Active machine learning-driven experimentation to determine compound effects on protein patterns

Accurate Prediction of CRISPR/Cas13a Guide Activity Using Feature Selection and Deep Learning

CRISPR/Cas13a serves as a key tool for nucleic acid tests; therefore, accurate prediction of its activity is essential for creating robust and sensitive diagnosis. In this study, we create a dual-branch neural network model that achieves high prediction accuracy and classification performance across two independent CRISPR/Cas13a data sets, outperforming previously published models relying solely on sequence features. The model integrates direct sequence encoding with descriptive features and yields 99 key descriptive features out of 1553, extracted through statistical analysis, which critically influence guide-target interactions and Cas13a guide activity. By employing Shapley Additive Explanations and Integrated Gradients for feature importance analysis, we show that sequence composition, mismatch type and frequency, and the protospacer flanking site region are primary features. These findings underscore the importance of using descriptive features as complementary inputs to deep learning-based encoding and provide valuable insights into the mechanisms underlying guide-target interaction. All in all, this study not only introduces a reliable and efficient model for Cas13a guide activity prediction but also offers a foundation for future rational design efforts.

Deep Bayesian active learning using in-memory computing hardware

Labeling data is a time-consuming, labor-intensive and costly procedure for many artificial intelligence tasks. Deep Bayesian active learning (DBAL) boosts labeling efficiency exponentially, substantially reducing costs. However, DBAL demands high-bandwidth data transfer and probabilistic computing, posing great challenges for conventional deterministic hardware. Here we propose a memristor stochastic gradient Langevin dynamics in situ learning method that uses the stochastic of memristor modulation to learn efficiency, enabling DBAL within the computation-in-memory (CIM) framework. To prove the feasibility and effectiveness of the proposed method, we implemented in-memory DBAL on a memristor-based stochastic CIM system and successfully demonstrated a robot's skill learning task. The inherent stochastic characteristics of memristors allow a four-layer memristor Bayesian deep neural network to efficiently identify and learn from uncertain samples. Compared with cutting-edge conventional complementary metal-oxide-semiconductor-based hardware implementation, the stochastic CIM system achieves a remarkable 44% boost in speed and could conserve 153 times more energy.

Finding the most potent compounds using active learning on molecular pairs

Active learning allows algorithms to steer iterative experimentation to accelerate and de-risk molecular optimizations, but actively trained models might still exhibit poor performance during early project stages where the training data is limited and model exploitation might lead to analog identification with limited scaffold diversity. Here, we present ActiveDelta, an adaptive approach that leverages paired molecular representations to predict improvements from the current best training compound to prioritize further data acquisition. We apply the ActiveDelta concept to both graph-based deep (Chemprop) and tree-based (XGBoost) models during exploitative active learning for 99 Ki benchmarking datasets. We show that both ActiveDelta implementations excel at identifying more potent inhibitors compared to the standard exploitative active learning implementations of Chemprop, XGBoost, and Random Forest. The ActiveDelta approach is also able to identify more chemically diverse inhibitors in terms of their Murcko scaffolds. Finally, deep models such as Chemprop trained on data selected through ActiveDelta approaches can more accurately identify inhibitors in test data created through simulated time-splits. Overall, this study highlights the large potential for molecular pairing approaches to further improve popular active learning strategies in low data regimes by enabling faster and more accurate identification of more diverse molecular hits against critical drug targets.

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.

Using Dimensionality Reduction to Visualize Phenotypic Changes in High-Throughput Microscopy

High-throughput microscopy has enabled screening of cell phenotypes at unprecedented scale. Systematic identification of cell phenotype changes (such as cell morphology and protein localization changes) is a major analysis goal. Because cell phenotypes are high-dimensional, unbiased approaches to detect and visualize the changes in phenotypes are still needed. Here, we suggest that changes in cellular phenotype can be visualized in reduced dimensionality representations of the image feature space. We describe a freely available analysis pipeline to visualize changes in protein localization in feature spaces obtained from deep learning. As an example, we use the pipeline to identify changes in subcellular localization after the yeast GFP collection was treated with hydroxyurea.

Challenges in developing cell culture media using machine learning

Microbial and mammalian cells are widely used in the food, pharmaceutical, and medical industries. Developing or optimizing culture media is essential to improve cell culture performance as a critical technology in cell culture engineering. Methodologies for media optimization have been developed to a great extent, such as the approaches of one-factor-at-a-time (OFAT) and response surface methodology (RSM). The present review introduces the emerging machine learning (ML) technology in cell culture engineering by combining high-throughput experimental technologies to develop highly efficient and effective culture media. The commonly used ML algorithms and the successful applications of employing ML in medium optimization are summarized. This review highlights the benefits of ML-assisted medium development and guides the selection of the media optimization method appropriate for various cell culture purposes.

Employing active learning in the optimization of culture medium for mammalian cells

Medium optimization is a crucial step during cell culture for biopharmaceutics and regenerative medicine; however, this step remains challenging, as both media and cells are highly complex systems. Here, we addressed this issue by employing active learning. Specifically, we introduced machine learning to cell culture experiments to optimize culture medium. The cell line HeLa-S3 and the gradient-boosting decision tree algorithm were used to find optimized media as pilot studies. To acquire the training data, cell culture was performed in a large variety of medium combinations. The cellular NAD(P)H abundance, represented as A450, was used to indicate the goodness of culture media. In active learning, regular and time-saving modes were developed using culture data at 168 h and 96 h, respectively. Both modes successfully fine-tuned 29 components to generate a medium for improved cell culture. Intriguingly, the two modes provided different predictions for the concentrations of vitamins and amino acids, and a significant decrease was commonly predicted for fetal bovine serum (FBS) compared to the commercial medium. In addition, active learning-assisted medium optimization significantly increased the cellular concentration of NAD(P)H, an active chemical with a constant abundance in living cells. Our study demonstrated the efficiency and practicality of active learning for medium optimization and provided valuable information for employing machine learning technology in cell biology experiments.

Active learning applied to automated physical systems increases the rate of discovery

Active machine learning is widely used in computational studies where repeated numerical simulations can be conducted on high performance computers without human intervention. But translation of these active learning methods to physical systems has proven more difficult and the accelerated pace of discoveries aided by these methods remains as yet unrealized. Through the presentation of a general active learning framework and its application to large-scale boundary layer wind tunnel experiments, we demonstrate that the active learning framework used so successfully in computational studies is directly applicable to the investigation of physical experimental systems and the corresponding improvements in the rate of discovery can be transformative. We specifically show that, for our wind tunnel experiments, we are able to achieve in approximately 300 experiments a learning objective that would be impossible using traditional methods.

A versatile active learning workflow for optimization of genetic and metabolic networks

Optimization of biological networks is often limited by wet lab labor and cost, and the lack of convenient computational tools. Here, we describe METIS, a versatile active machine learning workflow with a simple online interface for the data-driven optimization of biological targets with minimal experiments. We demonstrate our workflow for various applications, including cell-free transcription and translation, genetic circuits, and a 27-variable synthetic CO₂-fixation cycle (CETCH cycle), improving these systems between one and two orders of magnitude. For the CETCH cycle, we explore 10²⁵ conditions with only 1,000 experiments to yield the most efficient CO₂-fixation cascade described to date. Beyond optimization, our workflow also quantifies the relative importance of individual factors to the performance of a system identifying unknown interactions and bottlenecks. Overall, our workflow opens the way for convenient optimization and prototyping of genetic and metabolic networks with customizable adjustments according to user experience, experimental setup, and laboratory facilities.

Optimization of biological networks is often limited by wet lab labor and cost, and the lack of convenient computational tools. Here, aimed at democratization and standardization, the authors describe METIS, a modular and versatile active machine learning workflow with a simple online interface for the optimization of biological target functions with minimal experimental datasets.

Comparison of the Meta-Active Machine Learning Model Applied to Biological Data-Driven Experiments with Other Models

Currently, many methods that could estimate the effects of conditions on a given biological target require either strong modelling assumptions or separate screens. Traditionally, many conditions and targets, without doing all possible experiments, could be achieved by driven experimentation or several mathematical methods, especially conversational machine learning methods. However, these methods still could not avoid and replace manual labels completely. This paper presented a meta-active machine learning method to resolve this problem. This project has used nine traditional machine learning methods to compare their accuracy and running time. In addition, this paper analyzes the meta-active machine learning method (MAML) compared with a classical screening method and progressive experiments. The obtained results show that applying this method yields the best experimental results on the current dataset.

Categorical Matrix Completion With Active Learning for High-Throughput Screening

The recent advances in wet-lab automation enable high-throughput experiments to be conducted seamlessly. In particular, the exhaustive enumeration of all possible conditions is always involved in high-throughput screening. Nonetheless, such a screening strategy is hardly believed to be optimal and cost-effective. By incorporating artificial intelligence, we design an open-source model based on categorical matrix completion and active machine learning to guide high throughput screening experiments. Specifically, we narrow our scope to the high-throughput screening for chemical compound effects on diverse protein sub-cellular locations. In the proposed model, we believe that exploration is more important than the exploitation in the long-run of high-throughput screening experiment, Therefore, we design several innovations to circumvent the existing limitations. In particular, categorical matrix completion is designed to accurately impute the missing experiments while margin sampling is also implemented for uncertainty estimation. The model is systematically tested on both simulated and real data. The simulation results reflect that our model can be robust to diverse scenarios, while the real data results demonstrate the wet-lab applicability of our model for high-throughput screening experiments. Lastly, we attribute the model success to its exploration ability by revealing the related matrix ranks and distinct experiment coverage comparisons.

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.

Accelerated knowledge discovery from omics data by optimal experimental design

How to design experiments that accelerate knowledge discovery on complex biological landscapes remains a tantalizing question. We present an optimal experimental design method (coined OPEX) to identify informative omics experiments using machine learning models for both experimental space exploration and model training. OPEX-guided exploration of Escherichia coli’s populations exposed to biocide and antibiotic combinations lead to more accurate predictive models of gene expression with 44% less data. Analysis of the proposed experiments shows that broad exploration of the experimental space followed by fine-tuning emerges as the optimal strategy. Additionally, analysis of the experimental data reveals 29 cases of cross-stress protection and 4 cases of cross-stress vulnerability. Further validation reveals the central role of chaperones, stress response proteins and transport pumps in cross-stress exposure. This work demonstrates how active learning can be used to guide omics data collection for training predictive models, making evidence-driven decisions and accelerating knowledge discovery in life sciences.

How to design experiments that accelerate knowledge discovery on complex biological landscapes remains a tantalizing question. Here, the authors present OPEX, an optimal experimental design method to identify informative omics experiments for both experimental space exploration and model training.

Practical considerations for active machine learning in drug discovery

Active machine learning enables the automated selection of the most valuable next experiments to improve predictive modelling and hasten active retrieval in drug discovery. Although a long established theoretical concept and introduced to drug discovery approximately 15 years ago, the deployment of active learning technology in the discovery pipelines across academia and industry remains slow. With the recent re-discovered enthusiasm for artificial intelligence as well as improved flexibility of laboratory automation, active learning is expected to surge and become a key technology for molecular optimizations. This review recapitulates key findings from previous active learning studies to highlight the challenges and opportunities of applying adaptive machine learning to drug discovery. Specifically, considerations regarding implementation, infrastructural integration, and expected benefits are discussed. By focusing on these practical aspects of active learning, this review aims at providing insights for scientists planning to implement active learning workflows in their discovery pipelines.

Large scale active-learning-guided exploration for in vitro protein production optimization

Lysate-based cell-free systems have become a major platform to study gene expression but batch-to-batch variation makes protein production difficult to predict. Here we describe an active learning approach to explore a combinatorial space of ~4,000,000 cell-free buffer compositions, maximizing protein production and identifying critical parameters involved in cell-free productivity. We also provide a one-step-method to achieve high quality predictions for protein production using minimal experimental effort regardless of the lysate quality.

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.

Survey of Machine Learning Techniques in Drug Discovery

Background:

Drug discovery, which is the process of discovering new candidate medications, is very important for pharmaceutical industries. At its current stage, discovering new drugs is still a very expensive and time-consuming process, requiring Phases I, II and III for clinical trials. Recently, machine learning techniques in Artificial Intelligence (AI), especially the deep learning techniques which allow a computational model to generate multiple layers, have been widely applied and achieved state-of-the-art performance in different fields, such as speech recognition, image classification, bioinformatics, etc. One very important application of these AI techniques is in the field of drug discovery.

Methods:

We did a large-scale literature search on existing scientific websites (e.g, ScienceDirect, Arxiv) and startup companies to understand current status of machine learning techniques in drug discovery.

Results:

Our experiments demonstrated that there are different patterns in machine learning fields and drug discovery fields. For example, keywords like prediction, brain, discovery, and treatment are usually in drug discovery fields. Also, the total number of papers published in drug discovery fields with machine learning techniques is increasing every year.

Conclusion:

The main focus of this survey is to understand the current status of machine learning techniques in the drug discovery field within both academic and industrial settings, and discuss its potential future applications. Several interesting patterns for machine learning techniques in drug discovery fields are discussed in this survey.

Integration of Lead Discovery Tactics and the Evolution of the Lead Discovery Toolbox

There has been much debate around the success rates of various screening strategies to identify starting points for drug discovery. Although high-throughput target-based and phenotypic screening has been the focus of this debate, techniques such as fragment screening, virtual screening, and DNA-encoded library screening are also increasingly reported as a source of new chemical equity. Here, we provide examples in which integration of more than one screening approach has improved the campaign outcome and discuss how strengths and weaknesses of various methods can be used to build a complementary toolbox of approaches, giving researchers the greatest probability of successfully identifying leads. Among others, we highlight case studies for receptor-interacting serine/threonine-protein kinase 1 and the bromo- and extra-terminal domain family of bromodomains. In each example, the unique insight or chemistries individual approaches provided are described, emphasizing the synergy of information obtained from the various tactics employed and the particular question each tactic was employed to answer. We conclude with a short prospective discussing how screening strategies are evolving, what this screening toolbox might look like in the future, how to maximize success through integration of multiple tactics, and scenarios that drive selection of one combination of tactics over another.

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.

Biologically Relevant Heterogeneity: Metrics and Practical Insights

Heterogeneity is a fundamental property of biological systems at all scales that must be addressed in a wide range of biomedical applications, including basic biomedical research, drug discovery, diagnostics, and the implementation of precision medicine. There are a number of published approaches to characterizing heterogeneity in cells in vitro and in tissue sections. However, there are no generally accepted approaches for the detection and quantitation of heterogeneity that can be applied in a relatively high-throughput workflow. This review and perspective emphasizes the experimental methods that capture multiplexed cell-level data, as well as the need for standard metrics of the spatial, temporal, and population components of heterogeneity. A recommendation is made for the adoption of a set of three heterogeneity indices that can be implemented in any high-throughput workflow to optimize the decision-making process. In addition, a pairwise mutual information method is suggested as an approach to characterizing the spatial features of heterogeneity, especially in tissue-based imaging. Furthermore, metrics for temporal heterogeneity are in the early stages of development. Example studies indicate that the analysis of functional phenotypic heterogeneity can be exploited to guide decisions in the interpretation of biomedical experiments, drug discovery, diagnostics, and the design of optimal therapeutic strategies for individual patients.

Large-scale image-based screening and profiling of cellular phenotypes

Cellular phenotypes are observable characteristics of cells resulting from the interactions of intrinsic and extrinsic chemical or biochemical factors. Image-based phenotypic screens under large numbers of basal or perturbed conditions can be used to study the influences of these factors on cellular phenotypes. Hundreds to thousands of phenotypic descriptors can also be quantified from the images of cells under each of these experimental conditions. Therefore, huge amounts of data can be generated, and the analysis of these data has become a major bottleneck in large-scale phenotypic screens. Here, we review current experimental and computational methods for large-scale image-based phenotypic screens. Our focus is on phenotypic profiling, a computational procedure for constructing quantitative and compact representations of cellular phenotypes based on the images collected in these screens. © 2016 International Society for Advancement of Cytometry.