A variety of machine learning methods such as naive Bayesian, support vector machines and more recently deep neural networks are demonstrating their utility for drug discovery and development. These ...leverage the generally bigger datasets created from high-throughput screening data and allow prediction of bioactivities for targets and molecular properties with increased levels of accuracy. We have only just begun to exploit the potential of these techniques but they may already be fundamentally changing the research process for identifying new molecules and/or repurposing old drugs. The integrated application of such machine learning models for end-to-end (E2E) application is broadly relevant and has considerable implications for developing future therapies and their targeting.
Full text
Available for:
EMUNI, FIS, FZAB, GEOZS, GIS, IJS, IMTLJ, KILJ, KISLJ, MFDPS, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, SBMB, SBNM, UKNU, UL, UM, UPUK, VKSCE, ZAGLJ
Organic cation transporter (OCT) 2 mediates the entry step for organic cation secretion by renal proximal tubule cells and is a site of unwanted drug-drug interactions (DDIs). But reliance on ...decision tree-based predictions of DDIs at OCT2 that depend on IC
values can be suspect because they can be influenced by choice of transported substrate; for example, IC
values for the inhibition of metformin versus MPP transport can vary by 5- to 10-fold. However, it is not clear whether the substrate dependence of a ligand interaction is common among OCT2 substrates. To address this question, we screened the inhibitory effectiveness of 20
M concentrations of several hundred compounds against OCT2-mediated uptake of six structurally distinct substrates: MPP, metformin,
,
,
-trimethyl-2-methyl(7-nitrobenzoc1,2,5oxadiazol-4-yl)aminoethanaminium (NBD-MTMA), TEA, cimetidine, and 4-4-dimethylaminostyryl-
-methylpyridinium (ASP). Of these, MPP transport was least sensitive to inhibition. IC
values for 20 structurally diverse compounds confirmed this profile, with IC
values for MPP averaging 6-fold larger than those for the other substrates. Bayesian machine-learning models of ligand-induced inhibition displayed generally good statistics after cross-validation and external testing. Applying our ASP model to a previously published large-scale screening study for inhibition of OCT2-mediated ASP transport resulted in comparable statistics, with approximately 75% of "active" inhibitors predicted correctly. The differential sensitivity of MPP transport to inhibition suggests that multiple ligands can interact simultaneously with OCT2 and supports the recommendation that MPP not be used as a test substrate for OCT2 screening. Instead, metformin appears to be a comparatively representative OCT2 substrate for both in vitro and in vivo (clinical) use.
In an associated paper, we have described a reference implementation of Laplacian-corrected naïve Bayesian model building using extended connectivity (ECFP)- and molecular function class ...fingerprints of maximum diameter 6 (FCFP)-type fingerprints. As a follow-up, we have now undertaken a large-scale validation study in order to ensure that the technique generalizes to a broad variety of drug discovery datasets. To achieve this, we have used the ChEMBL (version 20) database and split it into more than 2000 separate datasets, each of which consists of compounds and measurements with the same target and activity measurement. In order to test these datasets with the two-state Bayesian classification, we developed an automated algorithm for detecting a suitable threshold for active/inactive designation, which we applied to all collections. With these datasets, we were able to establish that our Bayesian model implementation is effective for the large majority of cases, and we were able to quantify the impact of fingerprint folding on the receiver operator curve cross-validation metrics. We were also able to study the impact that the choice of training/testing set partitioning has on the resulting recall rates. The datasets have been made publicly available to be downloaded, along with the corresponding model data files, which can be used in conjunction with the CDK and several mobile apps. We have also explored some novel visualization methods which leverage the structural origins of the ECFP/FCFP fingerprints to attribute regions of a molecule responsible for positive and negative contributions to activity. The ability to score molecules across thousands of relevant datasets across organisms also may help to access desirable and undesirable off-target effects as well as suggest potential targets for compounds derived from phenotypic screens.
Full text
Available for:
IJS, KILJ, NUK, PNG, UL, UM
Many chemicals that disrupt endocrine function have been linked to a variety of adverse biological outcomes. However, screening for endocrine disruption using in vitro or in vivo approaches is costly ...and time-consuming. Computational methods, e.g., quantitative structure–activity relationship models, have become more reliable due to bigger training sets, increased computing power, and advanced machine learning algorithms, such as multilayered artificial neural networks. Machine learning models can be used to predict compounds for endocrine disrupting capabilities, such as binding to the estrogen receptor (ER), and allow for prioritization and further testing. In this work, an exhaustive comparison of multiple machine learning algorithms, chemical spaces, and evaluation metrics for ER binding was performed on public data sets curated using in-house cheminformatics software (Assay Central). Chemical features utilized in modeling consisted of binary fingerprints (ECFP6, FCFP6, ToxPrint, or MACCS keys) and continuous molecular descriptors from RDKit. Each feature set was subjected to classic machine learning algorithms (Bernoulli Naive Bayes, AdaBoost Decision Tree, Random Forest, Support Vector Machine) and Deep Neural Networks (DNN). Models were evaluated using a variety of metrics: recall, precision, F1-score, accuracy, area under the receiver operating characteristic curve, Cohen’s Kappa, and Matthews correlation coefficient. For predicting compounds within the training set, DNN has an accuracy higher than that of other methods; however, in 5-fold cross validation and external test set predictions, DNN and most classic machine learning models perform similarly regardless of the data set or molecular descriptors used. We have also used the rank normalized scores as a performance-criteria for each machine learning method, and Random Forest performed best on the validation set when ranked by metric or by data sets. These results suggest classic machine learning algorithms may be sufficient to develop high quality predictive models of ER activity.
Full text
Available for:
IJS, KILJ, NUK, PNG, UL, UM
A 31-year-old man with a medical history of well-controlled asthma presented with a 3-week history of midsternal chest pressure and shortness of breath. His symptoms were associated with malaise, ...weakness, 40-pound weight loss over several months, and intermittent fever up to 38.3ºC. A week and half earlier, he started experiencing a productive cough with white sputum and arthralgias in his knees. He denied any exacerbating or relieving factors for his symptoms. Additionally, he had a pruritic rash on his thighs for the last year that remained unresolved despite antifungal medication.
Substances of unknown or variable composition, complex reaction products, or biological materials (UVCBs) are over 70 000 “complex” chemical mixtures produced and used at significant levels ...worldwide. Due to their unknown or variable composition, applying chemical assessments originally developed for individual compounds to UVCBs is challenging, which impedes sound management of these substances. Across the analytical sciences, toxicology, cheminformatics, and regulatory practice, new approaches addressing specific aspects of UVCB assessment are being developed, albeit in a fragmented manner. This review attempts to convey the “big picture” of the state of the art in dealing with UVCBs by holistically examining UVCB characterization and chemical identity representation, as well as hazard, exposure, and risk assessment. Overall, information gaps on chemical identities underpin the fundamental challenges concerning UVCBs, and better reporting and substance characterization efforts are needed to support subsequent chemical assessments. To this end, an information level scheme for improved UVCB data collection and management within databases is proposed. The development of UVCB testing shows early progress, in line with three main methods: whole substance, known constituents, and fraction profiling. For toxicity assessment, one option is a whole-mixture testing approach. If the identities of (many) constituents are known, grouping, read across, and mixture toxicity modeling represent complementary approaches to overcome data gaps in toxicity assessment. This review highlights continued needs for concerted efforts from all stakeholders to ensure proper assessment and sound management of UVCBs.
Full text
Available for:
IJS, KILJ, NUK, PNG, UL, UM
Humans are exposed to tens of thousands of chemical substances that need to be assessed for their potential toxicity. Acute systemic toxicity testing serves as the basis for regulatory hazard ...classification, labeling, and risk management. However, it is cost- and time-prohibitive to evaluate all new and existing chemicals using traditional rodent acute toxicity tests.
models built using existing data facilitate rapid acute toxicity predictions without using animals.
The U.S. Interagency Coordinating Committee on the Validation of Alternative Methods (ICCVAM) Acute Toxicity Workgroup organized an international collaboration to develop
models for predicting acute oral toxicity based on five different end points: Lethal Dose 50 (
value, U.S. Environmental Protection Agency hazard (four) categories, Globally Harmonized System for Classification and Labeling hazard (five) categories, very toxic chemicals
(
), and nontoxic chemicals (
).
An acute oral toxicity data inventory for 11,992 chemicals was compiled, split into training and evaluation sets, and made available to 35 participating international research groups that submitted a total of 139 predictive models. Predictions that fell within the applicability domains of the submitted models were evaluated using external validation sets. These were then combined into consensus models to leverage strengths of individual approaches.
The resulting consensus predictions, which leverage the collective strengths of each individual model, form the Collaborative Acute Toxicity Modeling Suite (CATMoS). CATMoS demonstrated high performance in terms of accuracy and robustness when compared with
results.
CATMoS is being evaluated by regulatory agencies for its utility and applicability as a potential replacement for
rat acute oral toxicity studies. CATMoS predictions for more than 800,000 chemicals have been made available via the National Toxicology Program's Integrated Chemical Environment tools and data sets (ice.ntp.niehs.nih.gov). The models are also implemented in a free, standalone, open-source tool, OPERA, which allows predictions of new and untested chemicals to be made. https://doi.org/10.1289/EHP8495.
Full text
Available for:
CEKLJ, DOBA, IZUM, KILJ, NUK, OILJ, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK, VSZLJ
The human immunodeficiency virus (HIV) causes over a million deaths every year and has a huge economic impact in many countries. The first class of drugs approved were nucleoside reverse ...transcriptase inhibitors. A newer generation of reverse transcriptase inhibitors have become susceptible to drug resistant strains of HIV, and hence, alternatives are urgently needed. We have recently pioneered the use of Bayesian machine learning to generate models with public data to identify new compounds for testing against different disease targets. The current study has used the NIAID ChemDB HIV, Opportunistic Infection and Tuberculosis Therapeutics Database for machine learning studies. We curated and cleaned data from HIV-1 wild-type cell-based and reverse transcriptase (RT) DNA polymerase inhibition assays. Compounds from this database with ≤1 μM HIV-1 RT DNA polymerase activity inhibition and cell-based HIV-1 inhibition are correlated (Pearson r = 0.44, n = 1137, p < 0.0001). Models were trained using multiple machine learning approaches (Bernoulli Naive Bayes, AdaBoost Decision Tree, Random Forest, support vector classification, k-Nearest Neighbors, and deep neural networks as well as consensus approaches) and then their predictive abilities were compared. Our comparison of different machine learning methods demonstrated that support vector classification, deep learning, and a consensus were generally comparable and not significantly different from each other using 5-fold cross validation and using 24 training and test set combinations. This study demonstrates findings in line with our previous studies for various targets that training and testing with multiple data sets does not demonstrate a significant difference between support vector machine and deep neural networks.
Full text
Available for:
IJS, KILJ, NUK, PNG, UL, UM
2D Depiction of Protein−Ligand Complexes Clark, Alex M; Labute, Paul
Journal of chemical information and modeling,
09/2007, Volume:
47, Issue:
5
Journal Article
Peer reviewed
A method is presented for the automated preparation of schematic diagrams for protein−ligand complexes, in which the ligand is displayed in conventional 2D form, and the interactions to and between ...the residues in its vicinity are summarized in a concise and information-rich manner. The structural entities are arranged to maximize aesthetic ideals and to properly convey important distance relationships. The diagram is annotated with calculated hydrogen bonds, a substitution contour, solvent exposure, chelated metals, covalently bound linkages, π−π and π−cation interactions, and, for series of complexes, conserved residues and interactions. Residues, cofactors, ions, and solvent components are drawn in cartoon form as adjuncts to the ligand. The method can be applied to aligned sets which contain multiple ligands, or multiple members of a protein family, in which case the ligand orientations and protein residue placement will show consistent trends throughout the series.
Full text
Available for:
IJS, KILJ, NUK, PNG, UL, UM
RATIONALE:Prospective cohort studies question the value of HDL-C (high-density lipoprotein cholesterol) for stroke risk prediction.
OBJECTIVE:Investigate the relationship between long-term functional ...recovery and HDL proteome and function.
METHODS AND RESULTS:Changes in HDL protein composition and function (cholesterol efflux capacity) in patients after acute ischemic stroke at 2 time points (24 hours, 35 patients; 96 hours, 20 patients) and in 35 control subjects were measured. The recovery from stroke was assessed by 3 months, the National Institutes of Health Stroke Scale and modified Rankin scale scores. When compared with control subject after adjustments for sex and HDL-C levels, 12 proteins some of which participate in acute phase response and platelet activation (APMAP adipocyte plasma membrane-associated protein, GPLD1 phosphate inositol-glycan specific phospholipase D, APOE apolipoprotein E, IHH Indian hedgehog protein, ITIH4 inter-alpha-trypsin inhibitor chain H4, SAA2 serum amyloid A2, APOA4 apolipoprotein A-IV, CLU clusterin, ANTRX2 anthrax toxin receptor 2, PON1 serum paraoxonase/arylesterase, SERPINA1 alpha-1-antitrypsin, and APOF apolipoprotein F) were significantly (adjusted P<0.05) altered in stroke HDL at 96 hours. The first 8 of these proteins were also significantly altered at 24 hours. Consistent with inflammatory remodeling, cholesterol efflux capacity was reduced by 32% (P<0.001) at both time points. Baseline stroke severity adjusted regression model showed that changes within 96-hour poststroke in APOF, APOL1, APMAP, APOC4 (apolipoprotein C4), APOM (apolipoprotein M), PCYOX1 (prenylcysteine oxidase 1), PON1, and APOE correlate with stroke recovery scores (R=0.38–0.73, adjusted P<0.05). APOF (R=0.73) and APOL1 (R=0.60) continued to significantly correlate with recovery scores after accounting for tPA (tissue-type plasminogen activator) treatment.
CONCLUSIONS:Changes in HDL proteins during early acute phase of stroke associate with recovery. Monitoring HDL proteins may provide clinical biomarkers that inform on stroke recuperation.