Search

Deficiency in blood coagulation factor VIII (FVIII) results in life-threating bleeding (hemophilia A) treated by infusions of FVIII concentrates. To improve disease treatment, FVIII has been modified to increase its plasma half-life, which requires understanding mechanisms of FVIII catabolism. An important catabolic actor is hepatic low density lipoprotein receptor-related protein 1 (LRP1), which also regulates many other clinically significant processes. Previous studies showed complexity of FVIII site for binding LRP1.To characterize binding sites between FVIII and LRP1 and suggest a model of the interaction.A series of recombinant ligand-binding complement-type repeat (CR) fragments of LRP1 including mutated variants was generated in a baculovirus system and tested for FVIII interaction using surface plasmon resonance, tissue culture model, hydrogen-deuterium exchange mass spectrometry, and in silico.Multiple CR doublets within LRP1 clusters II and IV were identified as alternative FVIII-binding sites. These interactions follow the canonical binding mode providing major binding energy, and additional weak interactions are contributed by adjacent CR domains. A representative CR doublet was shown to have multiple contact sites on FVIII.FVIII and LRP1 interact via formation of multiple complex contacts involving both canonical and non-canonical binding combinations. We propose that FVIII-LRP1 interaction occurs via switching such alternative binding combinations in a dynamic mode, and that this mechanism is relevant to other ligand interactions of the low-density lipoprotein receptor family members including LRP1.

Studies on glutamine (Gln) metabolism have illuminated the vital role of Gln in cellular functions and its potential as a biomarker for disease detection. Despite the increasing interest in Gln metabolism, in-depth evaluations are challenging owing to limitations of conventional Gln-measuring methods. Thus, we developed a ligand-induced dimerization-based sensor for Gln, termed Q-SHINE, by splitting a glutamine binding protein into two separate domains. Q-SHINE enables highly accurate and convenient measurement of Gln concentration in bio-fluid samples, and the detection range is optimal for physiological Gln levels. Genetically encoded Q-SHINE sensors could also visualize intracellular Gln levels and quantify cytoplasmic and mitochondrial Gln change in living cells, which enabled detection of various cell responses to extracellular Gln supplement.

Amyloid-β (Aβ) in the form of neurotoxic aggregates is regarded as the main pathological initiator and key therapeutic target of Alzheimer's disease. However, anti-Aβ drug development has been impeded by the lack of a target needed for structure-based drug design and low permeability of the blood-brain barrier (BBB). An attractive therapeutic strategy is the development of amyloid-based anti-Aβ peptidomimetics that exploits the self-assembling nature of Aβ and penetrates the BBB. Herein, we designed a dimeric peptide drug candidate based on the N-terminal fragment of Aβ, DAB, found to cross the BBB and solubilize Aβ oligomers and fibrils. Administration of DAB reduced amyloid burden in 5XFAD mice, and downregulated neuroinflammation and prevented memory impairment in the Y-maze test. Peptide mapping assays and molecular docking studies were utilized to elucidate DAB-Aβ interaction. To further understand the active regions of DAB, we assessed the dissociative activity of DAB with sequence modifications.

Thyroid carcinoma, a disease in which malignant cells form in the thyroid tissue, is the most common endocrine carcinoma, with papillary thyroid carcinoma (PTC) accounting for nearly 80% of total thyroid carcinoma cases. However, the management of metastatic or recurrent therapy-refractory PTC is challenging and requires complex carcinoma therapy. In this study, we proposed a new clinical approach for the treatment of therapy-refractory PTC. We identified sarco/endoplasmic reticulum calcium ATPase (SERCA) as an essential factor for the survival of PTC cells refractory to the treatment with paclitaxel or sorafenib. We validated its use as a potential target for developing drugs against resistant PTC, by using patient-derived paclitaxel- or sorafenib-resistant PTC cells. We further discovered novel SERCA inhibitors, candidates 7 and 13, using the evolutionary chemical binding similarity method. These novel SERCA inhibitors determined a substantial reduction of tumors in a patient-derived xenograft tumor model developed using paclitaxel- or sorafenib-resistant PTC cells. These results could provide a basis for clinically meaningful progress in the treatment of refractory PTC by identifying a novel therapeutic strategy: using a combination therapy between sorafenib or paclitaxel and specific SERCA inhibitors for effectively and selectively targeting extremely malignant cells such as antineoplastic-resistant and carcinoma stem-like cells.

The tropolone-bearing sesquiterpenes juniperone A (1) and norjuniperone A (2) were isolated from the folk medicinal plant Juniperus chinensis, and their structures were determined by a combination of spectroscopic and crystallographic methods. Photojuniperones A1 (3) and A2 (4), bearing bicyclo[3,2,0]heptadienones derived from tropolone, were photochemically produced and structurally identified by spectroscopic methods. Predicted by the machine learning-based assay, 1 significantly inhibited the action of tyrosinase. The new compounds also inhibited lipid accumulation and enhanced the extracellular glycerol excretion.

Drug resistance causes therapeutic failure in refractory cancer. Cancer drug resistance stems from various factors, such as patient heterogeneity and genetic alterations in somatic cancer cells, including those from identical tissues. Generally, resistance is intrinsic for cancers; however, cancer resistance becomes common owing to an increased drug treatment. Unfortunately, overcoming this issue is not yet possible. The present study aimed to evaluate a clinical approach using candidate compounds 19 and 23, which are sarcoplasmic/endoplasmic reticulum calcium ATPase (SERCA) inhibitors, discovered using the evolutionary chemical binding similarity method. mRNA sequencing indicated SERCA as the dominant marker of patient-derived anti-cancer drug-resistant hepatocellular carcinoma (HCC), but not of patient-derived anti-cancer drug-sensitive HCC. Candidate compounds 19 and 23 led to significant tumor shrinkage in a tumor xenograft model of anti-cancer drug-resistant patient-derived HCC cells. Our results might be clinically significant for the development of novel combinatorial strategies that selectively and efficiently target highly malignant cells such as drug-resistant and cancer stem-like cells.

Background: Alzheimer’s disease (AD) is characterized by the aggregation of two pathological proteins, amyloid-β (Aβ) and tau, leading to neuronal and cognitive dysfunction. Clearance of either Aβ or tau aggregates by immunotherapy has become a potential therapy, as these aggregates are found in the brain ahead of the symptom onset. Given that Aβ and tau independently and cooperatively play critical roles in AD development, AD treatments might require therapeutic approaches to eliminate both aggregates together. Objective: We aimed to discover a chemical drug candidate from natural sources for direct dissociation of both insoluble Aβ and tau aggregates through in vitro assessments. Methods: We isolated four borrelidin chemicals from a saltern-derived halophilic actinomycete strain of rare genus Nocardiopsis and simulated their docking interactions with Aβ fibrils. Then, anti-cytotoxic, anti-Aβ, and anti-tau effects of borrelidins were examined by MTT assays with HT22 hippocampal cell line, thioflavin T assays, and gel electrophoresis. Results: When HT22 cells were exposed to Aβ aggregates, the treatment of borrelidins alleviates the Aβ-induced toxicity. These anti-cytotoxic effects can be derived from the inhibitory functions of borrelidins against the Aβ aggregation as shown in thioflavin T and gel electrophoretic analyses. Among them, especially borrelidin, which exhibits the highest probability of docking, not only dissociates Aβ aggregates but also directly regulates tau aggregation. Conclusion: Borrelidin dissociates insoluble Aβ and tau aggregates together and our findings support the view that it is possible to develop an alternative chemical approach mimicking anti-Aβ or anti-tau immunotherapy for clearance of both aggregates.

Rhizolutin (1) was discovered as a natural product of ginseng-rhizospheric Streptomyces sp. WON17. Its structure features an unprecedented 7/10/6-tricyclic dilactone carbon skeleton composed of dimethylcyclodecatriene flanked by a 7-membered and a 6-membered lactone ring based on spectroscopic analysis. During an unbiased screening of natural product libraries, this novel compound was found to dissociate amyloid-β (Aβ) plaques and tau tangles, which are key pathological hallmarks of Alzheimer's disease (AD). Rhizolutin treatment of APP/PS1 double transgenic mice with AD significantly dissociated hippocampal plaques. In vitro, rhizolutin substantially decreased Aβ-induced apoptosis and inflammation in neuronal and glial cells. Our findings introduce a unique chemical entity that targets Aβ and tau concurrently by mimicking misfolded protein clearance mechanisms of immunotherapy, which is prominently investigated in clinical trials.

Natural products (NPs) have played a significant role in drug discovery for diverse diseases, and numerous attempts have been made to discover promising NP inhibitors of tumor necrosis factor α (TNF-α), a major therapeutic target in autoimmune diseases. However, NP inhibitors of TNF-α, which have the potential to be developed as new drugs, have not been reported for over a decade. To facilitate the search for new promising inhibitors of TNF-α, we developed an efficient competitive binding screening assay based on analytical size exclusion chromatography coupled with liquid chromatography-tandem mass spectrometry. Application of this screening method to the NP library led to the discovery of a potent inhibitor of TNF-α, sennoside B, with an IC50 value of 0.32 µM in TNF-α induced HeLa cell toxicity assays. Surprisingly, the potency of sennoside B was 5.7-fold higher than that of the synthetic TNF-α inhibitor SPD304. Molecular docking was performed to determine the binding mode of sennoside B to TNF-α. In conclusion, we successfully developed a novel competition binding screening method to discover small molecule TNF-α inhibitors and identified the natural compound sennoside B as having exceptional potency.

Chemical and optogenetic methods for post-translationally controlling protein function have enabled new discoveries and the engineering of synthetic cellular functions. However, most of these methods only confer single-input, single-output control. To increase the diversity of post-translational behaviors that can be programmed we built a system based on a single protein receiver that can integrate multiple drug inputs, including approved therapeutics. Our system translates drug inputs into diverse outputs with engineered reader proteins that provide variable dimerization states of the receiver protein. We show that our single receiver protein architecture can be used to program diverse cellular responses, including graded and proportional dual-output control of transcription and mammalian cell signaling. We apply our tools to titrate the competing activities of the Rac and Rho GTPases to control cell morphology. Our receiver protein and suite of reader proteins provides researchers with a versatile toolset to post-translationally program mammalian cellular processes and to engineer cell therapies.

Circadian rhythms are controlled by transcriptional feedback loops of clock genes and proteins. The stability of clock proteins is regulated by post-translational modification, such as phosphorylation by kinases. In particular, casein kinase I (CKI) phosphorylates the PER protein to regulate proteasomal degradation and nuclear localization. Therefore, CKI inhibition can modulate mammalian circadian rhythms. In the present study, we have developed novel CKIα and CKIδ dual inhibitors by extensive structural modification of N9 and C2 position of longdaysin. We identified NCC007 that showed stronger period effects (0.32 μM for 5 h period lengthening) in a cell-based circadian assay. The following in vitro kinase assay showed that NCC007 inhibited CKIα and CKIδ with an IC(50) of 1.8 and 3.6 μM. We further demonstrated that NCC007 lengthened the period of mouse behavioral rhythms in vivo. Thus, NCC007 is a valuable tool compound to control circadian rhythms through CKI inhibition.

Neuropeptides function through G protein-coupled receptors (GPCRs) with high specificity, implying a significant degree of neuropeptide-GPCR coevolution. However, potential neuropeptide signaling systems in non-chordates are relatively elusive. We determined the specificity of the neuropeptide F (Hdh-NPF) signaling system with a cognate receptor (Hdh-NPFR) in the Pacific abalone, Haliotis discus hannai. Phylogenetic and exon–intron arrangement analyses of bilaterian NPF and the chordate ortholog NPY with their receptor sequences revealed a likely common ancestor, and Hdh-NPFR was similar to the NPYR2 subtype among the NPYR1, NPYR2, and NPYR5 subtypes. Among four Hdh-NPFR-related receptors, Hdh-NPFR specifically responded to Hdh-NPF peptide, supported by the dose–response luciferase reporter curve, intracellular Ca2+ mobilization, and phosphorylation of ERK1/2 and its inhibition with a protein kinase C inhibitor. Peptide fragmentations and shuffling of Hdh-NPF with human NPY could not activate the cellular response of Hdh-NPFR. Three-dimensional in silico modeling suggested that interaction of Hdh-NPF C-terminal amino acids with the extracellular loops of Hdh-NPFR is critical for Hdh-NPFR activation. In vivo injection of Hdh-NPF peptide increased food consumption, and knockdown of Hdh-NPF expression decreased food consumption in Pacific abalone. These findings provide evidence for co-evolution of the NPF/Y ligand-receptor system, enabling further research on mollusk orexigenic neuropeptides.

Tyrosinase is an enzyme that plays a crucial role in the melanogenesis of humans and the browning of food products. Thus, tyrosinase inhibitors that are useful to the cosmetic and food industries are required. In this study, we have used evolutionary chemical binding similarity (ECBS) to screen a virtual chemical database for human tyrosinase, which resulted in seven potential tyrosinase inhibitors confirmed through the tyrosinase inhibition assay. The tyrosinase inhibition percentage for three of the new actives was over 90% compared to 61.9% of kojic acid. From the structural analysis through pharmacophore modeling and molecular docking with the human tyrosinase model, the pi&ndash, pi interaction of tyrosinase inhibitors with conserved His367 and the polar interactions with Asn364, Glu345, and Glu203 were found to be essential for tyrosinase&ndash, ligand interactions. The pharmacophore features and the docking models showed high consistency, revealing the possible essential binding interactions of inhibitors to human tyrosinase. We have also presented the activity cliff analysis that successfully revealed the chemical features related to substantial activity changes found in the new tyrosinase inhibitors. The newly identified inhibitors and their structure&ndash, activity relationships presented here will help to identify or design new human tyrosinase inhibitors.

As the microbiome is composed of a variety of microbial interactions, it is imperative in microbiome research to identify a microbial sub-community that collectively conducts a specific function. However, current methodologies have been highly limited to analyzing conditional abundance changes of individual microorganisms without considering group-wise collective microbial features. To overcome this limitation, we developed a network-based method using nonnegative matrix factorization (NMF) to identify functional meta-microbial features (MMFs) that, as a group, better discriminate specific environmental conditions of samples using microbiome data. As proof of concept, large-scale human microbiome data collected from different body sites were used to identify body site-specific MMFs by applying NMF. The statistical test for MMFs led us to identify highly discriminative MMFs on sample classes, called synergistic MMFs (SYMMFs). Finally, we constructed a SYMMF-based microbial interaction network (SYMMF-net) by integrating all of the SYMMF information. Network analysis revealed core microbial modules closely related to critical sample properties. Similar results were also found when the method was applied to various disease-associated microbiome data. The developed method interprets high-dimensional microbiome data by identifying functional microbial modules on sample properties and intuitively representing their systematic relationships via a microbial network.

Background Despite continued efforts using chemical similarity methods in virtual screening, currently developed approaches suffer from time-consuming multistep procedures and low success rates. We recently developed a machine learning-based chemical binding similarity model considering common structural features from molecules binding to the same, or evolutionarily related targets. The chemical binding similarity measures the resemblance of chemical compounds in terms of binding site similarity to better describe functional similarities that arise from target binding. In this study, we have shown how the chemical binding similarity could be used in virtual screening together with the conventional structure-based methods. Results The chemical binding similarity, receptor-based pharmacophore, chemical structure similarity, and molecular docking methods were evaluated to identify an effective virtual screening procedure for desired target proteins. When we tested the chemical binding similarity method with test sets of 51 kinases, it outperformed the traditional structural similarity-based methods as well as structure-based methods, such as molecular docking and receptor-based pharmacophore modeling, in terms of finding active compounds. We further validated the results by performing virtual screening (using the chemical binding similarity and receptor-based pharmacophore methods) against a completely blind dataset for mitogen-activated protein kinase kinase 1 (MEK1), ephrin type-B receptor 4 (EPHB4) and wee1-like protein kinase (WEE1). The in vitro kinase binding assay confirmed that 6 out of 13 (46.2%) for MEK1 and 2 out of 12 (16.7%) for EPHB4 were newly identified only by the chemical binding similarity model. Conclusions We report that the virtual screening results could further be improved by combining the chemical binding similarity model with 3D-QSAR pharmacophore and molecular docking models. Not only the new inhibitors are identified in this study, but also many of the identified molecules have low structural similarity scores against already reported inhibitors and that show the revelation of novel scaffolds.

Amyloid-β (Aβ) oligomers are implicated in Alzheimer disease (AD). However, their unstable nature and heterogeneous state disrupts elucidation of their explicit role in AD progression, impeding the development of tools targeting soluble Aβ oligomers. Herein parallel and anti-parallel variants of Aβ(1-40) dimers were designed and synthesized, and their pathogenic properties in AD models characterized. Anti-parallel dimers induced cognitive impairments with increased amyloidogenesis and cytotoxicity, and this dimer was then used in a screening platform. Through screening, two FDA-approved drugs, Oxytetracycline and Sunitinib, were identified to dissociate Aβ oligomers and plaques to monomers in 5XFAD transgenic mice. In addition, fluorescent Astrophloxine was shown to detect aggregated Aβ in brain tissue and cerebrospinal fluid samples of AD mice. This screening platform provides a stable and homogeneous environment for observing Aβ interactions with dimer-specific molecules.

Since its first report in the Middle East in 2012, the Middle East respiratory syndrome-coronavirus (MERS-CoV) has become a global concern due to the high morbidity and mortality of individuals infected with the virus. Although the majority of MERS-CoV cases have been reported in Saudi Arabia, the overall risk in areas outside the Middle East remains significant as inside Saudi Arabia. Additional pandemics of MERS-CoV are expected, and thus novel tools and reagents for therapy and diagnosis are urgently needed. Here, we used phage display to develop novel monoclonal antibodies (mAbs) that target MERS-CoV. A human Fab phage display library was panned against the S2 subunit of the MERS-CoV spike protein (MERS-S2P), yielding three unique Fabs (S2A3, S2A6, and S2D5). The Fabs had moderate apparent affinities (Half maximal effective concentration (EC50 = 123&ndash, 421 nM) for MERS-S2P, showed no cross-reactivity to spike proteins from other CoVs, and were non-aggregating and thermostable (Tm = 61.5&ndash, 80.4 &deg, C). Reformatting the Fabs into IgGs (Immunoglobulin Gs) greatly increased their apparent affinities (KD = 0.17&ndash, 1.2 nM), presumably due to the effects of avidity. These apparent affinities were notably higher than that of a previously reported anti-MERS-CoV S2 reference mAb (KD = 8.7 nM). Furthermore, two of the three mAbs (S2A3 and S2D5) bound only MERS-CoV (Erasmus Medical Center (EMC)) and not other CoVs, reflecting their high binding specificity. However, the mAbs lacked MERS-CoV neutralizing activity. Given their high affinity, specificity, and desirable stabilities, we anticipate that these anti-MERS-CoV mAbs would be suitable reagents for developing antibody-based diagnostics in laboratory or hospital settings for point-of-care testing.

Recent clinical approvals of brain imaging radiotracers targeting amyloid-β provided clinicians the tools to detect and confirm Alzheimer's disease pathology without autopsy or biopsy. While current imaging agents are effective in postsymptomatic Alzheimer's patients, there is much room for improvement in earlier diagnosis, hence prompting a need for new and improved amyloid imaging agents. Here we synthesized 41 novel 1,4-naphthoquinone derivatives and initially discovered 14 antiamyloidogenic compounds via in vitro amyloid-β aggregation assay; however, qualitative analyses of these compounds produced conflicting results and required further investigation. Follow-up docking and biophysical studies revealed that four of these compounds penetrate the blood-brain barrier, directly bind to amyloid-β aggregates, and enhance fluorescence properties upon interaction. These compounds specifically stain both diffuse and dense-core amyloid-β plaques in brain sections of APP/PS1 double transgenic Alzheimer's mouse models. Our findings suggest 1,4-naphthoquinones as a new scaffold for amyloid-β imaging agents for early stage Alzheimer's.

Chemical and functional anisotropy in Janus materials offer intriguing possibilities for constructing complex nanostructures and regulating chemical and biological reactions. Here, the authors report the fabrication of Janus nanosheets from molecular building blocks composed of two information-carrying biopolymers, DNA and peptides. Experimental and structural modeling studies reveal that DNA-peptide diblock conjugates assemble into Janus nanosheets with distinct DNA and peptide faces. The surprising level of structural control is attributed to the exclusive parallel β-sheet formation of phenylalanine-rich peptides. This approach is extended to triblock DNA1-peptide-DNA2 conjugates, which assemble into nanosheets presenting two different DNA on opposite faces. The Janus nanosheets with independently addressable faces are utilized to organize an enzyme pair for concerted enzymatic reactions, where enhanced catalytic activities are observed. These results demonstrate that the predictable and designable peptide interaction is a promising tool for creating Janus nanostructures with regio-selective and sequence-specific molecular recognition properties.

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder characterized by the formation of toxic amyloid-β (Aβ) oligomers and plaques. Considering that Aβ misfolding and aggregation precedes the progressive development of cognitive impairment in AD, investigating a therapeutic means by clearance of pre-existing Aβ aggregates shows promise as a viable disease-modifying treatment. Here, we report that a small molecule, necrostatin-1 (Nec-1), reduces Aβ aggregates back to non-toxic monomers in vitro and in vivo. Intravenous administration of Nec-1 reduced the levels of Aβ plaques in the brains of aged APP/PS1 double transgenic mice. In addition, Nec-1 exhibited therapeutic effects against Aβ aggregates by inhibiting Aβ-induced brain cell death in neuronal and microglial cell lines. Nec-1 also showed anti-apoptotic and anti-necroptotic effects in the cortex of aged APP/PS1 mice by reducing levels of phosphorylated-RIPK3 and Bax and increasing the levels of Bcl-2. According to our data in vitro and in silico, the methyl group of the amine in the 2-thioxo-4-imidazolidinone is the key moiety of Nec-1 that directs its activity against aggregated Aβ. Given that the accumulation of Aβ aggregates is an important hallmark of AD, our studies provide strong evidence that Nec-1 may serve a key role in the development of AD treatment.

Glycoprotein Ibα (GpIbα), a family of LRR (leucine-rich repeat) proteins, is a membrane protein on the platelet, and plays an important role in atherothrombotic events. The complex formation of GpIbα with the von Willebrand Factor (vWF) has been revealed to lead to acute coronary syndrome (ACS) or stroke. A considerable attention has been paid to understand the biological functions of GpIbα and its regulation. However, difficulty with the soluble expression of human GpIbα in bacteria has hampered the relevant research. Herein, we present a soluble expression of GpIbα in Escherichiacoli by replacing the N-terminal capping domain of GpIbα with that of Internalin B using a computational approach. The resulting protein was expressed as a soluble form in E. coli, maintaining its structural feature and binding property for vWF. The present approach can be broadly used for the soluble expression of human LRR proteins in E. coli.

Interleukin-6 (IL-6) is a multifunctional cytokine that regulates immune responses for host defense and tumorigenic process. Upregulation of IL-6 is known to constitutively phosphorylate signal transducer and activator of transcription 3 (STAT3), leading to activation of multiple oncogene pathways and inflammatory cascade. Here, we present the development of a high-affinity protein binder, termed repebody, which effectively suppresses non–small cell lung cancer in vivo by blocking the IL-6/STAT3 signaling. We selected a repebody that prevents human IL-6 (hIL-6) from binding to its receptor by a competitive immunoassay, and modulated its binding affinity for hIL-6 up to a picomolar range by a modular approach that mimics the combinatorial assembly of diverse modules to form antigen-specific receptors in nature. The resulting repebody was highly specific for hIL-6, effectively inhibiting the STAT3 phosphorylation in a dose- and binding affinity-response manner in vitro. The repebody was shown to have a remarkable suppression effect on the growth of tumors and STAT3 phosphorylation in xenograft mice with non–small cell lung cancer by blocking the hIL-6/STAT3 signaling. Structural analysis of the repebody and IL-6 complex revealed that the repebody binds the site 2a of hIL-6, overlapping a number of epitope residues at site 2a with gp130, and consequently causes a steric hindrance to the formation of IL-6/IL-6Rα complex. Our results suggest that high-affinity repebody targeting the IL-6/STAT3 pathway can be developed as therapeutics for non–small cell lung cancer.

Chemical similarity searching is a basic research tool that can be used to find small molecules which are similar in shape to known active molecules. Despite its popularity, the retrieval of local molecular features that are critical to functional activity related to target binding often fails. To overcome this limitation, we developed a novel machine learning-based chemical binding similarity score by using various evolutionary relationships of binding targets. The chemical similarity was defined by the probability of chemical compounds binding to identical targets. Comprehensive and heterogeneous multiple target-binding chemical data were integrated into a paired data format and processed using multiple classification similarity-learning models with various levels of target evolutionary information. Encoding evolutionary information to chemical compounds through their binding targets substantially expanded available chemical-target interaction data and significantly improved model performance. The output probability of our integrated model, referred to as ensemble evolutionary chemical binding similarity (ensECBS), was effective for finding hidden chemical relationships. The developed method can serve as a novel chemical similarity tool that uses evolutionarily conserved target binding information.