Efficient discovery of responses of proteins to compounds using active learning

The present state and challenges of active learning in drug discovery

Active learning (AL) is an iterative feedback process that efficiently identifies valuable data within vast chemical space, even with limited labeled data. This characteristic renders it a valuable approach to tackle the ongoing challenges faced in drug discovery, such as the ever-expanding explore space and the limitations of labeled data. Consequently, AL is increasingly gaining prominence in the field of drug development. In this paper, we comprehensively review the application of AL at all stages of drug discovery, including compounds-target interaction prediction, virtual screening, molecular generation and optimization, as well as molecular properties prediction. Additionally, we discuss the challenges and prospects associated with the current applications of AL in drug discovery.

A Comprehensive Investigation of Active Learning Strategies for Conducting Anti-Cancer Drug Screening

It is well-known that cancers of the same histology type can respond differently to a treatment. Thus, computational drug response prediction is of paramount importance for both preclinical drug screening studies and clinical treatment design. To build drug response prediction models, treatment response data need to be generated through screening experiments and used as input to train the prediction models. In this study, we investigate various active learning strategies of selecting experiments to generate response data for the purposes of (1) improving the performance of drug response prediction models built on the data and (2) identifying effective treatments. Here, we focus on constructing drug-specific response prediction models for cancer cell lines. Various approaches have been designed and applied to select cell lines for screening, including a random, greedy, uncertainty, diversity, combination of greedy and uncertainty, sampling-based hybrid, and iteration-based hybrid approach. All of these approaches are evaluated and compared using two criteria: (1) the number of identified hits that are selected experiments validated to be responsive, and (2) the performance of the response prediction model trained on the data of selected experiments. The analysis was conducted for 57 drugs and the results show a significant improvement on identifying hits using active learning approaches compared with the random and greedy sampling method. Active learning approaches also show an improvement on response prediction performance for some of the drugs and analysis runs compared with the greedy sampling method.

Efficient design of peptide-binding polymers using active learning approaches

Active learning (AL) has become a subject of active recent research both in industry and academia as an efficient approach for rapid design and discovery of novel chemicals, materials, and polymers. Herein, we have assessed the applicability of AL for the discovery of polymeric micelle formulations for poorly soluble drugs. We were motivated by the key advantages of this approach making it a desirable strategy for rational design of drug delivery systems due toto its ability to (i) employ relatively small datasets for model development, (ii) iterate between model development and model assessment using small external datasets that can be either generated in focused experimental studies or formed from subsets of the initial training data, and (iii) progressively evolve models towards increasingly more reliable predictions and the identification of novel chemicals with the desired properties. In this study, we compared various AL protocols for their effectiveness in finding biologically active molecules using synthetic datasets. We have investigated the dependency of AL performance on the size of the initial training set, the relative complexity of the task, and the choice of the initial training dataset. We found that AL techniques as applied to regression modeling offer no benefits over random search, while AL used for classification tasks performs better than models built for randomly selected training sets but still quite far from perfect. Using the best performing AL protocol,. Finally, the best performing AL approach was employed to discover and experimentally validate novel binding polymers for a case study of asialoglycoprotein receptor (ASGPR).

Synergy between machine learning and natural products cheminformatics: Application to the lead discovery of anthraquinone derivatives

Cheminformatics utilizing machine learning (ML) techniques have opened up a new horizon in drug discovery. This is owing to vast chemical space expansion with rocketing numbers of expected hits and lead compounds that match druggable macromolecular targets, in particular from natural compounds. Due to the natural products' (NP) structural complexity, uniqueness, and diversity, they could occupy a bigger space in pharmaceuticals, allowing the industry to pursue more selective leads in the nanomolar range of binding affinity. ML is an essential part of each step of the drug design pipeline, such as target prediction, compound library preparation, and lead optimization. Notably, molecular mechanic and dynamic simulations, induced docking, and free energy perturbations are essential in predicting best binding poses, binding free energy values, and molecular mechanics force fields. Those applications have leveraged from artificial intelligence (AI), which decreases the computational costs required for such costly simulations. This review aimed to describe chemical space and compound libraries related to NPs. High-throughput screening utilized for fractionating NPs and high-throughput virtual screening and their strategies, and significance, are reviewed. Particular emphasis was given to AI approaches, ML tools, algorithms, and techniques, especially in drug discovery of macrocyclic compounds and approaches in computer-aided and ML-based drug discovery. Anthraquinone derivatives were discussed as a source of new lead compounds that can be developed using ML tools for diverse medicinal uses such as cancer, infectious diseases, and metabolic disorders. Furthermore, the power of principal component analysis in understanding relevant protein conformations, and molecular modeling of protein-ligand interaction were also presented. Apart from being a concise reference for cheminformatics, this review is a useful text to understand the application of ML-based algorithms to molecular dynamics simulation and in silico absorption, distribution, metabolism, excretion, and toxicity prediction.

Advancing pharmacy and healthcare with virtual digital technologies

Digitalisation of the healthcare sector promises to revolutionise patient healthcare globally. From the different technologies, virtual tools including artificial intelligence, blockchain, virtual, and augmented reality, to name but a few, are providing significant benefits to patients and the pharmaceutical sector alike, ranging from improving access to clinicians and medicines, as well as improving real-time diagnoses and treatments. Indeed, it is envisioned that such technologies will communicate together in real-time, as well as with their physical counterparts, to create a large-scale, cyber healthcare system. Despite the significant benefits that virtual-based digital health technologies can bring to patient care, a number of challenges still remain, ranging from data security to acceptance within the healthcare sector. This review provides a timely account of the benefits and challenges of virtual health interventions, as well an outlook on how such technologies can be transitioned from research-focused towards real-world healthcare and pharmaceutical applications to transform treatment pathways for patients worldwide.

Active Semisupervised Model for Improving the Identification of Anticancer Peptides

Cancer is one of the most dangerous threats to human health. Accurate identification of anticancer peptides (ACPs) is valuable for the development and design of new anticancer agents. However, most machine-learning algorithms have limited ability to identify ACPs, and their accuracy is sensitive to the amount of label data. In this paper, we construct a new technology that combines active learning (AL) and label propagation (LP) algorithm to solve this problem, called (ACP-ALPM). First, we develop an efficient feature representation method based on various descriptor information and coding information of the peptide sequence. Then, an AL strategy is used to filter out the most informative data for model training, and a more powerful LP classifier is cast through continuous iterations. Finally, we evaluate the performance of ACP-ALPM and compare it with that of some of the state-of-the-art and classic methods; experimental results show that our method is significantly superior to them. In addition, through the experimental comparison of random selection and AL on three public data sets, it is proved that the AL strategy is more effective. Notably, a visualization experiment further verified that AL can utilize unlabeled data to improve the performance of the model. We hope that our method can be extended to other types of peptides and provide more inspiration for other similar work.

Evaluation of Categorical Matrix Completion Algorithms: Towards Improved Active Learning for Drug Discovery

MOTIVATION

High throughput and high content screening are extensively used to determine the effect of small molecule compounds and other potential therapeutics upon particular targets as part of the early drug development process. However, screening is typically used to find compounds that have a desired effect but not to identify potential undesirable side effects. This is because the size of the search space precludes measuring the potential effect of all compounds on all targets. Active machine learning has been proposed as a solution to this problem.

RESULTS

In this article, we describe an improved imputation method, Impute By Committee, for completion of matrices containing categorical values. We compare this method to existing approaches in the context of modeling the effects of many compounds on many targets using latent similarities between compounds and conditions. We also compare these methods for the task of driving active learning in well-characterized settings for synthetic and real datasets. Our new approach performed the best overall both in the accuracy of matrix completion itself and in the number of experiments needed to train an accurate predictive model compared to random selection of experiments. We further improved upon the performance of our new method by developing an adaptive switching strategy for active learning that iteratively chooses between different matrix completion methods.

AVAILABILITY

A Reproducible Research Archive containing all data and code will be made available upon acceptance at http://murphylab.cbd.cmu.edu/software.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Active learning effectively identifies a minimal set of maximally informative and asymptotically performant cytotoxic structure-activity patterns in NCI-60 cell lines

The NCI-60 cancer cell line screening panel has provided insights for development of subtype-specific chemical therapies and repurposing. By extracting chemical structure and cytotoxicity patterns, virtual screening potentially complements the availability of high-throughput assay platforms and improves bioactive compound discovery rates by computational prefiltering of candidate compound libraries. Many groups report high prediction performances in computational models of NCI-60 data when using cross-validation or similar techniques, yet prospective therapy development in novel cancers may have little to no such data and further may not have the resources to perform hit identification using large compound libraries. In contrast to bulk screening and analysis, the active learning methodology has demonstrated how to identify compounds for screening in small batches and update computational models iteratively, leading to predictive models with a minimum number of compounds, and importantly clarifying data volumes at which limits in predictive ability are achieved. Here, in replicate per-cell line experiments using 50% of data (∼20 000 compounds) as the external prediction target, predictive limits are reproducibly demonstrated at the stage of systematic selection of 10-30% of the incorporable half. The pattern was consistent across all 60 cell lines. Limits of predictability are found to be correlated to the doubling times of cell lines and the number of cellular response discontinuities (activity cliffs) present per cell line. Organization into chemical scaffolds delineated degrees of predictive challenge. These results provide key insights for strategies in developing new inhibitors in existing cell lines or for future automated therapy selection in personalized oncotherapy.

Active semi-supervised learning for biological data classification

Due to datasets have continuously grown, efforts have been performed in the attempt to solve the problem related to the large amount of unlabeled data in disproportion to the scarcity of labeled data. Another important issue is related to the trade-off between the difficulty in obtaining annotations provided by a specialist and the need for a significant amount of annotated data to obtain a robust classifier. In this context, active learning techniques jointly with semi-supervised learning are interesting. A smaller number of more informative samples previously selected (by the active learning strategy) and labeled by a specialist can propagate the labels to a set of unlabeled data (through the semi-supervised one). However, most of the literature works neglect the need for interactive response times that can be required by certain real applications. We propose a more effective and efficient active semi-supervised learning framework, including a new active learning method. An extensive experimental evaluation was performed in the biological context (using the ALL-AML, Escherichia coli and PlantLeaves II datasets), comparing our proposals with state-of-the-art literature works and different supervised (SVM, RF, OPF) and semi-supervised (YATSI-SVM, YATSI-RF and YATSI-OPF) classifiers. From the obtained results, we can observe the benefits of our framework, which allows the classifier to achieve higher accuracies more quickly with a reduced number of annotated samples. Moreover, the selection criterion adopted by our active learning method, based on diversity and uncertainty, enables the prioritization of the most informative boundary samples for the learning process. We obtained a gain of up to 20% against other learning techniques. The active semi-supervised learning approaches presented a better trade-off (accuracies and competitive and viable computational times) when compared with the active supervised learning ones.

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.

Iterative experimental design based on active machine learning reduces the experimental burden associated with reaction screening

Through iterative selection of maximally informative experiments, active learning renders exhaustive screening obsolete. Chosen experiments are used to train models that are accurate over the entire domain, thus reducing the experiment burden.

Selection of Informative Examples in Chemogenomic Datasets

High-throughput and high-content screening campaigns have resulted in the creation of large chemogenomic matrices. These matrices form the training data which is used to build ligand-target interaction models for pharmacological and chemical biology research. While academic, government, and industrial efforts continuously add to the ligand-target data pairs available for modeling, major research efforts are devoted to improving machine learning techniques to cope with the sparseness, heterogeneity, and size of available datasets as well as inherent noise and bias. This "race of arms" has led to the creation of algorithms to generate highly complex models with high prediction performance at the cost of training efficiency as well as interpretability.In contrast, recent studies have challenged the necessity for "big data" in chemogenomic modeling and found that models built on larger numbers of examples do not necessarily result in better predictive abilities. Automated adaptive selection of the training data (ligand-target instances) used for model creation can result in considerably smaller training sets that retain prediction performance on par with training using hundreds of thousands of data points. In this chapter, we describe the protocols used for one such iterative chemogenomic selection technique, including model construction and update as well as possible techniques for evaluations of constructed models and analysis of the iterative model construction.

Active learning for computational chemogenomics

Aim: Computational chemogenomics models the compound–protein interaction space, typically for drug discovery, where existing methods predominantly either incorporate increasing numbers of bioactivity samples or focus on specific subfamilies of proteins and ligands. As an alternative to modeling entire large datasets at once, active learning adaptively incorporates a minimum of informative examples for modeling, yielding compact but high quality models. Results/methodology: We assessed active learning for protein/target family-wide chemogenomic modeling by replicate experiment. Results demonstrate that small yet highly predictive models can be extracted from only 10–25% of large bioactivity datasets, irrespective of molecule descriptors used. Conclusion: Chemogenomic active learning identifies small subsets of ligand–target interactions in a large screening database that lead to knowledge discovery and highly predictive models.

Finding an appropriate equation to measure similarity between binary vectors: case studies on Indonesian and Japanese herbal medicines

Background

The binary similarity and dissimilarity measures have critical roles in the processing of data consisting of binary vectors in various fields including bioinformatics and chemometrics. These metrics express the similarity and dissimilarity values between two binary vectors in terms of the positive matches, absence mismatches or negative matches. To our knowledge, there is no published work presenting a systematic way of finding an appropriate equation to measure binary similarity that performs well for certain data type or application. A proper method to select a suitable binary similarity or dissimilarity measure is needed to obtain better classification results.

Results

In this study, we proposed a novel approach to select binary similarity and dissimilarity measures. We collected 79 binary similarity and dissimilarity equations by extensive literature search and implemented those equations as an R package called bmeasures. We applied these metrics to quantify the similarity and dissimilarity between herbal medicine formulas belonging to the Indonesian Jamu and Japanese Kampo separately. We assessed the capability of binary equations to classify herbal medicine pairs into match and mismatch efficacies based on their similarity or dissimilarity coefficients using the Receiver Operating Characteristic (ROC) curve analysis. According to the area under the ROC curve results, we found Indonesian Jamu and Japanese Kampo datasets obtained different ranking of binary similarity and dissimilarity measures. Out of all the equations, the Forbes-2 similarity and the Variant of Correlation similarity measures are recommended for studying the relationship between Jamu formulas and Kampo formulas, respectively.

Conclusions

The selection of binary similarity and dissimilarity measures for multivariate analysis is data dependent. The proposed method can be used to find the most suitable binary similarity and dissimilarity equation wisely for a particular data. Our finding suggests that all four types of matching quantities in the Operational Taxonomic Unit (OTU) table are important to calculate the similarity and dissimilarity coefficients between herbal medicine formulas. Also, the binary similarity and dissimilarity measures that include the negative match quantity d achieve better capability to separate herbal medicine pairs compared to equations that exclude d.

Electronic supplementary material

The online version of this article (doi:10.1186/s12859-016-1392-z) contains supplementary material, which is available to authorized users.

In silico methods for drug repurposing and pharmacology

Data in the biological, chemical, and clinical domains are accumulating at ever-increasing rates and have the potential to accelerate and inform drug development in new ways. Challenges and opportunities now lie in developing analytic tools to transform these often complex and heterogeneous data into testable hypotheses and actionable insights. This is the aim of computational pharmacology, which uses in silico techniques to better understand and predict how drugs affect biological systems, which can in turn improve clinical use, avoid unwanted side effects, and guide selection and development of better treatments. One exciting application of computational pharmacology is drug repurposing-finding new uses for existing drugs. Already yielding many promising candidates, this strategy has the potential to improve the efficiency of the drug development process and reach patient populations with previously unmet needs such as those with rare diseases. While current techniques in computational pharmacology and drug repurposing often focus on just a single data modality such as gene expression or drug-target interactions, we argue that methods such as matrix factorization that can integrate data within and across diverse data types have the potential to improve predictive performance and provide a fuller picture of a drug's pharmacological action. WIREs Syst Biol Med 2016, 8:186-210. doi: 10.1002/wsbm.1337 For further resources related to this article, please visit the WIREs website.

Improving drug discovery with high-content phenotypic screens by systematic selection of reporter cell lines

High-content, image-based screens enable the identification of compounds that induce cellular responses similar to those of known drugs but through different chemical structures or targets. A central challenge in designing phenotypic screens is choosing suitable imaging biomarkers. Here we present a method for systematically identifying optimal reporter cell lines for annotating compound libraries (ORACLs), whose phenotypic profiles most accurately classify a training set of known drugs. We generate a library of fluorescently tagged reporter cell lines, and let analytical criteria determine which among them--the ORACL--best classifies compounds into multiple, diverse drug classes. We demonstrate that an ORACL can functionally annotate large compound libraries across diverse drug classes in a single-pass screen and confirm high prediction accuracy by means of orthogonal, secondary validation assays. Our approach will increase the efficiency, scale and accuracy of phenotypic screens by maximizing their discriminatory power.

Deciding when to stop: efficient experimentation to learn to predict drug-target interactions

BACKGROUND

Active learning is a powerful tool for guiding an experimentation process. Instead of doing all possible experiments in a given domain, active learning can be used to pick the experiments that will add the most knowledge to the current model. Especially, for drug discovery and development, active learning has been shown to reduce the number of experiments needed to obtain high-confidence predictions. However, in practice, it is crucial to have a method to evaluate the quality of the current predictions and decide when to stop the experimentation process. Only by applying reliable stopping criteria to active learning can time and costs in the experimental process actually be saved.

RESULTS

We compute active learning traces on simulated drug-target matrices in order to determine a regression model for the accuracy of the active learner. By analyzing the performance of the regression model on simulated data, we design stopping criteria for previously unseen experimental matrices. We demonstrate on four previously characterized drug effect data sets that applying the stopping criteria can result in upto 40 % savings of the total experiments for highly accurate predictions.

CONCLUSIONS

We show that active learning accuracy can be predicted using simulated data and results in substantial savings in the number of experiments required to make accurate drug-target predictions.

Experimental design strategy: weak reinforcement leads to increased hit rates and enhanced chemical diversity

High Throughput Screening (HTS) is a common approach in life sciences to discover chemical matter that modulates a biological target or phenotype. However, low assay throughput, reagents cost, or a flowchart that can deal with only a limited number of hits may impair screening large numbers of compounds. In this case, a subset of compounds is assayed, and in silico models are utilized to aid in iterative screening design, usually to expand around the found hits and enrich subsequent rounds for relevant chemical matter. However, this may lead to an overly narrow focus, and the diversity of compounds sampled in subsequent iterations may suffer. Active learning has been recently successfully applied in drug discovery with the goal of sampling diverse chemical space to improve model performance. Here we introduce a robust and straightforward iterative screening protocol based on naı̈ve Bayes models. Instead of following up on the compounds with the highest scores in the in silico model, we pursue compounds with very low but positive values. This includes unique chemotypes of weakly active compounds that enhance the applicability domain of the model and increase the cumulative hit rates. We show in a retrospective application to 81 Novartis assays that this protocol leads to consistently higher compound and scaffold hit rates compared to a standard expansion around hits or an active learning approach. We recommend using the weak reinforcement strategy introduced herein for iterative screening workflows.