Reinforcement learning in artificial and biological systems

Artificial Intelligence in Metabolomics: A Current Review

Metabolomics and artificial intelligence (AI) form a synergistic partnership. Metabolomics generates large datasets comprising hundreds to thousands of metabolites with complex relationships. AI, aiming to mimic human intelligence through computational modeling, possesses extraordinary capabilities for big data analysis. In this review, we provide a recent overview of the methodologies and applications of AI in metabolomics studies in the context of systems biology and human health. We first introduce the AI concept, history, and key algorithms for machine learning and deep learning, summarizing their strengths and weaknesses. We then discuss studies that have successfully used AI across different aspects of metabolomic analysis, including analytical detection, data preprocessing, biomarker discovery, predictive modeling, and multi-omics data integration. Lastly, we discuss the existing challenges and future perspectives in this rapidly evolving field. Despite limitations and challenges, the combination of metabolomics and AI holds great promises for revolutionary advancements in enhancing human health.

Machine learning for the advancement of genome-scale metabolic modeling

Constraint-based modeling (CBM) has evolved as the core systems biology tool to map the interrelations between genotype, phenotype, and external environment. The recent advancement of high-throughput experimental approaches and multi-omics strategies has generated a plethora of new and precise information from wide-ranging biological domains. On the other hand, the continuously growing field of machine learning (ML) and its specialized branch of deep learning (DL) provide essential computational architectures for decoding complex and heterogeneous biological data. In recent years, both multi-omics and ML have assisted in the escalation of CBM. Condition-specific omics data, such as transcriptomics and proteomics, helped contextualize the model prediction while analyzing a particular phenotypic signature. At the same time, the advanced ML tools have eased the model reconstruction and analysis to increase the accuracy and prediction power. However, the development of these multi-disciplinary methodological frameworks mainly occurs independently, which limits the concatenation of biological knowledge from different domains. Hence, we have reviewed the potential of integrating multi-disciplinary tools and strategies from various fields, such as synthetic biology, CBM, omics, and ML, to explore the biochemical phenomenon beyond the conventional biological dogma. How the integrative knowledge of these intersected domains has improved bioengineering and biomedical applications has also been highlighted. We categorically explained the conventional genome-scale metabolic model (GEM) reconstruction tools and their improvement strategies through ML paradigms. Further, the crucial role of ML and DL in omics data restructuring for GEM development has also been briefly discussed. Finally, the case-study-based assessment of the state-of-the-art method for improving biomedical and metabolic engineering strategies has been elaborated. Therefore, this review demonstrates how integrating experimental and in silico strategies can help map the ever-expanding knowledge of biological systems driven by condition-specific cellular information. This multiview approach will elevate the application of ML-based CBM in the biomedical and bioengineering fields for the betterment of society and the environment.

Contributions of Basal Ganglia Circuits to Perception, Attention, and Consciousness

Research into ascending sensory pathways and cortical networks has generated detailed models of perception. These same cortical regions are strongly connected to subcortical structures, such as the basal ganglia (BG), which have been conceptualized as playing key roles in reinforcement learning and action selection. However, because the BG amasses experiential evidence from higher and lower levels of cortical hierarchies, as well as higher-order thalamus, it is well positioned to dynamically influence perception. Here, we review anatomical, functional, and clinical evidence to demonstrate how the BG can influence perceptual processing and conscious states. This depends on the integrative relationship between cortex, BG, and thalamus, which allows contributions to sensory gating, predictive processing, selective attention, and representation of the temporal structure of events.

Bio-inspired multimodal learning with organic neuromorphic electronics for behavioral conditioning in robotics

Biological systems interact directly with the environment and learn by receiving multimodal feedback via sensory stimuli that shape the formation of internal neuronal representations. Drawing inspiration from biological concepts such as exploration and sensory processing that eventually lead to behavioral conditioning, we present a robotic system handling objects through multimodal learning. A small-scale organic neuromorphic circuit locally integrates and adaptively processes multimodal sensory stimuli, enabling the robot to interact intelligently with its surroundings. The real-time handling of sensory stimuli via low-voltage organic neuromorphic devices with synaptic functionality forms multimodal associative connections that lead to behavioral conditioning, and thus the robot learns to avoid potentially dangerous objects. This work demonstrates that adaptive neuro-inspired circuitry with multifunctional organic materials, can accommodate locally efficient bio-inspired learning for advancing intelligent robotics.

Reinforcement learning-guided control strategies for CAR T-cell activation and expansion

Reinforcement learning (RL), a subset of machine learning (ML), could optimize and control biomanufacturing processes, such as improved production of therapeutic cells. Here, the process of CAR T-cell activation by antigen-presenting beads and their subsequent expansion is formulated in silico. The simulation is used as an environment to train RL-agents to dynamically control the number of beads in culture to maximize the population of robust effector cells at the end of the culture. We make periodic decisions of incremental bead addition or complete removal. The simulation is designed to operate in OpenAI Gym, enabling testing of different environments, cell types, RL-agent algorithms, and state inputs to the RL-agent. RL-agent training is demonstrated with three different algorithms (PPO, A2C, and DQN), each sampling three different state input types (tabular, image, mixed); PPO-tabular performs best for this simulation environment. Using this approach, training of the RL-agent on different cell types is demonstrated, resulting in unique control strategies for each type. Sensitivity to input-noise (sensor performance), number of control step interventions, and advantages of pre-trained RL-agents are also evaluated. Therefore, we present an RL framework to maximize the population of robust effector cells in CAR T-cell therapy production.

Non-invasive stimulation of the human striatum disrupts reinforcement learning of motor skills

Reinforcement feedback can improve motor learning, but the underlying brain mechanisms remain underexplored. In particular, the causal contribution of specific patterns of oscillatory activity within the human striatum is unknown. To address this question, we exploited a recently developed non-invasive deep brain stimulation technique called transcranial temporal interference stimulation (tTIS) during reinforcement motor learning with concurrent neuroimaging, in a randomized, sham-controlled, double-blind study. Striatal tTIS applied at 80 Hz, but not at 20 Hz, abolished the benefits of reinforcement on motor learning. This effect was related to a selective modulation of neural activity within the striatum. Moreover, 80 Hz, but not 20 Hz, tTIS increased the neuromodulatory influence of the striatum on frontal areas involved in reinforcement motor learning. These results show that tTIS can non-invasively and selectively modulate a striatal mechanism involved in reinforcement learning, expanding our tools for the study of causal relationships between deep brain structures and human behaviour.

Review of applications of artificial intelligence (AI) methods in crop research

Sophisticated and modern crop improvement techniques can bridge the gap for feeding the ever-increasing population. Artificial intelligence (AI) refers to the simulation of human intelligence in machines, which refers to the application of computational algorithms, machine learning (ML) and deep learning (DL) techniques. This is aimed to generalise patterns and relationships from historical data, employing various mathematical optimisation techniques thus making prediction models for facilitating selection of superior genotypes. These techniques are less resource intensive and can solve the problem based on the analysis of large-scale phenotypic datasets. ML for genomic selection (GS) uses high-throughput genotyping technologies to gather genetic information on a large number of markers across the genome. The prediction of GS models is based on the mathematical relation between genotypic and phenotypic data from the training population. ML techniques have emerged as powerful tools for genome editing through analysing large-scale genomic data and facilitating the development of accurate prediction models. Precise phenotyping is a prerequisite to advance crop breeding for solving agricultural production-related issues. ML algorithms can solve this problem through generating predictive models, based on the analysis of large-scale phenotypic datasets. DL models also have the potential reliability of precise phenotyping. This review provides a comprehensive overview on various ML and DL models, their applications, potential to enhance the efficiency, specificity and safety towards advanced crop improvement protocols such as genomic selection, genome editing, along with phenotypic prediction to promote accelerated breeding.

Electroactive composite biofilms integrating Kombucha, Chlorella and synthetic proteinoid Proto-Brains

In this study, we present electroactive biofilms made from a combination of Kombucha zoogleal mats and thermal proteinoids. These biofilms have potential applications in unconventional computing and robotic skin. Proteinoids are synthesized by thermally polymerizing amino acids, resulting in the formation of synthetic protocells that display electrical signalling similar to neurons. By incorporating proteinoids into Kombucha zoogleal cellulose mats, hydrogel biofilms can be created that have the ability to efficiently transfer charges, perform sensory transduction and undergo processing. We conducted a study on the memfractance and memristance behaviours of composite biofilms, showcasing their capacity to carry out unconventional computing operations. The porous nanostructure and electroactivity of the biofilm create a biocompatible interface that can be used to record and stimulate neuronal networks. In addition to in vitro neuronal interfaces, these soft electroactive biofilms show potential as components for bioinspired robotics, smart wearables, unconventional computing devices and adaptive biorobotic systems. Kombucha-proteinoids composite films are a highly customizable material that can be synthesized to suit specific needs. These films belong to a unique category of 'living' materials, as they have the ability to support cellular systems and improve bioelectronic functionality. This makes them an exciting prospect in various applications. Ongoing efforts are currently being directed towards enhancing the compositional tuning of conductivity, signal processing and integration within hybrid bioelectronic circuits.

Toward the development of a molecular toolkit for the microbial remediation of per-and polyfluoroalkyl substances

Per- and polyfluoroalkyl substances (PFAS) are highly fluorinated synthetic organic compounds that have been used extensively in various industries owing to their unique properties. The PFAS family encompasses diverse classes, with only a fraction being commercially relevant. These substances are found in the environment, including in water sources, soil, and wildlife, leading to human exposure and fueling concerns about potential human health impacts. Although PFAS degradation is challenging, biodegradation offers a promising, eco-friendly solution. Biodegradation has been effective for a variety of organic contaminants but is yet to be successful for PFAS due to a paucity of identified microbial species capable of transforming these compounds. Recent studies have investigated PFAS biotransformation and fluoride release; however, the number of specific microorganisms and enzymes with demonstrable activity with PFAS remains limited. This review discusses enzymes that could be used in PFAS metabolism, including haloacid dehalogenases, reductive dehalogenases, cytochromes P450, alkane and butane monooxygenases, peroxidases, laccases, desulfonases, and the mechanisms of microbial resistance to intracellular fluoride. Finally, we emphasize the potential of enzyme and microbial engineering to advance PFAS degradation strategies and provide insights for future research in this field.

Decoding Nanomaterial-Biosystem Interactions through Machine Learning

The interactions between biosystems and nanomaterials regulate most of their theranostic and nanomedicine applications. These nanomaterial-biosystem interactions are highly complex and influenced by a number of entangled factors, including but not limited to the physicochemical features of nanomaterials, the types and characteristics of the interacting biosystems, and the properties of the surrounding microenvironments. Over the years, different experimental approaches coupled with computational modeling have revealed important insights into these interactions, although many outstanding questions remain unanswered. The emergence of machine learning has provided a timely and unique opportunity to revisit nanomaterial-biosystem interactions and to further push the boundary of this field. This minireview highlights the development and use of machine learning to decode nanomaterial-biosystem interactions and provides our perspectives on the current challenges and potential opportunities in this field.

Striatal dopamine signals reflect perceived cue-action-outcome associations in mice

Striatal dopamine drives associative learning by acting as a teaching signal. Much work has focused on simple learning paradigms, including Pavlovian and instrumental learning. However, higher cognition requires that animals generate internal concepts of their environment, where sensory stimuli, actions and outcomes become flexibly associated. Here, we performed fiber photometry dopamine measurements across the striatum of male mice as they learned cue-action-outcome associations based on implicit and changing task rules. Reinforcement learning models of the behavioral and dopamine data showed that rule changes lead to adjustments of learned cue-action-outcome associations. After rule changes, mice discarded learned associations and reset outcome expectations. Cue- and outcome-triggered dopamine signals became uncoupled and dependent on the adopted behavioral strategy. As mice learned the new association, coupling between cue- and outcome-triggered dopamine signals and task performance re-emerged. Our results suggest that dopaminergic reward prediction errors reflect an agent's perceived locus of control.

Artificial cognition vs. artificial intelligence for next-generation autonomous robotic agents

The trend in industrial/service robotics is to develop robots that can cooperate with people, interacting with them in an autonomous, safe and purposive way. These are the fundamental elements characterizing the fourth and the fifth industrial revolutions (4IR, 5IR): the crucial innovation is the adoption of intelligent technologies that can allow the development of cyber-physical systems, similar if not superior to humans. The common wisdom is that intelligence might be provided by AI (Artificial Intelligence), a claim that is supported more by media coverage and commercial interests than by solid scientific evidence. AI is currently conceived in a quite broad sense, encompassing LLMs and a lot of other things, without any unifying principle, but self-motivating for the success in various areas. The current view of AI robotics mostly follows a purely disembodied approach that is consistent with the old-fashioned, Cartesian mind-body dualism, reflected in the software-hardware distinction inherent to the von Neumann computing architecture. The working hypothesis of this position paper is that the road to the next generation of autonomous robotic agents with cognitive capabilities requires a fully brain-inspired, embodied cognitive approach that avoids the trap of mind-body dualism and aims at the full integration of Bodyware and Cogniware. We name this approach Artificial Cognition (ACo) and ground it in Cognitive Neuroscience. It is specifically focused on proactive knowledge acquisition based on bidirectional human-robot interaction: the practical advantage is to enhance generalization and explainability. Moreover, we believe that a brain-inspired network of interactions is necessary for allowing humans to cooperate with artificial cognitive agents, building a growing level of personal trust and reciprocal accountability: this is clearly missing, although actively sought, in current AI. The ACo approach is a work in progress that can take advantage of a number of research threads, some of them antecedent the early attempts to define AI concepts and methods. In the rest of the paper we will consider some of the building blocks that need to be re-visited in a unitary framework: the principles of developmental robotics, the methods of action representation with prospection capabilities, and the crucial role of social interaction.

Active reinforcement learning versus action bias and hysteresis: control with a mixture of experts and nonexperts

Active reinforcement learning enables dynamic prediction and control, where one should not only maximize rewards but also minimize costs such as of inference, decisions, actions, and time. For an embodied agent such as a human, decisions are also shaped by physical aspects of actions. Beyond the effects of reward outcomes on learning processes, to what extent can modeling of behavior in a reinforcement-learning task be complicated by other sources of variance in sequential action choices? What of the effects of action bias (for actions per se) and action hysteresis determined by the history of actions chosen previously? The present study addressed these questions with incremental assembly of models for the sequential choice data from a task with hierarchical structure for additional complexity in learning. With systematic comparison and falsification of computational models, human choices were tested for signatures of parallel modules representing not only an enhanced form of generalized reinforcement learning but also action bias and hysteresis. We found evidence for substantial differences in bias and hysteresis across participants-even comparable in magnitude to the individual differences in learning. Individuals who did not learn well revealed the greatest biases, but those who did learn accurately were also significantly biased. The direction of hysteresis varied among individuals as repetition or, more commonly, alternation biases persisting from multiple previous actions. Considering that these actions were button presses with trivial motor demands, the idiosyncratic forces biasing sequences of action choices were robust enough to suggest ubiquity across individuals and across tasks requiring various actions. In light of how bias and hysteresis function as a heuristic for efficient control that adapts to uncertainty or low motivation by minimizing the cost of effort, these phenomena broaden the consilient theory of a mixture of experts to encompass a mixture of expert and nonexpert controllers of behavior.

A neural network model for the evolution of learning in changing environments

Learning from past experience is an important adaptation and theoretical models may help to understand its evolution. Many of the existing models study simple phenotypes and do not consider the mechanisms underlying learning while the more complex neural network models often make biologically unrealistic assumptions and rarely consider evolutionary questions. Here, we present a novel way of modelling learning using small neural networks and a simple, biology-inspired learning algorithm. Learning affects only part of the network, and it is governed by the difference between expectations and reality. We use this model to study the evolution of learning under various environmental conditions and different scenarios for the trade-off between exploration (learning) and exploitation (foraging). Efficient learning readily evolves in our individual-based simulations. However, in line with previous studies, the evolution of learning is less likely in relatively constant environments, where genetic adaptation alone can lead to efficient foraging, or in short-lived organisms that cannot afford to spend much of their lifetime on exploration. Once learning does evolve, the characteristics of the learning strategy (i.e. the duration of the learning period and the learning rate) and the average performance after learning are surprisingly little affected by the frequency and/or magnitude of environmental change. In contrast, an organism's lifespan and the distribution of resources in the environment have a clear effect on the evolved learning strategy: a shorter lifespan or a broader resource distribution lead to fewer learning episodes and larger learning rates. Interestingly, a longer learning period does not always lead to better performance, indicating that the evolved neural networks differ in the effectiveness of learning. Overall, however, we show that a biologically inspired, yet relatively simple, learning mechanism can evolve to lead to an efficient adaptation in a changing environment.

From reinforcement learning to agency: Frameworks for understanding basal cognition

Organisms play, explore, and mimic those around them. Is there a purpose to this behavior? Are organisms just behaving, or are they trying to achieve goals? We believe this is a false dichotomy. To that end, to understand organisms, we attempt to unify two approaches for understanding complex agents, whether evolved or engineered. We argue that formalisms describing multiscale competencies and goal-directedness in biology (e.g., TAME), and reinforcement learning (RL), can be combined in a symbiotic framework. While RL has been largely focused on higher-level organisms and robots of high complexity, TAME is naturally capable of describing lower-level organisms and minimal agents as well. We propose several novel questions that come from using RL/TAME to understand biology as well as ones that come from using biology to formulate new theory in AI. We hope that the research programs proposed in this piece shape future efforts to understand biological organisms and also future efforts to build artificial agents.

A review of machine learning models applied to genomic prediction in animal breeding

The advent of modern genotyping technologies has revolutionized genomic selection in animal breeding. Large marker datasets have shown several drawbacks for traditional genomic prediction methods in terms of flexibility, accuracy, and computational power. Recently, the application of machine learning models in animal breeding has gained a lot of interest due to their tremendous flexibility and their ability to capture patterns in large noisy datasets. Here, we present a general overview of a handful of machine learning algorithms and their application in genomic prediction to provide a meta-picture of their performance in genomic estimated breeding values estimation, genotype imputation, and feature selection. Finally, we discuss a potential adoption of machine learning models in genomic prediction in developing countries. The results of the reviewed studies showed that machine learning models have indeed performed well in fitting large noisy data sets and modeling minor nonadditive effects in some of the studies. However, sometimes conventional methods outperformed machine learning models, which confirms that there's no universal method for genomic prediction. In summary, machine learning models have great potential for extracting patterns from single nucleotide polymorphism datasets. Nonetheless, the level of their adoption in animal breeding is still low due to data limitations, complex genetic interactions, a lack of standardization and reproducibility, and the lack of interpretability of machine learning models when trained with biological data. Consequently, there is no remarkable outperformance of machine learning methods compared to traditional methods in genomic prediction. Therefore, more research should be conducted to discover new insights that could enhance livestock breeding programs.

Reward prediction error in learning-related behaviors

Learning is a complex process, during which our opinions and decisions are easily changed due to unexpected information. But the neural mechanism underlying revision and correction during the learning process remains unclear. For decades, prediction error has been regarded as the core of changes to perception in learning, even driving the learning progress. In this article, we reviewed the concept of reward prediction error, and the encoding mechanism of dopaminergic neurons and the related neural circuities. We also discussed the relationship between reward prediction error and learning-related behaviors, including reversal learning. We then demonstrated the evidence of reward prediction error signals in several neurological diseases, including Parkinson's disease and addiction. These observations may help to better understand the regulatory mechanism of reward prediction error in learning-related behaviors.

Bird's Eye View feature selection for high-dimensional data

In machine learning, an informative dataset is crucial for accurate predictions. However, high dimensional data often contains irrelevant features, outliers, and noise, which can negatively impact model performance and consume computational resources. To tackle this challenge, the Bird's Eye View (BEV) feature selection technique is introduced. This approach is inspired by the natural world, where a bird searches for important features in a sparse dataset, similar to how a bird search for sustenance in a sprawling jungle. BEV incorporates elements of Evolutionary Algorithms with a Genetic Algorithm to maintain a population of top-performing agents, Dynamic Markov Chain to steer the movement of agents in the search space, and Reinforcement Learning to reward and penalize agents based on their progress. The proposed strategy in this paper leads to improved classification performance and a reduced number of features compared to conventional methods, as demonstrated by outperforming state-of-the-art feature selection techniques across multiple benchmark datasets.

Bridging adaptive management and reinforcement learning for more robust decisions

From out-competing grandmasters in chess to informing high-stakes healthcare decisions, emerging methods from artificial intelligence are increasingly capable of making complex and strategic decisions in diverse, high-dimensional and uncertain situations. But can these methods help us devise robust strategies for managing environmental systems under great uncertainty? Here we explore how reinforcement learning (RL), a subfield of artificial intelligence, approaches decision problems through a lens similar to adaptive environmental management: learning through experience to gradually improve decisions with updated knowledge. We review where RL holds promise for improving evidence-informed adaptive management decisions even when classical optimization methods are intractable and discuss technical and social issues that arise when applying RL to adaptive management problems in the environmental domain. Our synthesis suggests that environmental management and computer science can learn from one another about the practices, promises and perils of experience-based decision-making. This article is part of the theme issue 'Detecting and attributing the causes of biodiversity change: needs, gaps and solutions'.

Development and testing of a multi-lingual Natural Language Processing-based deep learning system in 10 languages for COVID-19 pandemic crisis: A multi-center study

Purpose

The COVID-19 pandemic has drastically disrupted global healthcare systems. With the higher demand for healthcare and misinformation related to COVID-19, there is a need to explore alternative models to improve communication. Artificial Intelligence (AI) and Natural Language Processing (NLP) have emerged as promising solutions to improve healthcare delivery. Chatbots could fill a pivotal role in the dissemination and easy accessibility of accurate information in a pandemic. In this study, we developed a multi-lingual NLP-based AI chatbot, DR-COVID, which responds accurately to open-ended, COVID-19 related questions. This was used to facilitate pandemic education and healthcare delivery.

Methods

First, we developed DR-COVID with an ensemble NLP model on the Telegram platform (https://t.me/drcovid_nlp_chatbot). Second, we evaluated various performance metrics. Third, we evaluated multi-lingual text-to-text translation to Chinese, Malay, Tamil, Filipino, Thai, Japanese, French, Spanish, and Portuguese. We utilized 2,728 training questions and 821 test questions in English. Primary outcome measurements were (A) overall and top 3 accuracies; (B) Area Under the Curve (AUC), precision, recall, and F1 score. Overall accuracy referred to a correct response for the top answer, whereas top 3 accuracy referred to an appropriate response for any one answer amongst the top 3 answers. AUC and its relevant matrices were obtained from the Receiver Operation Characteristics (ROC) curve. Secondary outcomes were (A) multi-lingual accuracy; (B) comparison to enterprise-grade chatbot systems. The sharing of training and testing datasets on an open-source platform will also contribute to existing data.

Results

Our NLP model, utilizing the ensemble architecture, achieved overall and top 3 accuracies of 0.838 [95% confidence interval (CI): 0.826-0.851] and 0.922 [95% CI: 0.913-0.932] respectively. For overall and top 3 results, AUC scores of 0.917 [95% CI: 0.911-0.925] and 0.960 [95% CI: 0.955-0.964] were achieved respectively. We achieved multi-linguicism with nine non-English languages, with Portuguese performing the best overall at 0.900. Lastly, DR-COVID generated answers more accurately and quickly than other chatbots, within 1.12-2.15 s across three devices tested.

Conclusion

DR-COVID is a clinically effective NLP-based conversational AI chatbot, and a promising solution for healthcare delivery in the pandemic era.

Using Machine Learning to make nanomaterials sustainable

Sustainable development is a key challenge for contemporary human societies; failure to achieve sustainability could threaten human survival. In this review article, we illustrate how Machine Learning (ML) could support more sustainable development, covering the basics of data gathering through each step of the Environmental Risk Assessment (ERA). The literature provides several examples showing how ML can be employed in most steps of a typical ERA.A key observation is that there are currently no clear guidance for using such autonomous technologies in ERAs or which standards/checks are required. Steering thus seems to be the most important task for supporting the use of ML in the ERA of nano- and smart-materials. Resources should be devoted to developing a strategy for implementing ML in ERA with a strong emphasis on data foundations, methodologies, and the related sensitivities/uncertainties. We should recognise historical errors and biases (e.g., in data) to avoid embedding them during ML programming.

Environmental uncertainty and the advantage of impulsive choice strategies

Choice impulsivity is characterized by the choice of immediate, smaller reward options over future, larger reward options, and is often thought to be associated with negative life outcomes. However, some environments make future rewards more uncertain, and in these environments impulsive choices can be beneficial. Here we examined the conditions under which impulsive vs. non-impulsive decision strategies would be advantageous. We used Markov Decision Processes (MDPs) to model three common decision-making tasks: Temporal Discounting, Information Sampling, and an Explore-Exploit task. We manipulated environmental variables to create circumstances where future outcomes were relatively uncertain. We then manipulated the discount factor of an MDP agent, which affects the value of immediate versus future rewards, to model impulsive and non-impulsive behavior. This allowed us to examine the performance of impulsive and non-impulsive agents in more or less predictable environments. In Temporal Discounting, we manipulated the transition probability to delayed rewards and found that the agent with the lower discount factor (i.e. the impulsive agent) collected more average reward than the agent with a higher discount factor (the non-impulsive agent) by selecting immediate reward options when the probability of receiving the future reward was low. In the Information Sampling task, we manipulated the amount of information obtained with each sample. When sampling led to small information gains, the impulsive MDP agent collected more average reward than the non-impulsive agent. Third, in the Explore-Exploit task, we manipulated the substitution rate for novel options. When the substitution rate was high, the impulsive agent again performed better than the non-impulsive agent, as it explored the novel options less and instead exploited options with known reward values. The results of these analyses show that impulsivity can be advantageous in environments that are unexpectedly uncertain.

Modularity in Nervous Systems—a Key to Efficient Adaptivity for Deep Reinforcement Learning

Modularity as observed in biological systems has proven valuable for guiding classical motor theories towards good answers about action selection and execution. New challenges arise when we turn to learning: Trying to scale current computational models, such as deep reinforcement learning (DRL), to action spaces, input dimensions, and time horizons seen in biological systems still faces severe obstacles unless vast amounts of training data are available. This leads to the question: does biological modularity also hold an important key for better answers to obtain efficient adaptivity for deep reinforcement learning? We review biological experimental work on modularity in biological motor control and link this with current examples of (deep) RL approaches. Analyzing outcomes of simulation studies, we show that these approaches benefit from forms of modularization as found in biological systems. We identify three different strands of modularity exhibited in biological control systems. Two of them—modularity in state (i) and in action (ii) spaces—appear as a consequence of local interconnectivity (as in reflexes) and are often modulated by higher levels in a control hierarchy. A third strand arises from chunking of action elements along a (iii) temporal dimension. Usually interacting in an overarching spatio-temporal hierarchy of the overall system, the three strands offer major “factors” decomposing the entire modularity structure. We conclude that modularity with its above strands can provide an effective prior for DRL approaches to speed up learning considerably and making learned controllers more robust and adaptive.

Advanced Reinforcement Learning and Its Connections with Brain Neuroscience

In recent years, brain science and neuroscience have greatly propelled the innovation of computer science. In particular, knowledge from the neurobiology and neuropsychology of the brain revolutionized the development of reinforcement learning (RL) by providing novel interpretable mechanisms of how the brain achieves intelligent and efficient decision making. Triggered by this, there has been a boom in research about advanced RL algorithms that are built upon the inspirations of brain neuroscience. In this work, to further strengthen the bidirectional link between the 2 communities and especially promote the research on modern RL technology, we provide a comprehensive survey of recent advances in the area of brain-inspired/related RL algorithms. We start with basis theories of RL, and present a concise introduction to brain neuroscience related to RL. Then, we classify these advanced RL methodologies into 3 categories according to different connections of the brain, i.e., micro-neural activity, macro-brain structure, and cognitive function. Each category is further surveyed by presenting several modern RL algorithms along with their mathematical models, correlations with the brain, and open issues. Finally, we introduce several important applications of RL algorithms, followed by the discussions of challenges and opportunities for future research.

From deterministic to stochastic: an interpretable stochastic model-free reinforcement learning framework for portfolio optimization

As a fundamental problem in algorithmic trading, portfolio optimization aims to maximize the cumulative return by continuously investing in various financial derivatives within a given time period. Recent years have witnessed the transformation from traditional machine learning trading algorithms to reinforcement learning algorithms due to their superior nature of sequential decision making. However, the exponential growth of the imperfect and noisy financial data that is supposedly leveraged by the deterministic strategy in reinforcement learning, makes it increasingly challenging for one to continuously obtain a profitable portfolio. Thus, in this work, we first reconstruct several deterministic and stochastic reinforcement algorithms as benchmarks. On this basis, we introduce a risk-aware reward function to balance the risk and return. Importantly, we propose a novel interpretable stochastic reinforcement learning framework which tailors a stochastic policy parameterized by Gaussian Mixtures and a distributional critic realized by quantiles for the problem of portfolio optimization. In our experiment, the proposed algorithm demonstrates its superior performance on U.S. market stocks with a 63.1% annual rate of return while at the same time reducing the market value max drawdown by 10% when back-testing during the stock market crash around March 2020.

Sampling motion trajectories during hippocampal theta sequences

Efficient planning in complex environments requires that uncertainty associated with current inferences and possible consequences of forthcoming actions is represented. Representation of uncertainty has been established in sensory systems during simple perceptual decision making tasks but it remains unclear if complex cognitive computations such as planning and navigation are also supported by probabilistic neural representations. Here, we capitalized on gradually changing uncertainty along planned motion trajectories during hippocampal theta sequences to capture signatures of uncertainty representation in population responses. In contrast with prominent theories, we found no evidence of encoding parameters of probability distributions in the momentary population activity recorded in an open-field navigation task in rats. Instead, uncertainty was encoded sequentially by sampling motion trajectories randomly and efficiently in subsequent theta cycles from the distribution of potential trajectories. Our analysis is the first to demonstrate that the hippocampus is well equipped to contribute to optimal planning by representing uncertainty.

A Midbrain Inspired Recurrent Neural Network Model for Robust Change Detection

We present a biologically inspired recurrent neural network (RNN) that efficiently detects changes in natural images. The model features sparse, topographic connectivity (st-RNN), closely modeled on the circuit architecture of a "midbrain attention network." We deployed the st-RNN in a challenging change blindness task, in which changes must be detected in a discontinuous sequence of images. Compared with a conventional RNN, the st-RNN learned 9x faster and achieved state-of-the-art performance with 15x fewer connections. An analysis of low-dimensional dynamics revealed putative circuit mechanisms, including a critical role for a global inhibitory (GI) motif, for successful change detection. The model reproduced key experimental phenomena, including midbrain neurons' sensitivity to dynamic stimuli, neural signatures of stimulus competition, as well as hallmark behavioral effects of midbrain microstimulation. Finally, the model accurately predicted human gaze fixations in a change blindness experiment, surpassing state-of-the-art saliency-based methods. The st-RNN provides a novel deep learning model for linking neural computations underlying change detection with psychophysical mechanisms.SIGNIFICANCE STATEMENT For adaptive survival, our brains must be able to accurately and rapidly detect changing aspects of our visual world. We present a novel deep learning model, a sparse, topographic recurrent neural network (st-RNN), that mimics the neuroanatomy of an evolutionarily conserved "midbrain attention network." The st-RNN achieved robust change detection in challenging change blindness tasks, outperforming conventional RNN architectures. The model also reproduced hallmark experimental phenomena, both neural and behavioral, reported in seminal midbrain studies. Lastly, the st-RNN outperformed state-of-the-art models at predicting human gaze fixations in a laboratory change blindness experiment. Our deep learning model may provide important clues about key mechanisms by which the brain efficiently detects changes.

Reinforcement-Learning-Based Disturbance Rejection Control for Uncertain Nonlinear Systems

This article investigates the reinforcement-learning (RL)-based disturbance rejection control for uncertain nonlinear systems having nonsimple nominal models. An extended state observer (ESO) is first designed to estimate the system state and the total uncertainty, which represents the perturbation to the nominal system dynamics. Based on the output of the observer, the control compensates for the total uncertainty in real time, and simultaneously, online approximates the optimal policy for the compensated system using a simulation of experience-based RL technique. Rigorous theoretical analysis is given to show the practical convergence of the system state to the origin and the developed policy to the ideal optimal policy. It is worth mentioning that the widely used restrictive persistence of excitation (PE) condition is not required in the established framework. Simulation results are presented to illustrate the effectiveness of the proposed method.

Circularly polarized light-sensitive, hot electron transistor with chiral plasmonic nanoparticles

The quantitative detection of circularly polarized light (CPL) is necessary in next-generation optical communication carrying high-density information and in phase-controlled displays exhibiting volumetric imaging. In the current technology, multiple pixels of different wavelengths and polarizers are required, inevitably resulting in high loss and low detection efficiency. Here, we demonstrate a highly efficient CPL-detecting transistor composed of chiral plasmonic nanoparticles with a high Khun's dissymmetry (g-factor) of 0.2 and a high mobility conducting oxide of InGaZnO. The device successfully distinguished the circular polarization state and displayed an unprecedented photoresponsivity of over 1 A/W under visible CPL excitation. This observation is mainly attributed to the hot electron generation in chiral plasmonic nanoparticles and to the effective collection of hot electrons in the oxide semiconducting transistor. Such characteristics further contribute to opto-neuromorphic operation and the artificial nervous system based on the device successfully performs image classification work. We anticipate that our strategy will aid in the rational design and fabrication of a high-performance CPL detector and opto-neuromorphic operation with a chiral plasmonic structure depending on the wavelength and circular polarization state.

Braitenberg Vehicles as Developmental Neurosimulation

Connecting brain and behavior is a longstanding issue in the areas of behavioral science, artificial intelligence, and neurobiology. As is standard among models of artificial and biological neural networks, an analogue of the fully mature brain is presented as a blank slate. However, this does not consider the realities of biological development and developmental learning. Our purpose is to model the development of an artificial organism that exhibits complex behaviors. We introduce three alternate approaches to demonstrate how developmental embodied agents can be implemented. The resulting developmental Braitenberg vehicles (dBVs) will generate behaviors ranging from stimulus responses to group behavior that resembles collective motion. We will situate this work in the domain of artificial brain networks along with broader themes such as embodied cognition, feedback, and emergence. Our perspective is exemplified by three software instantiations that demonstrate how a BV-genetic algorithm hybrid model, a multisensory Hebbian learning model, and multi-agent approaches can be used to approach BV development. We introduce use cases such as optimized spatial cognition (vehicle-genetic algorithm hybrid model), hinges connecting behavioral and neural models (multisensory Hebbian learning model), and cumulative classification (multi-agent approaches). In conclusion, we consider future applications of the developmental neurosimulation approach.

Hierarchical Reinforcement Learning, Sequential Behavior, and the Dorsal Frontostriatal System

To effectively behave within ever-changing environments, biological agents must learn and act at varying hierarchical levels such that a complex task may be broken down into more tractable subtasks. Hierarchical reinforcement learning (HRL) is a computational framework that provides an understanding of this process by combining sequential actions into one temporally extended unit called an option. However, there are still open questions within the HRL framework, including how options are formed and how HRL mechanisms might be realized within the brain. In this review, we propose that the existing human motor sequence literature can aid in understanding both of these questions. We give specific emphasis to visuomotor sequence learning tasks such as the discrete sequence production task and the M × N (M steps × N sets) task to understand how hierarchical learning and behavior manifest across sequential action tasks as well as how the dorsal cortical-subcortical circuitry could support this kind of behavior. This review highlights how motor chunks within a motor sequence can function as HRL options. Furthermore, we aim to merge findings from motor sequence literature with reinforcement learning perspectives to inform experimental design in each respective subfield.

Improving candidate Biosynthetic Gene Clusters in fungi through reinforcement learning

MOTIVATION

Precise identification of Biosynthetic Gene Clusters (BGCs) is a challenging task. Performance of BGC discovery tools is limited by their capacity to accurately predict components belonging to candidate BGCs, often overestimating cluster boundaries. To support optimizing the composition and boundaries of candidate BGCs, we propose reinforcement learning approach relying on protein domains and functional annotations from expert curated BGCs.

RESULTS

The proposed reinforcement learning method aims to improve candidate BGCs obtained with state-of-the-art tools. It was evaluated on candidate BGCs obtained for two fungal genomes, Aspergillus niger and Aspergillus nidulans. The results highlight an improvement of the gene precision by above 15% for TOUCAN, fungiSMASH and DeepBGC; and cluster precision by above 25% for fungiSMASH and DeepBCG, allowing these tools to obtain almost perfect precision in cluster prediction. This can pave the way of optimizing current prediction of candidate BGCs in fungi, while minimizing the curation effort required by domain experts.

AVAILABILITY AND IMPLEMENTATION

https://github.com/bioinfoUQAM/RL-bgc-components.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Prioritized Experience-Based Reinforcement Learning With Human Guidance for Autonomous Driving

Reinforcement learning (RL) requires skillful definition and remarkable computational efforts to solve optimization and control problems, which could impair its prospect. Introducing human guidance into RL is a promising way to improve learning performance. In this article, a comprehensive human guidance-based RL framework is established. A novel prioritized experience replay mechanism that adapts to human guidance in the RL process is proposed to boost the efficiency and performance of the RL algorithm. To relieve the heavy workload on human participants, a behavior model is established based on an incremental online learning method to mimic human actions. We design two challenging autonomous driving tasks for evaluating the proposed algorithm. Experiments are conducted to access the training and testing performance and learning mechanism of the proposed algorithm. Comparative results against the state-of-the-art methods suggest the advantages of our algorithm in terms of learning efficiency, performance, and robustness.

Representation learning in the artificial and biological neural networks underlying sensorimotor integration

The integration of deep learning and theories of reinforcement learning (RL) is a promising avenue to explore novel hypotheses on reward-based learning and decision-making in humans and other animals. Here, we trained deep RL agents and mice in the same sensorimotor task with high-dimensional state and action space and studied representation learning in their respective neural networks. Evaluation of thousands of neural network models with extensive hyperparameter search revealed that learning-dependent enrichment of state-value and policy representations of the task-performance-optimized deep RL agent closely resembled neural activity of the posterior parietal cortex (PPC). These representations were critical for the task performance in both systems. PPC neurons also exhibited representations of the internally defined subgoal, a feature of deep RL algorithms postulated to improve sample efficiency. Such striking resemblance between the artificial and biological networks and their functional convergence in sensorimotor integration offers new opportunities to better understand respective intelligent systems.

Simultaneous Release of Silver Ions and 10–Undecenoic Acid from Silver Iron–Oxide Nanoparticles Impregnated Membranes

The bio-medical benefits of silver ions and 10–undecenoic acid in various chemical-pharmaceutical preparations are indisputable, thus justifying numerous research studies on delayed and/or controlled release. This paper presents the effect of the polymer matrix in the simultaneous release of silver ions and 10–undecenoic acid in an aqueous medium of controlled pH and ionic strength. The study took into consideration polymeric matrices consisting of cellulose acetate (CA) and polysulfone (PSf), which were impregnated with oxide nanoparticles containing silver and 10–undecenoic acid. The studied oxide nanoparticles are nanoparticles of iron and silver oxides obtained by an accessible electrochemical method. The obtained results show that silver can be released, simultaneously with 10–undecenoic acid, from an impregnated polymeric membrane, at concentrations that ensure the biocidal and fungicidal capacity. Concentrations of active substances can be controlled by choosing the polymer matrix or, in some cases, by changing the pH of the target medium. In the studied case, higher concentrations of silver ions are released from the polysulfone matrix, while higher concentrations of 10–undecenoic acid are released from the cellulose acetate matrix. The results of the study show that a correlation can be established between the two released target substances, which is dependent on the solubility of the organic compound in the aqueous medium and the interaction of this compound with the silver ions. The ability of 10–undecenoic acid to interact with the silver ion, both through the carboxyl and alkene groups, contributes to the increase in the content of the silver ions transported in the aqueous medium.

Optimal reinforcement learning near the edge of a synchronization transition

Recent experimental and theoretical studies have indicated that the putative criticality of cortical dynamics may correspond to a synchronization phase transition. The critical dynamics near such a critical point needs further investigation specifically when compared to the critical behavior near the standard absorbing state phase transition. Since the phenomena of learning and self-organized criticality (SOC) at the edge of synchronization transition can emerge jointly in spiking neural networks due to the presence of spike-timing dependent plasticity (STDP), it is tempting to ask the following: what is the relationship between synchronization and learning in neural networks? Further, does learning benefit from SOC at the edge of synchronization transition? In this paper, we intend to address these important issues. Accordingly, we construct a biologically inspired model of a cognitive system which learns to perform stimulus-response tasks. We train this system using a reinforcement learning rule implemented through dopamine-modulated STDP. We find that the system exhibits a continuous transition from synchronous to asynchronous neural oscillations upon increasing the average axonal time delay. We characterize the learning performance of the system and observe that it is optimized near the synchronization transition. We also study neuronal avalanches in the system and provide evidence that optimized learning is achieved in a slightly supercritical state.

Multiplexed action-outcome representation by striatal striosome-matrix compartments detected with a mouse cost-benefit foraging task

Learning about positive and negative outcomes of actions is crucial for survival and underpinned by conserved circuits including the striatum. How associations between actions and outcomes are formed is not fully understood, particularly when the outcomes have mixed positive and negative features. We developed a novel foraging (‘bandit’) task requiring mice to maximize rewards while minimizing punishments. By 2-photon Ca⁺⁺ imaging, we monitored activity of visually identified anterodorsal striatal striosomal and matrix neurons. We found that action-outcome associations for reward and punishment were encoded in parallel in partially overlapping populations. Single neurons could, for one action, encode outcomes of opposing valence. Striosome compartments consistently exhibited stronger representations of reinforcement outcomes than matrix, especially for high reward or punishment prediction errors. These findings demonstrate multiplexing of action-outcome contingencies by single identified striatal neurons and suggest that striosomal neurons are particularly important in action-outcome learning.

The role that the striatum plays in tracking the association between actions and combinations of rewarding and aversive outcomes remains unclear. Here, by using both calcium imaging in mice and reinforcement learning models, the authors find that individual striatal neurons can encode associations between actions and multiple, sometimes conflicting, outcomes.

Cognitive Control as a Multivariate Optimization Problem

A hallmark of adaptation in humans and other animals is our ability to control how we think and behave across different settings. Research has characterized the various forms cognitive control can take-including enhancement of goal-relevant information, suppression of goal-irrelevant information, and overall inhibition of potential responses-and has identified computations and neural circuits that underpin this multitude of control types. Studies have also identified a wide range of situations that elicit adjustments in control allocation (e.g., those eliciting signals indicating an error or increased processing conflict), but the rules governing when a given situation will give rise to a given control adjustment remain poorly understood. Significant progress has recently been made on this front by casting the allocation of control as a decision-making problem. This approach has developed unifying and normative models that prescribe when and how a change in incentives and task demands will result in changes in a given form of control. Despite their successes, these models, and the experiments that have been developed to test them, have yet to face their greatest challenge: deciding how to select among the multiplicity of configurations that control can take at any given time. Here, we will lay out the complexities of the inverse problem inherent to cognitive control allocation, and their close parallels to inverse problems within motor control (e.g., choosing between redundant limb movements). We discuss existing solutions to motor control's inverse problems drawn from optimal control theory, which have proposed that effort costs act to regularize actions and transform motor planning into a well-posed problem. These same principles may help shed light on how our brains optimize over complex control configuration, while providing a new normative perspective on the origins of mental effort.

Differential coding of goals and actions in ventral and dorsal corticostriatal circuits during goal-directed behavior

Goal-directed behavior requires identifying objects in the environment that can satisfy internal needs and executing actions to obtain those objects. The current study examines ventral and dorsal corticostriatal circuits that support complementary aspects of goal-directed behavior. We analyze activity from the amygdala, ventral striatum, orbitofrontal cortex, and lateral prefrontal cortex (LPFC) while monkeys perform a three-armed bandit task. Information about chosen stimuli and their value is primarily encoded in the amygdala, ventral striatum, and orbitofrontal cortex, while the spatial information is primarily encoded in the LPFC. Before the options are presented, information about the to-be-chosen stimulus is represented in the amygdala, ventral striatum, and orbitofrontal cortex; at the time of choice, the information is passed to the LPFC to direct a saccade. Thus, learned value information specifying behavioral goals is maintained throughout the ventral corticostriatal circuit, and it is routed through the dorsal circuit at the time actions are selected.

Reinforcement-learning in fronto-striatal circuits

We review the current state of knowledge on the computational and neural mechanisms of reinforcement-learning with a particular focus on fronto-striatal circuits. We divide the literature in this area into five broad research themes: the target of the learning-whether it be learning about the value of stimuli or about the value of actions; the nature and complexity of the algorithm used to drive the learning and inference process; how learned values get converted into choices and associated actions; the nature of state representations, and of other cognitive machinery that support the implementation of various reinforcement-learning operations. An emerging fifth area focuses on how the brain allocates or arbitrates control over different reinforcement-learning sub-systems or "experts". We will outline what is known about the role of the prefrontal cortex and striatum in implementing each of these functions. We then conclude by arguing that it will be necessary to build bridges from algorithmic level descriptions of computational reinforcement-learning to implementational level models to better understand how reinforcement-learning emerges from multiple distributed neural networks in the brain.

How learning unfolds in the brain: toward an optimization view

How do changes in the brain lead to learning? To answer this question, consider an artificial neural network (ANN), where learning proceeds by optimizing a given objective or cost function. This "optimization framework" may provide new insights into how the brain learns, as many idiosyncratic features of neural activity can be recapitulated by an ANN trained to perform the same task. Nevertheless, there are key features of how neural population activity changes throughout learning that cannot be readily explained in terms of optimization and are not typically features of ANNs. Here we detail three of these features: (1) the inflexibility of neural variability throughout learning, (2) the use of multiple learning processes even during simple tasks, and (3) the presence of large task-nonspecific activity changes. We propose that understanding the role of these features in the brain will be key to describing biological learning using an optimization framework.

Prediction of genetic alteration of phospholipase C isozymes in brain disorders: Studies with deep learning

Genetic mutations leading to the development of various diseases, such as cancer, diabetes, and neurodegenerative disorders, can be attributed to multiple mechanisms and exposure to diverse environments. These disorders further increase gene mutation rates and affect the activity of translated proteins, both phenomena associated with cellular responses. Therefore, maintaining the integrity of genetic and epigenetic information is critical for disease suppression and prevention. With the advent of genome sequencing technologies, large-scale genomic data-based machine learning tools, including deep learning, have been used to predict and identify somatic inactivation or negative dominant expression of target genes in various diseases. Although deep learning studies have recently been highlighted for their ability to distinguish between the genetic information of diseases, conventional wisdom is also necessary to explain the correlation between genotype and phenotype. Herein, we summarize the current understanding of phosphoinositide-specific phospholipase C isozymes (PLCs) and an overview of their associations with genetic variation, as well as their emerging roles in several diseases. We also predicted and discussed new findings of cryptic PLC splice variants by deep learning and the clinical implications of the PLC genetic variations predicted using these tools.

Decentralized control and local information for robust and adaptive decentralized Deep Reinforcement Learning

Decentralization is a central characteristic of biological motor control that allows for fast responses relying on local sensory information. In contrast, the current trend of Deep Reinforcement Learning (DRL) based approaches to motor control follows a centralized paradigm using a single, holistic controller that has to untangle the whole input information space. This motivates to ask whether decentralization as seen in biological control architectures might also be beneficial for embodied sensori-motor control systems when using DRL. To answer this question, we provide an analysis and comparison of eight control architectures for adaptive locomotion that were derived for a four-legged agent, but with their degree of decentralization varying systematically between the extremes of fully centralized and fully decentralized. Our comparison shows that learning speed is significantly enhanced in distributed architectures-while still reaching the same high performance level of centralized architectures-due to smaller search spaces and local costs providing more focused information for learning. Second, we find an increased robustness of the learning process in the decentralized cases-it is less demanding to hyperparameter selection and less prone to becoming trapped in poor local minima. Finally, when examining generalization to uneven terrains-not used during training-we find best performance for an intermediate architecture that is decentralized, but integrates only local information from both neighboring legs. Together, these findings demonstrate beneficial effects of distributing control into decentralized units and relying on local information. This appears as a promising approach towards more robust DRL and better generalization towards adaptive behavior.

Why animals swirl and how they group

We report a possible solution for the long-standing problem of the biological function of swirling motion, when a group of animals orbits a common center of the group. We exploit the hypothesis that learning processes in the nervous system of animals may be modelled by reinforcement learning (RL) and apply it to explain the phenomenon. In contrast to hardly justified models of physical interactions between animals, we propose a small set of rules to be learned by the agents, which results in swirling. The rules are extremely simple and thus applicable to animals with very limited level of information processing. We demonstrate that swirling may be understood in terms of the escort behavior, when an individual animal tries to reside within a certain distance from the swarm center. Moreover, we reveal the biological function of swirling motion: a trained for swirling swarm is by orders of magnitude more resistant to external perturbations, than an untrained one. Using our approach we analyze another class of a coordinated motion of animals-a group locomotion in viscous fluid. On a model example we demonstrate that RL provides an optimal disposition of coherently moving animals with a minimal dissipation of energy.

Machine Learning Applications in Solid Organ Transplantation and Related Complications

The complexity of transplant medicine pushes the boundaries of innate, human reasoning. From networks of immune modulators to dynamic pharmacokinetics to variable postoperative graft survival to equitable allocation of scarce organs, machine learning promises to inform clinical decision making by deciphering prodigious amounts of available data. This paper reviews current research describing how algorithms have the potential to augment clinical practice in solid organ transplantation. We provide a general introduction to different machine learning techniques, describing their strengths, limitations, and barriers to clinical implementation. We summarize emerging evidence that recent advances that allow machine learning algorithms to predict acute post-surgical and long-term outcomes, classify biopsy and radiographic data, augment pharmacologic decision making, and accurately represent the complexity of host immune response. Yet, many of these applications exist in pre-clinical form only, supported primarily by evidence of single-center, retrospective studies. Prospective investigation of these technologies has the potential to unlock the potential of machine learning to augment solid organ transplantation clinical care and health care delivery systems.