The effect of imaging modality (magnetic resonance imaging vs. computed tomography) and patient position (supine vs. prone) on target and organ at risk doses in partial breast irradiation.

INTRODUCTION: Conventionally computed tomography (CT) has been used to delineate target volumes in radiotherapy; however, magnetic resonance imaging (MRI) is being continually integrated into clinical practice; therefore, the investigation into targets derived from MRI is warranted. The purpose of this study was to evaluate the impact of imaging modality (MRI vs. CT) and patient positioning (supine vs. prone) on planning target volumes (PTVs) and organs at risk (OARs) for partial breast irradiation (PBI). METHODS: A retrospective data set, of 35 patients, was accessed where each patient had undergone MRI and CT imaging for tangential whole breast radiotherapy in both the supine and prone position. PTVs were defined from seroma cavity (SC) volumes delineated on each respective image, resulting in 4 PTVs per patient. PBI plans were generated with 6MV external beam radiotherapy (EBRT) using the TROG 06.02 protocol guidelines. A prescription of 38.5Gy in 10 fractions was used for all cases. The impact analysis of imaging modality and patient positioning included dose to PTVs, and OARs based on agreed criteria. Statistical analysis was conducted though Mann-Whitey U, Fisher's exact and chi-squared testing (P < 0.005). RESULTS: Twenty-four patients were eligible for imaging analysis. However, positioning analysis could only be investigated on 19 of these data sets. No statistically significant difference was found in OAR doses based on imaging modality. Supine patient position resulted in lower contralateral breast dose (0.10Gy ± 0.35 vs. 0.33Gy ± 0.78, p = 0.011). Prone positioning resulted in a lower dose to ipsilateral lung volumes (10.85Gy ± 11.37 vs. 3.41Gy ± 3.93, P = <0.001). CONCLUSIONS: PBI plans with PTVs derived from MRI exhibited no clinically significant differences when compared to plans created from CT in relation to plan compliance and OAR dose. Patient position requires careful consideration regardless of imaging modality chosen. Although there was no proven superiority of MRI derived target volumes, it indicates that MRI could be considered for PBI target delineation.

Optimal Piecewise Linear Regression Algorithm for QSAR Modelling.

Quantitative Structure-Activity Relationship (QSAR) models have been successfully applied to lead optimisation, virtual screening and other areas of drug discovery over the years. Recent studies, however, have focused on the development of models that are predictive but often not interpretable. In this article, we propose the application of a piecewise linear regression algorithm, OPLRAreg, to develop both predictive and interpretable QSAR models. The algorithm determines a feature to best separate the data into regions and identifies linear equations to predict the outcome variable in each region. A regularisation term is introduced to prevent overfitting problems and implicitly selects the most informative features. As OPLRAreg is based on mathematical programming, a flexible and transparent representation for optimisation problems, the algorithm also permits customised constraints to be easily added to the model. The proposed algorithm is presented as a more interpretable alternative to other commonly used machine learning algorithms and has shown comparable predictive accuracy to Random Forest, Support Vector Machine and Random Generalised Linear Model on tests with five QSAR data sets compiled from the ChEMBL database.

Unexplored therapeutic opportunities in the human genome.

This corrects the article DOI: 10.1038/nrd.2018.14.

Unexplored therapeutic opportunities in the human genome.

A large proportion of biomedical research and the development of therapeutics is focused on a small fraction of the human genome. In a strategic effort to map the knowledge gaps around proteins encoded by the human genome and to promote the exploration of currently understudied, but potentially druggable, proteins, the US National Institutes of Health launched the Illuminating the Druggable Genome (IDG) initiative in 2014. In this article, we discuss how the systematic collection and processing of a wide array of genomic, proteomic, chemical and disease-related resource data by the IDG Knowledge Management Center have enabled the development of evidence-based criteria for tracking the target development level (TDL) of human proteins, which indicates a substantial knowledge deficit for approximately one out of three proteins in the human proteome. We then present spotlights on the TDL categories as well as key drug target classes, including G protein-coupled receptors, protein kinases and ion channels, which illustrate the nature of the unexplored opportunities for biomedical research and therapeutic development.

The impact of imaging modality (CT vs MRI) and patient position (supine vs prone) on tangential whole breast radiation therapy planning.

PURPOSE: The purpose of this study was to evaluate the impact of magnetic resonance imaging (MRI) versus computed tomography (CT)-derived planning target volumes (PTVs), in both supine and prone positions, for whole breast (WB) radiation therapy. METHODS AND MATERIALS: Four WB radiation therapy plans were generated for 28 patients in which PTVs were generated based on CT or MRI data alone in both supine and prone positions. A 6-MV tangential intensity modulated radiation therapy technique was used, with plans designated as ideal, acceptable, or noncompliant. Dose metrics for PTVs and organs at risk were compared to analyze any differences based on imaging modality (CT vs MRI) or patient position (supine vs prone). RESULTS: With respect to imaging modality 2/11 whole breast planning target volume (WB_PTV) dose metrics (percentage of PTV receiving 90% and 110% of prescribed dose) displayed statistically significant differences; however, these differences did not alter the average plan compliance rank. With respect to patient positioning, the odds of having an ideal plan versus a noncompliant plan were higher for the supine position compared with the prone position (P = .026). The minimum distance between the seroma cavity planning target volume (SC_PTV) and the chest wall was increased with prone positioning (P < .001, supine and prone values 1.1 mm and 8.7 mm, respectively). Heart volume was greater in the supine position (P = .005). Heart doses were lower in the supine position than prone (P < .01, mean doses 3.4 ± 1.55 Gy vs 4.4 ± 1.13 Gy for supine vs prone, respectively). Mean lung doses met ideal dose constraints in both positions, but were best spared in the prone position. The contralateral breast maximum dose to 1cc (D1cc) showed significantly lower doses in the supine position (P < .001, 4.64 Gy vs 9.51 Gy). CONCLUSIONS: Planning with PTVs generated from MRI data showed no clinically significant differences from planning with PTVs generated from CT with respect to PTV and doses to organs at risk. Prone positioning within this study reduced mean lung dose and whole heart volumes but increased mean heart and contralateral breast doses compared with supine.

Beyond the hype: deep neural networks outperform established methods using a ChEMBL bioactivity benchmark set.

The increase of publicly available bioactivity data in recent years has fueled and catalyzed research in chemogenomics, data mining, and modeling approaches. As a direct result, over the past few years a multitude of different methods have been reported and evaluated, such as target fishing, nearest neighbor similarity-based methods, and Quantitative Structure Activity Relationship (QSAR)-based protocols. However, such studies are typically conducted on different datasets, using different validation strategies, and different metrics. In this study, different methods were compared using one single standardized dataset obtained from ChEMBL, which is made available to the public, using standardized metrics (BEDROC and Matthews Correlation Coefficient). Specifically, the performance of Naïve Bayes, Random Forests, Support Vector Machines, Logistic Regression, and Deep Neural Networks was assessed using QSAR and proteochemometric (PCM) methods. All methods were validated using both a random split validation and a temporal validation, with the latter being a more realistic benchmark of expected prospective execution. Deep Neural Networks are the top performing classifiers, highlighting the added value of Deep Neural Networks over other more conventional methods. Moreover, the best method ('DNN_PCM') performed significantly better at almost one standard deviation higher than the mean performance. Furthermore, Multi-task and PCM implementations were shown to improve performance over single task Deep Neural Networks. Conversely, target prediction performed almost two standard deviations under the mean performance. Random Forests, Support Vector Machines, and Logistic Regression performed around mean performance. Finally, using an ensemble of DNNs, alongside additional tuning, enhanced the relative performance by another 27% (compared with unoptimized 'DNN_PCM'). Here, a standardized set to test and evaluate different machine learning algorithms in the context of multi-task learning is offered by providing the data and the protocols. Graphical Abstract .

Target Identification of Mycobacterium tuberculosis Phenotypic Hits Using a Concerted Chemogenomic, Biophysical, and Structural Approach.

Mycobacterium phenotypic hits are a good reservoir for new chemotypes for the treatment of tuberculosis. However, the absence of defined molecular targets and modes of action could lead to failure in drug development. Therefore, a combination of ligand-based and structure-based chemogenomic approaches followed by biophysical and biochemical validation have been used to identify targets for Mycobacterium tuberculosis phenotypic hits. Our approach identified EthR and InhA as targets for several hits, with some showing dual activity against these proteins. From the 35 predicted EthR inhibitors, eight exhibited an IC50 below 50 µM against M. tuberculosis EthR and three were confirmed to be also simultaneously active against InhA. Further hit validation was performed using X-ray crystallography yielding eight new crystal structures of EthR inhibitors. Although the EthR inhibitors attain their activity against M. tuberculosis by hitting yet undefined targets, these results provide new lead compounds that could be further developed to be used to potentiate the effect of EthA activated pro-drugs, such as ethionamide, thus enhancing their bactericidal effect.

Shared Consensus Machine Learning Models for Predicting Blood Stage Malaria Inhibition.

The development of new antimalarial therapies is essential, and lowering the barrier of entry for the screening and discovery of new lead compound classes can spur drug development at organizations that may not have large compound screening libraries or resources to conduct high-throughput screens. Machine learning models have been long established to be more robust and have a larger domain of applicability with larger training sets. Screens over multiple data sets to find compounds with potential malaria blood stage inhibitory activity have been used to generate multiple Bayesian models. Here we describe a method by which Bayesian quantitative structure-activity relationship models, which contain information on thousands to millions of proprietary compounds, can be shared between collaborators at both for-profit and not-for-profit institutions. This model-sharing paradigm allows for the development of consensus models that have increased predictive power over any single model and yet does not reveal the identity of any compounds in the training sets.

The ChEMBL database in 2017.

ChEMBL is an open large-scale bioactivity database (https://www.ebi.ac.uk/chembl), previously described in the 2012 and 2014 Nucleic Acids Research Database Issues. Since then, alongside the continued extraction of data from the medicinal chemistry literature, new sources of bioactivity data have also been added to the database. These include: deposited data sets from neglected disease screening; crop protection data; drug metabolism and disposition data and bioactivity data from patents. A number of improvements and new features have also been incorporated. These include the annotation of assays and targets using ontologies, the inclusion of targets and indications for clinical candidates, addition of metabolic pathways for drugs and calculation of structural alerts. The ChEMBL data can be accessed via a web-interface, RDF distribution, data downloads and RESTful web-services.

Open Source Drug Discovery: Highly Potent Antimalarial Compounds Derived from the Tres Cantos Arylpyrroles.

The development of new antimalarial compounds remains a pivotal part of the strategy for malaria elimination. Recent large-scale phenotypic screens have provided a wealth of potential starting points for hit-to-lead campaigns. One such public set is explored, employing an open source research mechanism in which all data and ideas were shared in real time, anyone was able to participate, and patents were not sought. One chemical subseries was found to exhibit oral activity but contained a labile ester that could not be replaced without loss of activity, and the original hit exhibited remarkable sensitivity to minor structural change. A second subseries displayed high potency, including activity within gametocyte and liver stage assays, but at the cost of low solubility. As an open source research project, unexplored avenues are clearly identified and may be explored further by the community; new findings may be cumulatively added to the present work.

Comparison of Magnetic Resonance Imaging and Computed Tomography for Breast Target Volume Delineation in Prone and Supine Positions.

PURPOSE: To determine whether T2-weighted MRI improves seroma cavity (SC) and whole breast (WB) interobserver conformity for radiation therapy purposes, compared with the gold standard of CT, both in the prone and supine positions. METHODS AND MATERIALS: Eleven observers (2 radiologists and 9 radiation oncologists) delineated SC and WB clinical target volumes (CTVs) on T2-weighted MRI and CT supine and prone scans (4 scans per patient) for 33 patient datasets. Individual observer's volumes were compared using the Dice similarity coefficient, volume overlap index, center of mass shift, and Hausdorff distances. An average cavity visualization score was also determined. RESULTS: Imaging modality did not affect interobserver variation for WB CTVs. Prone WB CTVs were larger in volume and more conformal than supine CTVs (on both MRI and CT). Seroma cavity volumes were larger on CT than on MRI. Seroma cavity volumes proved to be comparable in interobserver conformity in both modalities (volume overlap index of 0.57 (95% Confidence Interval (CI) 0.54-0.60) for CT supine and 0.52 (95% CI 0.48-0.56) for MRI supine, 0.56 (95% CI 0.53-0.59) for CT prone and 0.55 (95% CI 0.51-0.59) for MRI prone); however, after registering modalities together the intermodality variation (Dice similarity coefficient of 0.41 (95% CI 0.36-0.46) for supine and 0.38 (0.34-0.42) for prone) was larger than the interobserver variability for SC, despite the location typically remaining constant. CONCLUSIONS: Magnetic resonance imaging interobserver variation was comparable to CT for the WB CTV and SC delineation, in both prone and supine positions. Although the cavity visualization score and interobserver concordance was not significantly higher for MRI than for CT, the SCs were smaller on MRI, potentially owing to clearer SC definition, especially on T2-weighted MR images.

Unprecedently Large-Scale Kinase Inhibitor Set Enabling the Accurate Prediction of Compound-Kinase Activities: A Way toward Selective Promiscuity by Design?

Drug discovery programs frequently target members of the human kinome and try to identify small molecule protein kinase inhibitors, primarily for cancer treatment, additional indications being increasingly investigated. One of the challenges is controlling the inhibitors degree of selectivity, assessed by in vitro profiling against panels of protein kinases. We manually extracted, compiled, and standardized such profiles published in the literature: we collected 356 908 data points corresponding to 482 protein kinases, 2106 inhibitors, and 661 patents. We then analyzed this data set in terms of kinome coverage, results reproducibility, popularity, and degree of selectivity of both kinases and inhibitors. We used the data set to create robust proteochemometric models capable of predicting kinase activity (the ligand-target space was modeled with an externally validated RMSE of 0.41 ± 0.02 log units and R02 0.74 ± 0.03), in order to account for missing or unreliable measurements. The influence on the prediction quality of parameters such as number of measurements, Murcko scaffold frequency or inhibitor type was assessed. Interpretation of the models enabled to highlight inhibitors and kinases properties correlated with higher affinities, and an analysis in the context of kinases crystal structures was performed. Overall, the models quality allows the accurate prediction of kinase-inhibitor activities and their structural interpretation, thus paving the way for the rational design of compounds with a targeted selectivity profile.

Hypofractionated versus conventionally fractionated radiotherapy for ductal carcinoma in situ (DCIS) of the breast.

INTRODUCTION: Hypofractionated radiotherapy (RT) in the setting of early invasive breast cancer has been shown to have similar local control rates and cosmetic outcomes as conventionally fractionated RT. This study compares ipsilateral recurrence rates between hypofractionated and conventional RT, with and without a boost. The effect of hypofractionated RT and chest wall separation (CWS) on cosmetic outcome was also assessed. METHODS: All patients with ductal carcinoma in situ (DCIS) treated between 1998 and 2012 across two sites of a single cancer institution were retrospectively studied. Patients were analysed according to those receiving conventional RT (≤2 Gy per fraction) and those receiving hypofractionated RT (>2 Gy per fraction), as well as the presence or absence of a tumour bed boost. Data were collected through electronic medical records and local cancer registry. Cosmetic outcome was scored by physicians on a four-point scale during clinical follow-up appointments. RESULTS: One hundred and ninety-seven patients were treated for DCIS during the study period. One hundred and forty-one were treated with conventional RT, and 56 with hypofractionated RT. After a median follow up of 4.4 years, there were 12 ipsilateral recurrences, of which seven were invasive disease and five DCIS. Ten recurrences occurred in patients who received conventional RT (7.1% recurrence rate) and two in those who received hypofractionated RT (3.6% recurrence rate) (P = 0.48). Cosmetic outcomes were not significantly different between conventional and hypofractionated RT (P = 0.06). CONCLUSIONS: Hypofractionation represents a suitable alternative for treating DCIS in the absence of randomised data.

Patterns of database citation in articles and patents indicate long-term scientific and industry value of biological data resources.

Data from open access biomolecular data resources, such as the European Nucleotide Archive and the Protein Data Bank are extensively reused within life science research for comparative studies, method development and to derive new scientific insights. Indicators that estimate the extent and utility of such secondary use of research data need to reflect this complex and highly variable data usage. By linking open access scientific literature, via Europe PubMedCentral, to the metadata in biological data resources we separate data citations associated with a deposition statement from citations that capture the subsequent, long-term, reuse of data in academia and industry.  We extend this analysis to begin to investigate citations of biomolecular resources in patent documents. We find citations in more than 8,000 patents from 2014, demonstrating substantial use and an important role for data resources in defining biological concepts in granted patents to both academic and industrial innovators. Combined together our results indicate that the citation patterns in biomedical literature and patents vary, not only due to citation practice but also according to the data resource cited. The results guard against the use of simple metrics such as citation counts and show that indicators of data use must not only take into account citations within the biomedical literature but also include reuse of data in industry and other parts of society by including patents and other scientific and technical documents such as guidelines, reports and grant applications.

SureChEMBL: a large-scale, chemically annotated patent document database.

SureChEMBL is a publicly available large-scale resource containing compounds extracted from the full text, images and attachments of patent documents. The data are extracted from the patent literature according to an automated text and image-mining pipeline on a daily basis. SureChEMBL provides access to a previously unavailable, open and timely set of annotated compound-patent associations, complemented with sophisticated combined structure and keyword-based search capabilities against the compound repository and patent document corpus; given the wealth of knowledge hidden in patent documents, analysis of SureChEMBL data has immediate applications in drug discovery, medicinal chemistry and other commercial areas of chemical science. Currently, the database contains 17 million compounds extracted from 14 million patent documents. Access is available through a dedicated web-based interface and data downloads at: https://www.surechembl.org/.

Release of 50 new, drug-like compounds and their computational target predictions for open source anti-tubercular drug discovery.

As a follow up to the antimycobacterial screening exercise and the release of GSK´s first Tres Cantos Antimycobacterial Set (TCAMS-TB), this paper presents the results of a second antitubercular screening effort of two hundred and fifty thousand compounds recently added to the GSK collection. The compounds were further prioritized based on not only antitubercular potency but also on physicochemical characteristics. The 50 most attractive compounds were then progressed for evaluation in three different predictive computational biology algorithms based on structural similarity or GSK historical biological assay data in order to determine their possible mechanisms of action. This effort has resulted in the identification of novel compounds and their hypothesized targets that will hopefully fuel future TB drug discovery and target validation programs alike.

Managing expectations: assessment of chemistry databases generated by automated extraction of chemical structures from patents.

BACKGROUND: First public disclosure of new chemical entities often takes place in patents, which makes them an important source of information. However, with an ever increasing number of patent applications, manual processing and curation on such a large scale becomes even more challenging. An alternative approach better suited for this large corpus of documents is the automated extraction of chemical structures. A number of patent chemistry databases generated by using the latter approach are now available but little is known that can help to manage expectations when using them. This study aims to address this by comparing two such freely available sources, SureChEMBL and IBM SIIP (IBM Strategic Intellectual Property Insight Platform), with manually curated commercial databases. RESULTS: When looking at the percentage of chemical structures successfully extracted from a set of patents, using SciFinder as our reference, 59 and 51 % were also found in our comparison in SureChEMBL and IBM SIIP, respectively. When performing this comparison with compounds as starting point, i.e. establishing if for a list of compounds the databases provide the links between chemical structures and patents they appear in, we obtained similar results. SureChEMBL and IBM SIIP found 62 and 59 %, respectively, of the compound-patent pairs obtained from Reaxys. CONCLUSIONS: In our comparison of automatically generated vs. manually curated patent chemistry databases, the former successfully provided approximately 60 % of links between chemical structure and patents. It needs to be stressed that only a very limited number of patents and compound-patent pairs were used for our comparison. Nevertheless, our results will hopefully help to manage expectations of users of patent chemistry databases of this type and provide a useful framework for more studies like ours as well as guide future developments of the workflows used for the automated extraction of chemical structures from patents. The challenges we have encountered whilst performing this study highlight that more needs to be done to make such assessments easier. Above all, more adequate, preferably open access to relevant 'gold standards' is required.

A large-scale crop protection bioassay data set.

ChEMBL is a large-scale drug discovery database containing bioactivity information primarily extracted from scientific literature. Due to the medicinal chemistry focus of the journals from which data are extracted, the data are currently of most direct value in the field of human health research. However, many of the scientific use-cases for the current data set are equally applicable in other fields, such as crop protection research: for example, identification of chemical scaffolds active against a particular target or endpoint, the de-convolution of the potential targets of a phenotypic assay, or the potential targets/pathways for safety liabilities. In order to broaden the applicability of the ChEMBL database and allow more widespread use in crop protection research, an extensive data set of bioactivity data of insecticidal, fungicidal and herbicidal compounds and assays was collated and added to the database.

Activity, assay and target data curation and quality in the ChEMBL database.

The emergence of a number of publicly available bioactivity databases, such as ChEMBL, PubChem BioAssay and BindingDB, has raised awareness about the topics of data curation, quality and integrity. Here we provide an overview and discussion of the current and future approaches to activity, assay and target data curation of the ChEMBL database. This curation process involves several manual and automated steps and aims to: (1) maximise data accessibility and comparability; (2) improve data integrity and flag outliers, ambiguities and potential errors; and (3) add further curated annotations and mappings thus increasing the usefulness and accuracy of the ChEMBL data for all users and modellers in particular. Issues related to activity, assay and target data curation and integrity along with their potential impact for users of the data are discussed, alongside robust selection and filter strategies in order to avoid or minimise these, depending on the desired application.

ADME SARfari: comparative genomics of drug metabolizing systems.

MOTIVATION: ADME SARfari is a freely available web resource that enables comparative analyses of drug-disposition genes. It does so by integrating a number of publicly available data sources, which have subsequently been used to build data mining services, predictive tools and visualizations for drug metabolism researchers. The data include the interactions of small molecules with ADME (absorption, distribution, metabolism and excretion) proteins responsible for the metabolism and transport of molecules; available pharmacokinetic (PK) data; protein sequences of ADME-related molecular targets for pre-clinical model species and human; alignments of the orthologues including information on known SNPs (Single Nucleotide Polymorphism) and information on the tissue distribution of these proteins. In addition, in silico models have been developed, which enable users to predict which ADME relevant protein targets a novel compound is likely to interact with.