BIGCHEM: Challenges and Opportunities for Big Data Analysis in Chemistry

Quantum-Mechanics Calculations Elucidate Skin-Sensitizing Pharmaceutical Compounds

Skin sensitization is a critical end point in occupational toxicology that necessitates the use of fast, accurate, and affordable models to aid in establishing handling guidance for worker protection. While many in silico models have been developed, the scarcity of reliable data for active pharmaceutical ingredients (APIs) and their intermediates (together regarded as pharmaceutical compounds) brings into question the reliability of these tools, which are largely constructed using publicly available nonspecialty chemicals. Here, we present the quantum-mechanical (QM) Computer-Aided Discovery and REdesign (CADRE) model, which was developed with the bioactive and structurally complex chemical space in mind by relying on the fundamentals of chemical interactions in key events (versus structural attributes of training-set data). Validated in this study on 345 APIs and intermediates, CADRE achieved 95% accuracy, sensitivity, and specificity and a combined 79% accuracy in assigning potency categories compared to the mouse local lymph node assay data. We show how historical outcomes from CADRE testing in the pharmaceutical space, generated over the past 10 years on ca. 2500 chemicals, can be used to probe the relationships between sensitization mechanisms (or the underlying chemical classes) and the probability of eliciting a sensitization response in mice of a given potency. We believe this information to be of value to both practitioners, who can use it to quickly screen and triage their data sets, as well as to model developers to fine-tune their structure-based tools. Lastly, we leverage our experimentally validated subset of APIs and intermediates to show the importance of dermal permeability on the sensitization potential and potency. We demonstrate that common physicochemical properties used to assess permeation, such as the octanol-water partition coefficient and molecular weight, are poor proxies for the more accurate energy-pair distributions that can be computed from mixed QM and classical simulations using model representations of the stratum corneum.

MolCompass: multi-tool for the navigation in chemical space and visual validation of QSAR/QSPR models

The exponential growth of data is challenging for humans because their ability to analyze data is limited. Especially in chemistry, there is a demand for tools that can visualize molecular datasets in a convenient graphical way. We propose a new, ready-to-use, multi-tool, and open-source framework for visualizing and navigating chemical space. This framework adheres to the low-code/no-code (LCNC) paradigm, providing a KNIME node, a web-based tool, and a Python package, making it accessible to a broad cheminformatics community. The core technique of the MolCompass framework employs a pre-trained parametric t-SNE model. We demonstrate how this framework can be adapted for the visualisation of chemical space and visual validation of binary classification QSAR/QSPR models, revealing their weaknesses and identifying model cliffs. All parts of the framework are publicly available on GitHub, providing accessibility to the broad scientific community. Scientific contributionWe provide an open-source, ready-to-use set of tools for the visualization of chemical space. These tools can be insightful for chemists to analyze compound datasets and for the visual validation of QSAR/QSPR models.

Stereochemically-aware bioactivity descriptors for uncharacterized chemical compounds

Stereochemistry plays a fundamental role in pharmacology. Here, we systematically investigate the relationship between stereoisomerism and bioactivity on over 1 M compounds, finding that a very significant fraction (~ 40%) of spatial isomer pairs show, to some extent, distinct bioactivities. We then use the 3D representation of these molecules to train a collection of deep neural networks (Signaturizers3D) to generate bioactivity descriptors associated to small molecules, that capture their effects at increasing levels of biological complexity (i.e. from protein targets to clinical outcomes). Further, we assess the ability of the descriptors to distinguish between stereoisomers and to recapitulate their different target binding profiles. Overall, we show how these new stereochemically-aware descriptors provide an even more faithful description of complex small molecule bioactivity properties, capturing key differences in the activity of stereoisomers.Scientific contributionWe systematically assess the relationship between stereoisomerism and bioactivity on a large scale, focusing on compound-target binding events, and use our findings to train novel deep learning models to generate stereochemically-aware bioactivity signatures for any compound of interest.

Multi-Endpoint Acute Toxicity Assessment of Organic Compounds Using Large-Scale Machine Learning Modeling

In recent years, alternative animal testing methods such as computational and machine learning approaches have become increasingly crucial for toxicity testing. However, the complexity and scarcity of available biomedical data challenge the development of predictive models. Combining nonlinear machine learning together with multicondition descriptors offers a solution for using data from various assays to create a robust model. This work applies multicondition descriptors (MCDs) to develop a QSTR (Quantitative Structure-Toxicity Relationship) model based on a large toxicity data set comprising more than 80,000 compounds and 59 different end points (122,572 data points). The prediction capabilities of developed single-task multi-end point machine learning models as well as a novel data analysis approach with the use of Convolutional Neural Networks (CNN) are discussed. The results show that using MCDs significantly improves the model and using them with CNN-1D yields the best result (R2train = 0.93, R2ext = 0.70). Several structural features showed a high level of contribution to the toxicity, including van der Waals surface area (VSA), number of nitrogen-containing fragments (nN+), presence of S-P fragments, ionization potential, and presence of C-N fragments. The developed models can be very useful tools to predict the toxicity of various compounds under different conditions, enabling quick toxicity assessment of new compounds.

Implementation of IFPTML Computational Models in Drug Discovery Against Flaviviridae Family

The Flaviviridae family consists of single-stranded positive-sense RNA viruses, which contains the genera Flavivirus, Hepacivirus, Pegivirus, and Pestivirus. Currently, there is an outbreak of viral diseases caused by this family affecting millions of people worldwide, leading to significant morbidity and mortality rates. Advances in computational chemistry have greatly facilitated the discovery of novel drugs and treatments for diseases associated with this family. Chemoinformatic techniques, such as the perturbation theory machine learning method, have played a crucial role in developing new approaches based on ML models that can effectively aid drug discovery. The IFPTML models have shown its capability to handle, classify, and process large data sets with high specificity. The results obtained from different models indicates that this methodology is proficient in processing the data, resulting in a reduction of the false positive rate by 4.25%, along with an accuracy of 83% and reliability of 92%. These values suggest that the model can serve as a computational tool in assisting drug discovery efforts and the development of new treatments against Flaviviridae family diseases.

Trends and Applications in Computationally Driven Drug Repurposing

Drug repurposing is a widely used approach originally developed to aid in the identification of new uses of already existing drugs outside the scope of the original medical indication [...].

Practical and comparative application of efficient data reduction - Multivariate curve resolution

The term 'Big Data' has recently attracted much attention in science. Working with big data sets can be both challenging and rewarding. The complexity and big data sets make the analysis difficult to deal with, and the increasing volume of data sets requires the development of new practical methods for their handling. In this contribution, we explored the efficient data reduction-multivariate curve resolution (EDR-MCR) strategy based on the convex hull theory for quantitative and qualitative analysis of large chemical data sets. For the quantitative example, the potential of the EDR-MCR method for selecting a representative calibration set was investigated, and the results were compared with the widely used Kennard-Stone (KS) algorithm. The EDR-MCR strategy strongly limits the number of calibration samples with a high potency of prediction performance. The priority of EDR-MCR over KS is its ability to find informative variables and eliminate redundant features. Moreover, the EDR-MCR strategy was also applied for the qualitative analysis of a large-scale metabolomic data set. The comparable analysis results of EDR-MCR with the region of interest (ROI) method confirmed the ability of this method for quantitative analysis of big mass spectrophotometer data sets.

Global reactivity models are impactful in industrial synthesis applications

Artificial Intelligence is revolutionizing many aspects of the pharmaceutical industry. Deep learning models are now routinely applied to guide drug discovery projects leading to faster and improved findings, but there are still many tasks with enormous unrealized potential. One such task is the reaction yield prediction. Every year more than one fifth of all synthesis attempts result in product yields which are either zero or too low. This equates to chemical and human resources being spent on activities which ultimately do not progress the programs, leading to a triple loss when accounting for the cost of opportunity in time wasted. In this work we pre-train a BERT model on more than 16 million reactions from 4 different data sources, and fine tune it to achieve an uncertainty calibrated global yield prediction model. This model is an improvement upon state of the art not just from the increase in pre-train data but also by introducing a new embedding layer which solves a few limitations of SMILES and enables integration of additional information such as equivalents and molecule role into the reaction encoding, the model is called BERT Enriched Embedding (BEE). The model is benchmarked on an open-source dataset against a state-of-the-art synthesis focused BERT showing a near 20-point improvement in r2 score. The model is fine-tuned and tested on an internal company data benchmark, and a prospective study shows that the application of the model can reduce the total number of negative reactions (yield under 5%) ran in Janssen by at least 34%. Lastly, we corroborate the previous results through experimental validation, by directly deploying the model in an on-going drug discovery project and showing that it can also be used successfully as a reagent recommender due to its fast inference speed and reliable confidence estimation, a critical feature for industry application.

Machine Learning Prediction of Mycobacterial Cell Wall Permeability of Drugs and Drug-like Compounds

The cell wall of Mycobacterium tuberculosis and related organisms has a very complex and unusual organization that makes it much less permeable to nutrients and antibiotics, leading to the low activity of many potential antimycobacterial drugs against whole-cell mycobacteria compared to their isolated molecular biotargets. The ability to predict and optimize the cell wall permeability could greatly enhance the development of novel antitubercular agents. Using an extensive structure-permeability dataset for organic compounds derived from published experimental big data (5371 compounds including 2671 penetrating and 2700 non-penetrating compounds), we have created a predictive classification model based on fragmental descriptors and an artificial neural network of a novel architecture that provides better accuracy (cross-validated balanced accuracy 0.768, sensitivity 0.768, specificity 0.769, area under ROC curve 0.911) and applicability domain compared with the previously published results.

Discovery of TIGIT inhibitors based on DEL and machine learning

Drug discovery has entered a new period of vigorous development with advanced technologies such as DNA-encoded library (DEL) and artificial intelligence (AI). The previous DEL-AI combination has been successfully applied in the drug discovery of classical kinase and receptor targets mainly based on the known scaffold. So far, there is no report of the DEL-AI combination on inhibitors targeting protein-protein interaction, including those undruggable targets with few or unknown active scaffolds. Here, we applied DEL technology on the T cell immunoglobulin and ITIM domain (TIGIT) target, resulting in the unique hit compound 1 (IC50 = 20.7 μM). Based on the screening data from DEL and hit derivatives a1-a34, a machine learning (ML) modeling process was established to address the challenge of poor sample distribution uniformity, which is also frequently encountered in DEL screening on new targets. In the end, the established ML model achieved a satisfactory hit rate of about 75% for derivatives in a high-scored area.

Predicting clinical trial outcomes using drug bioactivities through graph database integration and machine learning

The ability to estimate the probability of a drug to receive approval in clinical trials provides natural advantages to optimizing pharmaceutical research workflows. Success rates of clinical trials have deep implications for costs, duration of development, and under pressure due to stringent regulatory approval processes. We propose a machine learning approach that can predict the outcome of the trial with reliable accuracies, using biological activities, physicochemical properties of the compounds, target-related features, and NLP-based compound representation. In the above list, biological activities have never been used as an independent variable towards the prediction of clinical trial outcomes. We have extracted the drug-disease pair from clinical trials and mapped target(s) to that pair using multiple data sources. Empirical results demonstrate that ensemble learning outperforms independently trained, small-data ML models. We report results and inferences derived from a Random forest classifier with an average accuracy of 93%, and an F1 score of 0.96 for the "Pass" class. "Pass" refers to one of the two classes (Pass/Fail) of all clinical trials, and the model performed well in predicting the "Pass" category. Through the analysis of feature contributions to predictive capability, we have demonstrated that bioactivity plays a statistically significant role in predicting clinical trial outcome. A significant effort has gone into the production of the dataset that, for the first time, integrates clinical trial information with protein targets. Cleaned, organized, integrated data and code to map these entities, created as a part of this work, are available open-source. This reproducibility and the freely available code ensure that researchers with access to deep curated and proprietary clinical trial databases (we only use open-source data in this study) can further expand the scope of the results.

GenUI: interactive and extensible open source software platform for de novo molecular generation and cheminformatics

Many contemporary cheminformatics methods, including computer-aided de novo drug design, hold promise to significantly accelerate and reduce the cost of drug discovery. Thanks to this attractive outlook, the field has thrived and in the past few years has seen an especially significant growth, mainly due to the emergence of novel methods based on deep neural networks. This growth is also apparent in the development of novel de novo drug design methods with many new generative algorithms now available. However, widespread adoption of new generative techniques in the fields like medicinal chemistry or chemical biology is still lagging behind the most recent developments. Upon taking a closer look, this fact is not surprising since in order to successfully integrate the most recent de novo drug design methods in existing processes and pipelines, a close collaboration between diverse groups of experimental and theoretical scientists needs to be established. Therefore, to accelerate the adoption of both modern and traditional de novo molecular generators, we developed Generator User Interface (GenUI), a software platform that makes it possible to integrate molecular generators within a feature-rich graphical user interface that is easy to use by experts of diverse backgrounds. GenUI is implemented as a web service and its interfaces offer access to cheminformatics tools for data preprocessing, model building, molecule generation, and interactive chemical space visualization. Moreover, the platform is easy to extend with customizable frontend React.js components and backend Python extensions. GenUI is open source and a recently developed de novo molecular generator, DrugEx, was integrated as a proof of principle. In this work, we present the architecture and implementation details of GenUI and discuss how it can facilitate collaboration in the disparate communities interested in de novo molecular generation and computer-aided drug discovery.

Machine learning approach to discovery of small molecules with potential inhibitory action against vasoactive metalloproteases

With the advancement of combinatorial chemistry and big data, drug repositioning has boomed. In this sense, machine learning and artificial intelligence techniques offer a priori information to identify the most promising candidates. In this study, we combine QSAR and docking methodologies to identify compounds with potential inhibitory activity of vasoactive metalloproteases for the treatment of cardiovascular diseases. To develop this study, we used a database of 191 thermolysin inhibitor compounds, which is the largest as far as we know. First, we use Dragon's molecular descriptors (0-3D) to develop classification models using Bayesian networks (Naive Bayes) and artificial neural networks (Multilayer Perceptron). The obtained models are used for virtual screening of small molecules in the international DrugBank database. Second, docking experiments are carried out for all three enzymes using the Autodock Vina program, to identify possible interactions with the active site of human metalloproteases. As a result, high-performance artificial intelligence QSAR models are obtained for training and prediction sets. These allowed the identification of 18 compounds with potential inhibitory activity and an adequate oral bioavailability profile, which were evaluated using docking. Four of them showed high binding energies for the three enzymes, and we propose them as potential dual ACE/NEP inhibitors for the control of blood pressure. In summary, the in silico strategies used here constitute an important tool for the early identification of new antihypertensive drug candidates, with substantial savings in time and money.

Vibrational Sum-Frequency Generation Hyperspectral Microscopy for Molecular Self-Assembled Systems

In this review, we discuss the recent developments and applications of vibrational sum-frequency generation (VSFG) microscopy. This hyperspectral imaging technique can resolve systems without inversion symmetry, such as surfaces, interfaces and noncentrosymmetric self-assembled materials, in the spatial, temporal, and spectral domains. We discuss two common VSFG microscopy geometries: wide-field and confocal point-scanning. We then introduce the principle of VSFG and the relationships between hyperspectral imaging with traditional spectroscopy, microscopy, and time-resolved measurements. We further highlight crucial applications of VSFG microscopy in self-assembled monolayers, cellulose in plants, collagen fibers, and lattice self-assembled biomimetic materials. In these systems, VSFG microscopy reveals relationships between physical properties that would otherwise be hidden without being spectrally, spatially, and temporally resolved. Lastly, we discuss the recent development of ultrafast transient VSFG microscopy, which can spatially measure the ultrafast vibrational dynamics of self-assembled materials. The review ends with an outlook on the technical challenges of and scientific potential for VSFG microscopy.

Predicting Reaction Yields via Supervised Learning

Numerous disciplines, such as image recognition and language translation, have been revolutionized by using machine learning (ML) to leverage big data. In organic synthesis, providing accurate chemical reactivity predictions with supervised ML could assist chemists with reaction prediction, optimization, and mechanistic interrogation.To apply supervised ML to chemical reactions, one needs to define the object of prediction (e.g., yield, enantioselectivity, solubility, or a recommendation) and represent reactions with descriptive data. Our group's effort has focused on representing chemical reactions using DFT-derived physical features of the reacting molecules and conditions, which serve as features for building supervised ML models.In this Account, we present a review and perspective on three studies conducted by our group where ML models have been employed to predict reaction yield. First, we focus on a small reaction data set where 16 phosphine ligands were evaluated in a single Ni-catalyzed Suzuki-Miyaura cross-coupling reaction, and the reaction yield was modeled with linear regression. In this setting, where the regression complexity is strongly limited by the amount of available data, we emphasize the importance of identifying single features that are directly relevant to reactivity. Next, we focus on models trained on two larger data sets obtained with high-throughput experimentation (HTE). With hundreds to thousands of reactions available, more complex models can be explored, for example, models that algorithmically perform feature selection from a broad set of candidate features. We examine how a variety of ML algorithms model these data sets and how well these models generalize to out-of-sample substrates. Specifically, we compare the ML models that use DFT-based featurization to a baseline model that is obtained with features that carry no physical information, that is, random features, and to a naive non-ML model that averages yields of reactions that share the same conditions and substrate combinations. We find that for only one of the two data sets, DFT-based featurization leads to a significant, although moderate, out-of-sample prediction improvement. The source of this improvement was further isolated to specific features which allowed us to formulate a testable mechanistic hypothesis that was validated experimentally. Finally, we offer remarks on supervised ML model building on HTE data sets focusing on algorithmic improvements in model training.Statistical methods in chemistry have a rich history, but only recently has ML gained widespread attention in reaction development. As the untapped potential of ML is explored, novel tools are likely to arise from future research. Our studies suggest that supervised ML can lead to improved predictions of reaction yield over simpler modeling methods and facilitate mechanistic understanding of reaction dynamics. However, further research and development is required to establish ML as an indispensable tool in reactivity modeling.

Generative Algorithm for Molecular Graphs Uncovers Products of Oil Oxidation

The autoxidation of triglyceride (or triacylglycerol, TAG) is a poorly understood complex system. It is known from mass spectrometry measurements that, although initiated by a single molecule, this system involves an abundance of intermediate species and a complex network of reactions. For this reason, the attribution of the mass peaks to exact molecular structures is difficult without additional information about the system. We provide such information using a graph theory-based algorithm. Our algorithm performs an automatic discovery of the chemical reaction network that is responsible for the complexity of the mass spectra in drying oils. This knowledge is then applied to match experimentally measured mass spectra with computationally predicted molecular graphs. We demonstrate this methodology on the autoxidation of triolein as measured by electrospray ionization-mass spectrometry (ESI-MS). Our protocol can be readily applied to investigate other oils and their mixtures.

Troubleshooting unstable molecules in chemical space

A key challenge in automated chemical compound space explorations is ensuring veracity in minimum energy geometries-to preserve intended bonding connectivities. We discuss an iterative high-throughput workflow for connectivity preserving geometry optimizations exploiting the nearness between quantum mechanical models. The methodology is benchmarked on the QM9 dataset comprising DFT-level properties of 133 885 small molecules, wherein 3054 have questionable geometric stability. Of these, we successfully troubleshoot 2988 molecules while maintaining a bijective mapping with the Lewis formulae. Our workflow, based on DFT and post-DFT methods, identifies 66 molecules as unstable; 52 contain -NNO-, and the rest are strained due to pyramidal sp2 C. In the curated dataset, we inspect molecules with long C-C bonds and identify ultralong candidates (r > 1.70 Å) supported by topological analysis of electron density. The proposed strategy can aid in minimizing unintended structural rearrangements during quantum chemistry big data generation.

Large-Scale Modeling of Multispecies Acute Toxicity End Points Using Consensus of Multitask Deep Learning Methods

Computational methods to predict molecular properties regarding safety and toxicology represent alternative approaches to expedite drug development, screen environmental chemicals, and thus significantly reduce associated time and costs. There is a strong need and interest in the development of computational methods that yield reliable predictions of toxicity, and many approaches, including the recently introduced deep neural networks, have been leveraged towards this goal. Herein, we report on the collection, curation, and integration of data from the public data sets that were the source of the ChemIDplus database for systemic acute toxicity. These efforts generated the largest publicly available such data set comprising > 80,000 compounds measured against a total of 59 acute systemic toxicity end points. This data was used for developing multiple single- and multitask models utilizing random forest, deep neural networks, convolutional, and graph convolutional neural network approaches. For the first time, we also reported the consensus models based on different multitask approaches. To the best of our knowledge, prediction models for 36 of the 59 end points have never been published before. Furthermore, our results demonstrated a significantly better performance of the consensus model obtained from three multitask learning approaches that particularly predicted the 29 smaller tasks (less than 300 compounds) better than other models developed in the study. The curated data set and the developed models have been made publicly available at https://github.com/ncats/ld50-multitask, https://predictor.ncats.io/, and https://cactus.nci.nih.gov/download/acute-toxicity-db (data set only) to support regulatory and research applications.

Open Innovation in Medical and Pharmaceutical Research: A Literature Landscape Analysis

Open innovation in medical and pharmaceutical research has grown steadily over the last decade. However, the performance of the published literature in terms of the scientific impact and gaining social media attention remains largely unexplored. The scientific literature of open innovation was examined by means of bibliometric analyses to identify the most prolific authors, organizations, countries, journals, research areas, and recurring terms. By accessing the Web of Science Core Collection and Altmetric electronic databases, citation-related and Altmetric data were evaluated. Public-private partnerships and a selection of newly introduced potential novel drugs in the analyzed publications were identified. North America and Europe were the major literature contributors. Research outputs were mainly published in journals focused on business and economics, pharmacology and pharmacy, and engineering. Many pharmaceutical and biotechnological companies contributed to the analyzed publications, with higher mean citation counts and social media attention (Altmetric score) than nonindustry articles. Public-private partnerships fostered financial support, sharing of expertise and intellectual property, and research collaborations. In summary, open innovation might serve as a powerful strategy to both benefit the involved industry entities and accelerate the development of solutions and products for the betterment of human health.

Big data and machine learning for materials science

Herein, we review aspects of leading-edge research and innovation in materials science that exploit big data and machine learning (ML), two computer science concepts that combine to yield computational intelligence. ML can accelerate the solution of intricate chemical problems and even solve problems that otherwise would not be tractable. However, the potential benefits of ML come at the cost of big data production; that is, the algorithms demand large volumes of data of various natures and from different sources, from material properties to sensor data. In the survey, we propose a roadmap for future developments with emphasis on computer-aided discovery of new materials and analysis of chemical sensing compounds, both prominent research fields for ML in the context of materials science. In addition to providing an overview of recent advances, we elaborate upon the conceptual and practical limitations of big data and ML applied to materials science, outlining processes, discussing pitfalls, and reviewing cases of success and failure.

Artificial intelligence and automation in computer aided synthesis planning

In this perspective we deal with questions pertaining to the development of synthesis planning technologies over the course of recent years.

From Big Data to Artificial Intelligence: chemoinformatics meets new challenges

The increasing volume of biomedical data in chemistry and life sciences requires development of new methods and approaches for their analysis. Artificial Intelligence and machine learning, especially neural networks, are increasingly used in the chemical industry, in particular with respect to Big Data. This editorial highlights the main results presented during the special session of the International Conference on Neural Networks organized by "Big Data in Chemistry" project and draws perspectives on the future progress of the field.

Big Data in metagenomics: Apache Spark vs MPI

The progress of next-generation sequencing has lead to the availability of massive data sets used by a wide range of applications in biology and medicine. This has sparked significant interest in using modern Big Data technologies to process this large amount of information in distributed memory clusters of commodity hardware. Several approaches based on solutions such as Apache Hadoop or Apache Spark, have been proposed. These solutions allow developers to focus on the problem while the need to deal with low level details, such as data distribution schemes or communication patterns among processing nodes, can be ignored. However, performance and scalability are also of high importance when dealing with increasing problems sizes, making in this way the usage of High Performance Computing (HPC) technologies such as the message passing interface (MPI) a promising alternative. Recently, MetaCacheSpark, an Apache Spark based software for detection and quantification of species composition in food samples has been proposed. This tool can be used to analyze high throughput sequencing data sets of metagenomic DNA and allows for dealing with large-scale collections of complex eukaryotic and bacterial reference genome. In this work, we propose MetaCache-MPI, a fast and memory efficient solution for computing clusters which is based on MPI instead of Apache Spark. In order to evaluate its performance a comparison is performed between the original single CPU version of MetaCache, the Spark version and the MPI version we are introducing. Results show that for 32 processes, MetaCache-MPI is 1.65× faster while consuming 48.12% of the RAM memory used by Spark for building a metagenomics database. For querying this database, also with 32 processes, the MPI version is 3.11× faster, while using 55.56% of the memory used by Spark. We conclude that the new MetaCache-MPI version is faster in both building and querying the database and uses less RAM memory, when compared with MetaCacheSpark, while keeping the accuracy of the original implementation.

Autonomous Discovery in the Chemical Sciences Part II: Outlook

This two-part Review examines how automation has contributed to different aspects of discovery in the chemical sciences. In this second part, we reflect on a selection of exemplary studies. It is increasingly important to articulate what the role of automation and computation has been in the scientific process and how that has or has not accelerated discovery. One can argue that even the best automated systems have yet to "discover" despite being incredibly useful as laboratory assistants. We must carefully consider how they have been and can be applied to future problems of chemical discovery in order to effectively design and interact with future autonomous platforms. The majority of this Review defines a large set of open research directions, including improving our ability to work with complex data, build empirical models, automate both physical and computational experiments for validation, select experiments, and evaluate whether we are making progress towards the ultimate goal of autonomous discovery. Addressing these practical and methodological challenges will greatly advance the extent to which autonomous systems can make meaningful discoveries.

Going All In: A Strategic Investment in In Silico Toxicology

As vast numbers of new chemicals are introduced to market annually, we are faced with the grand challenge of protecting humans and the environment while minimizing economically and ethically costly animal testing. In silico models promise to be the solution we seek, but we find ourselves at crossroads of future development efforts that would ensure standalone applicability and reliability of these tools. A conscientious effort that prioritizes experimental testing to support the needs of in silico models (versus regulatory needs) is called for to achieve this goal. Using economic analogy in the title of this work, we argue that a prudent investment is to go all-in to support in silico model development, rather than gamble our future by keeping the status quo of a "balanced portfolio" of testing approaches. We discuss two paths to future in silico toxicology-one based on big-data statistics ("broadsword"), and the other based on direct modeling of molecular interactions ("scalpel")-and offer rationale that the latter approach is more transparent, is better aligned with our quest for fundamental knowledge, and has a greater potential to succeed if we are willing to transform our toxicity-testing paradigm.

User online behavior based on big data distributed clustering algorithm

With the development of big data technology more and more perfect, many colleges and universities have begun to use it to analyze the construction work. In daily life, such as class, study, and entertainment, the campus network exists. The purpose of this article is to study the online behavior of users, analyze students’ use of the campus network by analyzing students, and not only have a clear understanding of the students’ online access but also feedback on the operation and maintenance of the campus network. Based on the big data, this article uses distributed clustering algorithm to study the online behavior of users. This article selects a college online user as the research object and studies and analyzes the online behavior of school users. This study found that the second-year student network usage is as high as 330,000, which is 60.98% more than the senior. In addition, the majority of student users spend most of their online time on the weekend, and the other time is not much different. The duration is concentrated within 1 h, 1–2 h, 2–3 h in these three time periods. By studying the user’s online behavior, you can understand the utilization rate of the campus network bandwidth resources and the distribution of the use of the network, to prevent students from indulging in the virtual network world, and to ensure that the network users can improve the online experience of the campus network while accessing the network resources reasonably. The research provides a reference for network administrators to adjust network bandwidth and optimize the network.

Secure multiparty computation for privacy-preserving drug discovery

Motivation

Quantitative structure–activity relationship (QSAR) and drug–target interaction (DTI) prediction are both commonly used in drug discovery. Collaboration among pharmaceutical institutions can lead to better performance in both QSAR and DTI prediction. However, the drug-related data privacy and intellectual property issues have become a noticeable hindrance for inter-institutional collaboration in drug discovery.

Results

We have developed two novel algorithms under secure multiparty computation (MPC), including QSARMPC and DTIMPC, which enable pharmaceutical institutions to achieve high-quality collaboration to advance drug discovery without divulging private drug-related information. QSARMPC, a neural network model under MPC, displays good scalability and performance and is feasible for privacy-preserving collaboration on large-scale QSAR prediction. DTIMPC integrates drug-related heterogeneous network data and accurately predicts novel DTIs, while keeping the drug information confidential. Under several experimental settings that reflect the situations in real drug discovery scenarios, we have demonstrated that DTIMPC possesses significant performance improvement over the baseline methods, generates novel DTI predictions with supporting evidence from the literature and shows the feasible scalability to handle growing DTI data. All these results indicate that QSARMPC and DTIMPC can provide practically useful tools for advancing privacy-preserving drug discovery.

Availability and implementation

The source codes of QSARMPC and DTIMPC are available on the GitHub: https://github.com/rongma6/QSARMPC_DTIMPC.git.

Supplementary information

Supplementary data are available at Bioinformatics online.

A curious formulation robot enables the discovery of a novel protocell behavior

We describe a chemical robotic assistant equipped with a curiosity algorithm (CA) that can efficiently explore the states a complex chemical system can exhibit. The CA-robot is designed to explore formulations in an open-ended way with no explicit optimization target. By applying the CA-robot to the study of self-propelling multicomponent oil-in-water protocell droplets, we are able to observe an order of magnitude more variety in droplet behaviors than possible with a random parameter search and given the same budget. We demonstrate that the CA-robot enabled the observation of a sudden and highly specific response of droplets to slight temperature changes. Six modes of self-propelled droplet motion were identified and classified using a time-temperature phase diagram and probed using a variety of techniques including NMR. This work illustrates how CAs can make better use of a limited experimental budget and significantly increase the rate of unpredictable observations, leading to new discoveries with potential applications in formulation chemistry.

Identification of Target Associations for Polypharmacology from Analysis of Crystallographic Ligands of the Protein Data Bank

The design of a chemical entity that potently and selectively binds to a biological target of therapeutic relevance has dominated the scene of drug discovery so far. However, recent findings suggest that multitarget ligands may be endowed with superior efficacy and be less prone to drug resistance. The Protein Data Bank (PDB) provides experimentally validated structural information about targets and bound ligands. Therefore, it represents a valuable source of information to help identifying active sites, understanding pharmacophore requirements, designing novel ligands, and inferring structure-activity relationships. In this study, we performed a large-scale analysis of the PDB by integrating different ligand-based and structure-based approaches, with the aim of identifying promising target associations for polypharmacology based on reported crystal structure information. First, the 2D and 3D similarity profiles of the crystallographic ligands were evaluated using different ligand-based methods. Then, activity data of pairs of similar ligands binding to different targets were inspected by comparing structural information with bioactivity annotations reported in the ChEMBL, BindingDB, BindingMOAD, and PDBbind databases. Afterward, extensive docking screenings of ligands in the identified cross-targets were made in order to validate and refine the ligand-based results. Finally, the therapeutic relevance of the identified target combinations for polypharmacology was evaluated from comparison with information on therapeutic targets reported in the Therapeutic Target Database (TTD). The results led to the identification of several target associations with high therapeutic potential for polypharmacology.

Computational Drug Repurposing: Current Trends

:

Biomedical discovery has been reshaped upon the exploding digitization of data which can be retrieved from a number of sources, ranging from clinical pharmacology to cheminformatics-driven databases. Now, supercomputing platforms and publicly available resources such as biological, physicochemical, and clinical data, can all be integrated to construct a detailed map of signaling pathways and drug mechanisms of action in relation to drug candidates. Recent advancements in computer-aided data mining have facilitated analyses of ‘big data’ approaches and the discovery of new indications for pre-existing drugs has been accelerated. Linking gene-phenotype associations to predict novel drug-disease signatures or incorporating molecular structure information of drugs and protein targets with other kinds of data derived from systems biology provide great potential to accelerate drug discovery and improve the success of drug repurposing attempts. In this review, we highlight commonly used computational drug repurposing strategies, including bioinformatics and cheminformatics tools, to integrate large-scale data emerging from the systems biology, and consider both the challenges and opportunities of using this approach. Moreover, we provide successful examples and case studies that combined various in silico drug-repurposing strategies to predict potential novel uses for known therapeutics.

Data Mining Approach for Extraction of Useful Information About Biologically Active Compounds from Publications

A lot of high quality data on the biological activity of chemical compounds are required throughout the whole drug discovery process: from development of computational models of the structure-activity relationship to experimental testing of lead compounds and their validation in clinics. Currently, a large amount of such data is available from databases, scientific publications, and patents. Biological data are characterized by incompleteness, uncertainty, and low reproducibility. Despite the existence of free and commercially available databases of biological activities of compounds, they usually lack unambiguous information about peculiarities of biological assays. On the other hand, scientific papers are the primary source of new data disclosed to the scientific community for the first time. In this study, we have developed and validated a data-mining approach for extraction of text fragments containing description of bioassays. We have used this approach to evaluate compounds and their biological activity reported in scientific publications. We have found that categorization of papers into relevant and irrelevant may be performed based on the machine-learning analysis of the abstracts. Text fragments extracted from the full texts of publications allow their further partitioning into several classes according to the peculiarities of bioassays. We demonstrate the applicability of our approach to the comparison of the endpoint values of biological activity and cytotoxicity of reference compounds.

Guiding Drugs to Target-Harboring Organelles: Stretching Drug-Delivery to a Higher Level of Resolution

The ratio between the dose of drug required for optimal efficacy and the dose that causes toxicity is referred to as the therapeutic window. This ratio can be increased by directing the drug to the diseased tissue or pathogenic cell. For drugs targeting fungi and malignant cells, the therapeutic window can be further improved by increasing the resolution of drug delivery to the specific organelle that harbors the drug's target. Organelle targeting is challenging and is, therefore, an under-exploited strategy. Here we provide an overview of recent advances in control of the subcellular distribution of small molecules with the focus on chemical modifications. Highlighted are recent examples of active and passive organelle-specific targeting by incorporation of organelle-directing molecular determinants or by chemical modifications of the pharmacophore. The outstanding potential that lies in the development of organelle-specific drugs is becoming increasingly apparent.

[Discovering new antiretroviral compounds in "Big Data" chemical space of the SAVI library]

Despite significant advances in the application of highly active antiretroviral therapy, the development of new drugs for the treatment of HIV infection remains an important task because the existing drugs do not provide a complete cure, cause serious side effects and lead to the emergence of resistance. In 2015, a consortium of American and European scientists and specialists launched a project to create the SAVI (Synthetically Accessible Virtual Inventory) library. Its 2016 version of over 283 million structures of new easily synthesizable organic molecules, each annotated with a proposed synthetic route, were generated <i>in silico</i> for the purpose of searching for safer and more potent pharmacological substances. We have developed an algorithm for comparing large chemical databases (DB) based on the representation of structural formulas in SMILES codes, and evaluated the possibility of detecting new antiretroviral compounds in the SAVI database. After analyzing the intersection of SAVI with 97 million structures of the PubChem database, we found that only a small part of the SAVI (~0.015%) is represented in PubChem, which indicates a significant novelty of this virtual library. However, among those structures, 632 compounds tested for anti-HIV activity were detected, 41 of which had the desired activity. Thus, our studies for the first time demonstrated that SAVI is a promising source for the search for new anti-HIV compounds.

Intuition-Enabled Machine Learning Beats the Competition When Joint Human-Robot Teams Perform Inorganic Chemical Experiments

Traditionally, chemists have relied on years of training and accumulated experience in order to discover new molecules. But the space of possible molecules is so vast that only a limited exploration with the traditional methods can be ever possible. This means that many opportunities for the discovery of interesting phenomena have been missed, and in addition, the inherent variability of these phenomena can make them difficult to control and understand. The current state-of-the-art is moving toward the development of automated and eventually fully autonomous systems coupled with in-line analytics and decision-making algorithms. Yet even these, despite the substantial progress achieved recently, still cannot easily tackle large combinatorial spaces, as they are limited by the lack of high-quality data. Herein, we explore the utility of active learning methods for exploring the chemical space by comparing the collaboration between human experimenters with an algorithm-based search against their performance individually to probe the self-assembly and crystallization of the polyoxometalate cluster Na₆[Mo₁₂₀Ce₆O₃₆₆H₁₂(H₂O)₇₈]·200H₂O (1). We show that the robot-human teams are able to increase the prediction accuracy to 75.6 ± 1.8%, from 71.8 ± 0.3% with the algorithm alone and 66.3 ± 1.8% from only the human experimenters demonstrating that human-robot teams can beat robots or humans working alone.

A Survey of Multi-task Learning Methods in Chemoinformatics

Despite the increasing volume of available data, the proportion of experimentally measured data remains small compared to the virtual chemical space of possible chemical structures. Therefore, there is a strong interest in simultaneously predicting different ADMET and biological properties of molecules, which are frequently strongly correlated with one another. Such joint data analyses can increase the accuracy of models by exploiting their common representation and identifying common features between individual properties. In this work we review the recent developments in multi-learning approaches as well as cover the freely available tools and packages that can be used to perform such studies.

Comparative Study of Multitask Toxicity Modeling on a Broad Chemical Space

Acute toxicity is one of the most challenging properties to predict purely with computational methods due to its direct relationship to biological interactions. Moreover, toxicity can be represented by different end points: it can be measured for different species using different types of administration, etc., and it is questionable if the knowledge transfer between end points is possible. We performed a comparative study of prediction multitask toxicity for a broad chemical space using different descriptors and modeling algorithms and applied multitask learning for a large toxicity data set extracted from the Registry of Toxic Effects of Chemical Substances (RTECS). We demonstrated that multitask modeling provides significant improvement over single-output models and other machine learning methods. Our research reveals that multitask learning can be very useful to improve the quality of acute toxicity modeling and raises a discussion about the usage of multitask approaches for regulation purposes. Our MultiTox models are freely available in OCHEM platform ( ochem.eu/multitox ) under CC-BY-NC license.

A Strength-Weaknesses-Opportunities-Threats (SWOT) Analysis of Cheminformatics in Natural Product Research

Cheminformatics-based techniques, such as molecular modeling, docking, virtual screening, and machine learning, are well accepted for their usefulness in drug discovery and development of therapeutically relevant small molecules. Although delayed by several decades, their application in natural product research has led to outstanding findings. Combining information obtained from different sources, i.e., virtual predictions, traditional medicine, structural, biochemical, and biological data, and handling big data effectively will open up new possibilities, but also challenges in the future. Strategies and examples will be presented on how to integrate cheminformatics in pharmacognostic workflows to benefit from these two highly complementary disciplines toward streamlining experimental efforts. While considering their limits and pitfalls and by exploiting their potential, computer-aided strategies should successfully guide future studies and thereby augment our knowledge of bioactive natural lead structures.

Artificial intelligence for aging and longevity research: Recent advances and perspectives

The applications of modern artificial intelligence (AI) algorithms within the field of aging research offer tremendous opportunities. Aging is an almost universal unifying feature possessed by all living organisms, tissues, and cells. Modern deep learning techniques used to develop age predictors offer new possibilities for formerly incompatible dynamic and static data types. AI biomarkers of aging enable a holistic view of biological processes and allow for novel methods for building causal models-extracting the most important features and identifying biological targets and mechanisms. Recent developments in generative adversarial networks (GANs) and reinforcement learning (RL) permit the generation of diverse synthetic molecular and patient data, identification of novel biological targets, and generation of novel molecular compounds with desired properties and geroprotectors. These novel techniques can be combined into a unified, seamless end-to-end biomarker development, target identification, drug discovery and real world evidence pipeline that may help accelerate and improve pharmaceutical research and development practices. Modern AI is therefore expected to contribute to the credibility and prominence of longevity biotechnology in the healthcare and pharmaceutical industry, and to the convergence of countless areas of research.

Telechemistry: monitoring chemical reactionsviathe cloud using the Particle Photon Wi-Fi module

A popular electronic module and the associated Internet-of-Things tools provide chemists with more control over long-term experimental procedures and enhance lab work safety.