Compound-protein Interactions Research Articles

CKG-IMC: An inductive matrix completion method enhanced by CKG and GNN for Alzheimer’s disease compound-protein interactions prediction

Alzheimer’s disease (AD) is one of the most prevalent chronic neurodegenerative disorders globally, with a rapidly growing population of AD patients and currently no effective therapeutic interventions available. Consequently, the development of therapeutic anti-AD drugs and the identification of AD targets represent one of the most urgent tasks. In this study, in addition to considering known drugs and targets, we explore compound-protein interactions (CPIs) between compounds and proteins relevant to AD. We propose a deep learning model called CKG-IMC to predict Alzheimer’s disease compound-protein interaction relationships. CKG-IMC comprises three modules: a collaborative knowledge graph (CKG), a principal neighborhood aggregation graph neural network (PNA), and an inductive matrix completion (IMC). The collaborative knowledge graph is used to learn semantic associations between entities, PNA is employed to extract structural features of the relationship network, and IMC is utilized for CPIs prediction. Compared with a total of 16 baseline models based on similarities, knowledge graphs, and graph neural networks, our model achieves state-of-the-art performance in experiments of 10-fold cross-validation and independent test. Furthermore, we use CKG-IMC to predict compounds interacting with two confirmed AD targets, 42-amino-acid β-amyloid (Aβ42) protein and microtubule-associated protein tau (tau protein), as well as proteins interacting with five FDA-approved anti-AD drugs. The results indicate that the majority of predictions are supported by literature, and molecular docking experiments demonstrate a strong affinity between the predicted compounds and targets.

Comprehensive analysis of different solvent extracts of Ferula communis L. fruit reveals phenolic compounds and their biological properties via in vitro and in silico assays

Although giant fennel is recognized as a “superfood” rich in phytochemicals with antioxidant activity, research into the antibacterial properties of its fruits has been relatively limited, compared to studies involving the root and aerial parts of the plant. In this study, seven solvents—acetone, methanol, ethanol, ethyl acetate, chloroform, water, and hexane—were used to extract the chemical constituents of the fruit of giant fennel (Ferula communis), a species of flowering plant in the carrot family Apiaceae. Specific attributes of these extracts were investigated using in silico simulations and in vitro bioassays. High-performance liquid chromatography equipped with a diode-array detector (HPLC–DAD) identified 15 compounds in giant fennel extract, with p-coumaric acid, 3-hydroxybenzoic acid, sinapic acid, and syringic acid being dominant. Among the solvents tested, ethanol demonstrated superior antioxidant activity and phenolic and flavonoid contents. F. communis extracts showed advanced inhibition of gram-negative pathogens (Escherichia coli and Proteus mirabilis) and variable antifungal activity against tested strains. Molecular docking simulations assessed the antioxidative, antibacterial, and antifungal properties of F. communis, facilitating innovative therapeutic development through predicted compound–protein interactions. In conclusion, the results validate the ethnomedicinal use and potential of F. communis. This highlights its significance in natural product research and ethnopharmacology.

PSC-CPI: Multi-Scale Protein Sequence-Structure Contrasting for Efficient and Generalizable Compound-Protein Interaction Prediction

Compound-Protein Interaction (CPI) prediction aims to predict the pattern and strength of compound-protein interactions for rational drug discovery. Existing deep learning-based methods utilize only the single modality of protein sequences or structures and lack the co-modeling of the joint distribution of the two modalities, which may lead to significant performance drops in complex real-world scenarios due to various factors, e.g., modality missing and domain shifting. More importantly, these methods only model protein sequences and structures at a single fixed scale, neglecting more fine-grained multi-scale information, such as those embedded in key protein fragments. In this paper, we propose a novel multi-scale Protein Sequence-structure Contrasting framework for CPI prediction (PSC-CPI), which captures the dependencies between protein sequences and structures through both intra-modality and cross-modality contrasting. We further apply length-variable protein augmentation to allow contrasting to be performed at different scales, from the amino acid level to the sequence level. Finally, in order to more fairly evaluate the model generalizability, we split the test data into four settings based on whether compounds and proteins have been observed during the training stage. Extensive experiments have shown that PSC-CPI generalizes well in all four settings, particularly in the more challenging ``Unseen-Both" setting, where neither compounds nor proteins have been observed during training. Furthermore, even when encountering a situation of modality missing, i.e., inference with only single-modality protein data, PSC-CPI still exhibits comparable or even better performance than previous approaches.

GraphsformerCPI: Graph Transformer for Compound-Protein Interaction Prediction.

Accurately predicting compound-protein interactions (CPI) is a critical task in computer-aided drug design. In recent years, the exponential growth of compound activity and biomedical data has highlighted the need for efficient and interpretable prediction approaches. In this study, we propose GraphsformerCPI, an end-to-end deep learning framework that improves prediction performance and interpretability. GraphsformerCPI treats compounds and proteins as sequences of nodes with spatial structures, and leverages novel structure-enhanced self-attention mechanisms to integrate semantic and graph structural features within molecules for deep molecule representations. To capture the vital association between compound atoms and protein residues, we devise a dual-attention mechanism to effectively extract relational features through .cross-mapping. By extending the powerful learning capabilities of Transformers to spatial structures and extensively utilizing attention mechanisms, our model offers strong interpretability, a significant advantage over most black-box deep learning methods. To evaluate GraphsformerCPI, extensive experiments were conducted on benchmark datasets including human, C. elegans, Davis and KIBA datasets. We explored the impact of model depth and dropout rate on performance and compared our model against state-of-the-art baseline models. Our results demonstrate that GraphsformerCPI outperforms baseline models in classification datasets and achieves competitive performance in regression datasets. Specifically, on the human dataset, GraphsformerCPI achieves an average improvement of 1.6% in AUC, 0.5% in precision, and 5.3% in recall. On the KIBA dataset, the average improvement in Concordance index (CI) and mean squared error (MSE) is 3.3% and 7.2%, respectively. Molecular docking shows that our model provides novel insights into the intrinsic interactions and binding mechanisms. Our research holds practical significance in effectively predicting CPIs and binding affinities, identifying key atoms and residues, enhancing model interpretability.

A bidirectional interpretable compound-protein interaction prediction framework based on cross attention

The identification of compound-protein interactions (CPIs) plays a vital role in drug discovery. However, the huge cost and labor-intensive nature in vitro and vivo experiments make it urgent for researchers to develop novel CPI prediction methods. Despite emerging deep learning methods have achieved promising performance in CPI prediction, they also face ongoing challenges: (i) providing bidirectional interpretability from both the chemical and biological perspective for the prediction results; (ii) comprehensively evaluating model generalization performance; (iii) demonstrating the practical applicability of these models. To overcome the challenges posed by current deep learning methods, we propose a cross multi-head attention oriented bidirectional interpretable CPI prediction model (CmhAttCPI). First, CmhAttCPI takes molecular graphs and protein sequences as inputs, utilizing the GCW module to learn atom features and the CNN module to learn residue features, respectively. Second, the model applies cross multi-head attention module to compute attention weights for atoms and residues. Finally, CmhAttCPI employs a fully connected neural network to predict scores for CPIs. We evaluated the performance of CmhAttCPI on balanced datasets and imbalanced datasets. The results consistently show that CmhAttCPI outperforms multiple state-of-the-art methods. We constructed three scenarios based on compound and protein clustering and comprehensively evaluated the model generalization ability within these scenarios. The results demonstrate that the generalization ability of CmhAttCPI surpasses that of other models. Besides, the visualizations of attention weights reveal that CmhAttCPI provides chemical and biological interpretation for CPI prediction. Moreover, case studies confirm the practical applicability of CmhAttCPI in discovering anticancer candidates.

Heterogeneous sampled subgraph neural networks with knowledge distillation to enhance double-blind compound-protein interaction prediction

Identifying binding compounds against a target protein is crucial for large-scale virtual screening in drug development. Recently, network-based methods have been developed for compound-protein interaction (CPI) prediction. However, they are difficult to be applied to unseen (i.e., never-seen-before) proteins and compounds. In this study, we propose SgCPI to incorporate local known interacting networks to predict CPI interactions. SgCPI randomly samples the local CPI network of the query compound-protein pair as a subgraph and applies a heterogeneous graph neural network (HGNN) to embed the active/inactive message of the subgraph. For unseen compounds and proteins, SgCPI-KD takes SgCPI as the teacher model to distillate its knowledge by estimating the potential neighbors. Experimental results indicate: (1) the sampled subgraphs of the CPI network introduce efficient knowledge for unseen molecular prediction with the HGNNs, and (2) the knowledge distillation strategy is beneficial to the double-blind interaction prediction by estimating molecular neighbors and distilling knowledge.

Discovery of 5-Hydroxy-1,4-naphthoquinone (Juglone) Derivatives as Dual Effective Agents Targeting Platelet-Cancer Interplay through Protein Disulfide Isomerase Inhibition.

In this study, a series of 2- and/or 3-substituted juglone derivatives were designed and synthesized. Among them, 9, 18, 22, 30, and 31 showed stronger inhibition activity against cell surface PDI or recombinant PDI and higher inhibitory effects on U46619- and/or collagen-induced platelet aggregation than juglone. The glycosylated derivatives 18 and 22 showed improved selectivity for inhibiting the proliferation of multiple myeloma RPMI 8226 cells, and the IC50 values reached 61 and 48 nM, respectively, in a 72 h cell viability test. In addition, 18 and 22 were able to prevent tumor cell-induced platelet aggregation and platelet-enhanced tumor cell proliferation. The molecular docking showed the amino acid residues Gln243, Phe440, and Leu443 are important for the compound-protein interaction. Our results reveal the potential of juglone derivatives to serve as novel antiplatelet and anticancer dual agents, which are available to interrupt platelet-cancer interplay through covalent binding to PDI catalytic active site.

Fufang Luohanguo Qingfei granules reduces influenza virus susceptibility via MAVS-dependent type I interferon antiviral signaling

Ethnopharmacological relevanceFufang Luohanguo Qingfei granules (LQG) is a Chinese patent medicine, clinically used to treat flu-like symptoms including cough with yellow phlegm, impeded phlegm, dry throat and tongue. However, the protective activity of LQG against influenza infection is indeterminate. Aim of the studyThis study is to investigate the therapeutic effect of LQG on influenza infection and elucidate its underlying mechanism. Materials and methodsIn vivo: A viral susceptible mouse model induced by restraint stress was established to investigate LQG's beneficial effects on influenza susceptibility. MAVS knockout (Mavs−/−) mice were used to verify the potential mechanism of LQG. In vitro: Corticosteroid (CORT)-treated A549 cells were employed to identify the active ingredients in LQG. Mice morbidity and mortality were monitored daily for 21 days. Histopathologic changes and inflammatory cytokines in lung tissues were examined by H&E staining and ELISA. RNA-seq was used to explore the signaling pathway influenced by LQG and further confirmed by qPCR. Immunoblotting and immunohistochemistry (IHC) were used to determine the protein levels. CO-IP and DARTS were applied to detect protein-protein interaction and compound-protein interaction, respectively. ResultsLQG effectively attenuated the susceptibility of restrained mice to H1N1 infection. LQG significantly boosted the production of IFN-β transduced by mitochondrial antiviral-signaling protein (MAVS), while MAVS deficiency abrogated its protective effects on restrained mice infected with H1N1. Moreover, in vitro studies further revealed that mogroside Ⅱ B, amygdalin, and luteolin are potentially active components of LQG. ConclusionThese results suggested that LQG inhibited the mitofusin 2 (Mfn2)-mediated ubiquitination of MAVS by impeding the E3 ligase synoviolin 1 (SYVN1) recruitment, thereby enhancing IFN-β antiviral response. Overall, our work elaborates a potential regimen for influenza treatment through reduction of stress-induced susceptibility.

CONSMI: Contrastive Learning in the Simplified Molecular Input Line Entry System Helps Generate Better Molecules.

In recent years, the application of deep learning in molecular de novo design has gained significant attention. One successful approach involves using SMILES representations of molecules and treating the generation task as a text generation problem, yielding promising results. However, the generation of more effective and novel molecules remains a key research area. Due to the fact that a molecule can have multiple SMILES representations, it is not sufficient to consider only one of them for molecular generation. To make up for this deficiency, and also motivated by the advancements in contrastive learning in natural language processing, we propose a contrastive learning framework called CONSMI to learn more comprehensive SMILES representations. This framework leverages different SMILES representations of the same molecule as positive examples and other SMILES representations as negative examples for contrastive learning. The experimental results of generation tasks demonstrate that CONSMI significantly enhances the novelty of generated molecules while maintaining a high validity. Moreover, the generated molecules have similar chemical properties compared to the original dataset. Additionally, we find that CONSMI can achieve favorable results in classifier tasks, such as the compound-protein interaction task.

ParaCPI: A Parallel Graph Convolutional Network for Compound-Protein Interaction Prediction.

Identifying compound-protein interactions (CPIs) is critical in drug discovery, as accurate prediction of CPIs can remarkably reduce the time and cost of new drug development. The rapid growth of existing biological knowledge has opened up possibilities for leveraging known biological knowledge to predict unknown CPIs. However, existing CPI prediction models still fall short of meeting the needs of practical drug discovery applications. A novel parallel graph convolutional network model for CPI prediction (ParaCPI) is proposed in this study. This model constructs feature representation of compounds using a unique approach to predict unknown CPIs from known CPI data more effectively. Experiments are conducted on five public datasets, and the results are compared with current state-of-the-art (SOTA) models under three different experimental settings to evaluate the model's performance. In the three cold-start settings, ParaCPI achieves an average performance gain of 26.75%, 23.84%, and 14.68% in terms of area under the curve compared with the other SOTA models. In addition, the results of the experiments in the case study show ParaCPI's superior ability to predict unknown CPIs based on known data, with higher accuracy and stronger generalization compared with the SOTA models. Researchers can leverage ParaCPI to accelerate the drug discovery process.

Antinociceptive Effects of Cannabichromene (CBC) in Mice: Insights from von Frey, Tail-Flick, Formalin, and Acetone Tests.

Cannabis sativa contains minor cannabinoids that have potential therapeutic value in pain management. However, detailed experimental evidence for the antinociceptive effects of many of these minor cannabinoids remains lacking. Here, we employed artificial intelligence (AI) to perform compound-protein interaction estimates with cannabichromene (CBC) and receptors involved in nociceptive signaling. Based on our findings, we investigated the antinociceptive properties of CBC in naïve or neuropathic C57BL/6 male and female mice using von Frey (mechanical allodynia), tail-flick (noxious radiant heat), formalin (acute and persistent inflammatory pain), and acetone (cold thermal) tests. For von Frey assessments, CBC dose (0-20 mg/kg, i.p.) and time (0-6 h) responses were measured in male and female neuropathic mice. For tail-flick, formalin, and acetone assays, CBC (20 mg/kg, i.p.) was administered to naïve male and female mice 1 h prior to testing. The results show that CBC (10 and 20 mg/kg, i.p.) significantly reduced mechanical allodynia in neuropathic male and female mice 1-2 h after treatment. Additionally, CBC treatment caused significant reductions in nociceptive behaviors in the tail-flick assay and in both phase 1 and phase 2 of the formalin test. Finally, we found a significant interaction in neuropathic male mice in the acetone test. In conclusion, our results suggest that CBC targets receptors involved in nociceptive signaling and imparts antinociceptive properties that may benefit males and females afflicted with diverse forms of acute or chronic/persistent pain.

Biochemical Analysis of Leonurus Sibiricus and Prediction of Its Bioactive Compound-Protein Interactions in Homo Sapiens

This study was conducted to investigate the proximate composition of L. sibiricus, an herbaceous medicinal plant, and explore the potential effects of its bioactive compounds, rutin and quercetin. Samples were collected from Dinajpur and Nilphamari to assess proximate composition. Proximate composition analysis revealed variations of ash, starch, fat, protein, non-reducing sugar (sucrose), invert (total) sugar, and reducing sugar contents of L. sibiricus. These findings indicate that proximate compositions and mineral contents varied depending on the growing place, soil and environmental factors. Furthermore, bioinformatics tools were utilized to investigate the effects of bioactive compounds rutin and quercetin of L. sibiricus in Homo sapiens. In this study, both rutin and quercetin interacted with 10 proteins, separately. Each individual protein interacted with another 10 proteins and found 100 proteins for rutin and 99 proteins for quercetin. However, 199 proteins were used to blast search in NCBI database and blasted results found only 177 proteins. Venn diagram analysis showed only four (4) common proteins interacted with rutin and quercetin. Functional annotation analysis revealed both positive and negative regulations of rutin and quercetin for biological process, molecular functions and cellular component in human health. Interestingly, KEGG pathway, compound and drug analysis exhibited that some potential drugs have already been discovered by rutin and quercetin that are mostly used for vascular protectant, ophthalmic, liver function improving agent and antimicrobial activity. A number of genes or enzymes involved in rutin and quercetin biosynthesis pathway retrieved in KEGG database. This study revealed that genetic engineering might enhances the biosynthesis of rutin and quercetin in honeyweed that could be utilized for production of valuable drug in industry for controlling different human and animal diseases in Bangladesh. Bioresearch Commu. 10(1): 1398-1412, 2024 (January)

FOTF-CPI: A compound-protein interaction prediction transformer based on the fusion of optimal transport fragments

Compound-protein interaction (CPI) affinity prediction plays an important role in reducing the cost and time of drug discovery. However, the interpretability of how fragments function in CPI is impacted by the fact that current methods ignore the affinity relationships between fragments of compounds and fragments of proteins in CPI modeling. This article introduces an improved Transformer called FOTF-CPI (aFusion of Optimal Transport Fragments compound-protein interaction prediction model). We use an optimal transport-based fragmentation approach to improve the model's understanding of compound and protein sequences. Additionally, a fused attention mechanism is employed, which combines the features of fragments to capture full affinity information. This fused attention redistributes higher attention scores to fragments with higher affinity. Experimental results show FOTF-CPI achieves an average 2% higher performance than other models on all three datasets. Furthermore, the visualization confirms the potential of FOTF-CPI for drug discovery applications.

UPLC-Q-Exactive-MS Combined with Network Pharmacology to Explore the Antitumor Effect of Polygonatum sibiricum Leaf Tea

Background. Currently, the substance basis and function of Polygonatum sibiricum leaf remain unknown. Objective. This study aims to investigate the antitumor mechanism of P. sibiricum leaf tea through network pharmacology. Methods. Ultraperformance liquid chromatography quadrupole exactive mass spectrometry (UPLC-Q-Exactive-MS) was employed to analyze the chemical components in the extract of P. sibiricum leaf tea. Compounds were screened using the PubChem database and SwissADME platform. The compound targets were identified using the Swiss Target Prediction database, while the disease targets were obtained from the GeneCards database. Subsequently, a compound-protein interaction network was constructed, and KEGG pathway enrichment analysis was performed to elucidate the antitumor activity pathway of P. sibiricum leaf tea. Molecular docking verification was carried out as well. Results. From the extract of P. sibiricum leaf tea, a total of fifty-six components were screened, including 27 active components. Seventy-two corresponding targets closely associated with the antitumor activity of P. sibiricum leaf tea were identified. By constructing a compound-target-pathway network diagram, three key compounds (pubescenol, avenanthramide E, and 13-cis-acitretin) and eleven key targets (AKT1, EGFR, CASP3, CCND1, MTOR, MMP9, ERBB2, BCL2L1, MAPK1, PPARG, and PIK3CA) were determined. Additionally, KEGG pathway analysis identified 30 antitumor related pathways. The results of molecular docking between the three key compounds and the top three targets (AKT1, EGFR, and CASP3) were consistent with the findings of network pharmacology. Conclusion. This study highlights the distinctive features of P. sibiricum leaf tea extract, which possesses multiple components, targets, and pathways. It successfully identifies the active components of P. sibiricum leaf tea that exhibit antitumor properties, along with their potential mechanisms of action. These findings offer valuable insights and inspiration for further research on novel mechanisms of action.

DeepCompoundNet: enhancing compound–protein interaction prediction with multimodal convolutional neural networks

Virtual screening has emerged as a valuable computational tool for predicting compound–protein interactions, offering a cost-effective and rapid approach to identifying potential candidate drug molecules. Current machine learning-based methods rely on molecular structures and their relationship in the network. The former utilizes information such as amino acid sequences and chemical structures, while the latter leverages interaction network data, such as protein–protein interactions, drug–disease interactions, and protein–disease interactions. However, there has been limited exploration of integrating molecular information with interaction networks. This study presents DeepCompoundNet, a deep learning-based model that integrates protein features, drug properties, and diverse interaction data to predict chemical–protein interactions. DeepCompoundNet outperforms state-of-the-art methods for compound–protein interaction prediction, as demonstrated through performance evaluations. Our findings highlight the complementary nature of multiple interaction data, extending beyond amino acid sequence homology and chemical structure similarity. Moreover, our model’s analysis confirms that DeepCompoundNet gets higher performance in predicting interactions between proteins and chemicals not observed in the training samples. Communicated by Ramaswamy H. Sarma

Abstract LB_A20: Overcoming cancer drug resistance with AI-designed RNA epigenetic inhibitors

Abstract Background: Drug resistance is a major obstacle to successful treatment of cancer and leukemia. The role of RNA epigenetics in cancer drug resistance is largely unknown. Our previous studies demonstrated that specific RNA cytosine methyltransferases (RCMTs), namely NSUN1 (aka NOL1, NPO2) and NSUN2, mediate the formation of drug-resistant active chromatin structures (ACS) at nascent RNAs to regulate drug resistance in leukemia cells (Cheng, J.X. et al. Nat Commun, 2018). The Cancer Genome Atlas Program (TCGA) data demonstrate that elevated expression levels of NSUN1 and NSUN2 are correlated with significantly shorter patients’ survival in almost all cancer subtypes (https://www.proteinatlas.org/ENSG00000111641-NOP2/pathology). However, due to the lack of NSUN1 and NSUN2 proteins’ crystal structures, no NSUN1/2-targeting therapeutics have been developed yet. Methods: 1. Argonne artificial intelligence (AI)/supercomputer design of NSUN1/2-targeting small-molecule compound libraries, simulation of compound-protein interactions and analysis of structure activity relationship (SAR). 2. Novel RNA epigenetic technologies, including NSUN1/2-targeting fluorescence releasing assay (FRA), 5-ethynyl uridine click chemistry (EC) and proximity ligation rolling cycle amplification (PL-RCA)-coupled confocal microscopy (CM), flow cytometry (FCM) and RNA sequencing (RNA-seq). 3. Functional drug screening, H&E histology and immunohistochemistry (IHC). 4. Enforced NSUN1/2 expression and knockout (KO) cell lines and syngeneic AML mouse models. Results:1. Identification of the ligand-binding modules/surfaces in NSUN1 and NSUN2 proteins and generation of NSUN1/2-targeting small-molecule libraries by AI/supercomputing. 2. Identification of several NSUN1/2 inhibitors that effectively inhibit growth of the venetoclax-resistant human monocytic leukemia (SC), erythroid leukemia (K562) and lung cancer (H82) cells. 3. Demonstration of the lead inhibitors execute their effects through disruption of NSUN1/2-mediated (ACS) and translational complexes (TLC). 4. Characterization of the lead inhibitors’ binding modules with AI/supercomputing SAR analysis. 5. In vivo validation of the efficacies of the identified lead inhibitors using syngeneic AML mouse models. Conclusion:By leveraging the power of the Argonne AI/supercomputer and our functional assays, we identified several small-molecule inhibitors that can disrupt the NSUN1/2-mediated ACS and TLC to overcome venetoclax resistance in AML cell lines and syngeneic mice. This study has not only illustrated the importance of NSUN1 and NSUN2 in oncogenic bioprocesses and drug (venetoclax) resistance, but also paved the way to the development of novel RNA epigenetics-driven therapeutics for leukemia and other cancer subtypes. Citation Format: Jason X Cheng, Shaun Wood, Derrick Tang, Linda Degenstein, Andrzej Joachimiak, Rick Stevens. Overcoming cancer drug resistance with AI-designed RNA epigenetic inhibitors [abstract]. In: Proceedings of the AACR-NCI-EORTC Virtual International Conference on Molecular Targets and Cancer Therapeutics; 2023 Oct 11-15; Boston, MA. Philadelphia (PA): AACR; Mol Cancer Ther 2023;22(12 Suppl):Abstract nr LB_A20.

Acalypha wilkesiana L - A potential anti-stearoyl-CoA desaturase agent: Insilico and network pharmacology studies

The activity of Seborrheic dermatitis on the skin of children still remains of the dermatoses of male and female babies in the early days of their existence. Acalypha wilkesiana L have been employed by mothers to combat Seborrheic dermatitis, yet, the descriptors responsible for such activity as well as the nonbonding interactions between the selected phytochemicals and stearoyl-CoA desaturase has not been explored. The studied compounds were optimized using Spartan’14 software as well as molecular operating environments (MOE) for docking, Cytoscape software for compound-protein interaction network, Gromacs for molecular dynamic simulation as well ADMETSar for pharmacokinetics studies. The selected compounds proved to have anti-stearoyl-CoA desaturase properties via the calculated descriptors obtained from the chemical compounds obtained from Acalypha wilkesiana L as well as from the result from molecular modeling studies. The Pharmacokinetics results were observed and reported appropriately.

MulinforCPI: enhancing precision of compound-protein interaction prediction through novel perspectives on multi-level information integration.

Forecasting the interaction between compounds and proteins is crucial for discovering new drugs. However, previous sequence-based studies have not utilized three-dimensional (3D) information on compounds and proteins, such as atom coordinates and distance matrices, to predict binding affinity. Furthermore, numerous widely adopted computational techniques have relied on sequences of amino acid characters for protein representations. This approach may constrain the model's ability to capture meaningful biochemical features, impeding a more comprehensive understanding of the underlying proteins. Here, we propose a two-step deep learning strategy named MulinforCPI that incorporates transfer learning techniques with multi-level resolution features to overcome these limitations. Our approach leverages 3D information from both proteins and compounds and acquires a profound understanding of the atomic-level features of proteins. Besides, our research highlights the divide between first-principle and data-driven methods, offering new research prospects for compound-protein interaction tasks. We applied the proposed method to six datasets: Davis, Metz, KIBA, CASF-2016, DUD-E and BindingDB, to evaluate the effectiveness of our approach.

CrossFuse-XGBoost: accurate prediction of the maximum recommended daily dose through multi-feature fusion, cross-validation screening and extreme gradient boosting.

In the drug development process, approximately 30% of failures are attributed to drug safety issues. In particular, the first-in-human (FIH) trial of a new drug represents one of the highest safety risks, and initial dose selection is crucial for ensuring safety in clinical trials. With traditional dose estimation methods, which extrapolate data from animals to humans, catastrophic events have occurred during Phase I clinical trials due to interspecies differences in compound sensitivity and unknown molecular mechanisms. To address this issue, this study proposes a CrossFuse-extreme gradient boosting (XGBoost) method that can directly predict the maximum recommended daily dose of a compound based on existing human research data, providing a reference for FIH dose selection. This method not only integrates multiple features, including molecular representations, physicochemical properties and compound-protein interactions, but also improves feature selection based on cross-validation. The results demonstrate that the CrossFuse-XGBoost method not only improves prediction accuracy compared to that of existing local weighted methods [k-nearest neighbor (k-NN) and variable k-NN (v-NN)] but also solves the low prediction coverage issue of v-NN, achieving full coverage of the external validation set and enabling more reliable predictions. Furthermore, this study offers a high level of interpretability by identifying the importance of different features in model construction. The 241 features with the most significant impact on the maximum recommended daily dose were selected, providing references for optimizing the structure of new compounds and guiding experimental research. The datasets and source code are freely available at https://github.com/cqmu-lq/CrossFuse-XGBoost.

GcForest-based compound-protein interaction prediction model and its application in discovering small-molecule drugs targeting CD47.

Identifying compound-protein interaction plays a vital role in drug discovery. Artificial intelligence (AI), especially machine learning (ML) and deep learning (DL) algorithms, are playing increasingly important roles in compound-protein interaction (CPI) prediction. However, ML relies on learning from large sample data. And the CPI for specific target often has a small amount of data available. To overcome the dilemma, we propose a virtual screening model, in which word2vec is used as an embedding tool to generate low-dimensional vectors of SMILES of compounds and amino acid sequences of proteins, and the modified multi-grained cascade forest based gcForest is used as the classifier. This proposed method is capable of constructing a model from raw data, adjusting model complexity according to the scale of datasets, especially for small scale datasets, and is robust with few hyper-parameters and without over-fitting. We found that the proposed model is superior to other CPI prediction models and performs well on the constructed challenging dataset. We finally predicted 2 new inhibitors for clusters of differentiation 47(CD47) which has few known inhibitors. The IC50s of enzyme activities of these 2 new small molecular inhibitors targeting CD47-SIRPα interaction are 3.57 and 4.79μM respectively. These results fully demonstrate the competence of this concise but efficient tool for CPI prediction.