Synergies Between Quantum Mechanics and Machine Learning in Reaction Prediction.

Machine learning (ML) and quantum mechanical (QM) methods can be used in two-way synergy to build chemical reaction expert systems. The proposed ML approach identifies electron sources and sinks among reactants and then ranks all source-sink pairs. This addresses a bottleneck of QM calculations by providing a prioritized list of mechanistic reaction steps. QM modeling can then be used to compute the transition states and activation energies of the top-ranked reactions, providing additional or improved examples of ranked source-sink pairs. Retraining the ML model closes the loop, producing more accurate predictions from a larger training set. The approach is demonstrated in detail using a small set of organic radical reactions.

Atmospheric Oxidation of Squalene: Molecular Study Using COBRA Modeling and High-Resolution Mass Spectrometry.

Squalene is a major component of skin and plant surface lipids and is known to be present at high concentrations in indoor dust. Its high reactivity toward ozone makes it an important ozone sink and a natural protectant against atmospheric oxidizing agents. While the volatile products of squalene ozonolysis are known, the condensed-phase products have not been characterized. We present an analysis of condensed-phase products resulting from an extensive oxidation of squalene by ozone probed by electrospray ionization (ESI) high-resolution mass spectrometry (HR-MS). A complex distribution of nearly 1300 peaks assignable to molecular formulas is observed in direct infusion positive ion mode ESI mass spectra. The distribution of peaks in the mass spectra suggests that there are extensive cross-coupling reactions between hydroxy-carbonyl products of squalene ozonolysis. To get additional insights into the mechanism, we apply a Computational Brewing Application (COBRA) to simulate the oxidation of squalene in the presence of ozone, and compare predicted results with those observed by the HR-MS experiments. The system predicts over one billion molecular structures between 0 and 1450 Da, which correspond to about 27 000 distinct elemental formulas. Over 83% of the squalene oxidation products inferred from the mass spectrometry data are matched by the simulation. The simulation indicates a prevalence of peroxy groups, with hydroxyl and ether groups being the second-most important O-containing functional groups formed during squalene oxidation. These highly oxidized products of squalene ozonolysis may accumulate on indoor dust and surfaces and contribute to their redox capacity.

Accurate and efficient target prediction using a potency-sensitive influence-relevance voter.

BACKGROUND: A number of algorithms have been proposed to predict the biological targets of diverse molecules. Some are structure-based, but the most common are ligand-based and use chemical fingerprints and the notion of chemical similarity. These methods tend to be computationally faster than others, making them particularly attractive tools as the amount of available data grows. RESULTS: Using a ChEMBL-derived database covering 490,760 molecule-protein interactions and 3236 protein targets, we conduct a large-scale assessment of the performance of several target-prediction algorithms at predicting drug-target activity. We assess algorithm performance using three validation procedures: standard tenfold cross-validation, tenfold cross-validation in a simulated screen that includes random inactive molecules, and validation on an external test set composed of molecules not present in our database. CONCLUSIONS: We present two improvements over current practice. First, using a modified version of the influence-relevance voter (IRV), we show that using molecule potency data can improve target prediction. Second, we demonstrate that random inactive molecules added during training can boost the accuracy of several algorithms in realistic target-prediction experiments. Our potency-sensitive version of the IRV (PS-IRV) obtains the best results on large test sets in most of the experiments. Models and software are publicly accessible through the chemoinformatics portal at http://chemdb.ics.uci.edu/.

HRAS mutations and resistance to the epidermal growth factor receptor tyrosine kinase inhibitor erlotinib in head and neck squamous cell carcinoma cells.

BACKGROUND: The purpose of this study was to identify mechanisms of innate resistance to an epidermal growth factor receptor (EGFR) tyrosine kinase inhibitor, erlotinib, in a panel of head and neck squamous cell carcinoma (HNSCC) cell lines. Specifically, we analyzed the role of HRAS mutations in erlotinib resistance. METHODS: Erlotinib sensitivity was determined by methyl thiazolyl-tetrazolium (MTT) assays. Molecular signaling pathways and somatic mutations were examined. Changes in sensitivity after modulation of HRAS expression were evaluated. RESULTS: All 7 cell lines were wild-type for EGFR and KRAS regardless of erlotinib sensitivity; however, 1 erlotinib-resistant cell line (HN31) harbored an HRAS G12D mutation. Downregulation of HRAS expression by small interfering RNA (siRNA) or short hairpin RNA (shRNA) in HN31 led to increased erlotinib sensitivity in vitro and in vivo. Transfection of activating HRAS-mutant (G12D and G12V) constructs into erlotinib-sensitive cell lines made them more resistant to erlotinib. CONCLUSION: Activating HRAS mutations can confer erlotinib resistance in an HRAS mutant HNSCC cell line.

ReactionMap: an efficient atom-mapping algorithm for chemical reactions.

Large databases of chemical reactions provide new data-mining opportunities and challenges. Key challenges result from the imperfect quality of the data and the fact that many of these reactions are not properly balanced or atom-mapped. Here, we describe ReactionMap, an efficient atom-mapping algorithm. Our approach uses a combination of maximum common chemical subgraph search and minimization of an assignment cost function derived empirically from training data. We use a set of over 259,000 balanced atom-mapped reactions from the SPRESI commercial database to train the system, and we validate it on random sets of 1000 and 17,996 reactions sampled from this pool. These large test sets represent a broad range of chemical reaction types, and ReactionMap correctly maps about 99% of the atoms and about 96% of the reactions, with a mean time per mapping of 2 s. Most correctly mapped reactions are mapped with high confidence. Mapping accuracy compares favorably with ChemAxon's AutoMapper, versions 5 and 6.1, and the DREAM Web tool. These approaches correctly map 60.7%, 86.5%, and 90.3% of the reactions, respectively, on the same data set. A ReactionMap server is available on the ChemDB Web portal at http://cdb.ics.uci.edu .

COBRA: a computational brewing application for predicting the molecular composition of organic aerosols.

Atmospheric organic aerosols (OA) represent a significant fraction of airborne particulate matter and can impact climate, visibility, and human health. These mixtures are difficult to characterize experimentally due to their complex and dynamic chemical composition. We introduce a novel Computational Brewing Application (COBRA) and apply it to modeling oligomerization chemistry stemming from condensation and addition reactions in OA formed by photooxidation of isoprene. COBRA uses two lists as input: a list of chemical structures comprising the molecular starting pool and a list of rules defining potential reactions between molecules. Reactions are performed iteratively, with products of all previous iterations serving as reactants for the next. The simulation generated thousands of structures in the mass range of 120-500 Da and correctly predicted ∼70% of the individual OA constituents observed by high-resolution mass spectrometry. Select predicted structures were confirmed with tandem mass spectrometry. Esterification was shown to play the most significant role in oligomer formation, with hemiacetal formation less important, and aldol condensation insignificant. COBRA is not limited to atmospheric aerosol chemistry; it should be applicable to the prediction of reaction products in other complex mixtures for which reasonable reaction mechanisms and seed molecules can be supplied by experimental or theoretical methods.

Targeted molecular therapy of head and neck squamous cell carcinoma with the tyrosine kinase inhibitor vandetanib in a mouse model.

BACKGROUND: We investigated the effects of vandetanib, an inhibitor of vascular endothelial growth factor receptor 2 (VEGFR-2) and epidermal growth factor receptor (EGFR), alone and in combination with paclitaxel in an orthotopic mouse model of human head and neck squamous cell carcinoma (HNSCC). METHODS: The in vitro effects of vandetanib (ZACTIMA) were assessed in 2 HNSCC cell lines on cell growth, apoptosis, receptor and downstream signaling molecule expression, and phosphorylation levels. We assessed in vivo effects of vandetanib and/or paclitaxel by measuring tumor cell apoptosis, endothelial cell apoptosis, microvessel density, tumor size, and animal survival. RESULTS: In vitro, vandetanib inhibited the phosphorylation of EGFR and its downstream targets in HNSCC cells and inhibited proliferation and induced apoptosis of HNSCC cells and extended survival and inhibited tumor growth in nude mice orthotopically injected with human HNSCC. CONCLUSION: Vandetanib has the potential to be a novel molecular targeted therapy for HNSCC.

The tyrosine kinase inhibitor, AZD2171, inhibits vascular endothelial growth factor receptor signaling and growth of anaplastic thyroid cancer in an orthotopic nude mouse model.

PURPOSE: Anaplastic thyroid cancer (ATC) is a locally aggressive type of thyroid tumor with high rate of distant metastases. With conventional treatment, the median survival ranges from 4 to 12 months; therefore, new treatment options are needed. AZD2171 is a tyrosine kinase inhibitor of the vascular endothelial growth factor receptors (VEGFR) VEGFR-1, VEGFR-2, and VEGFR-3. The objective of the study is to determine whether AZD2171 can inhibit VEGFR-2 signaling and decrease tumor growth and prolong survival of ATC in an orthotopic nude mouse model. EXPERIMENTAL DESIGN: We examined the effects of AZD2171 on phosphorylation of VEGFR-2, mitogen-activated protein kinase, and AKT in human umbilical vascular endothelial cells. To determine the antiproliferative and antiapoptotic effects of AZD2171, we did 3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide and flow cytometry assays, respectively. We assessed the antitumor effects of AZD2171 in a xenograft model of ATC using control, AZD2171, paclitaxel, and combination groups by measuring tumor size and survival. RESULTS: Treatment with AZD2171 led to dose-dependent inhibition of VEGFR-2 phosphorylation and its downstream signaling in human umbilical vascular endothelial cells (IC(50) for cell proliferation, 500 nmol/L). In the ATC cell lines DRO and ARO, IC(50) was 7.5 micromol/L. AZD2171 induced apoptosis in 50% of endothelial and ATC cells at 3 and 10 micromol/L concentrations, respectively. In vivo, AZD2171 led to a significant reduction in tumor size between control and AZD2171 (P = 0.002) or AZD2171 + paclitaxel group (P = 0.002) but not the paclitaxel alone group (P = 0.11). Survival was significantly higher among AZD2171 (P < 0.001) and combination groups (P < 0.001) compared with control. CONCLUSIONS: AZD2171 effectively inhibits tumor growth and prolongs survival of ATC-bearing mice. The main effect of AZD2171 is mediated through angiogenesis inhibition.

A semi-automatic method for peak and valley detection in free-breathing respiratory waveforms.

The existing commercial software often inadequately determines respiratory peaks for patients in respiration correlated computed tomography. A semi-automatic method was developed for peak and valley detection in free-breathing respiratory waveforms. First the waveform is separated into breath cycles by identifying intercepts of a moving average curve with the inspiration and expiration branches of the waveform. Peaks and valleys were then defined, respectively, as the maximum and minimum between pairs of alternating inspiration and expiration intercepts. Finally, automatic corrections and manual user interventions were employed. On average for each of the 20 patients, 99% of 307 peaks and valleys were automatically detected in 2.8 s. This method was robust for bellows waveforms with large variations.

Comparison of spirometry and abdominal height as four-dimensional computed tomography metrics in lung.

An important consideration in four-dimensional CT scanning is the selection of a breathing metric for sorting the CT data and modeling internal motion. This study compared two noninvasive breathing metrics, spirometry and abdominal height, against internal air content, used as a surrogate for internal motion. Both metrics were shown to be accurate, but the spirometry showed a stronger and more reproducible relationship than the abdominal height in the lung. The abdominal height was known to be affected by sensor placement and patient positioning while the spirometer exhibited signal drift. By combining these two, a normalization of the drift-free metric to tidal volume may be generated and the overall metric precision may be improved.

Comparison of spirometry and abdominal height as four-dimensional computed tomography metrics in lung.

An important consideration in four-dimensional CT scanning is the selection of a breathing metric for sorting the CT data and modeling internal motion. This study compared two noninvasive breathing metrics, spirometry and abdominal height, against internal air content, used as a surrogate for internal motion. Both metrics were shown to be accurate, but the spirometry showed a stronger and more reproducible relationship than the abdominal height in the lung. The abdominal height was known to be affected by sensor placement and patient positioning while the spirometer exhibited signal drift. By combining these two, a normalization of the drift-free metric to tidal volume may be generated and the overall metric precision may be improved.