Deep Learning Localizes and Identifies Polyps in Real Time With 96% Accuracy in Screening Colonoscopy.

We present a supervised learning approach to predict the products of organic reactions given their reactants, reagents, and solvent(s). The prediction task is factored into two stages comparable to manual expert approaches: considering possible sites of reactivity and evaluating their relative likelihoods. By training on hundreds of thousands of reaction precedents covering a broad range of reaction types from the patent literature, the neural model makes informed predictions of chemical reactivity. The model predicts the major product correctly over 85% of the time requiring around 100 ms per example, a significantly higher accuracy than achieved by previous machine learning approaches, and performs on par with expert chemists with years of formal training. We gain additional insight into predictions via the design of the neural model, revealing an understanding of chemistry qualitatively consistent with manual approaches.

/pdf/a-graph-convolutional-neural-network-model-for-the-4nuqy3oaxh.pdf

A graph-convolutional neural network model for the prediction of chemical reactivity

ConspectusComputer-aided synthesis planning (CASP) is focused on the goal of accelerating the process by which chemists decide how to synthesize small molecule compounds. The ideal CASP program would take a molecular structure as input and output a sorted list of detailed reaction schemes that each connect that target to purchasable starting materials via a series of chemically feasible reaction steps. Early work in this field relied on expert-crafted reaction rules and heuristics to describe possible retrosynthetic disconnections and selectivity rules but suffered from incompleteness, infeasible suggestions, and human bias. With the relatively recent availability of large reaction corpora (such as the United States Patent and Trademark Office (USPTO), Reaxys, and SciFinder databases), consisting of millions of tabulated reaction examples, it is now possible to construct and validate purely data-driven approaches to synthesis planning. As a result, synthesis planning has been opened to machine learning te...

Machine Learning in Computer-Aided Synthesis Planning

In the space of only a few years, deep generative modeling has revolutionized how we think of artificial creativity, yielding autonomous systems which produce original images, music, and text. Inspired by these successes, researchers are now applying deep generative modeling techniques to the generation and optimization of molecules—in our review we found 45 papers on the subject published in the past two years. These works point to a future where such systems will be used to generate lead molecules, greatly reducing resources spent downstream synthesizing and characterizing bad leads in the lab. In this review we survey the increasingly complex landscape of models and representation schemes that have been proposed. The four classes of techniques we describe are recursive neural networks, autoencoders, generative adversarial networks, and reinforcement learning. After first discussing some of the mathematical fundamentals of each technique, we draw high level connections and comparisons with other techniques and expose the pros and cons of each. Several important high level themes emerge as a result of this work, including the shift away from the SMILES string representation of molecules towards more sophisticated representations such as graph grammars and 3D representations, the importance of reward function design, the need for better standards for benchmarking and testing, and the benefits of adversarial training and reinforcement learning over maximum likelihood based training.

Deep learning for molecular design—a review of the state of the art

The key objectives of medicinal chemistry are to efficiently design and synthesize bioactive compounds that have the potential to become safe and efficacious drugs. Most medicinal chemistry programmes rely on screening compound collections populated by a range of molecules derived from a set of known and robust chemistry reactions. Analysis of the role of synthetic organic chemistry in subsequent hit and lead optimization efforts suggests that only a few reactions dominate. Thus, the uptake of new synthetic methodologies in drug discovery is limited. Starting from the known limitations of reaction parameters, synthesis design tools, synthetic strategies and innovative chemistries, here we highlight opportunities for the expansion of the medicinal chemists' synthetic toolbox. More intense crosstalk between synthetic and medicinal chemists in industry and academia should enable enhanced impact of new methodologies in future drug discovery.

Expanding the medicinal chemistry synthetic toolbox

Reaction predictor is an application for predicting chemical reactions and reaction pathways. It uses deep learning to predict and rank elementary reactions by first identifying electron sources and sinks, pairing those sources and sinks to propose elementary reactions, and finally ranking the reactions by favorability. Global reactions can be identified by chaining together these elementary reaction predictions. We carefully curated a data set consisting of over 11 000 elementary reactions, covering a broad range of advanced organic chemistry. Using this data for training, we demonstrate an 80% top-5 recovery rate on a separate, challenging benchmark set of reactions drawn from modern organic chemistry literature. A fundamental problem of synthetic chemistry is the identification of unknown products observed via mass spectrometry. Reaction predictor includes a pathway search feature that can help identify such products through multi-target mass search. Finally, we discuss an alternative approach to predicting electron sources and sinks using recurrent neural networks, specifically long short-term memory (LSTM) architectures, operating directly on SMILES strings. This approach has shown promising preliminary results.

Deep learning for chemical reaction prediction

Four phthalazinones (CIDs 22334057, 22333974, 22334032, 22334012) and one isoquinolone (CID 5224943) were previously shown to be potent enhancers of antifungal activity of fluconazole against Candida albicans. Several even more potent analogues of these compounds were identified, some with EC50 as low as 1 nM, against C. albicans. The compounds exhibited pharmacological synergy (FIC < 0.5) with fluconazole. The compounds were also shown to enhance the antifungal activity of isavuconazole, a recently FDA approved azole antifungal. Isoquinolone 15 and phthalazinone 24 were shown to be active against several resistant clinical isolates of C. albicans.

/pdf/potent-antifungal-synergy-of-phthalazinone-and-isoquinolones-3iyomlu0dg.pdf

Potent Antifungal Synergy of Phthalazinone and Isoquinolones with Azoles Against Candida albicans

Calculated methyl anion affinities are known to correlate with experimentally determined Mayr E parameters for individual organic functional group classes but not between neutral and cationic organic electrophiles. We demonstrate that methyl anion affinities calculated with a solvation model (MAA*) give a linear correlation with Mayr E parameters for a broad range of functional groups. Methyl anion affinities (MAA*), plotted on the log scale of Mayr E, provide insights into the full range of electrophilicity of organic functional groups. On the Mayr E scale, the electrophilicity toward the methyl anion spans 180 orders of magnitude.

/pdf/methyl-anion-affinities-of-the-canonical-organic-functional-44kefqgmz9.pdf

Methyl Anion Affinities of the Canonical Organic Functional Groups.

There is a lack of scalable quantitative measures of reactivity for functional groups in organic chemistry Measuring reactivity experimentally is costly and time-consuming and does not scale to the astronomical size of chemical space In previous quantum chemistry studies, we have introduced Methyl Cation Affinities (MCA*) and Methyl Anion Affinities (MAA*), using a solvation model, as quantitative measures of reactivity for organic functional groups over the broadest range Although MCA* and MAA* offer good estimates of reactivity parameters, their calculation through Density Functional Theory (DFT) simulations is time-consuming To circumvent this problem, we first use DFT to calculate MCA* and MAA* for more than 2,400 organic molecules thereby establishing a large dataset of chemical reactivity scores We then design deep learning methods to predict the reactivity of molecular structures and train them using this curated dataset in combination with different representations of molecular structures Using ten-fold cross-validation, we show that graph attention neural networks applied to informative input fingerprints produce the most accurate estimates of reactivity, achieving over 91% test accuracy for predicting the MCA* plus-minus 30 or MAA* plus-minus 30, over 50 orders of magnitude Finally, we demonstrate the application of these reactivity scores to two tasks: (1) chemical reaction prediction; (2) combinatorial generation of reaction mechanisms The curated dataset of MCA* and MAA* scores is available through the ChemDB chemoinformatics web portal at this http URL

Quantum Mechanics and Machine Learning Synergies: Graph Attention Neural Networks to Predict Chemical Reactivity.

Small molecules comprised of spiroindolinone analogues are provided. Some spiroindolinones are provided with a particular relative stereochemistry in which the indolone carbonyl and all three hydrogens are on the same face of the central pyrrolidine ring. A stereoselective method of synthesis is provided for making some of the spiroindolinones described above. Formulations and medicaments are also provided that are directed to the treatment of disease, such as, for example, fungal infections. Therapeutics are also provided containing a therapeutically effective dose of one or more small molecule compounds, present either as pharmaceutically effective salt or in pure form, including, but not limited to, formulations for oral, intravenous, or intramuscular administration.

Aaron Mood

Papers

Deep learning for chemical reaction prediction

Potent Antifungal Synergy of Phthalazinone and Isoquinolones with Azoles Against Candida albicans

Methyl Anion Affinities of the Canonical Organic Functional Groups.

Quantum Mechanics and Machine Learning Synergies: Graph Attention Neural Networks to Predict Chemical Reactivity.

Spiroindolinones and therapeutic uses thereof