Biology subjects

Muratov, E. N.

Publications and source records attributed to Muratov, E. N..

3 recordsLinked to original sources

bioRxiv2025

Multimodal Cross-Attentive Graph-Based Framework for Predicting In Vivo Endocrine Disruptors

Endocrine hazard assessment needs models that are accurate and mechanistically transparent. We present a multimodal cross-attentive graph framework that fuses molecular graphs with adverse-outcome-pathway (AOP)-anchored assay signals to predict organism-level outcomes in the OECD Hershberger and uterotrophic assays. In Tier-1, multitask GNNs learn ER/AR molecular-initiating and key events across 46 ToxCast/Tox21 assays. In Tier-2, a cross-attentive multimodal GNN integrates Tier-1 pathway signals with molecular graphs, achieving AUROC{square}={square}0.90 (Hershberger) and 0.96 (uterotrophic). External validation on literature compounds showed 84% concordance (Hershberger 15/18; uterotrophic 22/26). Bidirectional cross-attention links molecular substructures to pathway assays and vice-versa, while counterfactual perturbations rank assays and structural motifs most responsible for each decision. The framework couples high accuracy with assay-traceable explanations, supporting targeted testing within the Integrated Approaches.

pharmacology and toxicology↗

bioRxiv2024

Dona Flor and her two husbands: Discovery of novel HDAC6/AKT2 inhibitors for myeloid cancer treatment

Hematological cancer treatment with hybrid kinase/HDAC inhibitors is a novel strategy to overcome the challenge of acquired resistance to drugs. We collected IC50 datasets from the ChEMBL database for 13 cancer cell lines (72 h cytotoxicity, measured by MTT), known inhibitors for 38 kinases, and 10 HDACs isoforms, that we identified by target fishing and literature review. The data was subjected to rigorous biological and chemical curation leaving the final datasets ranging from 76 to 8173 compounds depending on the target. We generated Random Forest classification models, whereby 14 showed greater than 80% predictability after 5-fold external cross-validation. We screened 30 hybrid kinase/HDAC inhibitor analogs through each of these models. Fragment-contribution maps were constructed to aid the understanding of SARs and the optimization of these compounds as selective kinase/HDAC inhibitors for cancer treatment. Among the predicted compounds, 9 representative hybrids were synthesized and subjected to biological evaluation to validate the models. We observed high hit rates after biological testing for the following models: K562 (62.5%), MV4-11 (75.0%), MM1S (100%), NB-4 (62.5%), U937 (75.0), and HDAC6 (86.0%). This aided the identification of 6b and 6k as potent anticancer inhibitors with IC50 of 0.2-0.8 {micro}M in three cancer cell lines, linked to HDAC6 inhibition below 2 nM, and blockade of AKT2 phosphorylation at 2 M, validating the ability of our models to predict novel drug candidates. Graphical Abstract O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=47 SRC="FIGDIR/small/626092v1_ufig1.gif" ALT="Figure 1"> View larger version (13K): org.highwire.dtl.DTLVardef@76705dorg.highwire.dtl.DTLVardef@1cb1d32org.highwire.dtl.DTLVardef@1e9cbdforg.highwire.dtl.DTLVardef@47b819_HPS_FORMAT_FIGEXP M_FIG C_FIG HighlightsO_LINovel kinase/HDAC inhibitors for cancer treatment were found using machine learning C_LIO_LI61 QSAR models for hematological cancers and its targets were built and validated C_LIO_LIK562, MV4-11, MM1S, NB-4, U937, and HDAC6 models had hit rates above 62.5% in tests C_LIO_LI6b and 6k presented potent IC50 of 0.2-0.8 {micro}M in three cancer cell lines C_LIO_LI6b and 6k inhibited HDAC6 below 2 nM, and blockade of AKT2 phosphorylation at 2 M C_LI

cancer biology↗

bioRxiv2020

Discovery of Synergistic and Antagonistic Drug Combinations against SARS-CoV-2 In Vitro

COVID-19 is undoubtedly the most impactful viral disease of the current century, afflicting millions worldwide. As yet, there is not an approved vaccine, as well as limited options from existing drugs for treating this disease. We hypothesized that combining drugs with independent mechanisms of action could result in synergy against SARS-CoV-2. Using in silico approaches, we prioritized 73 combinations of 32 drugs with potential activity against SARS-CoV-2 and then tested them in vitro. Overall, we identified 16 synergistic and 8 antagonistic combinations, 4 of which were both synergistic and antagonistic in a dose-dependent manner. Among the 16 synergistic cases, combinations of nitazoxanide with three other compounds (remdesivir, amodiaquine and umifenovir) were the most notable, all exhibiting significant synergy against SARS-CoV-2. The combination of nitazoxanide, an FDA-approved drug, and remdesivir, FDA emergency use authorization for the treatment of COVID-19, demonstrate a strong synergistic interaction. Notably, the combination of remdesivir and hydroxychloroquine demonstrated strong antagonism. Overall, our results emphasize the importance of both drug repurposing and preclinical testing of drug combinations for potential therapeutic use against SARS-CoV-2 infections.

microbiology↗