The Impact of COVID-19 on Multidrug-Resistant Bacteria at a Slovenian Tertiary Medical Center.

The COVID-19 pandemic has strained healthcare systems globally. Shortages of hospital beds, reassignment of healthcare workers to COVID-19-dedicated wards, an increased workload, and evolving infection prevention and control measures have potentially contributed to the spread of multidrug-resistant bacteria (MDRB). To determine the impact of the COVID-19 pandemic at the University Medical Center Ljubljana, a tertiary teaching hospital, we analyzed the monthly incidence of select bacterial species per patient from 2018 to 2022. The analysis was performed for all isolates and for MDRB isolates. The data were analyzed separately for isolates from all clinical samples, from blood culture only, and from clinical and surveillance samples. Our findings revealed an increased incidence density of patients with Enterococcus faecium, Staphylococcus aureus, Escherichia coli, and Pseudomonas aeruginosa isolates from clinical samples during the COVID-19 period in the studied hospital. Notably, the incidence density of MDRB isolates-vancomycin-resistant E. faecium, extended-spectrum betalactamase-producing K. pneumoniae, and betalactam-resistant P. aeruginosa-from clinical samples increased during the COVID-19 period. There were no statistically significant differences in the incidence density of patients with blood culture MDRB isolates. We observed an increase in the overall MDRB burden (patients with MDRB isolates from both clinical and surveillance samples per 1000 patient days) in the COVID-19 period in the studied hospital for vancomycin-resistant E. faecium, carbapenem-resistant K. pneumoniae, and betalactam-resistant P. aeruginosa and a decrease in the methicillin-resistant S. aureus burden.

Designed allosteric protein logic.

The regulation of protein function by external or internal signals is one of the key features of living organisms. The ability to directly control the function of a selected protein would represent a valuable tool for regulating biological processes. Here, we present a generally applicable regulation of proteins called INSRTR, based on inserting a peptide into a loop of a target protein that retains its function. We demonstrate the versatility and robustness of coiled-coil-mediated regulation, which enables designs for either inactivation or activation of selected protein functions, and implementation of two-input logic functions with rapid response in mammalian cells. The selection of insertion positions in tested proteins was facilitated by using a predictive machine learning model. We showcase the robustness of the INSRTR strategy on proteins with diverse folds and biological functions, including enzymes, signaling mediators, DNA binders, transcriptional regulators, reporters, and antibody domains implemented as chimeric antigen receptors in T cells. Our findings highlight the potential of INSRTR as a powerful tool for precise control of protein function, advancing our understanding of biological processes and developing biotechnological and therapeutic interventions.

Empowering Participatory Research in Urban Health: Wearable Biometric and Environmental Sensors for Activity Recognition.

Participatory exposure research, which tracks behaviour and assesses exposure to stressors like air pollution, traditionally relies on time-activity diaries. This study introduces a novel approach, employing machine learning (ML) to empower laypersons in human activity recognition (HAR), aiming to reduce dependence on manual recording by leveraging data from wearable sensors. Recognising complex activities such as smoking and cooking presents unique challenges due to specific environmental conditions. In this research, we combined wearable environment/ambient and wrist-worn activity/biometric sensors for complex activity recognition in an urban stressor exposure study, measuring parameters like particulate matter concentrations, temperature, and humidity. Two groups, Group H (88 individuals) and Group M (18 individuals), wore the devices and manually logged their activities hourly and minutely, respectively. Prioritising accessibility and inclusivity, we selected three classification algorithms: k-nearest neighbours (IBk), decision trees (J48), and random forests (RF), based on: (1) proven efficacy in existing literature, (2) understandability and transparency for laypersons, (3) availability on user-friendly platforms like WEKA, and (4) efficiency on basic devices such as office laptops or smartphones. Accuracy improved with finer temporal resolution and detailed activity categories. However, when compared to other published human activity recognition research, our accuracy rates, particularly for less complex activities, were not as competitive. Misclassifications were higher for vague activities (resting, playing), while well-defined activities (smoking, cooking, running) had few errors. Including environmental sensor data increased accuracy for all activities, especially playing, smoking, and running. Future work should consider exploring other explainable algorithms available on diverse tools and platforms. Our findings underscore ML's potential in exposure studies, emphasising its adaptability and significance for laypersons while also highlighting areas for improvement.

Xerophilic fungi contaminating historically valuable easel paintings from Slovenia.

Historically valuable canvas paintings are often exposed to conditions enabling microbial deterioration. Painting materials, mainly of organic origin, in combination with high humidity and other environmental conditions, favor microbial metabolism and growth. These preconditions are often present during exhibitions or storage in old buildings, such as churches and castles, and also in museum storage depositories. The accumulated dust serves as an inoculum for both indoor and outdoor fungi. In our study, we present the results on cultivable fungi isolated from 24 canvas paintings, mainly exhibited in Slovenian sacral buildings, dating from the 16th to 21st centuries. Fungi were isolated from the front and back of damaged and undamaged surfaces of the paintings using culture media with high- and low-water activity. A total of 465 isolates were identified using current taxonomic DNA markers and assigned to 37 genera and 98 species. The most abundant genus was Aspergillus, represented by 32 species, of which 9 xerophilic species are for the first time mentioned in contaminated paintings. In addition to the most abundant xerophilic A. vitricola, A. destruens, A. tardicrescens, and A. magnivesiculatus, xerophilic Wallemia muriae and W. canadensis, xerotolerant Penicillium chrysogenum, P. brevicompactum, P. corylophilum, and xerotolerant Cladosporium species were most frequent. When machine learning methods were used to predict the relationship between fungal contamination, damage to the painting, and the type of material present, proteins were identified as one of the most important factors and cracked paint was identified as a hotspot for fungal growth. Aspergillus species colonize paintings regardless of materials, while Wallemia spp. can be associated with animal fat. Culture media with low-water activity are suggested in such inventories to isolate and obtain an overview of fungi that are actively contaminating paintings stored indoors at low relative humidity.

Effect of Location, Disinfection, and Building Materials on the Presence and Richness of Culturable Mycobiota through Oligotrophic Drinking Water Systems.

Safe drinking water is a constant challenge due to global environmental changes and the rise of emerging pathogens-lately, these also include fungi. The fungal presence in water greatly varies between sampling locations. Little is known about fungi from water in combination with a selection of materials used in water distribution systems. Our research was focused on five water plants located in the Pannonian Plain, Slovenia. Sampled water originated from different natural water sources and was subjected to different cleaning methods before distribution. The average numbers of fungi from natural water, water after disinfection, water at the first sampling point in the water network, and water at the last sampling point were 260, 49, 64, and 97 CFU/L, respectively. Chlorination reduced the number of fungi by a factor of 5, but its effect decreased with the length of the water network. The occurrence of different fungi in water and on materials depended on the choice of material. The presence of the genera Aspergillus, Acremonium, Furcasterigmium, Gliomastix, and Sarocladium was mostly observed on cement, while Cadophora, Cladosporium, Cyphellophora, and Exophiala prevailed on metals. Plastic materials were more susceptible to colonization with basidiomycetous fungi. Opportunistically pathogenic fungi were isolated sporadically from materials and water and do not represent a significant health risk for water consumers. In addition to cultivation data, physico-chemical features of water were measured and later processed with machine learning methods, revealing the sampling location and water cleaning processes as the main factors affecting fungal presence and richness in water and materials in contact with water.

Machine learning-ready remote sensing data for Maya archaeology.

In our study, we set out to collect a multimodal annotated dataset for remote sensing of Maya archaeology, that is suitable for deep learning. The dataset covers the area around Chactún, one of the largest ancient Maya urban centres in the central Yucatán Peninsula. The dataset includes five types of data records: raster visualisations and canopy height model from airborne laser scanning (ALS) data, Sentinel-1 and Sentinel-2 satellite data, and manual data annotations. The manual annotations (used as binary masks) represent three different types of ancient Maya structures (class labels: buildings, platforms, and aguadas - artificial reservoirs) within the study area, their exact locations, and boundaries. The dataset is ready for use with machine learning, including convolutional neural networks (CNNs) for object recognition, object localization (detection), and semantic segmentation. We would like to provide this dataset to help more research teams develop their own computer vision models for investigations of Maya archaeology or improve existing ones.

GC-EI-MS datasets of trimethylsilyl (TMS) and tert-butyl dimethyl silyl (TBDMS) derivatives for development of machine learning-based compound identification approaches.

In the field of environment and health studies, recent trends have focused on the identification of contaminants of emerging concern (CEC). This is a complex, challenging task, as resources, such as compound databases (DBs) and mass spectral libraries (MSLs) concerning these compounds are very poor. This is particularly true for semi polar organic contaminants that have to be derivatized prior to gas chromatography-mass spectrometry (GC-MS) analysis with electron impact ionization (EI), for which it is barely possible to find any records. In particular, there is a severe lack of datasets of GC-EI-MS spectra generated and made publicly available for the purpose of development, validation and performance evaluation of cheminformatics-assisted compound structure identification (CSI) approaches, including novel cutting-edge machine learning (ML)-based approaches [1]. We set out to fill this gap and support the machine learning-assisted compound identification, thus aiding cheminformatics-assisted identification of silylated derivatives in GC-MS laboratories working in the field of environment and health. To this end, we have generated 12 datasets of GC-EI-MS spectra, six of which contain GC-EI-MS spectra of trimethylsilyl (TMS) and six GC-EI-MS spectra of tert-butyldimethylsilyl (TBDMS) derivatives. Four of these datasets, named testing datasets, contain mass spectra acquired by the authors. They are available in full, together with corresponding metadata. Eight datasets, named training datasets, were derived from mass spectra in the NIST 17 Mass Spectral Library. For these, we have only made the metadata publicly available, due to licensing reasons. For each type of derivative, two testing datasets are generated by acquiring and processing GC-EI-MS spectra, such that they include raw and processed GC-EI-MS spectra of TMS and TBDMS derivatives of CECs, along with their corresponding metadata. The metadata contains IUPAC name, exact mass, molecular formula, InChI, InChIKey, SMILES and PubChemID, of each CEC and CEC-TMS or CEC-TBDMS derivative, where available. Eight GC-EI-MS training datasets are generated by using the National Institute of Standards and Technology (NIST)/U.S. Environmental Protection Agency (EPA)/National Institute of Health (NIH) 17 Mass Spectral Library. For each derivative type (TMS and TBDMS), four datasets are given, each corresponding to an original dataset obtained from NIST/EPA/NIH 17 and three variants thereof, obtained after each of the filtering steps of the procedure described below. Only the metadata about the training datasets are available, describing the corresponding NIST/EPA/NIH 17 entires: These include the compound name, CAS Registry number, InChIKey, exact mass, Mw, NIST number and ID number. The datasets we present here were used to train and test predictive models for identification of silylated derivatives built with ML approaches [4]. The models were built by using data curated from the NIST Mass Spectral Library 17 [2] and the machine learning approach of CSI:Output Kernel Regression (CSI:OKR) [2]. Data from the NIST Mass Spectral Library 17 are commercially available from the National Institute of Standards and Technology (NIST)/U.S. Environmental Protection Agency (EPA)/National Institute of Health (NIH) and thus cannot be made publicly available. This highlights the need for publicly available GC-EI-MS spectra, which we address by releasing in full the four testing datasets.

On the Influence of Aging on Classification Performance in the Visual EEG Oddball Paradigm Using Statistical and Temporal Features.

The utilization of a non-invasive electroencephalogram (EEG) as an input sensor is a common approach in the field of the brain-computer interfaces (BCI). However, the collected EEG data pose many challenges, one of which may be the age-related variability of event-related potentials (ERPs), which are often used as primary EEG BCI signal features. To assess the potential effects of aging, a sample of 27 young and 43 older healthy individuals participated in a visual oddball study, in which they passively viewed frequent stimuli among randomly occurring rare stimuli while being recorded with a 32-channel EEG set. Two types of EEG datasets were created to train the classifiers, one consisting of amplitude and spectral features in time and another with extracted time-independent statistical ERP features. Among the nine classifiers tested, linear classifiers performed best. Furthermore, we show that classification performance differs between dataset types. When temporal features were used, maximum individuals' performance scores were higher, had lower variance, and were less affected overall by within-class differences such as age. Finally, we found that the effect of aging on classification performance depends on the classifier and its internal feature ranking. Accordingly, performance will differ if the model favors features with large within-class differences. With this in mind, care must be taken in feature extraction and selection to find the correct features and consequently avoid potential age-related performance degradation in practice.

Correlative Fluorescence and Raman Microscopy to Define Mitotic Stages at the Single-Cell Level: Opportunities and Limitations in the AI Era.

Nowadays, morphology and molecular analyses at the single-cell level have a fundamental role in understanding biology better. These methods are utilized for cell phenotyping and in-depth studies of cellular processes, such as mitosis. Fluorescence microscopy and optical spectroscopy techniques, including Raman micro-spectroscopy, allow researchers to examine biological samples at the single-cell level in a non-destructive manner. Fluorescence microscopy can give detailed morphological information about the localization of stained molecules, while Raman microscopy can produce label-free images at the subcellular level; thus, it can reveal the spatial distribution of molecular fingerprints, even in live samples. Accordingly, the combination of correlative fluorescence and Raman microscopy (CFRM) offers a unique approach for studying cellular stages at the single-cell level. However, subcellular spectral maps are complex and challenging to interpret. Artificial intelligence (AI) may serve as a valuable solution to characterize the molecular backgrounds of phenotypes and biological processes by finding the characteristic patterns in spectral maps. The major contributions of the manuscript are: (I) it gives a comprehensive review of the literature focusing on AI techniques in Raman-based cellular phenotyping; (II) via the presentation of a case study, a new neural network-based approach is described, and the opportunities and limitations of AI, specifically deep learning, are discussed regarding the analysis of Raman spectroscopy data to classify mitotic cellular stages based on their spectral maps.

Analysis of hallux valgus angles automatically extracted from 3D foot scans taken in North America, Europe, and Asia.

The forefoot is the foot part most affected by ill-fitting shoes. Footwear fitting considers the measurements of length, width, and arch length. Toe shape has not yet been used in sizing feet and fitting shoes. This study aims to investigate the variation in toe shape, as measured by the hallux valgus angle. An automatic and reproducible hallux valgus angle measuring method using 3D foot scans with no palpation markers is proposed and applied to about half a million samples collected across North America, Europe, and Asia. The measuring method is robust and can detect the medial contour along the proximal phalanx even in extreme cases. The hallux valgus angle has a normal distribution with long tails on both sides in the general population. Large dispersions of HVA values were observed for both genders and in all three geographical regions. Practitioner summary: The hallux valgus angle has a broad distribution in the general population. Females have larger hallux valgus angles than males, and people from Asia have larger hallux valgus angles than people from North America and Europe. Shoe toe boxes should be designed to fit the actual shapes of shoppers' toes. The proposed method for measuring HVA opens a new opportunity to study the causal relationship between shoe wearing habits and HVA on a large scale.

Determining Exception Context in Assembly Operations from Multimodal Data.

Robot assembly tasks can fail due to unpredictable errors and can only continue with the manual intervention of a human operator. Recently, we proposed an exception strategy learning framework based on statistical learning and context determination, which can successfully resolve such situations. This paper deals with context determination from multimodal data, which is the key component of our framework. We propose a novel approach to generate unified low-dimensional context descriptions based on image and force-torque data. For this purpose, we combine a state-of-the-art neural network model for image segmentation and contact point estimation using force-torque measurements. An ensemble of decision trees is used to combine features from the two modalities. To validate the proposed approach, we have collected datasets of deliberately induced insertion failures both for the classic peg-in-hole insertion task and for an industrially relevant task of car starter assembly. We demonstrate that the proposed approach generates reliable low-dimensional descriptors, suitable as queries necessary in statistical learning.

Machine learning for identification of silylated derivatives from mass spectra.

MOTIVATION: Compound structure identification is using increasingly more sophisticated computational tools, among which machine learning tools are a recent addition that quickly gains in importance. These tools, of which the method titled Compound Structure Identification:Input Output Kernel Regression (CSI:IOKR) is an excellent example, have been used to elucidate compound structure from mass spectral (MS) data with significant accuracy, confidence and speed. They have, however, largely focused on data coming from liquid chromatography coupled to tandem mass spectrometry (LC-MS). Gas chromatography coupled to mass spectrometry (GC-MS) is an alternative which offers several advantages as compared to LC-MS, including higher data reproducibility. Of special importance is the substantial compound coverage offered by GC-MS, further expanded by derivatization procedures, such as silylation, which can improve the volatility, thermal stability and chromatographic peak shape of semi-volatile analytes. Despite these advantages and the increasing size of compound databases and MS libraries, GC-MS data have not yet been used by machine learning approaches to compound structure identification. RESULTS: This study presents a successful application of the CSI:IOKR machine learning method for the identification of environmental contaminants from GC-MS spectra. We use CSI:IOKR as an alternative to exhaustive search of MS libraries, independent of instrumental platform and data processing software. We use a comprehensive dataset of GC-MS spectra of trimethylsilyl derivatives and their molecular structures, derived from a large commercially available MS library, to train a model that maps between spectra and molecular structures. We test the learned model on a different dataset of GC-MS spectra of trimethylsilyl derivatives of environmental contaminants, generated in-house and made publicly available. The results show that 37% (resp. 50%) of the tested compounds are correctly ranked among the top 10 (resp. 20) candidate compounds suggested by the model. Even though spectral comparisons with reference standards or de novo structural elucidations are neccessary to validate the predictions, machine learning provides efficient candidate prioritization and reduction of the time spent for compound annotation.

Occurrence, Diversity and Anti-Fungal Resistance of Fungi in Sand of an Urban Beach in Slovenia-Environmental Monitoring with Possible Health Risk Implications.

Beach safety regulation is based on faecal indicators in water, leaving out sand and fungi, whose presence in both matrices has often been reported. To study the abundance, diversity and possible fluctuations of mycobiota, fungi from sand and seawater were isolated from the Portoroz beach (Slovenia) during a 1-year period. Sand analyses yielded 64 species of 43 genera, whereas seawater samples yielded 29 species of 18 genera. Environmental and taxonomical data of fungal communities were analysed using machine learning approaches. Changes in the air and water temperature, sunshine hours, humidity and precipitation, air pressure and wind speed appeared to affect mycobiota. The core genera Aphanoascus, Aspergillus, Fusarium, Bisifusarium, Penicillium, Talaromyces, and Rhizopus were found to compose a stable community within sand, although their presence and abundance fluctuated along with weather changes. Aspergillus spp. were the most abundant and thus tested against nine antimycotics using Sensititre Yeast One kit. Aspergillus niger and A. welwitschiae isolates were found to be resistant to amphotericin B. Additionally, four possible human pollution indicators were isolated during the bathing season, including Meyerozyma, which can be used in beach microbial regulation. Our findings provide the foundations for additional research on sand and seawater mycobiota and show the potential effect of global warming and extreme weather events on fungi in sand and sea.

Machine-learning ready data on the thermal power consumption of the Mars Express Spacecraft.

We present six datasets containing telemetry data of the Mars Express Spacecraft (MEX), a spacecraft orbiting Mars operated by the European Space Agency. The data consisting of context data and thermal power consumption measurements, capture the status of the spacecraft over three Martian years, sampled at six different time resolutions that range from 1 min to 60 min. From a data analysis point-of-view, these data are challenging even for the more sophisticated state-of-the-art artificial intelligence methods. In particular, given the heterogeneity, complexity, and magnitude of the data, they can be employed in a variety of scenarios and analyzed through the prism of different machine learning tasks, such as multi-target regression, learning from data streams, anomaly detection, clustering, etc. Analyzing MEX's telemetry data is critical for aiding very important decisions regarding the spacecraft's status and operation, extracting novel knowledge, and monitoring the spacecraft's health, but the data can also be used to benchmark artificial intelligence methods designed for a variety of tasks.

A catalogue with semantic annotations makes multilabel datasets FAIR.

Multilabel classification (MLC) is a machine learning task where the goal is to learn to label an example with multiple labels simultaneously. It receives increasing interest from the machine learning community, as evidenced by the increasing number of papers and methods that appear in the literature. Hence, ensuring proper, correct, robust, and trustworthy benchmarking is of utmost importance for the further development of the field. We believe that this can be achieved by adhering to the recently emerged data management standards, such as the FAIR (Findable, Accessible, Interoperable, and Reusable) and TRUST (Transparency, Responsibility, User focus, Sustainability, and Technology) principles. We introduce an ontology-based online catalogue of MLC datasets originating from various application domains following these principles. The catalogue extensively describes many MLC datasets with comprehensible meta-features, MLC-specific semantic descriptions, and different data provenance information. The MLC data catalogue is available at: http://semantichub.ijs.si/MLCdatasets .

Survival analysis with semi-supervised predictive clustering trees.

Many clinical studies follow patients over time and record the time until the occurrence of an event of interest (e.g., recovery, death, …). When patients drop out of the study or when their event did not happen before the study ended, the collected dataset is said to contain censored observations. Given the rise of personalized medicine, clinicians are often interested in accurate risk prediction models that predict, for unseen patients, a survival profile, including the expected time until the event. Survival analysis methods are used to detect associations or compare subpopulations of patients in this context. In this article, we propose to cast the time-to-event prediction task as a multi-target regression task, with censored observations modeled as partially labeled examples. We then apply semi-supervised learning to the resulting data representation. More specifically, we use semi-supervised predictive clustering trees and ensembles thereof. Empirical results over eleven real-life datasets demonstrate superior or equivalent predictive performance of the proposed approach as compared to three competitor methods. Moreover, smaller models are obtained compared to random survival forests, another tree ensemble method. Finally, we illustrate the informative feature selection mechanism of our method, by interpreting the splits induced by a single tree model when predicting survival for amyotrophic lateral sclerosis patients.

Wet-dry-wet drug screen leads to the synthesis of TS1, a novel compound reversing lung fibrosis through inhibition of myofibroblast differentiation.

Therapies halting the progression of fibrosis are ineffective and limited. Activated myofibroblasts are emerging as important targets in the progression of fibrotic diseases. Previously, we performed a high-throughput screen on lung fibroblasts and subsequently demonstrated that the inhibition of myofibroblast activation is able to prevent lung fibrosis in bleomycin-treated mice. High-throughput screens are an ideal method of repurposing drugs, yet they contain an intrinsic limitation, which is the size of the library itself. Here, we exploited the data from our "wet" screen and used "dry" machine learning analysis to virtually screen millions of compounds, identifying novel anti-fibrotic hits which target myofibroblast differentiation, many of which were structurally related to dopamine. We synthesized and validated several compounds ex vivo ("wet") and confirmed that both dopamine and its derivative TS1 are powerful inhibitors of myofibroblast activation. We further used RNAi-mediated knock-down and demonstrated that both molecules act through the dopamine receptor 3 and exert their anti-fibrotic effect by inhibiting the canonical transforming growth factor ß pathway. Furthermore, molecular modelling confirmed the capability of TS1 to bind both human and mouse dopamine receptor 3. The anti-fibrotic effect on human cells was confirmed using primary fibroblasts from idiopathic pulmonary fibrosis patients. Finally, TS1 prevented and reversed disease progression in a murine model of lung fibrosis. Both our interdisciplinary approach and our novel compound TS1 are promising tools for understanding and combating lung fibrosis.

Biomarker discovery by feature ranking: Evaluation on a case study of embryonal tumors.

The task of biomarker discovery is best translated to the machine learning task of feature ranking. Namely, the goal of biomarker discovery is to identify a set of potentially viable targets for addressing a given biological status. This is aligned with the definition of feature ranking and its goal - to produce a list of features ordered by their importance for the target concept. This differs from the task of feature selection (typically used for biomarker discovery) in that it catches viable biomarkers that have redundant or overlapping information with often highly important biomarkers, while with feature selection this is not the case. We propose to use a methodology for evaluating feature rankings to assess the quality of a given feature ranking and to discover the best cut-off point. We demonstrate the effectiveness of the proposed methodology on 10 datasets containing data about embryonal tumors. We evaluate two most commonly used feature ranking algorithms (Random forests and RReliefF) and using the evaluation methodology identifies a set of viable biomarkers that have been confirmed to be related to cancer.

Multi-task learning for the simultaneous reconstruction of the human and mouse gene regulatory networks.

The reconstruction of Gene Regulatory Networks (GRNs) from gene expression data, supported by machine learning approaches, has received increasing attention in recent years. The task at hand is to identify regulatory links between genes in a network. However, existing methods often suffer when the number of labeled examples is low or when no negative examples are available. In this paper we propose a multi-task method that is able to simultaneously reconstruct the human and the mouse GRNs using the similarities between the two. This is done by exploiting, in a transfer learning approach, possible dependencies that may exist among them. Simultaneously, we solve the issues arising from the limited availability of examples of links by relying on a novel clustering-based approach, able to estimate the degree of certainty of unlabeled examples of links, so that they can be exploited during the training together with the labeled examples. Our experiments show that the proposed method can reconstruct both the human and the mouse GRNs more effectively compared to reconstructing each network separately. Moreover, it significantly outperforms three state-of-the-art transfer learning approaches that, analogously to our method, can exploit the knowledge coming from both organisms. Finally, a specific robustness analysis reveals that, even when the number of labeled examples is very low with respect to the number of unlabeled examples, the proposed method is almost always able to outperform its single-task counterpart.

Predictive model for the quantitative analysis of human skin using photothermal radiometry and diffuse reflectance spectroscopy.

We have recently introduced a novel methodology for the noninvasive analysis of the structure and composition of human skin in vivo. The approach combines pulsed photothermal radiometry (PPTR), involving time-resolved measurements of mid-infrared emission after irradiation with a millisecond light pulse, and diffuse reflectance spectroscopy (DRS) in the visible part of the spectrum. Simultaneous fitting of both data sets with respective predictions from a numerical model of light transport in human skin enables the assessment of the contents of skin chromophores (melanin, oxy-, and deoxy-hemoglobin), as well as scattering properties and thicknesses of the epidermis and dermis. However, the involved iterative optimization of 14 skin model parameters using a numerical forward model (i.e., inverse Monte Carlo - IMC) is computationally very expensive. In order to overcome this drawback, we have constructed a very fast predictive model (PM) based on machine learning. The PM involves random forests, trained on ∼9,000 examples computed using our forward MC model. We show that the performance of such a PM is very satisfying, both in objective testing using cross-validation and in direct comparisons with the IMC procedure. We also present a hybrid approach (HA), which combines the speed of the PM with versatility of the IMC procedure. Compared with the latter, the HA improves both the accuracy and robustness of the inverse analysis, while significantly reducing the computation times.