Search

Developments in computational omics technologies have provided new means to access the hidden diversity of natural products, unearthing new potential for drug discovery. In parallel, artificial intelligence approaches such as machine learning have led to exciting developments in the computational drug design field, facilitating biological activity prediction and de novo drug design for molecular targets of interest. Here, we describe current and future synergies between these developments to effectively identify drug candidates from the plethora of molecules produced by nature. We also discuss how to address key challenges in realizing the potential of these synergies, such as the need for high-quality datasets to train deep learning algorithms and appropriate strategies for algorithm validation.

Chromatin-binding proteins are critical regulators of cell state in haematopoiesis1,2. Acute leukaemias driven by rearrangement of the mixed lineage leukaemia 1 gene (KMT2Ar) or mutation of the nucleophosmin gene (NPM1) require the chromatin adapter protein menin, encoded by the MEN1gene, to sustain aberrant leukaemogenic gene expression programs3–5. In a phase 1 first-in-human clinical trial, the menin inhibitor revumenib, which is designed to disrupt the menin–MLL1 interaction, induced clinical responses in patients with leukaemia with KMT2Ar or mutated NPM1(ref. 6). Here we identified somatic mutations in MEN1at the revumenib–menin interface in patients with acquired resistance to menin inhibition. Consistent with the genetic data in patients, inhibitor–menin interface mutations represent a conserved mechanism of therapeutic resistance in xenograft models and in an unbiased base-editor screen. These mutants attenuate drug–target binding by generating structural perturbations that impact small-molecule binding but not the interaction with the natural ligand MLL1, and prevent inhibitor-induced eviction of menin and MLL1 from chromatin. To our knowledge, this study is the first to demonstrate that a chromatin-targeting therapeutic drug exerts sufficient selection pressure in patients to drive the evolution of escape mutants that lead to sustained chromatin occupancy, suggesting a common mechanism of therapeutic resistance.

Computational methods such as machine learning approaches have a strong track record of success in predicting the outcomes of in vitro assays. In contrast, their ability to predict in vivo endpoints is more limited due to the high number of parameters and processes that may influence the outcome. Recent studies have shown that the combination of chemical and biological data can yield better models for in vivo endpoints. The ChemBioSim approach presented in this work aims to enhance the performance of conformal prediction models for in vivo endpoints by combining chemical information with (predicted) bioactivity assay outcomes. Three in vivo toxicological endpoints, capturing genotoxic (MNT), hepatic (DILI), and cardiological (DICC) issues, were selected for this study due to their high relevance for the registration and authorization of new compounds. Since the sparsity of available biological assay data is challenging for predictive modeling, predicted bioactivity descriptors were introduced instead. Thus, a machine learning model for each of the 373 collected biological assays was trained and applied on the compounds of the in vivo toxicity data sets. Besides the chemical descriptors (molecular fingerprints and physicochemical properties), these predicted bioactivities served as descriptors for the models of the three in vivo endpoints. For this study, a workflow based on a conformal prediction framework (a method for confidence estimation) built on random forest models was developed. Furthermore, the most relevant chemical and bioactivity descriptors for each in vivo endpoint were preselected with lasso models. The incorporation of bioactivity descriptors increased the mean F1 scores of the MNT model from 0.61 to 0.70 and for the DICC model from 0.72 to 0.82 while the mean efficiencies increased by roughly 0.10 for both endpoints. In contrast, for the DILI endpoint, no significant improvement in model performance was observed. Besides pure performance improvements, an analysis of the most important bioactivity features allowed detection of novel and less intuitive relationships between the predicted biological assay outcomes used as descriptors and the in vivo endpoints. This study presents how the prediction of in vivo toxicity endpoints can be improved by the incorporation of biological information—which is not necessarily captured by chemical descriptors—in an automated workflow without the need for adding experimental workload for the generation of bioactivity descriptors as predicted outcomes of bioactivity assays were utilized. All bioactivity CP models for deriving the predicted bioactivities, as well as the in vivo toxicity CP models, can be freely downloaded from https://doi.org/10.5281/zenodo.4761225.

Protein kinases play a crucial role in many cell signaling processes, making them one of the most important families of drug targets. In this context, fragment-based drug design strategies have been successfully applied to develop novel kinase inhibitors. These strategies usually follow a knowledge-driven approach to optimize a focused set of fragments to a potent kinase inhibitor. Alternatively, KinFragLib explores and extends the chemical space of kinase inhibitors using data-driven fragmentation and recombination. The method builds on available structural kinome data from the KLIFS database for over 2500 kinase DFG-in structures cocrystallized with noncovalent kinase ligands. The computational fragmentation method splits the ligands into fragments with respect to their 3D proximity to six predefined functionally relevant subpocket centers. The resulting fragment library consists of six subpocket pools with over 7000 fragments, available at https://github.com/volkamerlab/KinFragLib. KinFragLib offers two main applications: on the one hand, in-depth analyses of the chemical space of known kinase inhibitors, subpocket characteristics, and connections, and on the other hand, subpocket-informed recombination of fragments to generate potential novel inhibitors. The latter showed that recombining only a subset of 624 representative fragments generated 6.7 million molecules. This combinatorial library contains, besides some known kinase inhibitors, more than 99% novel chemical matter compared to ChEMBL and 63% molecules compliant with Lipinski’s rule of five.

Alchemical free-energy calculations are now widely used to drive or maintain potency in small-molecule lead optimization with a roughly 1 kcal/mol accuracy. Despite this, the potential to use free-energy calculations to drive optimization of compound selectivity among two similar targets has been relatively unexplored in published studies. In the most optimistic scenario, the similarity of binding sites might lead to a fortuitous cancellation of errors and allow selectivity to be predicted more accurately than affinity. Here, we assess the accuracy with which selectivity can be predicted in the context of small-molecule kinase inhibitors, considering the very similar binding sites of human kinases CDK2 and CDK9 as well as another series of ligands attempting to achieve selectivity between the more distantly related kinases CDK2 and ERK2. Using a Bayesian analysis approach, we separate systematic from statistical errors and quantify the correlation in systematic errors between selectivity targets. We find that, in the CDK2/CDK9 case, a high correlation in systematic errors suggests that free-energy calculations can have significant impact in aiding chemists in achieving selectivity, while in more distantly related kinases (CDK2/ERK2), the correlation in systematic error suggests that fortuitous cancellation may even occur between systems that are not as closely related. In both cases, the correlation in systematic error suggests that longer simulations are beneficial to properly balance statistical error with systematic error to take full advantage of the increase in apparent free-energy calculation accuracy in selectivity prediction.

The tyrosine phosphatase SHP2 controls the activity of pivotal signaling pathways, including MAPK, JAK-STAT, and PI3K-Akt. Aberrant SHP2 activity leads to uncontrolled cell proliferation, tumorigenesis, and metastasis. SHP2 signaling was recently linked to drug resistance against cancer medications such as MEK and BRAF inhibitors. In this work, we present the development of a novel class of azaindole SHP2 inhibitors. We applied scaffold hopping and bioisosteric replacement concepts to eliminate unwanted structural motifs and to improve the inhibitor characteristics of the previously reported pyrazolone SHP2 inhibitors. The most potent azaindole 45inhibits SHP2 with an IC50= 0.031 μM in an enzymatic assay and with an IC50= 2.6 μM in human pancreas cells (HPAF-II). Evaluation in a series of cellular assays for metastasis and drug resistance demonstrated efficient SHP2 blockade. Finally, 45inhibited proliferation of two cancer cell lines that are resistant to cancer drugs and diminished ERK signaling.

Molecular Property Prediction (MPP) is vital for drug discovery, crop protection, and environmental science. Over the last decades, diverse computational techniques have been developed, from using simple physical and chemical properties and molecular fingerprints in statistical models and classical machine learning to advanced deep learning approaches. In this review, we aim to distill insights from current research on employing transformer models for MPP. We analyze the currently available models and explore key questions that arise when training and fine-tuning a transformer model for MPP. These questions encompass the choice and scale of the pretraining data, optimal architecture selections, and promising pretraining objectives. Our analysis highlights areas not yet covered in current research, inviting further exploration to enhance the field’s understanding. Additionally, we address the challenges in comparing different models, emphasizing the need for standardized data splitting and robust statistical analysis.

Drug discovery pipelines nowadays rely on machine learning models to explore and evaluate large chemical spaces. While including 3D structural information is considered beneficial, structural models are hindered by the availability of protein–ligand complex structures. Exemplified for kinase drug discovery, we address this issue by generating kinase-ligand complex data using template docking for the kinase compound subset of available ChEMBL assay data. To evaluate the benefit of the created complex data, we use it to train a structure-based E(3)-invariant graph neural network. Our evaluation shows that binding affinities can be predicted with significantly higher precision by models that take synthetic binding poses into account compared to ligand- or drug-target interaction models alone.

Open-source workflows have become more and more an integral part of computer-aided drug design (CADD) projects since they allow reproducible and shareable research that can be easily transferred to other projects. Setting up, understanding, and applying such workflows involves either coding or using workflow managers that offer a graphical user interface. We previously reported the TeachOpenCADD teaching platform that provides interactive Jupyter Notebooks (talktorials) on central CADD topics using open-source data and Python packages. Here we present the conversion of these talktorials to KNIME workflows that allow users to explore our teaching material without any line of code. TeachOpenCADD KNIME workflows are freely available on the KNIME Hub: https://hub.knime.com/volkamerlab/space/TeachOpenCADD.

Target deconvolution is a vital initial step in preclinical drug development to determine research focus and strategy. In this respect, computational target prediction is used to identify the most probable targets of an orphan ligand or the most similar targets to a protein under investigation. Applications range from the fundamental analysis of the mode-of-action over polypharmacology or adverse effect predictions to drug repositioning. Here, we provide a review on published ligand- and target-based as well as hybrid approaches for computational target prediction, together with current limitations and future directions.

Many doctoral students and postdoctoral fellows face at some point in their career the decision between continuing in academia or pursuing a job in industry. Both career paths come with their advantages and disadvantages as well as associated clichés. Our scientific journeys have led us from an university Ph.D. degree to an industrial postdoctoral stay and back to a young faculty position in academia. In this perspective, we share our experiences while changing perspectives. We will discuss the insights we gained through the phase as industrial postdoctoral fellows, the motivation to return and take up a young faculty position in academia, and the freedom and the burden of starting out as a principal investigator (PI). We end with our thoughts on “quo vadis” computational chemistry.

Protein kinases are among the most important drug targets because their dysregulation can cause cancer, inflammatory and degenerative diseases, and many more. Developing selective inhibitors is challenging due to the highly conserved binding sites across the roughly 500 human kinases. Thus, detecting subtle similarities on a structural level can help explain and predict off-targets among the kinase family. Here, we present the kinase-focused, subpocket-enhanced KiSSim fingerprint (Kinase Structural Similarity). The fingerprint builds on the KLIFS pocket definition, composed of 85 residues aligned across all available protein kinase structures, which enables residue-by-residue comparison without a computationally expensive alignment. The residues’ physicochemical and spatial properties are encoded within their structural context including key subpockets at the hinge region, the DFG motif, and the front pocket. Since structure was found to contain information complementary to sequence, we used the fingerprint to calculate all-against-all similarities within the structurally covered kinome. We could identify off-targets that are unexpected if solely considering the sequence-based kinome tree grouping; for example, Erlobinib’s known kinase off-targets SLK and LOK show high similarities to the key target EGFR (TK group), although belonging to the STE group. KiSSim reflects profiling data better or at least as well as other approaches such as KLIFS pocket sequence identity, KLIFS interaction fingerprints (IFPs), or SiteAlign. To rationalize observed (dis)similarities, the fingerprint values can be visualized in 3D by coloring structures with residue and feature resolution. We believe that the KiSSim fingerprint is a valuable addition to the kinase research toolbox to guide off-target and polypharmacology prediction. The method is distributed as an open-source Python package on GitHub and as a conda package: https://github.com/volkamerlab/kissim.