Realizing Molecular Machine Learning through Communications for Biological AI: Future Directions and Challenges.

Artificial Intelligence (AI) and Machine Learning (ML) are weaving their way into the fabric of society, where they are playing a crucial role in numerous facets of our lives. As we witness the increased deployment of AI and ML in various types of devices, we benefit from their use into energy-efficient algorithms for low powered devices. In this paper, we investigate a scale and medium that is far smaller than conventional devices as we move towards molecular systems that can be utilized to perform machine learning functions, i.e., Molecular Machine Learning (MML). Fundamental to the operation of MML is the transport, processing, and interpretation of information propagated by molecules through chemical reactions. We begin by reviewing the current approaches that have been developed for MML, before we move towards potential new directions that rely on gene regulatory networks inside biological organisms as well as their population interactions to create neural networks. We then investigate mechanisms for training machine learning structures in biological cells based on calcium signaling and demonstrate their application to build an Analog to Digital Converter (ADC). Lastly, we look at potential future directions as well as challenges that this area could solve.

Subjective Information and Survival in a Simulated Biological System.

Information transmission and storage have gained traction as unifying concepts to characterize biological systems and their chances of survival and evolution at multiple scales. Despite the potential for an information-based mathematical framework to offer new insights into life processes and ways to interact with and control them, the main legacy is that of Shannon's, where a purely syntactic characterization of information scores systems on the basis of their maximum information efficiency. The latter metrics seem not entirely suitable for biological systems, where transmission and storage of different pieces of information (carrying different semantics) can result in different chances of survival. Based on an abstract mathematical model able to capture the parameters and behaviors of a population of single-celled organisms whose survival is correlated to information retrieval from the environment, this paper explores the aforementioned disconnect between classical information theory and biology. In this paper, we present a model, specified as a computational state machine, which is then utilized in a simulation framework constructed specifically to reveal emergence of a "subjective information", i.e., trade-off between a living system's capability to maximize the acquisition of information from the environment, and the maximization of its growth and survival over time. Simulations clearly show that a strategy that maximizes information efficiency results in a lower growth rate with respect to the strategy that gains less information but contains a higher meaning for survival.

Metabolic Synergy between Human Symbionts Bacteroides and Methanobrevibacter.

Trophic interactions between microbes are postulated to determine whether a host microbiome is healthy or causes predisposition to disease. Two abundant taxa, the Gram-negative heterotrophic bacterium Bacteroides thetaiotaomicron and the methanogenic archaeon Methanobrevibacter smithii, are proposed to have a synergistic metabolic relationship. Both organisms play vital roles in human gut health; B. thetaiotaomicron assists the host by fermenting dietary polysaccharides, whereas M. smithii consumes end-stage fermentation products and is hypothesized to relieve feedback inhibition of upstream microbes such as B. thetaiotaomicron. To study their metabolic interactions, we defined and optimized a coculture system and used software testing techniques to analyze growth under a range of conditions representing the nutrient environment of the host. We verify that B. thetaiotaomicron fermentation products are sufficient for M. smithii growth and that accumulation of fermentation products alters secretion of metabolites by B. thetaiotaomicron to benefit M. smithii. Studies suggest that B. thetaiotaomicron metabolic efficiency is greater in the absence of fermentation products or in the presence of M. smithii. Under certain conditions, B. thetaiotaomicron and M. smithii form interspecies granules consistent with behavior observed for syntrophic partnerships between microbes in soil or sediment enrichments and anaerobic digesters. Furthermore, when vitamin B12, hematin, and hydrogen gas are abundant, coculture growth is greater than the sum of growth observed for monocultures, suggesting that both organisms benefit from a synergistic mutual metabolic relationship. IMPORTANCE The human gut functions through a complex system of interactions between the host human tissue and the microbes which inhabit it. These diverse interactions are difficult to model or examine under controlled laboratory conditions. We studied the interactions between two dominant human gut microbes, B. thetaiotaomicron and M. smithii, using a seven-component culturing approach that allows the systematic examination of the metabolic complexity of this binary microbial system. By combining high-throughput methods with machine learning techniques, we were able to investigate the interactions between two dominant genera of the gut microbiome in a wide variety of environmental conditions. Our approach can be broadly applied to studying microbial interactions and may be extended to evaluate and curate computational metabolic models. The software tools developed for this study are available as user-friendly tutorials in the Department of Energy KBase.

Elucidation of dynamic microRNA regulations in cancer progression using integrative machine learning.

MOTIVATION: Empowered by advanced genomics discovery tools, recent biomedical research has produced a massive amount of genomic data on (post-)transcriptional regulations related to transcription factors, microRNAs, long non-coding RNAs, epigenetic modifications and genetic variations. Computational modeling, as an essential research method, has generated promising testable quantitative models that represent complex interplay among different gene regulatory mechanisms based on these data in many biological systems. However, given the dynamic changes of interactome in chaotic systems such as cancers, and the dramatic growth of heterogeneous data on this topic, such promise has encountered unprecedented challenges in terms of model complexity and scalability. In this study, we introduce a new integrative machine learning approach that can infer multifaceted gene regulations in cancers with a particular focus on microRNA regulation. In addition to new strategies for data integration and graphical model fusion, a supervised deep learning model was integrated to identify conditional microRNA-mRNA interactions across different cancer stages. RESULTS: In a case study of human breast cancer, we have identified distinct gene regulatory networks associated with four progressive stages. The subsequent functional analysis focusing on microRNA-mediated dysregulation across stages has revealed significant changes in major cancer hallmarks, as well as novel pathological signaling and metabolic processes, which shed light on microRNAs' regulatory roles in breast cancer progression. We believe this integrative model can be a robust and effective discovery tool to understand key regulatory characteristics in complex biological systems. AVAILABILITY: http://sbbi-panda.unl.edu/pin/.

Molecular Communications in Viral Infections Research: Modeling, Experimental Data, and Future Directions.

Hundreds of millions of people worldwide are affected by viral infections each year, and yet, several of them neither have vaccines nor effective treatment during and post-infection. This challenge has been highlighted by the COVID-19 pandemic, showing how viruses can quickly spread and impact society as a whole. Novel interdisciplinary techniques must emerge to provide forward-looking strategies to combat viral infections, as well as possible future pandemics. In the past decade, an interdisciplinary area involving bioengineering, nanotechnology and information and communication technology (ICT) has been developed, known as Molecular Communications. This new emerging area uses elements of classical communication systems to molecular signalling and communication found inside and outside biological systems, characterizing the signalling processes between cells and viruses. In this paper, we provide an extensive and detailed discussion on how molecular communications can be integrated into the viral infectious diseases research, and how possible treatment and vaccines can be developed considering molecules as information carriers. We provide a literature review on molecular communications models for viral infection (intra-body and extra-body), a deep analysis on their effects on immune response, how experimental can be used by the molecular communications community, as well as open issues and future directions.

Nanonetworks in Biomedical Applications.

By interconnecting nanomachines and forming nanonetworks, the capacities of single nanomachines are expected to be enhanced, as the ensuing information exchange will allow them to cooperate towards a common goal. Nowadays, systems normally use electromagnetic signals to encode, send and receive information, however, in a novel communication paradigm, molecular transceivers, channel models or protocols use molecules. This article presents the current developments in nanomachines along with their future architecture to better understand nanonetwork scenarios in biomedical applications. Furthermore, to highlight the communication needs between nanomachines, two applications for nanonetworks are also presented: i) a new networking paradigm, called the Internet of NanoThings, that allows nanoscale devices to interconnect with existing communication networks, and ii) Molecular Communication, where the propagation of chemical compounds like drug particles, carry out the information exchange.

Computational Models for Trapping Ebola Virus Using Engineered Bacteria.

The outbreak of the Ebola virus in recent years has resulted in numerous research initiatives to seek new solutions to contain the virus. A number of approaches that have been investigated include new vaccines to boost the immune system. An alternative post-exposure treatment is presented in this paper. The proposed approach for clearing the Ebola virus can be developed through a microfluidic attenuator, which contains the engineered bacteria that traps Ebola flowing through the blood onto its membrane. The paper presents the analysis of the chemical binding force between the virus and a genetically engineered bacterium considering the opposing forces acting on the attachment point, including hydrodynamic tension and drag force. To test the efficacy of the technique, simulations of bacterial motility within a confined area to trap the virus were performed. More than 60 percent of the displaced virus could be collected within 15 minutes. While the proposed approach currently focuses on in vitro environments for trapping the virus, the system can be further developed into a future treatment system whereby blood can be cycled out of the body into a microfluidic device that contains the engineered bacteria to trap viruses.

BioSIMP: Using Software Testing Techniques for Sampling and Inference in Biological Organisms.

Years of research in software engineering has given us novel ways to reason about, test, and predict the behavior of complex software systems that contain hundreds of thousands of lines of code. Many of these techniques have been inspired by nature such as genetic algorithms, swarm intelligence, and ant colony optimization. In this paper we reverse the direction and present BioSIMP, a process that models and predicts the behavior of biological organisms to aid in the emerging field of systems biology. It utilizes techniques from testing and modeling of highly-configurable software systems. Using both experimental and simulation data we show that BioSIMP can find important environmental factors in two microbial organisms. However, we learn that in order to fully reason about the complexity of biological systems, we will need to extend existing or create new software engineering techniques.

Subthreshold linear modeling of dendritic trees: a computational approach.

The design of communication systems based on the transmission of information through neurons is envisioned as a key technology for the pervasive interconnection of future wearable and implantable devices. While previous literature has mainly focused on modeling propagation of electrochemical spikes carrying natural information through the nervous system, in recent work the authors of this paper proposed the so-called subthreshold electrical stimulation as a viable technique to propagate artificial information through neurons. This technique promises to limit the interference with natural communication processes, and it can be successfully approximated with linear models. In this paper, a novel model is proposed to account for the subthreshold stimuli propagation from the dendritic tree to the soma of a neuron. A computational approach is detailed to obtain this model for a given realistic 3D dendritic tree with an arbitrary morphology. Numerical results from the model are obtained over a stimulation signal bandwidth of 1KHz, and compared with the results of a simulation through the NEURON software.

Pharmacokinetic Modeling and Biodistribution Estimation Through the Molecular Communication Paradigm.

Targeted drug delivery systems (TDDSs) are therapeutic methods based on the injection and delivery of drug-loaded particles. The engineering of TDDSs must take into account both the therapeutic effects of the drug at the target delivery location and the toxicity of the drug while it accumulates in other regions of the body. These characteristics are directly related to how the drug-loaded particles distribute within the body, i.e., biodistribution, as a consequence of the processes involved in the particle propagation, i.e., pharmacokinetics. In this paper, the pharmacokinetics of TDDSs is analytically modeled through the abstraction of molecular communication, a novel paradigm in communication theory. Not only is the particle advection and diffusion, considered in our previous study, included in this model, but also are other physicochemical processes in the particle propagation, such as absorption, reaction, and adhesion. In addition, the proposed model includes the impact of cardiovascular diseases, such as arteriosclerosis and tumor-induced blood vessel leakage. Based on this model, the biodistribution at the delivery location is estimated through communication engineering metrics, such as channel delay and path loss, together with the drug accumulation in the rest of the body. The proposed pharmacokinetic model is validated against multiphysics finite-element simulations, and numerical results are provided for the biodistribution estimation in different scenarios. Finally, based on the proposed model, a procedure to optimize the drug injection rate is proposed to achieve a desired drug delivery rate. The outcome of this study is a multiscale physics-based analytical pharmacokinetic model.

A Molecular Communication System Model for Particulate Drug Delivery Systems.

The goal of a drug delivery system (DDS) is to convey a drug where the medication is needed, while, at the same time, preventing the drug from affecting other healthy parts of the body. Drugs composed of micro- or nano-sized particles (particulate DDS) that are able to cross barriers which prevent large particles from escaping the bloodstream are used in the most advanced solutions. Molecular communication (MC) is used as an abstraction of the propagation of drug particles in the body. MC is a new paradigm in communication research where the exchange of information is achieved through the propagation of molecules. Here, the transmitter is the drug injection, the receiver is the drug delivery, and the channel is realized by the transport of drug particles, thus enabling the analysis and design of a particulate DDS using communication tools. This is achieved by modeling the MC channel as two separate contributions, namely, the cardiovascular network model and the drug propagation network. The cardiovascular network model allows to analytically compute the blood velocity profile in every location of the cardiovascular system given the flow input by the heart. The drug propagation network model allows the analytical expression of the drug delivery rate at the targeted site given the drug injection rate. Numerical results are also presented to assess the flexibility and accuracy of the developed model. The study of novel optimization techniques for a more effective and less invasive drug delivery will be aided by this model, while paving the way for novel communication techniques for Intrabody communication networks.