Rationally designed chimeric PI3K-BET bromodomain inhibitors elicit curative responses in MYC-driven lymphoma.

Targeted inhibitors of bromodomain and extraterminal (BET)-bromodomains and phosphatidylinositol-3-kinase (PI3K) signaling demonstrate potent but self-limited antilymphoma activity as single agents in the context of cellular Myelocytomatosis (cMYC) oncogene-dysregulation. However, combined PI3K and BET inhibition imparts synergistic anticancer activity with the potential for more sustained disease responses due to the mutual antagonism of compensatory epigenetic and signaling networks. Here, we describe the mechanistic and therapeutic validation of rationally designed dual PI3K/BET bromodomain inhibitors, built by linkage of established PI3K and BET inhibitor pharmacophores. The lead candidate demonstrates high selectivity, nanomolar range cellular potency, and compelling in vivo efficacy, including curative responses in the aggressive Eµ-Myc lymphoma model. These studies further support the therapeutic strategy of combined PI3K and BET inhibition and provide a potential step-change in approach to orthogonal MYC antagonism using optimized chimeric small-molecule technology.

Regenerative engineering of long bones using the small molecule forskolin.

Bone grafting procedures have become increasingly common in the United States, with approximately 500,000 cases occurring each year at a societal cost exceeding $2.4 billion. Recombinant human bone morphogenetic proteins (rhBMPs) are therapeutic agents that have been widely used by orthopedic surgeons to stimulate bone tissue formation alone and when paired with biomaterials. However, significant limitations such as immunogenicity, high production cost, and ectopic bone growth from these therapies remain. Therefore, efforts have been made to discover and repurpose osteoinductive small-molecule therapeutics to promote bone regeneration. Previously, we have demonstrated that a single-dose treatment with the small-molecule forskolin for just 24 h induces osteogenic differentiation of rabbit bone marrow-derived stem cells in vitro, while mitigating adverse side effects attributed with prolonged small-molecule treatment schemes. In this study, we engineered a composite fibrin-PLGA [poly(lactide-co-glycolide)]-sintered microsphere scaffold for the localized, short-term delivery of the osteoinductive small molecule, forskolin. In vitro characterization studies showed that forskolin released out of the fibrin gel within the first 24 h and retained its bioactivity toward osteogenic differentiation of bone marrow-derived stem cells. The forskolin-loaded fibrin-PLGA scaffold was also able to guide bone formation in a 3-mo rabbit radial critical-sized defect model comparable to recombinant human bone morphogenetic protein-2 (rhBMP-2) treatment, as demonstrated through histological and mechanical evaluation, with minimal systemic off-target side effects. Together, these results demonstrate the successful application of an innovative small-molecule treatment approach within long bone critical-sized defects.

Small molecule inhibitors targeting regulatory T cells for cancer treatment.

Regulatory T cells (Tregs) are important controllers of the immune system homeostasis by preventing disproportionate immune responses. In the context of cancer, Tregs contribute to tumor development by suppressing other immune cells in the tumor microenvironment (TME). Infiltration of Tregs in the TME has been associated with poor prognosis in cancer patients. Thus, understanding the mechanisms underlying Treg recruitment and suppressive functions is essential for developing cancer immunotherapies to boost antitumor immune responses. While antibody-based strategies targeting Tregs have shown promise, small molecule inhibitors offer distinct advantages, including oral bioavailability and the ability to penetrate the TME and target intracellular proteins. Here, we provide an overview of small molecule inhibitors that have demonstrated efficacy in modulating Tregs activity in cancer and highlight the need for phenotypic assays to characterize therapeutic compounds.

Targeting splicing factors for cancer therapy.

Alternative splicing (AS) of mRNAs is an essential regulatory mechanism in eukaryotic gene expression. AS misregulation, caused by either dysregulation or mutation of splicing factors, has been shown to be involved in cancer development and progression, making splicing factors suitable targets for cancer therapy. In recent years, various types of pharmacological modulators, such as small molecules and oligonucleotides, targeting distinct components of the splicing machinery, have been under development to treat multiple disorders. Although these approaches have promise, targeting the core spliceosome components disrupts the early stages of spliceosome assembly and can lead to nonspecific and toxic effects. New research directions have been focused on targeting specific splicing factors for a more precise effect. In this Perspective, we will highlight several approaches for targeting splicing factors and their functions and suggest ways to improve their specificity.

Targeting RNA with small molecules: lessons learned from Xist RNA.

Although more than 98% of the human genome is noncoding, nearly all drugs on the market target one of about 700 disease-related proteins. However, an increasing number of diseases are now being attributed to noncoding RNA and the ability to target them would vastly expand the chemical space for drug development. We recently devised a screening strategy based upon affinity-selection mass spectrometry and succeeded in identifying bioactive compounds for the noncoding RNA prototype, Xist. One such compound, termed X1, has drug-like properties and binds specifically to the RepA motif of Xist in vitro and in vivo. Small-angle X-ray scattering analysis reveals that X1 changes the conformation of RepA in solution, thereby explaining the displacement of cognate interacting protein factors (PRC2 and SPEN) and inhibition of X-chromosome inactivation. In this Perspective, we discuss lessons learned from these proof-of-concept experiments and suggest that RNA can be systematically targeted by drug-like compounds to disrupt RNA structure and function.

Structural interaction fingerprints and machine learning for predicting and explaining binding of small molecule ligands to RNA.

Ribonucleic acids (RNAs) play crucial roles in living organisms and some of them, such as bacterial ribosomes and precursor messenger RNA, are targets of small molecule drugs, whereas others, e.g. bacterial riboswitches or viral RNA motifs are considered as potential therapeutic targets. Thus, the continuous discovery of new functional RNA increases the demand for developing compounds targeting them and for methods for analyzing RNA-small molecule interactions. We recently developed fingeRNAt-a software for detecting non-covalent bonds formed within complexes of nucleic acids with different types of ligands. The program detects several non-covalent interactions and encodes them as structural interaction fingerprint (SIFt). Here, we present the application of SIFts accompanied by machine learning methods for binding prediction of small molecules to RNA. We show that SIFt-based models outperform the classic, general-purpose scoring functions in virtual screening. We also employed Explainable Artificial Intelligence (XAI)-the SHapley Additive exPlanations, Local Interpretable Model-agnostic Explanations and other methods to help understand the decision-making process behind the predictive models. We conducted a case study in which we applied XAI on a predictive model of ligand binding to human immunodeficiency virus type 1 trans-activation response element RNA to distinguish between residues and interaction types important for binding. We also used XAI to indicate whether an interaction has a positive or negative effect on binding prediction and to quantify its impact. Our results obtained using all XAI methods were consistent with the literature data, demonstrating the utility and importance of XAI in medicinal chemistry and bioinformatics.

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.

Targeting ubiquitination machinery in cystic fibrosis: Where do we stand?

Cystic Fibrosis (CF) is a genetic disease caused by mutations in CFTR gene expressing the anion selective channel CFTR located at the plasma membrane of different epithelial cells. The most commonly investigated variant causing CF is F508del. This mutation leads to structural defects in the CFTR protein, which are recognized by the endoplasmic reticulum (ER) quality control system. As a result, the protein is retained in the ER and degraded via the ubiquitin-proteasome pathway. Although blocking ubiquitination to stabilize the CFTR protein has long been considered a potential pharmacological approach in CF, progress in this area has been relatively slow. Currently, no compounds targeting this pathway have entered clinical trials for CF. On the other hand, the emergence of Orkambi initially, and notably the subsequent introduction of Trikafta/Kaftrio, have demonstrated the effectiveness of molecular chaperone-based therapies for patients carrying the F508del variant and even showed efficacy against other variants. These treatments directly target the CFTR variant protein without interfering with cell signaling pathways. This review discusses the limits and potential future of targeting protein ubiquitination in CF.

Identification of novel neuroprotectants against vincristine-induced neurotoxicity in iPSC-derived neurons.

Chemotherapy-induced peripheral neuropathy (CIPN) is a disabling side effect of cancer chemotherapy that can often limit treatment options for cancer patients or have life-long neurodegenerative consequences that reduce the patient's quality of life. CIPN is caused by the detrimental actions of various chemotherapeutic agents on peripheral axons. Currently, there are no approved preventative measures or treatment options for CIPN, highlighting the need for the discovery of novel therapeutics and improving our understanding of disease mechanisms. In this study, we utilized human-induced pluripotent stem cell (hiPSC)-derived motor neurons as a platform to mimic axonal damage after treatment with vincristine, a chemotherapeutic used for the treatment of breast cancers, osteosarcomas, and leukemia. We screened a total of 1902 small molecules for neuroprotective properties in rescuing vincristine-induced axon growth deficits. From our primary screen, we identified 38 hit compounds that were subjected to secondary dose response screens. Six compounds showed favorable pharmacological profiles - AZD7762, A-674563, Blebbistatin, Glesatinib, KW-2449, and Pelitinib, all novel neuroprotectants against vincristine toxicity to neurons. In addition, four of these six compounds also showed efficacy against vincristine-induced growth arrest in human iPSC-derived sensory neurons. In this study, we utilized high-throughput screening of a large library of compounds in a therapeutically relevant assay. We identified several novel compounds that are efficacious in protecting different neuronal subtypes from the toxicity induced by a common chemotherapeutic agent, vincristine which could have therapeutic potential in the clinic.

Reporter cell lines to screen for inhibitors or regulators of the KRAS-RAF-MEK1/2-ERK1/2 pathway.

The RAS-regulated RAF-MEK1/2-ERK1/2 signalling pathway is activated in cancer due to mutations in RAS proteins (especially KRAS), BRAF, CRAF, MEK1 and MEK2. Whilst inhibitors of KRASG12C (lung adenocarcinoma) and BRAF and MEK1/2 (melanoma and colorectal cancer) are clinically approved, acquired resistance remains a problem. Consequently, the search for new inhibitors (especially of RAS proteins), new inhibitor modalities and regulators of this pathway, which may be new drug targets, continues and increasingly involves cell-based screens with small molecules or genetic screens such as RNAi, CRISPR or protein interference. Here we describe cell lines that exhibit doxycycline-dependent expression KRASG12V or BRAFV600E and harbour a stably integrated EGR1:EmGFP reporter gene that can be detected by flow cytometry, high-content microscopy or immunoblotting. KRASG12V or BRAFV600E-driven EmGFP expression is inhibited by MEK1/2 or ERK1/2 inhibitors (MEKi and ERKi). BRAFi inhibit BRAFV600E-driven EmGFP expression but enhance the response to KRASG12V, recapitulating paradoxical activation of wild type RAF proteins. In addition to small molecules, expression of iDab6, encoding a RAS-specific antibody fragment inhibited KRASG12V- but not BRAFV600E-driven EmGFP expression. Finally, substitution of EmGFP for a bacterial nitroreductase gene allowed KRASG12V or BRAFV600E to drive cell death in the presence of a pro-drug, which may allow selection of pathway inhibitors that promote survival. These cell lines should prove useful for cell-based screens to identify new regulators of KRAS- or BRAF-dependent ERK1/2 signalling (drug target discovery) as well as screening or triaging 'hits' from drug discovery screens.

A screen of repurposed drugs identifies AMHR2/MISR2 agonists as potential contraceptives.

We identified the anti-Mullerian hormone (also known as Müllerian inhibiting substance or MIS) as an inhibitory hormone that induces long-term contraception in mammals. The type II receptor to this hormone, AMHR2 (also known as MISR2), represents a promising druggable target for the modulation of female reproduction with a mechanism of action distinct from steroidal contraceptives. We designed an in vitro platform to screen and validate small molecules that can activate MISR2 signaling and suppress ovarian folliculogenesis. Using a bone morphogenesis protein (BMP)­response element luciferase reporter cell­based assay, we screened 5,440 compounds from a repurposed drug library. Positive hits in this screen were tested for specificity and potency in luciferase dose­response assays, and biological activity was tested in ex vivo Mullerian duct regression bioassays. Selected candidates were further evaluated in ex vivo follicle/ovary culture assays and in vivo in mice and rats. Here, we report that SP600125, CYC-116, gandotinib, and ruxolitinib can specifically inhibit primordial follicle activation and repress folliculogenesis by stimulating the MISR2 pathway.

Nematode ascarosides attenuate mammalian type 2 inflammatory responses.

Mounting evidence suggests that nematode infection can protect against disorders of immune dysregulation. Administration of live parasites or their excretory/secretory (ES) products has shown therapeutic effects across a wide range of animal models for immune disorders, including asthma. Human clinical trials of live parasite ingestion for the treatment of immune disorders have produced promising results, yet concerns persist regarding the ingestion of pathogenic organisms and the immunogenicity of protein components. Despite extensive efforts to define the active components of ES products, no small molecules with immune regulatory activity have been identified from nematodes. Here we show that an evolutionarily conserved family of nematode pheromones called ascarosides strongly modulates the pulmonary immune response and reduces asthma severity in mice. Screening the inhibitory effects of ascarosides produced by animal-parasitic nematodes on the development of asthma in an ovalbumin (OVA) murine model, we found that administration of nanogram quantities of ascr#7 prevented the development of lung eosinophilia, goblet cell metaplasia, and airway hyperreactivity. Ascr#7 suppressed the production of IL-33 from lung epithelial cells and reduced the number of memory-type pathogenic Th2 cells and ILC2s in the lung, both key drivers of the pathology of asthma. Our findings suggest that the mammalian immune system recognizes ascarosides as an evolutionarily conserved molecular signature of parasitic nematodes. The identification of a nematode-produced small molecule underlying the well-documented immunomodulatory effects of ES products may enable the development of treatment strategies for allergic diseases.

Interplay of precision therapeutics and MD study: Calocybe indica's potentials against cervical cancer and its interaction with VEGF via octadecanoic acid.

The evolving landscape of personalized medicine necessitates a shift from traditional therapeutic interventions towards precision-driven approaches. Embracing this paradigm, our research probes the therapeutic efficacy of the aqueous crude extract (ACE) of Calocybe indica in cervical cancer treatment, merging botanical insights with advanced molecular research. We observed that ACE exerts significant influences on nuclear morphology and cell cycle modulation, further inducing early apoptosis and showcasing prebiotic attributes. Characterization of ACE have identified several phytochemicals including significant presence of octadeconoic acid. Simultaneously, utilizing advanced Molecular Dynamics (MD) simulations, we deciphered the intricate molecular interactions between Vascular Endothelial Growth Factor (VEGF) and Octadecanoic acid to establish C.indica's role as an anticancer agent. Our study delineates Octadecanoic acid's potential as a robust binding partner for VEGF, with comprehensive analyses from RMSD and RMSF profiles highlighting the stability and adaptability of the protein-ligand interactions. Further in-depth thermodynamic explorations via MM-GBSA calculations reveal the binding landscape of the VEGF-Octadecanoic acid complex. Emerging therapeutic innovations, encompassing proteolysis-targeting chimeras (PROTACs) and avant-garde nanocarriers, are discussed in the context of their synergy with compounds like Calocybe indica P&C. This convergence underscores the profound therapeutic potential awaiting clinical exploration. This study offers a holistic perspective on the promising therapeutic avenues facilitated by C. indica against cervical cancer, intricately woven with advanced molecular interactions and the prospective integration of precision therapeutics in modern oncology.

ARTS and small-molecule ARTS mimetics upregulate p53 levels by promoting the degradation of XIAP.

Mutations resulting in decreased activity of p53 tumor suppressor protein promote tumorigenesis. P53 protein levels are tightly regulated through the Ubiquitin Proteasome System (UPS). Several E3 ligases were shown to regulate p53 stability, including MDM2. Here we report that the ubiquitin E3 ligase XIAP (X-linked Inhibitors of Apoptosis) is a direct ligase for p53 and describe a novel approach for modulating the levels of p53 by targeting the XIAP pathway. Using in vivo (live-cell) and in vitro (cell-free reconstituted system) ubiquitylation assays, we show that the XIAP-antagonist ARTS regulates the levels of p53 by promoting the degradation of XIAP. XIAP directly binds and ubiquitylates p53. In apoptotic cells, ARTS inhibits the ubiquitylation of p53 by antagonizing XIAP. XIAP knockout MEFs express higher p53 protein levels compared to wild-type MEFs. Computational screen for small molecules with high affinity to the ARTS-binding site within XIAP identified a small-molecule ARTS-mimetic, B3. This compound stimulates apoptosis in a wide range of cancer cells but not normal PBMC (Peripheral Blood Mononuclear Cells). Like ARTS, the B3 compound binds to XIAP and promotes its degradation via the UPS. B3 binding to XIAP stabilizes p53 by disrupting its interaction with XIAP. These results reveal a novel mechanism by which ARTS and p53 regulate each other through an amplification loop to promote apoptosis. Finally, these data suggest that targeting the ARTS binding pocket in XIAP can be used to increase p53 levels as a new strategy for developing anti-cancer therapeutics.

Targeted therapy in Burkitt lymphoma: Small molecule inhibitors under investigation.

Multiagent chemoimmunotherapy remains the standard of care treatment for Burkitt lymphoma leading to a cure in the majority of cases. However, frontline treatment regimens are associated with a significant risk of treatment related toxicity especially in elderly and immunocompromised patients. Additionally, prognosis remains dismal in refractory/relapsed Burkitt lymphoma. Thus, novel therapies are required to not only improve outcomes in relapsed/refractory Burkitt lymphoma but also minimize frontline treatment related toxicities. Recurrent genomic changes and signalling pathway alterations that have been implicated in the Burkitt lymphomagenesis include cell cycle dysregulation, cell proliferation, inhibition of apoptosis, epigenetic dysregulation and tonic B-cell receptor-phosphatidylinositol 3-kinase (BCR-PI3K) signalling. Here, we will discuss novel targeted therapy approaches using small molecule inhibitors that could pave the way to the future treatment landscape based on the understanding of recurrent genomic changes and signalling pathway alterations in the lymphomagenesis of adult Burkitt lymphoma.

AGA Clinical Practice Update on Management of Inflammatory Bowel Disease in Patients With Malignancy: Commentary.

DESCRIPTION: The purpose of this American Gastroenterological Association (AGA) Institute Clinical Practice Update (CPU) Commentary is to discuss the risks of various malignancies in patients with inflammatory bowel diseases (IBD) and the impact of the available medical therapies on these risks. The CPU will also guide the approach to the patient with IBD who develops a malignancy or the patient with a history of cancer in terms of IBD medication management. METHODS: This CPU was commissioned and approved by the AGA Institute CPU committee and the AGA Governing Board to provide timely guidance on a topic of high clinical importance to the AGA membership and underwent internal peer review by the CPU committee and external peer review through standard procedures of Clinical Gastroenterology and Hepatology. This communication incorporates important and recently published studies in the field, and it reflects the experiences of the authors who are experts in the diagnosis and management of IBD.

Comparative Efficacy of Biologics and Small Molecule in Ulcerative Colitis: A Systematic Review and Network Meta-analysis.

BACKGROUND & AIMS: Treatment options for moderate to severe ulcerative colitis (UC) are increasing rapidly, but the lack of comparative efficacy trials makes treatment choices a clinical challenge. This network-meta-analysis aimed to compare the relative efficacy of biologics and small molecules in achieving remission in patients with moderate to severe UC. METHODS: The literature was searched up to May 2024. Phase 3 placebo or active comparator randomized controlled trials (RCTs) were included. The primary outcome was induction and maintenance of endoscopic improvement (Mayo endoscopic score [MES] ≤1). Secondary outcomes were the induction and maintenance of clinical remission, endoscopic (MES = 0) and histological remission. A sub-analysis was performed based on the RCT design and previous exposure to biologic therapy. RESULTS: We identified 36 studies that met our inclusion criteria, with 14,270 patients with UC. Upadacitinib ranked highest in inducing clinical remission (99.6%), and endoscopic improvement (99.2%), followed by risankizumab (91.4%) and (82.3%) respectively. In maintenance of endoscopic improvement, upadacitinib ranked first (98.6%) followed by filgotinib 200 mg (79.2%). Risankizumab ranked first in the induction of histological remission (89.4%). Followed by guselkumab (88.3%). Upadacitinib ranked first (93.1%) in maintaining histological remission followed by guselkumab (89.5%). CONCLUSION: Upadacitinib appears to be superior to other therapies in achieving clinical remission, endoscopic improvement and remission, and histological remission. Furthermore, novel biologics such as risankizumab and guselkumab ranked high in achieving these outcomes. This study highlights the efficacy of small molecule drugs and novel selective IL-23s as alternatives to other biologics.

Development of a cellular model to study CCR8 signaling in tumor-infiltrating regulatory T cells.

The human CC chemokine receptor 8 (CCR8) is specifically expressed on tumor-infiltrating regulatory T cells (TITRs) and is a promising drug target for cancer immunotherapy. However, the role of CCR8 signaling in TITR biology and the effectiveness of CCR8 small molecule antagonists as TITR-targeting immunotherapy remain subjects of ongoing debate. In this work, we generated a novel cellular model of TITRs by culturing peripheral blood mononuclear cell-derived regulatory T cells in medium containing tumor cell-conditioned medium, CD3/CD28 activator, interleukin-2 and 1α,25-dihydroxyvitamin D3. This cellular model (named TITR mimics) highly and stably expressed a series of TITR signature molecules, including CCR8, FOXP3, CD30, CD39, CD134, CD137, TIGIT and Tim-3. Moreover, TITR mimics displayed robust in vitro immunosuppressive activity. To unravel the functional role of CCR8 in TITR mimics, a chemotaxis assay was performed showing strong and CCR8-specific migration toward CCL1, the natural chemokine agonist of CCR8. However, either stimulation (with CCL1) or blocking (with the small molecule antagonist NS-15) of CCR8 signaling did not affect the immunosuppressive activity, proliferation and survival of TITR mimics. Collectively, our work provides a method for the generation of TITR mimics in vitro, which can be used to study TITR biology and to evaluate drug candidates targeting TITRs. Furthermore, our findings suggest that CCR8 signaling primarily regulates migration of these cells.

Endosomal recycling inhibitors downregulate estrogen receptor-alpha and synergise with endocrine therapies.

PURPOSE: Breast cancer (BC) accounts for roughly 30% of new cancers diagnosed in women each year; thus, this cancer type represents a substantial burden for people and health care systems. Despite the existence of effective therapies to treat BC, drug resistance remains a problem and is a major cause of treatment failure. Therefore, new drugs and treatment regimens are urgently required to overcome resistance. Recent research indicates that inhibition of the endosomal recycling pathway, an intracellular membrane trafficking pathway that returns endocytosed proteins back to the plasma membrane, may be a promising strategy to downregulate clinically relevant cell surface proteins such as HER2 and HER3, and to overcome drug resistance. METHODS: To investigate the molecular mechanism of action of an endosomal recycling inhibitor (ERI) called primaquine, we performed a reverse-phase protein array (RPPA) assay using a HER2-positive breast cancer cell line. The RPPA findings were confirmed by Western blot and RT-qPCR in several BC cell lines. Novel drug combinations were tested by MTT cell viability and clonogenic assays. RESULTS: Among the signalling molecules downregulated by ERIs were estrogen receptor-alpha (ER-α) and androgen receptor. We confirmed this finding in other breast cancer cell lines and show that downregulation occurs at the transcriptional level. We also found that ERIs synergise with tamoxifen, a standard-of-care therapy for breast cancer. DISCUSSION: Our data suggest that combining ERIs with hormone receptor antagonists may enhance their efficacy and reduce the emergence of drug resistance.

GNN-DDAS: Drug discovery for identifying anti-schistosome small molecules based on graph neural network.

Schistosomiasis is a tropical disease that poses a significant risk to hundreds of millions of people, yet often goes unnoticed. While praziquantel, a widely used anti-schistosome drug, has a low cost and a high cure rate, it has several drawbacks. These include ineffectiveness against schistosome larvae, reduced efficacy in young children, and emerging drug resistance. Discovering new and active anti-schistosome small molecules is therefore critical, but this process presents the challenge of low accuracy in computer-aided methods. To address this issue, we proposed GNN-DDAS, a novel deep learning framework based on graph neural networks (GNN), designed for drug discovery to identify active anti-schistosome (DDAS) small molecules. Initially, a multi-layer perceptron was used to derive sequence features from various representations of small molecule SMILES. Next, GNN was employed to extract structural features from molecular graphs. Finally, the extracted sequence and structural features were then concatenated and fed into a fully connected network to predict active anti-schistosome small molecules. Experimental results showed that GNN-DDAS exhibited superior performance compared to the benchmark methods on both benchmark and real-world application datasets. Additionally, the use of GNNExplainer model allowed us to analyze the key substructure features of small molecules, providing insight into the effectiveness of GNN-DDAS. Overall, GNN-DDAS provided a promising solution for discovering new and active anti-schistosome small molecules.