Proximity Graph Networks: Predicting Ligand Affinity with Message Passing Neural Networks.

Message passing neural networks (MPNNs) on molecular graphs generate continuous and differentiable encodings of small molecules with state-of-the-art performance on protein-ligand complex scoring tasks. Here, we describe the proximity graph network (PGN) package, an open-source toolkit that constructs ligand-receptor graphs based on atom proximity and allows users to rapidly apply and evaluate MPNN architectures for a broad range of tasks. We demonstrate the utility of PGN by introducing benchmarks for affinity and docking score prediction tasks. Graph networks generalize better than fingerprint-based models and perform strongly for the docking score prediction task. Overall, MPNNs with proximity graph data structures augment the prediction of ligand-receptor complex properties when ligand-receptor data are available.

CREMP: Conformer-rotamer ensembles of macrocyclic peptides for machine learning.

Computational and machine learning approaches to model the conformational landscape of macrocyclic peptides have the potential to enable rational design and optimization. However, accurate, fast, and scalable methods for modeling macrocycle geometries remain elusive. Recent deep learning approaches have significantly accelerated protein structure prediction and the generation of small-molecule conformational ensembles, yet similar progress has not been made for macrocyclic peptides due to their unique properties. Here, we introduce CREMP, a resource generated for the rapid development and evaluation of machine learning models for macrocyclic peptides. CREMP contains 36,198 unique macrocyclic peptides and their high-quality structural ensembles generated using the Conformer-Rotamer Ensemble Sampling Tool (CREST). Altogether, this new dataset contains nearly 31.3 million unique macrocycle geometries, each annotated with energies derived from semi-empirical extended tight-binding (xTB) DFT calculations. Additionally, we include 3,258 macrocycles with reported passive permeability data to couple conformational ensembles to experiment. We anticipate that this dataset will enable the development of machine learning models that can improve peptide design and optimization for novel therapeutics.

Copper-catalyzed diastereoselective arylation of tryptophan derivatives: total synthesis of (+)-naseseazines A and B.

A copper-catalyzed arylation of tryptophan derivatives is reported. The reaction proceeds with high site- and diastereoselectivity to provide aryl pyrroloindoline products in one step from simple starting materials. The utility of this transformation is highlighted in the five-step syntheses of the natural products (+)-naseseazine A and B.

Learning Molecular Representations for Medicinal Chemistry.

The accurate modeling and prediction of small molecule properties and bioactivities depend on the critical choice of molecular representation. Decades of informatics-driven research have relied on expert-designed molecular descriptors to establish quantitative structure-activity and structure-property relationships for drug discovery. Now, advances in deep learning make it possible to efficiently and compactly learn molecular representations directly from data. In this review, we discuss how active research in molecular deep learning can address limitations of current descriptors and fingerprints while creating new opportunities in cheminformatics and virtual screening. We provide a concise overview of the role of representations in cheminformatics, key concepts in deep learning, and argue that learning representations provides a way forward to improve the predictive modeling of small molecule bioactivities and properties.

Interpretable classification of Alzheimer's disease pathologies with a convolutional neural network pipeline.

Neuropathologists assess vast brain areas to identify diverse and subtly-differentiated morphologies. Standard semi-quantitative scoring approaches, however, are coarse-grained and lack precise neuroanatomic localization. We report a proof-of-concept deep learning pipeline that identifies specific neuropathologies-amyloid plaques and cerebral amyloid angiopathy-in immunohistochemically-stained archival slides. Using automated segmentation of stained objects and a cloud-based interface, we annotate > 70,000 plaque candidates from 43 whole slide images (WSIs) to train and evaluate convolutional neural networks. Networks achieve strong plaque classification on a 10-WSI hold-out set (0.993 and 0.743 areas under the receiver operating characteristic and precision recall curve, respectively). Prediction confidence maps visualize morphology distributions at high resolution. Resulting network-derived amyloid beta (Aß)-burden scores correlate well with established semi-quantitative scores on a 30-WSI blinded hold-out. Finally, saliency mapping demonstrates that networks learn patterns agreeing with accepted pathologic features. This scalable means to augment a neuropathologist's ability suggests a route to neuropathologic deep phenotyping.

Adversarial Controls for Scientific Machine Learning.

New machine learning methods to analyze raw chemical and biological data are now widely accessible as open-source toolkits. This positions researchers to leverage powerful, predictive models in their own domains. We caution, however, that the application of machine learning to experimental research merits careful consideration. Machine learning algorithms readily exploit confounding variables and experimental artifacts instead of relevant patterns, leading to overoptimistic performance and poor model generalization. In parallel to the strong control experiments that remain a cornerstone of experimental research, we advance the concept of adversarial controls for scientific machine learning: the design of exacting and purposeful experiments to ensure that predictive performance arises from meaningful models.

Comment on "Predicting reaction performance in C-N cross-coupling using machine learning".

Ahneman et al (Reports, 13 April 2018) applied machine learning models to predict C-N cross-coupling reaction yields. The models use atomic, electronic, and vibrational descriptors as input features. However, the experimental design is insufficient to distinguish models trained on chemical features from those trained solely on random-valued features in retrospective and prospective test scenarios, thus failing classical controls in machine learning.

A 15-step synthesis of (+)-ryanodol.

(+)-Ryanodine and (+)-ryanodol are complex diterpenoids that modulate intracellular calcium-ion release at ryanodine receptors, ion channels critical for skeletal and cardiac muscle excitation-contraction coupling and synaptic transmission. Chemical derivatization of these diterpenoids has demonstrated that certain peripheral structural modifications can alter binding affinity and selectivity among ryanodine receptor isoforms. Here, we report a short chemical synthesis of (+)-ryanodol that proceeds in only 15 steps from the commercially available terpene (S)-pulegone. The efficiency of the synthesis derives from the use of a Pauson-Khand reaction to rapidly build the carbon framework and a SeO2-mediated oxidation to install three oxygen atoms in a single step. This work highlights how strategic C-O bond constructions can streamline the synthesis of polyhydroxylated terpenes by minimizing protecting group and redox adjustments.

A Mild and General Larock Indolization Protocol for the Preparation of Unnatural Tryptophans.

A mild and general protocol for the Pd(0)-catalyzed heteroannulation of o-bromoanilines and alkynes is described. Application of a Pd(0)/P((t)Bu)3 catalyst system enables the efficient coupling of o-bromoanilines at 60 °C, mitigating deleterious side reactions and enabling access to a broad range of useful unnatural tryptophans. The utility of this new protocol is demonstrated in the highly convergent total synthesis of the bisindole natural product (-)-aspergilazine A.

A Copper-Catalyzed Arylation of Tryptamines for the Direct Synthesis of Aryl Pyrroloindolines.

An operationally simple, copper-catalyzed arylation of N-tosyltryptamines provides direct access to C3-aryl pyrroloindolines. A range of electron-donating and electron-withdrawing substituents is tolerated on both the indole backbone and the aryl electrophile. These reactions occur under ambient temperatures and with equimolar quantities of the coupling partners.