detailed study was carried out on the full-length protein sequence. In the present study, we have made a thorough sequence and structure analysis on FnBP_A of Staphylococcus aureus and explored the presence of dual ligand-binding ability of fibrinogen (fg)-binding region and its molecular recognition processes. Multiple sequence alignment and protein-protein docking analysis reveal the regions which are likely involved in dual ligand binding. Further analysis of docking of FnBP_A fg-binding region and fn N-terminal modules suggests that if the latter binds to the fg-binding region of FnBP_A, it would inhibit the subsequent binding of fg because of steric hindrance. The sequence analysis further suggests that the abundance of disorder promoting residue glutamic acid and dual personality (both order/disorder promoting) residue threonine in tandem repeats of FnBP_A and B proteins possibly would help the molecule to undergo a conformational change while binding with fn by ß-zipper mechanism. The segment-based power spectral analysis was carried out which helps to understand the distribution of hydrophobic residues along the sequence particularly in intrinsic disordered tandem repeats. The results presented here will help to understand the role of internal repeats and intrinsic disorder in the molecular recognition process of a pathogenic cell surface protein.

Dihedral angle preferences of amino acid residues forming various non-local interactions in proteins.

In theory, a polypeptide chain can adopt a vast number of conformations, each corresponding to a set of backbone rotation angles. Many of these conformations are excluded due to steric overlaps. Ramachandran and coworkers were the first to look into this problem by plotting backbone dihedral angles in a two-dimensional plot. The conformational space in the Ramachandran map is further refined by considering the energetic contributions of various non-bonded interactions. Alternatively, the conformation adopted by a polypeptide chain may also be examined by investigating interactions between the residues. Since the Ramachandran map essentially focuses on local interactions (residues closer in sequence), out of interest, we have analyzed the dihedral angle preferences of residues that make non-local interactions (residues far away in sequence and closer in space) in the folded structures of proteins. The non-local interactions have been grouped into different types such as hydrogen bond, van der Waals interactions between hydrophobic groups, ion pairs (salt bridges), and ππ-stacking interactions. The results show the propensity of amino acid residues in proteins forming local and non-local interactions. Our results point to the vital role of different types of non-local interactions and their effect on dihedral angles in forming secondary and tertiary structural elements to adopt their native fold.

Preliminary phytochemical screening, Antibacterial potential and GC-MS analysis of two medicinal plant extracts.

The presence study was aimed to catalyze the primary metabolites and their confirmation by using GC-MS analysis and antibacterial potential of leaf extract of two important medicinal plant viz., Eucalyptus and Azadirachta indica. The antibacterial potential of the methanol leaf extract of the studied species was tested against Escherichia coli, Pseudomonas aeruginosa, Klebsiellap neumoniae, Streptococcus pyogens, Staphylococcus aureus using by agar well diffusion method. The higher zone of inhibition (16mm) was observed against the bacterium Pseudomonas aeruginosa at 100µl concentration of methanol leaf extract. Preliminary phytochemical analysis of studied species shows that presence of phytochemical compounds like steroids, phenolic compounds and flavonoids. GC-MS analysis confirms the occurrence of 20 different compounds in the methanol leaf extract of the both studied species.

Hexadecanoic acid analogs as potential CviR-mediated quorum sensing inhibitors in Chromobacterium violaceum: an in silico study.

Chromobacterium violaceum is a Gram-negative, rod-shaped and opportunistic human pathogen. C. violaceum is resistant to various antibiotics due to the production of quorum sensing (QS)-controlled virulence factor and biofilm formation. Hence, we need to find alternative strategies to overcome the antimicrobial resistance and biofilm formation in Gram-negative bacteria. QS is a mechanism in which bacteria's ability to regulate the virulence factors and biofilm formations leads to disease progression. Previously, hexadecanoic acid was identified as a CviR-mediated quorum-sensing inhibitor. In this study, we aimed to discover potential analogs of hexadecanoic acid as a CviR-mediated quorum-sensing inhibitor against C. violaceum by using ADME/T prediction, density functional theory, molecular docking, molecular dynamics and free energy binding calculations. ADME/T properties predicted for analogs were acceptable for human oral absorption and feasibility. The highest occupied molecular orbitals and lowest unoccupied molecular orbitals gap energies predicted and found oleic acid with -0.3748 energies. Docosatrienoic acid exhibited the highest binding affinity -8.15 Kcal/mol and strong and stable interactions with the amino acid residues on the active site of the CviR protein. These compounds on MD simulations for 100 ns show strong hydrogen-bonding interactions with the protein and remain stable inside the active site. Our results suggest hexadecanoic acid analogs could serve as anti-QS and anti-biofilm molecules for treating C. violaceum infections. However, further validation and investigation of these inhibitors against CviR are needed to claim their candidacy for clinical trials.Communicated by Ramaswamy H. Sarma.

Importance of Inter-residue Contacts for Understanding Protein Folding and Unfolding Rates, Remote Homology, and Drug Design.

Inter-residue interactions in protein structures provide valuable insights into protein folding and stability. Understanding these interactions can be helpful in many crucial applications, including rational design of therapeutic small molecules and biologics, locating functional protein sites, and predicting protein-protein and protein-ligand interactions. The process of developing machine learning models incorporating inter-residue interactions has been improved recently. This review highlights the theoretical models incorporating inter-residue interactions in predicting folding and unfolding rates of proteins. Utilizing contact maps to depict inter-residue interactions aids researchers in developing computer models for detecting remote homologs and interface residues within protein-protein complexes which, in turn, enhances our knowledge of the relationship between sequence and structure of proteins. Further, the application of contact maps derived from inter-residue interactions is highlighted in the field of drug discovery. Overall, this review presents an extensive assessment of the significant models that use inter-residue interactions to investigate folding rates, unfolding rates, remote homology, and drug development, providing potential future advancements in constructing efficient computational models in structural biology.

Bibliometric analysis of artificial intelligence in healthcare research: Trends and future directions.

Objective: The presence of artificial intelligence (AI) in healthcare is a powerful and game-changing force that is completely transforming the industry as a whole. Using sophisticated algorithms and data analytics, AI has unparalleled prospects for improving patient care, streamlining operational efficiency, and fostering innovation across the healthcare ecosystem. This study conducts a comprehensive bibliometric analysis of research on AI in healthcare, utilising the SCOPUS database as the primary data source. Methods: Preliminary findings from 2013 identified 153 publications on AI and healthcare. Between 2019 and 2023, the number of publications increased exponentially, indicating significant growth and development in the field. The analysis employs various bibliometric indicators to assess research production performance, science mapping techniques, and thematic mapping analysis. Results: The study reveals insights into research hotspots, thematic focus, and emerging trends in AI and healthcare research. Based on an extensive examination of the Scopus database provides a brief overview and suggests potential avenues for further investigation. Conclusion: This article provides valuable contributions to understanding the current landscape of AI in healthcare, offering insights for future research directions and informing strategic decision making in the field.

Waking Up the Sleep Field: An Overview on the Implications of Genetics and Bioinformatics of Sleep.

Sleep genetics is an intriguing, as yet less understood, understudied, emerging area of biological and medical discipline. A generalist may not be aware of the current status of the field given the variety of journals that have published studies on the genetics of sleep and the circadian clock over the years. For researchers venturing into this fascinating area, this review thus includes fundamental features of circadian rhythm and genetic variables impacting sleep-wake cycles. Sleep/wake pathway medication exposure and susceptibility are influenced by genetic variations, and the responsiveness of sleep-related medicines is influenced by several functional polymorphisms. This review highlights the features of the circadian timing system and then a genetic perspective on wakefulness and sleep, as well as the relationship between sleep genetics and sleep disorders. Neurotransmission genes, as well as circadian and sleep/wake receptors, exhibit functional variability. Experiments on animals and humans have shown that these genetic variants impact clock systems, signaling pathways, nature, amount, duration, type, intensity, quality, and quantity of sleep. In this regard, the overview covers research on sleep genetics, the genomic properties of several popular model species used in sleep studies, homologs of mammalian genes, sleep disorders, and related genes. In addition, the study includes a brief discussion of sleep, narcolepsy, and restless legs syndrome from the viewpoint of a model organism. It is suggested that the understanding of genetic clues on sleep function and sleep disorders may, in future, result in an evidence-based, personalized treatment of sleep disorders.

Carbon nanoparticles fabricated microfilm: A potent filter for microplastics debased water.

Microplastics were found to be the major pollutant across the globe. Plastic microbeads, like 0.5 mm, are very small and mainly used for exfoliation. The marine species cannot distinguish between their usual food and these microbeads. Microbeads have the potential to transfer up the food chain, which may lead to consumption by humans in the end. Activated carbon from inexpensive sources has greatly interested separation systems, especially in water treatment. In that view, carbon nanoparticles were produced, combined with polyvinylidene fluoride (PVDF) polymer, and used as a membrane to trap the microplastic particles. UV-Vis, FTIR, TEM, and powder X-ray diffraction (XRD) analysis confirmed the produced carbon nanoparticles. FT-RAMAN Spectroscopy studies, microbial viable cell count, and turbidity analysis followed the membrane preparation and post-treatment. The carbon nanoparticle fabricated nanofilm effectively eliminates the microbial count and microplastics and reduces the turbidity (0.13 NTU). This study confirms that the membrane effectively filters microplastics and other contaminants. Nowadays, nanofiltration technologies have been considered beneficial for eliminating microplastics to an efficiency of 95%. Further research is needed to determine a feasible low-cost, ecologically suitable, and effective solution to remove the microplastics in water.

Methanodibenzo[b,f][1,5]dioxocins as Novel Glutaminase Inhibitor with Anti-Glioblastoma Potential.

Glutamine metabolism is an important hallmark of several cancers with demonstrated antitumor activity in glioblastoma cancer cells (GBM). GBM cells regulate glutamine and use it as a major energy source for their proliferation through the glutaminolysis process. Enzymes, such as glutaminase in glutaminolysis, can be targeted by small-molecule inhibitors, thus exhibiting promising anticancer properties. The resistance to glutaminolysis demands the development of new therapeutic molecules to overcome drug resistance. Herein, we have reported a novel library of constrained methanodibenzo[b,f][1,5]dioxocin derivatives as glutaminase (GLS) inhibitors and their anti-GBM potential. The library consisting of seven molecules was obtained through self-condensation of 2'-hydroxyacetophenones, out of which three molecules, namely compounds 3, 5, and 6, were identified with higher binding energy values ranging between -10.2 and -9.8 kcal/mol with GLS (PDB ID; 4O7D). Pharmacological validation of these compounds also showed a higher growth inhibition effect in GBM cells than the standard drug temozolomide (TMZ). The most promising compound, 6, obeyed Lipinski's rule of five and was identified to interact with key residues Arg307, Asp326, Lys328, Lys399, and Glu403 of GLS. This compound exhibited the best cytotoxic effect with IC50 values of 63 µM and 83 µM in LN229 and SNB19 cells, respectively. The potential activation of GLS by the best-constrained dibenzo[b,f][1,5]dioxocin in the tested series increased apoptosis via reactive oxygen species production in both GBM cells, and exhibited anti-migratory and anti-proliferative properties over time in both cell lines. Our results highlight the activation mechanism of a dibenzo[b,f][1,5]dioxocin from the structural basis and demonstrate that inhibition of glutaminolysis may facilitate the pharmacological intervention for GBM treatment.

Harbingers of Hope: Scientists and the Pursuit of World Peace.

The ongoing wars in many regions-such as the conflict between Israel and Hamas-as well as the effects of war on communities, social services, and mental health are covered in this special editorial. This article emphasizes the need for international efforts to promote peace, offer humanitarian aid, and address the mental health challenges faced by individuals and communities affected by war and violence.