CENsible: Interpretable Insights into Small-Molecule Binding with Context Explanation Networks.

We present a novel and interpretable approach for assessing small-molecule binding using context explanation networks. Given the specific structure of a protein/ligand complex, our CENsible scoring function uses a deep convolutional neural network to predict the contributions of precalculated terms to the overall binding affinity. We show that CENsible can effectively distinguish active vs inactive compounds for many systems. Its primary benefit over related machine-learning scoring functions, however, is that it retains interpretability, allowing researchers to identify the contribution of each precalculated term to the final affinity prediction, with implications for subsequent lead optimization.

BigBind: Learning from Nonstructural Data for Structure-Based Virtual Screening.

Deep learning methods that predict protein-ligand binding have recently been used for structure-based virtual screening. Many such models have been trained using protein-ligand complexes with known crystal structures and activities from the PDBBind data set. However, because PDBbind only includes 20K complexes, models typically fail to generalize to new targets, and model performance is on par with models trained with only ligand information. Conversely, the ChEMBL database contains a wealth of chemical activity information but includes no information about binding poses. We introduce BigBind, a data set that maps ChEMBL activity data to proteins from the CrossDocked data set. BigBind comprises 583 K ligand activities and includes 3D structures of the protein binding pockets. Additionally, we augmented the data by adding an equal number of putative inactives for each target. Using this data, we developed Banana (basic neural network for binding affinity), a neural network-based model to classify active from inactive compounds, defined by a 10 µM cutoff. Our model achieved an AUC of 0.72 on BigBind's test set, while a ligand-only model achieved an AUC of 0.59. Furthermore, Banana achieved competitive performance on the LIT-PCBA benchmark (median EF1% 1.81) while running 16,000 times faster than molecular docking with Gnina. We suggest that Banana, as well as other models trained on this data set, will significantly improve the outcomes of prospective virtual screening tasks.

Interpreting forces as deep learning gradients improves quality of predicted protein structures.

Protein structure predictions from deep learning models like AlphaFold2, despite their remarkable accuracy, are likely insufficient for direct use in downstream tasks like molecular docking. The functionality of such models could be improved with a combination of increased accuracy and physical intuition. We propose a new method to train deep learning protein structure prediction models using molecular dynamics force fields to work toward these goals. Our custom PyTorch loss function, OpenMM-Loss, represents the potential energy of a predicted structure. OpenMM-Loss can be applied to any all-atom representation of a protein structure capable of mapping into our software package, SidechainNet. We demonstrate our method's efficacy by finetuning OpenFold. We show that subsequently predicted protein structures, both before and after a relaxation procedure, exhibit comparable accuracy while displaying lower potential energy and improved structural quality as assessed by MolProbity metrics.

Conformer Generation for Structure-Based Drug Design: How Many and How Good?

Conformer generation, the assignment of realistic 3D coordinates to a small molecule, is fundamental to structure-based drug design. Conformational ensembles are required for rigid-body matching algorithms, such as shape-based or pharmacophore approaches, and even methods that treat the ligand flexibly, such as docking, are dependent on the quality of the provided conformations due to not sampling all degrees of freedom (e.g., only sampling torsions). Here, we empirically elucidate some general principles about the size, diversity, and quality of the conformational ensembles needed to get the best performance in common structure-based drug discovery tasks. In many cases, our findings may parallel "common knowledge" well-known to practitioners of the field. Nonetheless, we feel that it is valuable to quantify these conformational effects while reproducing and expanding upon previous studies. Specifically, we investigate the performance of a state-of-the-art generative deep learning approach versus a more classical geometry-based approach, the effect of energy minimization as a postprocessing step, the effect of ensemble size (maximum number of conformers), and construction (filtering by root-mean-square deviation for diversity) and how these choices influence the ability to recapitulate bioactive conformations and perform pharmacophore screening and molecular docking.

Open-ComBind: harnessing unlabeled data for improved binding pose prediction.

Determination of the bound pose of a ligand is a critical first step in many in silico drug discovery tasks. Molecular docking is the main tool for the prediction of non-covalent binding of a protein and ligand system. Molecular docking pipelines often only utilize the information of one ligand binding to the protein despite the commonly held hypothesis that different ligands share binding interactions when bound to the same receptor. Here we describe Open-ComBind, an easy-to-use, open-source version of the ComBind molecular docking pipeline that leverages information from multiple ligands without known bound structures to enhance pose selection. We first create distributions of feature similarities between ligand pose pairs, comparing near-native poses with all sampled docked poses. These distributions capture the likelihood of observing similar features, such as hydrogen bonds or hydrophobic contacts, in different pose configurations. These similarity distributions are then combined with a per-ligand docking score to enhance overall pose selection by 5% and 4.5% for high-affinity and congeneric series helper ligands, respectively. Open-ComBind reduces the average RMSD of ligands in our benchmark dataset by 9.0%. We provide Open-ComBind as an easy-to-use command line and Python API to increase pose prediction performance at www.github.com/drewnutt/open_combind .

Caregiver survey in glioblastoma focused on cognitive dysfunction: development and results from a multicenter study.

Aim: To develop a cognitive dysfunction (CD) focused questionnaire to evaluate caregiver burden in glioblastoma. Materials & methods: The survey was developed from stakeholder consultations and a pilot study, and disseminated at eight US academic cancer centers. Caregivers self-reported caring for an adult with glioblastoma and CD. Results: The 89-item survey covered demographics, CD symptoms and caregiver burden domains. Among 185 caregivers, most were white, educated females and reported memory problems as the most common CD symptom. An exposure-effect was observed, with increase in number of CD symptoms significantly associated with greater caregiver burden. Conclusion: This questionnaire could guide caregiver interventions and be adapted for use longitudinally, in community cancer settings, and in patients with brain metastases.

Glioblastoma (GBM) is a very aggressive brain cancer. People who have GBM have trouble remembering things and are unable to do things they used to do. These changes can be very hard. Researchers are trying to better understand what it is like for people who take care of people with GBM (or caregivers). In this study, researchers created a new survey for caregivers. The survey included questions about what caregivers see happening in their loved one with GBM. Caregivers said that memory problems were common. Also, when the patient had more problems the caregiver had a harder time, too. Researchers hope to improve the survey and use it in the future for more studies.

Improving ΔΔG Predictions with a Multitask Convolutional Siamese Network.

The lead optimization phase of drug discovery refines an initial hit molecule for desired properties, especially potency. Synthesis and experimental testing of the small perturbations during this refinement can be quite costly and time-consuming. Relative binding free energy (RBFE, also referred to as ΔΔG) methods allow the estimation of binding free energy changes after small changes to a ligand scaffold. Here, we propose and evaluate a Siamese convolutional neural network (CNN) for the prediction of RBFE between two bound ligands. We show that our multitask loss is able to improve on a previous state-of-the-art Siamese network for RBFE prediction via increased regularization of the latent space. The Siamese network architecture is well suited to the prediction of RBFE in comparison to a standard CNN trained on the same data (Pearson's R of 0.553 and 0.5, respectively). When evaluated on a left-out protein family, our Siamese CNN shows variability in its RBFE predictive performance depending on the protein family being evaluated (Pearson's R ranging from -0.44 to 0.97). RBFE prediction performance can be improved during generalization by injecting only a few examples (few-shot learning) from the evaluation data set during model training.

SidechainNet: An all-atom protein structure dataset for machine learning.

Despite recent advancements in deep learning methods for protein structure prediction and representation, little focus has been directed at the simultaneous inclusion and prediction of protein backbone and sidechain structure information. We present SidechainNet, a new dataset that directly extends the ProteinNet dataset. SidechainNet includes angle and atomic coordinate information capable of describing all heavy atoms of each protein structure and can be extended by users to include new protein structures as they are released. In this article, we provide background information on the availability of protein structure data and the significance of ProteinNet. Thereafter, we argue for the potentially beneficial inclusion of sidechain information through SidechainNet, describe the process by which we organize SidechainNet, and provide a software package (https://github.com/jonathanking/sidechainnet) for data manipulation and training with machine learning models.

Virtual Screening with Gnina 1.0.

Virtual screening-predicting which compounds within a specified compound library bind to a target molecule, typically a protein-is a fundamental task in the field of drug discovery. Doing virtual screening well provides tangible practical benefits, including reduced drug development costs, faster time to therapeutic viability, and fewer unforeseen side effects. As with most applied computational tasks, the algorithms currently used to perform virtual screening feature inherent tradeoffs between speed and accuracy. Furthermore, even theoretically rigorous, computationally intensive methods may fail to account for important effects relevant to whether a given compound will ultimately be usable as a drug. Here we investigate the virtual screening performance of the recently released Gnina molecular docking software, which uses deep convolutional networks to score protein-ligand structures. We find, on average, that Gnina outperforms conventional empirical scoring. The default scoring in Gnina outperforms the empirical AutoDock Vina scoring function on 89 of the 117 targets of the DUD-E and LIT-PCBA virtual screening benchmarks with a median 1% early enrichment factor that is more than twice that of Vina. However, we also find that issues of bias linger in these sets, even when not used directly to train models, and this bias obfuscates to what extent machine learning models are achieving their performance through a sophisticated interpretation of molecular interactions versus fitting to non-informative simplistic property distributions.

The 3Dmol.js learning environment: a classroom response system for 3D chemical structures.

Classroom response systems are an important tool in many active learning pedagogies. They support real-time feedback on student learning and promote student engagement, even in large classrooms, by allowing instructors to solicit an answer to a question from all students and show the results. Existing classroom response systems are general purpose and not tailored to the specific needs of a chemistry classroom. In particular, it is not easy to deploy molecular representations except as static images. Here we present the 3Dmol.js learning environment, a classroom response system that uses the open source web-based 3Dmol.js JavaScript framework to provide interactive viewing and querying of 3D molecules. 3Dmol.js is available under a BSD 3-clause open source license, and the learning environment features are all available through http://3dmol.csb.pitt.edu/ without any software installation required.

Convolutional neural network scoring and minimization in the D3R 2017 community challenge.

We assess the ability of our convolutional neural network (CNN)-based scoring functions to perform several common tasks in the domain of drug discovery. These include correctly identifying ligand poses near and far from the true binding mode when given a set of reference receptors and classifying ligands as active or inactive using structural information. We use the CNN to re-score or refine poses generated using a conventional scoring function, Autodock Vina, and compare the performance of each of these methods to using the conventional scoring function alone. Furthermore, we assess several ways of choosing appropriate reference receptors in the context of the D3R 2017 community benchmarking challenge. We find that our CNN scoring function outperforms Vina on most tasks without requiring manual inspection by a knowledgeable operator, but that the pose prediction target chosen for the challenge, Cathepsin S, was particularly challenging for de novo docking. However, the CNN provided best-in-class performance on several virtual screening tasks, underscoring the relevance of deep learning to the field of drug discovery.

Pharmit: interactive exploration of chemical space.

Pharmit (http://pharmit.csb.pitt.edu) provides an online, interactive environment for the virtual screening of large compound databases using pharmacophores, molecular shape and energy minimization. Users can import, create and edit virtual screening queries in an interactive browser-based interface. Queries are specified in terms of a pharmacophore, a spatial arrangement of the essential features of an interaction, and molecular shape. Search results can be further ranked and filtered using energy minimization. In addition to a number of pre-built databases of popular compound libraries, users may submit their own compound libraries for screening. Pharmit uses state-of-the-art sub-linear algorithms to provide interactive screening of millions of compounds. Queries typically take a few seconds to a few minutes depending on their complexity. This allows users to iteratively refine their search during a single session. The easy access to large chemical datasets provided by Pharmit simplifies and accelerates structure-based drug design. Pharmit is available under a dual BSD/GPL open-source license.

Protein-Ligand Scoring with Convolutional Neural Networks.

Computational approaches to drug discovery can reduce the time and cost associated with experimental assays and enable the screening of novel chemotypes. Structure-based drug design methods rely on scoring functions to rank and predict binding affinities and poses. The ever-expanding amount of protein-ligand binding and structural data enables the use of deep machine learning techniques for protein-ligand scoring. We describe convolutional neural network (CNN) scoring functions that take as input a comprehensive three-dimensional (3D) representation of a protein-ligand interaction. A CNN scoring function automatically learns the key features of protein-ligand interactions that correlate with binding. We train and optimize our CNN scoring functions to discriminate between correct and incorrect binding poses and known binders and nonbinders. We find that our CNN scoring function outperforms the AutoDock Vina scoring function when ranking poses both for pose prediction and virtual screening.

Characterization of Thyroid Nodules by 4-Dimensional Computed Tomography: Initial Experience.

OBJECTIVE: We aimed to evaluate the use of 4-dimensional computed tomography (4DCT) for characterization of thyroid nodules. METHODS: Our study drew from 100 consecutive patients with primary hyperparathyroidism who underwent 4D parathyroid CT imaging for adenoma localization. Included subjects had tissue sampling of a thyroid nodule within 3 months of 4DCT. RESULTS: Twenty subjects (18 women and 2 men) had thyroid nodules that were pathologically confirmed. Precontrast nodule attenuation was significantly lower in malignant nodules when compared with benign nodules (36 vs 61 HU, P = 0.05). Arterial phase and delayed phase nodule attenuations were not significantly different in malignant and benign nodules (128 vs 144 HU, P = 0.7; 74 vs 98 HU, P = 0.3). CONCLUSIONS: Our initial experience with a small group of patients was unable to support the use of 4DCT for characterizing thyroid nodules; however, precontrast nodule attenuation was significantly lower in malignant nodules when compared with benign nodules.

Root Cause Analysis: An Examination of Odontogenic Origins of Acute Maxillary Sinusitis in Both Immunocompetent & Immunocompromised Patients.

BACKGROUND AND PURPOSE: Dental and periodontal diseases represent important but often overlooked causes of acute sinusitis. Our goal was to examine the prevalence of potential odontogenic sources of acute maxillary sinusitis according to immune status and their associations with sinusitis. MATERIALS AND METHODS: A retrospective review of maxillofacial computed tomography studies from 2013 to 2014 was performed. Each maxillary sinus and its ipsilateral dentition were evaluated for findings of acute sinusitis and dental/periodontal disease. RESULTS: Eighty-four patients (24 immunocompetent, 60 immunocompromised) had 171 maxillary sinuses that met inclusion criteria for acute maxillary sinusitis. Inspection of dentition revealed oroantral fistula in 1%, periapical lucencies in 16%, and projecting tooth root(s) in 71% of cases. Immunocompromised patients were more likely to have bilateral sinusitis than immunocompetent patients (67% vs 33%, P = 0.005). A paired case-control analysis in a subset of patients with unilateral maxillary sinusitis (n = 39) showed a higher prevalence of periapical lucency in association with sinuses that had an air fluid level-29% of sinuses with a fluid level had periapical lucency compared with 12% without sinus fluid (P = 0.033). CONCLUSIONS: Potential odontogenic sources of acute maxillary sinusitis are highly prevalent in both immunocompetent and immunocompromised patients, although the 2 patient populations demonstrate no difference in the prevalence of these potential odontogenic sources. Periapical lucencies were found to be associated with an ipsilateral sinus fluid level. Increased awareness of the importance of dental and periodontal diseases as key components of maxillofacial computed tomography interpretation would facilitate a more appropriate and timely treatment.

A D3R prospective evaluation of machine learning for protein-ligand scoring.

We assess the performance of several machine learning-based scoring methods at protein-ligand pose prediction, virtual screening, and binding affinity prediction. The methods and the manner in which they were trained make them sufficiently diverse to evaluate the utility of various strategies for training set curation and binding pose generation, but they share a novel approach to classification in the context of protein-ligand scoring. Rather than explicitly using structural data such as affinity values or information extracted from crystal binding poses for training, we instead exploit the abundance of data available from high-throughput screening to approach the problem as one of discriminating binders from non-binders. We evaluate the performance of our various scoring methods in the 2015 D3R Grand Challenge and find that although the merits of some features of our approach remain inconclusive, our scoring methods performed comparably to a state-of-the-art scoring function that was fit to binding affinity data.

Outcome of Patients Discharged From a Heart Failure Disease Management Program following Their Clinical and Echocardiographic Recovery.

OBJECTIVES: Heart failure (HF) is associated with high mortality and frequent hospitalizations. Disease management programs (DMPs) have a favorable impact on patients with HF. No data exist regarding the outcomes of patients discharged from such a program. METHODS: We examined the outcome of patients with severe systolic HF who were discharged from a DMP following full clinical and echocardiographic recovery. Data were reviewed for mortality, emergency room visits, hospitalizations, medication adherence and left ventricular ejection fraction (EF). RESULTS: At enrollment and discharge, the mean EF was 19 and 53%, respectively. At follow-up 46.2 months after discharge, 56% of patients had been to the emergency room, 34% were hospitalized a total of 41 times and 20% had died. In the patients who required hospitalization for HF, the mean EF upon rehospitalization had dropped to 23.4%. CONCLUSIONS: Many patients with initially severe systolic HF who had an almost full recovery in a multidisciplinary DMP had very poor outcomes once they were discharged from the program. It may be appropriate to revisit the practice of discharging patients from DMPs once they have reached a specific clinical target.

Indexing Volumetric Shapes with Matching and Packing.

We describe a novel algorithm for bulk-loading an index with high-dimensional data and apply it to the problem of volumetric shape matching. Our matching and packing algorithm is a general approach for packing data according to a similarity metric. First an approximate k-nearest neighbor graph is constructed using vantage-point initialization, an improvement to previous work that decreases construction time while improving the quality of approximation. Then graph matching is iteratively performed to pack related items closely together. The end result is a dense index with good performance. We define a new query specification for shape matching that uses minimum and maximum shape constraints to explicitly specify the spatial requirements of the desired shape. This specification provides a natural language for performing volumetric shape matching and is readily supported by the geometry-based similarity search (GSS) tree, an indexing structure that maintains explicit representations of volumetric shape. We describe our implementation of a GSS tree for volumetric shape matching and provide a comprehensive evaluation of parameter sensitivity, performance, and scalability. Compared to previous bulk-loading algorithms, we find that matching and packing can construct a GSS-tree index in the same amount of time that is denser, flatter, and better performing, with an observed average performance improvement of 2X.

Shape-based virtual screening with volumetric aligned molecular shapes.

Shape-based virtual screening is an established and effective method for identifying small molecules that are similar in shape and function to a reference ligand. We describe a new method of shape-based virtual screening, volumetric aligned molecular shapes (VAMS). VAMS uses efficient data structures to encode and search molecular shapes. We demonstrate that VAMS is an effective method for shape-based virtual screening and that it can be successfully used as a prefilter to accelerate more computationally demanding search algorithms. Unique to VAMS is a novel minimum/maximum shape constraint query for precisely specifying the desired molecular shape. Shape constraint searches in VAMS are particularly efficient and millions of shapes can be searched in a fraction of a second. We compare the performance of VAMS with two other shape-based virtual screening algorithms a benchmark of 102 protein targets consisting of more than 32 million molecular shapes and find that VAMS provides a competitive trade-off between run-time performance and virtual screening performance.

Clinical orthopedic examination findings in the upper extremity: correlation with imaging studies and diagnostic efficacy.

Different orthopedic tests are used to evaluate internal derangements of joints. Radiologic examinations like magnetic resonance (MR) imaging are ordered on the basis of results of these tests to narrow the clinical diagnosis and formulate a treatment plan. Although these tests are clinically useful, the test terminology can be confusing and the significance of the tests not clearly understood. This article helps explain the clinical jargon of tests performed for the major joints of the upper extremity and their proper use and diagnostic value in conjunction with MR imaging. The article presents a structured algorithmic approach to explain the tests. For each joint, a hierarchy of clinical tests is performed, starting with general observation and range of motion, followed by more specific tests tailored to evaluate individual or grouped anatomic structures. MR imaging findings and clinical tests complement each other in making a final diagnosis. However, because of the varied sensitivity and specificity of the clinical tests and MR imaging, it is important to be familiar with their diagnostic value before making clinical decisions. Knowledge of clinical jargon and the proper use and diagnostic value of orthopedic tests can aid in interpretation of radiologic images by focusing search patterns, thus allowing comprehensive evaluation and optimized reporting. It also enhances communication with the orthopedist, thereby helping maintain continuity of care. Online supplemental material is available for this article.