AbLEF: antibody language ensemble fusion for thermodynamically empowered property predictions.

MOTIVATION: Pre-trained protein language and/or structural models are often fine-tuned on drug development properties (i.e. developability properties) to accelerate drug discovery initiatives. However, these models generally rely on a single structural conformation and/or a single sequence as a molecular representation. We present a physics-based model, whereby 3D conformational ensemble representations are fused by a transformer-based architecture and concatenated to a language representation to predict antibody protein properties. Antibody language ensemble fusion enables the direct infusion of thermodynamic information into latent space and this enhances property prediction by explicitly infusing dynamic molecular behavior that occurs during experimental measurement. RESULTS: We showcase the antibody language ensemble fusion model on two developability properties: hydrophobic interaction chromatography retention time and temperature of aggregation (Tagg). We find that (i) 3D conformational ensembles that are generated from molecular simulation can further improve antibody property prediction for small datasets, (ii) the performance benefit from 3D conformational ensembles matches shallow machine learning methods in the small data regime, and (iii) fine-tuned large protein language models can match smaller antibody-specific language models at predicting antibody properties. AVAILABILITY AND IMPLEMENTATION: AbLEF codebase is available at https://github.com/merck/AbLEF.

A machine learning strategy for the identification of key in silico descriptors and prediction models for IgG monoclonal antibody developability properties.

Identification of favorable biophysical properties for protein therapeutics as part of developability assessment is a crucial part of the preclinical development process. Successful prediction of such properties and bioassay results from calculated in silico features has potential to reduce the time and cost of delivering clinical-grade material to patients, but nevertheless has remained an ongoing challenge to the field. Here, we demonstrate an automated and flexible machine learning workflow designed to compare and identify the most powerful features from computationally derived physiochemical feature sets, generated from popular commercial software packages. We implement this workflow with medium-sized datasets of human and humanized IgG molecules to generate predictive regression models for two key developability endpoints, hydrophobicity and poly-specificity. The most important features discovered through the automated workflow corroborate several previous literature reports, and newly discovered features suggest directions for further research and potential model improvement.

Discovery and multimerization of cross-reactive single-domain antibodies against SARS-like viruses to enhance potency and address emerging SARS-CoV-2 variants.

Coronaviruses have been the causative agent of three epidemics and pandemics in the past two decades, including the ongoing COVID-19 pandemic. A broadly-neutralizing coronavirus therapeutic is desirable not only to prevent and treat COVID-19, but also to provide protection for high-risk populations against future emergent coronaviruses. As all coronaviruses use spike proteins on the viral surface to enter the host cells, and these spike proteins share sequence and structural homology, we set out to discover cross-reactive biologic agents targeting the spike protein to block viral entry. Through llama immunization campaigns, we have identified single domain antibodies (VHHs) that are cross-reactive against multiple emergent coronaviruses (SARS-CoV, SARS-CoV-2, and MERS). Importantly, a number of these antibodies show sub-nanomolar potency towards all SARS-like viruses including emergent CoV-2 variants. We identified nine distinct epitopes on the spike protein targeted by these VHHs. Further, by engineering VHHs targeting distinct, conserved epitopes into multi-valent formats, we significantly enhanced their neutralization potencies compared to the corresponding VHH cocktails. We believe this approach is ideally suited to address both emerging SARS-CoV-2 variants during the current pandemic as well as potential future pandemics caused by SARS-like coronaviruses.

Structural insights into selective small molecule activation of PKG1α.

cGMP-dependent protein kinase I-α (PKG1α) is a target for pulmonary arterial hypertension due to its role in the regulation of smooth muscle function. While most work has focused on regulation of cGMP turnover, we recently described several small molecule tool compounds which were capable of activating PKG1α via a cGMP independent pathway. Selected molecules were crystallized in the presence of PKG1α and were found to bind to an allosteric site proximal to the low-affinity nucleotide binding domain. These molecules act to displace the switch helix and cause activation of PKG1α representing a new mechanism for the activation and control of this critical therapeutic path. The described structures are vital to understanding the function and control of this key regulatory pathway.

Optimization and Mechanistic Investigations of Novel Allosteric Activators of PKG1α.

Activation of PKG1α is a compelling strategy for the treatment of cardiovascular diseases. As the main effector of cyclic guanosine monophosphate (cGMP), activation of PKG1α induces smooth muscle relaxation in blood vessels, lowers pulmonary blood pressure, prevents platelet aggregation, and protects against cardiac stress. The development of activators has been mostly limited to cGMP mimetics and synthetic peptides. Described herein is the optimization of a piperidine series of small molecules to yield activators that demonstrate in vitro phosphorylation of vasodilator-stimulated phosphoprotein as well as antiproliferative effects in human pulmonary arterial smooth muscle cells. Hydrogen/deuterium exchange mass spectrometry experiments with the small molecule activators revealed a mechanism of action consistent with cGMP-induced activation, and an X-ray co-crystal structure with a construct encompassing the regulatory domains illustrated a binding mode in an allosteric pocket proximal to the low-affinity cyclic nucleotide-binding domain.

Exploring Deep Learning of Quantum Chemical Properties for Absorption, Distribution, Metabolism, and Excretion Predictions.

Quantum mechanical (QM) descriptors of small molecules have wide applicability in understanding organic reactivity and molecular properties, but the substantial compute cost required for ab initio QM calculations limits their broad usage. Here, we investigate the use of deep learning for predicting QM descriptors, with the goal of enabling usage of near-QM accuracy electronic properties on large molecular data sets such as those seen in drug discovery. Several deep learning approaches have previously been benchmarked on a published data set called QM9, where 12 ground-state properties have been calculated for molecules with up to nine heavy atoms, limited to C, H, N, O, and F elements. To advance the work beyond the QM9 chemical space and enable application to molecules encountered in drug discovery, we extend the QM9 data set by creating a QM9-extended data set covering an additional ∼20,000 molecules containing S and Cl atoms. Using this extended set, we generate new deep learning models as well as leverage ANI-2x models to provide predictions on larger, more diverse molecules common in drug discovery, and we find the models estimate 11 of 12 ground-state properties reasonably. We use the predicted QM descriptors to augment graph convolutional neural network (GCNN) models for selected ADME end points (rat microsomal clearance, hepatic clearance, total clearance, and P-glycoprotein efflux) and found varying degrees of performance improvement compared to nonaugmented GCNN models, including pronounced improvement in P-glycoprotein efflux prediction.

Hexamerization of Anti-SARS CoV IgG1 Antibodies Improves Neutralization Capacity.

The SARS-CoV-2 pandemic and particularly the emerging variants have deepened the need for widely available therapeutic options. We have demonstrated that hexamer-enhancing mutations in the Fc region of anti-SARS-CoV IgG antibodies lead to a noticeable improvement in IC50 in both pseudo and live virus neutralization assay compared to parental molecules. We also show that hexamer-enhancing mutants improve C1q binding to target surface. To our knowledge, this is the first time this format has been explored for application in viral neutralization and the studies provide proof-of-concept for the use of hexamer-enhanced IgG1 molecules as potential anti-viral therapeutics.

Discovery of a new class of integrin antibodies for fibrosis.

Lung fibrosis, or the scarring of the lung, is a devastating disease with huge unmet medical need. There are limited treatment options and its prognosis is worse than most types of cancer. We previously discovered that MK-0429 is an equipotent pan-inhibitor of αv integrins that reduces proteinuria and kidney fibrosis in a preclinical model. In the present study, we further demonstrated that MK-0429 significantly inhibits fibrosis progression in a bleomycin-induced lung injury model. In search of newer integrin inhibitors for fibrosis, we characterized monoclonal antibodies discovered using Adimab's yeast display platform. We identified several potent neutralizing integrin antibodies with unique human and mouse cross-reactivity. Among these, Ab-31 blocked the binding of multiple αv integrins to their ligands with IC50s comparable to those of MK-0429. Furthermore, both MK-0429 and Ab-31 suppressed integrin-mediated cell adhesion and latent TGFß activation. In IPF patient lung fibroblasts, TGFß treatment induced profound αSMA expression in phenotypic imaging assays and Ab-31 demonstrated potent in vitro activity at inhibiting αSMA expression, suggesting that the integrin antibody is able to modulate TGFß action though mechanisms beyond the inhibition of latent TGFß activation. Together, our results highlight the potential to develop newer integrin therapeutics for the treatment of fibrotic lung diseases.

Improvement in ADMET Prediction with Multitask Deep Featurization.

The absorption, distribution, metabolism, elimination, and toxicity (ADMET) properties of drug candidates are important for their efficacy and safety as therapeutics. Predicting ADMET properties has therefore been of great interest to the computational chemistry and medicinal chemistry communities in recent decades. Traditional cheminformatics approaches, using learners such as random forests and deep neural networks, leverage fingerprint feature representations of molecules. Here, we learn the features most relevant to each chemical task at hand by representing each molecule explicitly as a graph. By applying graph convolutions to this explicit molecular representation, we achieve, to our knowledge, unprecedented accuracy in prediction of ADMET properties. By challenging our methodology with rigorous cross-validation procedures and prognostic analyses, we show that deep featurization better enables molecular predictors to not only interpolate but also extrapolate to new regions of chemical space.

Experimental Error, Kurtosis, Activity Cliffs, and Methodology: What Limits the Predictivity of Quantitative Structure-Activity Relationship Models?

Given a particular descriptor/method combination, some quantitative structure-activity relationship (QSAR) datasets are very predictive by random-split cross-validation while others are not. Recent literature in modelability suggests that the limiting issue for predictivity is in the data, not the QSAR methodology, and the limits are due to activity cliffs. Here, we investigate, on in-house data, the relative usefulness of experimental error, distribution of the activities, and activity cliff metrics in determining how predictive a dataset is likely to be. We include unmodified in-house datasets, datasets that should be perfectly predictive based only on the chemical structure, datasets where the distribution of activities is manipulated, and datasets that include a known amount of added noise. We find that activity cliff metrics determine predictivity better than the other metrics we investigated, whatever the type of dataset, consistent with the modelability literature. However, such metrics cannot distinguish real activity cliffs due to large uncertainties in the activities. We also show that a number of modern QSAR methods, and some alternative descriptors, are equally bad at predicting the activities of compounds on activity cliffs, consistent with the assumptions behind "modelability." Finally, we relate time-split predictivity with random-split predictivity and show that different coverages of chemical space are at least as important as uncertainty in activity and/or activity cliffs in limiting predictivity.

Discovery and in Vivo Evaluation of Macrocyclic Mcl-1 Inhibitors Featuring an α-Hydroxy Phenylacetic Acid Pharmacophore or Bioisostere.

Overexpression of the antiapoptotic protein Mcl-1 provides a survival advantage to some cancer cells, making inhibition of this protein an attractive therapeutic target for the treatment of certain types of tumors. Herein, we report our efforts toward the identification of a novel series of macrocyclic Mcl-1 inhibitors featuring an α-hydroxy phenylacetic acid pharmacophore or bioisostere. This work led to the discovery of 1, a potent Mcl-1 inhibitor (IC50 = 19 nM in an OPM-2 cell viability assay) with good pharmacokinetic properties and excellent in vivo efficacy in an OPM-2 multiple myeloma xenograft model.

AMG 176, a Selective MCL1 Inhibitor, Is Effective in Hematologic Cancer Models Alone and in Combination with Established Therapies.

The prosurvival BCL2 family member MCL1 is frequently dysregulated in cancer. To overcome the significant challenges associated with inhibition of MCL1 protein-protein interactions, we rigorously applied small-molecule conformational restriction, which culminated in the discovery of AMG 176, the first selective MCL1 inhibitor to be studied in humans. We demonstrate that MCL1 inhibition induces a rapid and committed step toward apoptosis in subsets of hematologic cancer cell lines, tumor xenograft models, and primary patient samples. With the use of a human MCL1 knock-in mouse, we demonstrate that MCL1 inhibition at active doses of AMG 176 is tolerated and correlates with clear pharmacodynamic effects, demonstrated by reductions in B cells, monocytes, and neutrophils. Furthermore, the combination of AMG 176 and venetoclax is synergistic in acute myeloid leukemia (AML) tumor models and in primary patient samples at tolerated doses. These results highlight the therapeutic promise of AMG 176 and the potential for combinations with other BH3 mimetics. SIGNIFICANCE: AMG 176 is a potent, selective, and orally bioavailable MCL1 inhibitor that induces a rapid commitment to apoptosis in models of hematologic malignancies. The synergistic combination of AMG 176 and venetoclax demonstrates robust activity in models of AML at tolerated doses, highlighting the promise of BH3-mimetic combinations in hematologic cancers.See related commentary by Leber et al., p. 1511.This article is highlighted in the In This Issue feature, p. 1494.

Structure-guided Discovery of Dual-recognition Chemibodies.

Small molecules and antibodies each have advantages and limitations as therapeutics. Here, we present for the first time to our knowledge, the structure-guided design of "chemibodies" as small molecule-antibody hybrids that offer dual recognition of a single target by both a small molecule and an antibody, using DPP-IV enzyme as a proof of concept study. Biochemical characterization demonstrates that the chemibodies present superior DPP-IV inhibition compared to either small molecule or antibody component alone. We validated our design by successfully solving a co-crystal structure of a chemibody in complex with DPP-IV, confirming specific binding of the small molecule portion at the interior catalytic site and the Fab portion at the protein surface. The discovery of chemibodies presents considerable potential for novel therapeutics that harness the power of both small molecule and antibody modalities to achieve superior specificity, potency, and pharmacokinetic properties.

Collaborating to improve the use of free-energy and other quantitative methods in drug discovery.

In May and August, 2016, several pharmaceutical companies convened to discuss and compare experiences with Free Energy Perturbation (FEP). This unusual synchronization of interest was prompted by Schrödinger's FEP+ implementation and offered the opportunity to share fresh studies with FEP and enable broader discussions on the topic. This article summarizes key conclusions of the meetings, including a path forward of actions for this group to aid the accelerated evaluation, application and development of free energy and related quantitative, structure-based design methods.

The prognostic value of standardized reference values for speckle-tracking global longitudinal strain in hypertrophic cardiomyopathy.

Speckle-tracking left ventricular global longitudinal strain (GLS) assessment may provide substantial prognostic information for hypertrophic cardiomyopathy (HCM) patients. Reference values for GLS have been recently published. We aimed to evaluate the prognostic value of standardized reference values for GLS in HCM patients. An analysis of HCM clinic patients who underwent GLS was performed. GLS was defined as normal (more negative or equal to -16%) and abnormal (less negative than -16%) based on recently published reference values. Patients were followed for a composite of events including heart failure hospitalization, sustained ventricular arrhythmia, and all-cause death. The power of GLS to predict outcomes was assessed relative to traditional clinical and echocardiographic variables present in HCM. 79 HCM patients were followed for a median of 22 months (interquartile range 9-30 months) after imaging. During follow-up, 15 patients (19%) met the primary outcome. Abnormal GLS was the only echocardiographic variable independently predictive of the primary outcome [multivariate Hazard ratio 5.05 (95% confidence interval 1.09-23.4, p = 0.038)]. When combined with traditional clinical variables, abnormal GLS remained independently predictive of the primary outcome [multivariate Hazard ratio 5.31 (95 % confidence interval 1.18-24, p = 0.030)]. In a model including the strongest clinical and echocardiographic predictors of the primary outcome, abnormal GLS demonstrated significant incremental benefit for risk stratification [net reclassification improvement 0.75 (95 % confidence interval 0.21-1.23, p < 0.0001)]. Abnormal GLS is an independent predictor of adverse outcomes in HCM patients. Standardized use of GLS may provide significant incremental value over traditional variables for risk stratification.

Development of 2-aminooxazoline 3-azaxanthenes as orally efficacious ß-secretase inhibitors for the potential treatment of Alzheimer's disease.

The ß-site amyloid precursor protein (APP) cleaving enzyme 1 (BACE1) is one of the most hotly pursued targets for the treatment of Alzheimer's disease. We used a structure- and property-based drug design approach to identify 2-aminooxazoline 3-azaxanthenes as potent BACE1 inhibitors which significantly reduced CSF and brain Aß levels in a rat pharmacodynamic model. Compared to the initial lead 2, compound 28 exhibited reduced potential for QTc prolongation in a non-human primate cardiovascular safety model.

Inhibitors of ß-site amyloid precursor protein cleaving enzyme (BACE1): identification of (S)-7-(2-fluoropyridin-3-yl)-3-((3-methyloxetan-3-yl)ethynyl)-5'H-spiro[chromeno[2,3-b]pyridine-5,4'-oxazol]-2'-amine (AMG-8718).

We have previously shown that the aminooxazoline xanthene scaffold can generate potent and orally efficacious BACE1 inhibitors although certain of these compounds exhibited potential hERG liabilities. In this article, we describe 4-aza substitution on the xanthene core as a means to increase BACE1 potency while reducing hERG binding affinity. Further optimization of the P3 and P2' side chains resulted in the identification of 42 (AMG-8718), a compound with a balanced profile of BACE1 potency, hERG binding affinity, and Pgp recognition. This compound produced robust and sustained reductions of CSF and brain Aß levels in a rat pharmacodynamic model and exhibited significantly reduced potential for QTc elongation in a cardiovascular safety model.

Lead optimization and modulation of hERG activity in a series of aminooxazoline xanthene ß-site amyloid precursor protein cleaving enzyme (BACE1) inhibitors.

The optimization of a series of aminooxazoline xanthene inhibitors of ß-site amyloid precursor protein cleaving enzyme 1 (BACE1) is described. An early lead compound showed robust Aß lowering activity in a rat pharmacodynamic model, but advancement was precluded by a low therapeutic window to QTc prolongation in cardiovascular models consistent with in vitro activity on the hERG ion channel. While the introduction of polar groups was effective in reducing hERG binding affinity, this came at the expense of higher than desired Pgp-mediated efflux. A balance of low Pgp efflux and hERG activity was achieved by lowering the polar surface area of the P3 substituent while retaining polarity in the P2' side chain. The introduction of a fluorine in position 4 of the xanthene ring improved BACE1 potency (5-10-fold). The combination of these optimized fragments resulted in identification of compound 40, which showed robust Aß reduction in a rat pharmacodynamic model (78% Aß reduction in CSF at 10 mg/kg po) and also showed acceptable cardiovascular safety in vivo.

Structure-based druggability assessment of the mammalian structural proteome with inclusion of light protein flexibility.

Advances reported over the last few years and the increasing availability of protein crystal structure data have greatly improved structure-based druggability approaches. However, in practice, nearly all druggability estimation methods are applied to protein crystal structures as rigid proteins, with protein flexibility often not directly addressed. The inclusion of protein flexibility is important in correctly identifying the druggability of pockets that would be missed by methods based solely on the rigid crystal structure. These include cryptic pockets and flexible pockets often found at protein-protein interaction interfaces. Here, we apply an approach that uses protein modeling in concert with druggability estimation to account for light protein backbone movement and protein side-chain flexibility in protein binding sites. We assess the advantages and limitations of this approach on widely-used protein druggability sets. Applying the approach to all mammalian protein crystal structures in the PDB results in identification of 69 proteins with potential druggable cryptic pockets.