Search bioRxiv⌕ Search
Home/Archive/bioRxiv

bioRxiv · 10.1101/512459

Kinome-wide activity classification of small molecules by deep learning

Allen, B. K.·Ayad, N. G.·Schürer, S. C.
View original source ↗Export metadata ↓

Abstract

Deep learning is a machine learning technique that attempts to model high-level abstractions in data by utilizing a graph composed of multiple processing layers that experience various linear and non-linear transformations. This technique has been shown to perform well for applications in drug discovery, utilizing structural features of small molecules to predict activity. However, the application of deep learning to discriminating features of kinase inhibitors has not been well explored. Small molecule kinase inhibitors are an important class of anti-cancer agents and have demonstrated impressive clinical efficacy in several different diseases. However, resistance is often observed mediated by adaptive Kinome reprogramming or subpopulation diversity. Therefore, polypharmacology and combination therapies offer potential therapeutic strategies for patients with resistant disease. Their development would benefit from more comprehensive and dense knowledge of small-molecule inhibition across the human Kinome. Because such data is not publicly available, we evaluated multiple machine learning methods to predict small molecule inhibition of 342 kinases using over 650K aggregated bioactivity annotations for over 300K small molecules curated from ChEMBL and the Kinase Knowledge Base (KKB). Our results demonstrated that multi-task deep neural networks outperform classical single-task methods, offering potential towards predicting activity profiles and filling gaps in the available data.\n\n\n\nO_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=76 SRC=\"FIGDIR/small/512459_ufig1.gif\" ALT=\"Figure 1\">\nView larger version (34K):\norg.highwire.dtl.DTLVardef@16045feorg.highwire.dtl.DTLVardef@1935382org.highwire.dtl.DTLVardef@14fb60eorg.highwire.dtl.DTLVardef@39926e_HPS_FORMAT_FIGEXP M_FIG TOC Graphic\n\nC_FIG

Explore related subjects

pharmacology and toxicologyPreprint

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Allen, B. K., Ayad, N. G., Schürer, S. C.. 2019-01-04. Kinome-wide activity classification of small molecules by deep learning. https://doi.org/10.1101/512459

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

Lipid-ASO therapeutics exhibit differential tissue targeted delivery upon systemic or local CNS administration

Antisense oligonucleotides (ASOs) are a powerful therapeutic modality, but their full potential is hindered by pharmacokinetic properties that affect tissue and cellular delivery. Lipid conjugation is increasingly used to modulate ASO's biodistribution and promote extrahepatic activity, yet lipid dependent effects on in vivo functional delivery, particularly in the central nervous system (CNS), remain less explored. Here, we performed a side by side in vivo comparison of cholesterol, palmitic acid (C16:0), docosanoic acid (C22:0), and eicosapentaenoic acid (C20:5) conjugated to a fully phosphorothioated 3 10 3 LNA gapmer ASO targeting the Malat1 long non coding RNA. Lipid-ASO conjugates were administered systemically or locally in the brain of mice and evaluated for tissue level and cellular level distribution by imaging, qPCR and single-cell RNA sequencing, simultaneously annotating cell origin and global transcriptional changes within the cell. Following systemic administration in mice, lipid conjugation improved overall multi organ efficacy compared to unconjugated ASO, but with pronounced tissue specific differences. Single cell sequencing of liver and heart transcriptomes revealed lipid dependent cellular uptake patterns and transcriptional responses distinct from administration of unconjugated ASO. After intracerebroventricular administration, selected fatty acid conjugates enhanced silencing in deep brain regions such as the striatum, whereas cholesterol conjugation impaired functional delivery despite increased CNS retention. Light-sheet microscopy showed restricted parenchymal penetration of cholesterol ASOs compared with broader but heterogeneous distribution of palmitic acid conjugate. Together, these findings demonstrate that lipid identity critically determines ASO efficacy, productive cellular uptake, and regional CNS engagement, emphasizing the need for context specific lipid design in ASO therapeutic development.

pharmacology and toxicology↗
bioRxiv2026

Novel Dissymmetric Ionizable Lipid-Assembled Lipid Nanoparticles for Delivery of Ferroptosis-Related siRNA in Diabetic Treatment

Small interfering RNA (siRNA) enables precise post-transcriptional gene silencing for refractory diseases, yet its clinical translation remains limited by the lack of safe and efficient delivery vectors. Inspired by the dissymmetric alkyl chain architecture of natural membrane phospholipids, we designed and synthesized 34 novel ionizable lipids with dissymmetric hydrophobic tails and formulated them into lipid nanoparticles (LNPs). Through systematic physicochemical and biological assessments, we established clear structure-activity relationships and identified two lead LNPs (O14-LNP, H18a-LNP) with superior endosomal escape capacity, enhanced in vivo gene silencing potency, and favorable biosafety relative to the clinical benchmark MC3-LNP. In both streptozotocin-induced and spontaneous db/db type 2 diabetes (T2D) mouse models, lead LNPs delivering ferroptosis-related siRNAs effectively ameliorated glucose and lipid metabolic disorders, restored islet function, and alleviated hepatic steatosis. This study not only lays a theoretical foundation for the rational design of novel ionizable lipids, but also validates the therapeutic potential of siRNA therapy targeting ferroptosis, providing a versatile delivery platform and targeted therapeutic strategy for the treatment of T2D.

pharmacology and toxicology↗
bioRxiv2019

Predicting kinase inhibitors using bioactivity matrix derived informer sets

Prediction of compounds that are active against a desired biological target is a common step in drug discovery efforts. Virtual screening methods seek some active-enriched fraction of a library for experimental testing. Where data are too scarce to train supervised learning models for compound prioritization, initial screening must provide the necessary data. Commonly, such an initial library is selected on the basis of chemical diversity by some pseudo-random process (for example, the first few plates of a larger library) or by selecting an entire smaller library. These approaches may not produce a sufficient number or diversity of actives. An alternative approach is to select an informer set of screening compounds on the basis of chemogenomic information from previous testing of compounds against a large number of targets. We compare different ways of using chemogenomic data to choose a small informer set of compounds based on previously measured bioactivity data. We develop this Informer-Based-Ranking (IBR) approach using the Published Kinase Inhibitor Sets (PKIS) as the chemogenomic data to select the informer sets. We test the informer compounds on a target that is not part of the chemogenomic data, then predict the activity of the remaining compounds based on the experimental informer data and the chemogenomic data. Through new chemical screening experiments, we demonstrate the utility of IBR strategies in a prospective test on two kinase targets not included in the PKIS. Using limited training data in both retrospective and prospective tests, bioactivity fingerprints based on chemogenomic data outperform chemical fingerprints in predicting active compounds in both standard virtual screening metrics and accurate identification of hits from novel chemical classes. Author SummaryIn the early stages of drug discovery efforts, computational models are used to predict activity and prioritize compounds for experimental testing. New targets commonly lack the data necessary to build effective models, and the screening needed to generate that experimental data can be costly. We seek to improve the efficiency of the initial screening phase, and of the process of prioritizing compounds for subsequent screening. We choose a small informer set of compounds based on publicly available prior screening data on distinct (though related) targets. We then use experimental data on these informer compounds to predict the activity of other compounds in the set against the target of interest. Computational and statistical tools are needed to identify informer compounds and to prioritize other compounds for subsequent phases of screening. Using limited training data, we find that selection of informer compounds on the basis of bioactivity data from previous screening efforts is superior to the traditional approach of selection of a chemically diverse subset of compounds. We demonstrate the success of this approach in retrospective tests on the Published Kinase Inhibitor Sets (PKIS) chemogenomic data and in prospective experimental screens against two additional non-human kinase targets.

pharmacology and toxicology↗