Machine learning (ML) has emerged as a vital asset for researchers to analyze and extract valuable information from complex datasets. However, developing an effective and robust ML pipeline can present a real challenge, demanding considerable time and effort, thereby impeding research progress. Existing tools in this landscape require a profound understanding of ML principles and programming skills. Furthermore, users are required to engage in the comprehensive configuration of their ML pipeline to obtain optimal performance.

Twitter presents a valuable and relevant social media platform to study the prevalence of information and sentiment on vaping that may be useful for public health surveillance. Machine learning classifiers that identify vaping-relevant tweets and characterize sentiments in them can underpin a Twitter-based vaping surveillance system. Compared with traditional machine learning classifiers that are reliant on annotations that are expensive to obtain, deep learning classifiers offer the advantage of requiring fewer annotated tweets by leveraging the large numbers of readily available unannotated tweets.

Obtaining the exciton dynamics of large photosynthetic complexes by using mixed quantum mechanics/molecular mechanics (QM/MM) is computationally demanding. We propose a machine learning technique, multi-layer perceptrons, as a tool to reduce the time required to compute excited state energies. With this approach we predict time-dependent density functional theory (TDDFT) excited state energies of bacteriochlorophylls in the Fenna-Matthews-Olson (FMO) complex. Additionally we compute spectral densities and exciton populations from the predictions. Different methods to determine multi-layer perceptron training sets are introduced, leading to several initial data selections. In addition, we compute spectral densities and exciton populations. Once multi-layer perceptrons are trained, predicting excited state energies was found to be significantly faster than the corresponding QM/MM calculations. We showed that multi-layer perceptrons can successfully reproduce the energies of QM/MM calculations to a high degree of accuracy with prediction errors contained within 0.01 eV (0.5%). Spectral densities and exciton dynamics are also in agreement with the TDDFT results. The acceleration and accurate prediction of dynamics strongly encourage the combination of machine learning techniques with ab initio methods.

Machine learning is proving invaluable across disciplines. However, its success is often limited by the quality and quantity of available data, while its adoption is limited by the level of trust afforded by given models. Human vs. machine performance is commonly compared empirically to decide whether a certain task should be performed by a computer or an expert. In reality, the optimal learning strategy may involve combining the complementary strengths of humans and machines. Here, we present expert-augmented machine learning (EAML), an automated method that guides the extraction of expert knowledge and its integration into machine-learned models. We used a large dataset of intensive-care patient data to derive 126 decision rules that predict hospital mortality. Using an online platform, we asked 15 clinicians to assess the relative risk of the subpopulation defined by each rule compared to the total sample. We compared the clinician-assessed risk to the empirical risk and found that, while clinicians agreed with the data in most cases, there were notable exceptions where they overestimated or underestimated the true risk. Studying the rules with greatest disagreement, we identified problems with the training data, including one miscoded variable and one hidden confounder. Filtering the rules based on the extent of disagreement between clinician-assessed risk and empirical risk, we improved performance on out-of-sample data and were able to train with less data. EAML provides a platform for automated creation of problem-specific priors, which help build robust and dependable machine-learning models in critical applications.

With the advances in machine learning (ML) and deep learning (DL) techniques, and the potency of cloud computing in offering services efficiently and cost-effectively, Machine Learning as a Service (MLaaS) cloud platforms have become popular. In addition, there is increasing adoption of third-party cloud services for outsourcing training of DL models, which requires substantial costly computational resources (e.g., high-performance graphics processing units (GPUs)). Such widespread usage of cloud-hosted ML/DL services opens a wide range of attack surfaces for adversaries to exploit the ML/DL system to achieve malicious goals. In this article, we conduct a systematic evaluation of literature of cloud-hosted ML/DL models along both the important dimensions-attacks and defenses-related to their security. Our systematic review identified a total of 31 related articles out of which 19 focused on attack, six focused on defense, and six focused on both attack and defense. Our evaluation reveals that there is an increasing interest from the research community on the perspective of attacking and defending different attacks on Machine Learning as a Service platforms. In addition, we identify the limitations and pitfalls of the analyzed articles and highlight open research issues that require further investigation.

No abstract available

Conventional microwave imagers usually require either time-consuming data acquisition, or complicated reconstruction algorithms for data post-processing, making them largely ineffective for complex in-situ sensing and monitoring. Here, we experimentally report a real-time digital-metasurface imager that can be trained in-situ to generate the radiation patterns required by machine-learning optimized measurement modes. This imager is electronically reprogrammed in real time to access the optimized solution for an entire data set, realizing storage and transfer of full-resolution raw data in dynamically varying scenes. High-accuracy image coding and recognition are demonstrated in situ for various image sets, including hand-written digits and through-wall body gestures, using a single physical hardware imager, reprogrammed in real time. Our electronically controlled metasurface imager opens new venues for intelligent surveillance, fast data acquisition and processing, imaging at various frequencies, and beyond.

High-throughput technologies such as next-generation sequencing allow biologists to observe cell function with unprecedented resolution, but the resulting datasets are too large and complicated for humans to understand without the aid of advanced statistical methods. Machine learning (ML) algorithms, which are designed to automatically find patterns in data, are well suited to this task. Yet these models are often so complex as to be opaque, leaving researchers with few clues about underlying mechanisms. Interpretable machine learning (iML) is a burgeoning subdiscipline of computational statistics devoted to making the predictions of ML models more intelligible to end users. This article is a gentle and critical introduction to iML, with an emphasis on genomic applications. I define relevant concepts, motivate leading methodologies, and provide a simple typology of existing approaches. I survey recent examples of iML in genomics, demonstrating how such techniques are increasingly integrated into research workflows. I argue that iML solutions are required to realize the promise of precision medicine. However, several open challenges remain. I examine the limitations of current state-of-the-art tools and propose a number of directions for future research. While the horizon for iML in genomics is wide and bright, continued progress requires close collaboration across disciplines.

16S sequencing results are often used for Machine Learning (ML) tasks. 16S gene sequences are represented as feature counts, which are associated with taxonomic representation. Raw feature counts may not be the optimal representation for ML.

This paper presents the Edge Learning Machine (ELM), a machine learning framework for edge devices, which manages the training phase on a desktop computer and performs inferences on microcontrollers. The framework implements, in a platform-independent C language, three supervised machine learning algorithms (Support Vector Machine (SVM) with a linear kernel, k-Nearest Neighbors (K-NN), and Decision Tree (DT)), and exploits STM X-Cube-AI to implement Artificial Neural Networks (ANNs) on STM32 Nucleo boards. We investigated the performance of these algorithms on six embedded boards and six datasets (four classifications and two regression). Our analysis-which aims to plug a gap in the literature-shows that the target platforms allow us to achieve the same performance score as a desktop machine, with a similar time latency. ANN performs better than the other algorithms in most cases, with no difference among the target devices. We observed that increasing the depth of an NN improves performance, up to a saturation level. k-NN performs similarly to ANN and, in one case, even better, but requires all the training sets to be kept in the inference phase, posing a significant memory demand, which can be afforded only by high-end edge devices. DT performance has a larger variance across datasets. In general, several factors impact performance in different ways across datasets. This highlights the importance of a framework like ELM, which is able to train and compare different algorithms. To support the developer community, ELM is released on an open-source basis.

We present a fiber tractography approach based on a random forest classification and voting process, guiding each step of the streamline progression by directly processing raw diffusion-weighted signal intensities. For comparison to the state-of-the-art, i.e. tractography pipelines that rely on mathematical modeling, we performed a quantitative and qualitative evaluation with multiple phantom and in vivo experiments, including a comparison to the 96 submissions of the ISMRM tractography challenge 2015. The results demonstrate the vast potential of machine learning for fiber tractography.

Directed evolution and rational design are powerful strategies in protein engineering to tailor enzyme properties to meet the demands in academia and industry. Traditional approaches for enzyme engineering and directed evolution are often experimentally driven, in particular when the protein structure-function relationship is not available. Though they have been successfully applied to engineer many enzymes, these methods are still facing significant challenges due to the tremendous size of the protein sequence space and the combinatorial problem. It can be ascertained that current experimental techniques and computational techniques might never be able to sample through the entire protein sequence space and benefit from nature's full potential for the generation of better enzymes. With advancements in next generation sequencing, high throughput screening methods, the growth of protein databases and artificial intelligence, especially machine learning (ML), data-driven enzyme engineering is emerging as a promising solution to these challenges. To date, ML-assisted approaches have efficiently and accurately determined the quantitative structure-property/activity relationship for the prediction of diverse enzyme properties. In addition, enzyme engineering can be accelerated much faster than ever through the combination of experimental library generation and ML-based prediction. In this chapter, we review the recent progresses in ML-assisted enzyme engineering and highlight several successful examples (e.g., to enhance activity, enantioselectivity, or thermostability). Herein we explain enzyme engineering strategies that combine random or (semi-)rational approaches with ML methods and allow an effective reengineering of enzymes to improve targeted properties. We further discuss the main challenges to solve in order to realize the full potential of ML methods in enzyme engineering. Finally, we describe the current limitations of ML-assisted enzyme engineering, and our perspective on future opportunities in this growing field.

Phospholipidosis is an adverse effect caused by numerous cationic amphiphilic drugs and can affect many cell types. It is characterized by the excess accumulation of phospholipids and is most reliably identified by electron microscopy of cells revealing the presence of lamellar inclusion bodies. The development of phospholipidosis can cause a delay in the drug development process, and the importance of computational approaches to the problem has been well documented. Previous work on predictive methods for phospholipidosis showed that state of the art machine learning methods produced the best results. Here we extend this work by looking at a larger data set mined from the literature. We find that circular fingerprints lead to better models than either E-Dragon descriptors or a combination of the two. We also observe very similar performance in general between Random Forest and Support Vector Machine models.

To present an overview of current machine learning methods and their use in medical research, focusing on select machine learning techniques, best practices, and deep learning.

Fast and reliable detection of patients with severe and heterogeneous illnesses is a major goal of precision medicine1,2. Patients with leukaemia can be identified using machine learning on the basis of their blood transcriptomes3. However, there is an increasing divide between what is technically possible and what is allowed, because of privacy legislation4,5. Here, to facilitate the integration of any medical data from any data owner worldwide without violating privacy laws, we introduce Swarm Learning-a decentralized machine-learning approach that unites edge computing, blockchain-based peer-to-peer networking and coordination while maintaining confidentiality without the need for a central coordinator, thereby going beyond federated learning. To illustrate the feasibility of using Swarm Learning to develop disease classifiers using distributed data, we chose four use cases of heterogeneous diseases (COVID-19, tuberculosis, leukaemia and lung pathologies). With more than 16,400 blood transcriptomes derived from 127 clinical studies with non-uniform distributions of cases and controls and substantial study biases, as well as more than 95,000 chest X-ray images, we show that Swarm Learning classifiers outperform those developed at individual sites. In addition, Swarm Learning completely fulfils local confidentiality regulations by design. We believe that this approach will notably accelerate the introduction of precision medicine.

To understand the intricacies of microorganisms at the molecular level requires making sense of copious volumes of data such that it may now be humanly impossible to detect insightful data patterns without an artificial intelligence application called machine learning. Applying machine learning to address biological problems is expected to grow at an unprecedented rate, yet it is perceived by the uninitiated as a mysterious and daunting entity entrusted to the domain of mathematicians and computer scientists. The aim of this review is to identify key points required to start the journey of becoming an effective machine learning practitioner. These key points are further reinforced with an evaluation of how machine learning has been applied so far in a broad scope of real-life microbiology examples. This includes predicting drug targets or vaccine candidates, diagnosing microorganisms causing infectious diseases, classifying drug resistance against antimicrobial medicines, predicting disease outbreaks and exploring microbial interactions. Our hope is to inspire microbiologists and other related researchers to join the emerging machine learning revolution.

The complexity of the human sense of smell is increasingly reflected in complex and high-dimensional data, which opens opportunities for data-driven approaches that complement hypothesis-driven research. Contemporary developments in computational and data science, with its currently most popular implementation as machine learning, facilitate complex data-driven research approaches. The use of machine learning in human olfactory research included major approaches comprising 1) the study of the physiology of pattern-based odor detection and recognition processes, 2) pattern recognition in olfactory phenotypes, 3) the development of complex disease biomarkers including olfactory features, 4) odor prediction from physico-chemical properties of volatile molecules, and 5) knowledge discovery in publicly available big databases. A limited set of unsupervised and supervised machine-learned methods has been used in these projects, however, the increasing use of contemporary methods of computational science is reflected in a growing number of reports employing machine learning for human olfactory research. This review provides key concepts of machine learning and summarizes current applications on human olfactory data.

The availability of large-scale datasets on which to train, benchmark and test algorithms has been central to the rapid development of machine learning as a discipline. Despite considerable advancements, the field of quantum machine learning has thus far lacked a set of comprehensive large-scale datasets upon which to benchmark the development of algorithms for use in applied and theoretical quantum settings. In this paper, we introduce such a dataset, the QDataSet, a quantum dataset designed specifically to facilitate the training and development of quantum machine learning algorithms. The QDataSet comprises 52 high-quality publicly available datasets derived from simulations of one- and two-qubit systems evolving in the presence and/or absence of noise. The datasets are structured to provide a wealth of information to enable machine learning practitioners to use the QDataSet to solve problems in applied quantum computation, such as quantum control, quantum spectroscopy and tomography. Accompanying the datasets on the associated GitHub repository are a set of workbooks demonstrating the use of the QDataSet in a range of optimisation contexts.

Nanocrystals have exhibited great advantage for enhancing the dissolution rate of water insoluble drugs due to the reduced size to nanoscale. However, current pharmaceutical approaches for nanocrystals formulation development highly depend on the expert experience and trial-and-error attempts which remain time and resource consuming. In this research, we utilized machine learning techniques to predict the particle size and polydispersity index (PDI) of nanocrystals. Firstly, 910 nanocrystal size data and 341 PDI data by three preparation methods (ball wet milling (BWM) method, high-pressure homogenization (HPH) method and antisolvent precipitation (ASP) method) were collected for the construction of the prediction models. The results demonstrated that light gradient boosting machine (LightGBM) exhibited well performance for the nanocrystals size and PDI prediction with BWM and HPH methods, but relatively poor predictions for ASP method. The possible reasons for the poor prediction refer to low quality of data because of the poor reproducibility and instability of nanocrystals by ASP method, which also confirm that current commercialized products were mainly manufactured by BWM and HPH approaches. Notably, the contribution of the influence factors was ranked by the LightGBM, which demonstrated that milling time, cycle index and concentration of stabilizer are crucial factors for nanocrystals prepared by BWM, HPH and ASP, respectively. Furthermore, the model generalizations and prediction accuracies of LightGBM were confirmed experimentally by the newly prepared nanocrystals. In conclusion, the machine learning techniques can be successfully utilized for the predictions of nanocrystals prepared by BWM and HPH methods. Our research also reveals a new way for nanotechnology manufacture.

Animal movement drives important ecological processes such as migration and the spread of infectious disease. Current approaches to modeling animal tracking data focus on parametric models used to understand environmental effects on movement behavior and to fill in missing tracking data. Machine Learning and Deep learning algorithms are powerful and flexible predictive modeling tools but have rarely been applied to animal movement data. In this study we present a general framework for predicting animal movement that is a combination of two steps: first predicting movement behavioral states and second predicting the animal's velocity. We specify this framework at the individual level as well as for collective movement. We use Random Forests, Neural and Recurrent Neural Networks to compare performance predicting one step ahead as well as long range simulations. We compare results against a custom constructed Stochastic Differential Equation (SDE) model. We apply this approach to high resolution ant movement data. We found that the individual level Machine Learning and Deep Learning methods outperformed the SDE model for one step ahead prediction. The SDE model did comparatively better at simulating long range movement behaviour. Of the Machine Learning and Deep Learning models the Long Short Term Memory (LSTM) individual level model did best at long range simulations. We also applied the Random Forest and LSTM individual level models to model gull migratory movement to demonstrate the generalizability of this framework. Machine Learning and deep learning models are easier to specify compared to traditional parametric movement models which can have restrictive assumptions. However, machine learning and deep learning models are less interpretable than parametric movement models. The type of model used should be determined by the goal of the study, if the goal is prediction, our study provides evidence that machine learning and deep learning models could be useful tools.