Find research datasets worth reusing

openother-ncMar 2020View details →

The "Last.fm" data set used in the article "Cumulative effects of triadic closure and homophily in social networks"

This is the "Last.fm" network used in the article: A. Asikainen, G. Iñiguez,  J. Ureña-Carrión,  K. Kaski, M. Kivelä. Cumulative effects of triadic closure and homophily in social networks. Science Advances (in press) https://doi.org/10.1126/sciadv.aax7310 The data set is described in the article. Please cite the original article when using this data set. The original data in which this network is based on was donwloaded from audioscrobbler.net where it was licensed under the "Creative Commons Attribution-NonCommercial-ShareAlike 2.0 UK: England & Wales" licese, and accordinly this data set uses the same license. The data contains two files: lastfm.edg This is the network formatted as an edge list, where each row in the file is an edge connecting the two nodes indicated by the two numbers separated by a whitespace. Each node number corresponds to a single account in the website. lastfm_genders.txt This is the list of genders of the nodes. Each row corresponds to one node. The first number is the node id (matching the one in the edge list) and the second number indicates the gender such that 0=male and 1=female.

opencc-by-nc-4.0Jun 2019View details →

Benchmarking algorithms for gene regulatory network inference from single-cell transcriptomic data

This repository contains input files from the synthetic, curated, and processed experimental single-cell gene expression datasets used in BEELINE. New in version 3: 1) Ground-truth networks used for analysis of experimental scRNA-seq datasets for mouse and human datasets 2) Changed license to CC BY-NC 4.0 from GPL v3.0 to account for the non-commercial clause for the network data

opennotspecifiedMay 2020View details →

Fig. 1 Viral sharing GAMM outputs and data distribution. a in Predicting the global mammalian viral sharing network using phylogeography

Fig. 1 Viral sharing GAMM outputs and data distribution. a Predicted viral sharing probability increases with increasing phylogenetic relatedness; the different coloured lines represent different geographic overlap values. b Predicted viral sharing probability increases with increasing geographic overlap; the different coloured lines represent different phylogenetic relatedness values. c The geographic overlap:phylogenetic similarity interaction surface, where the darker colours represent increased probability of viral sharing. White contour lines denote 10% increments of sharing probability. Labels have been removed from some contours to avoid overplotting. d Hexagonal bin chart displaying the data distribution, which was highly aggregated at low values of phylogenetic similarity and especially of geographic overlap.

opencc-zeroApr 2020View details →

Data from: Assessing the effectiveness of a national protected area network in maintaining carnivore populations

Protected areas (PAs) are essential to prevent further biodiversity loss yet their effectiveness varies largely with governance and external threats. Although methodological advances have permitted assessments of PA effectiveness in mitigating deforestation, we still lack similar studies for the impact of PAs on wildlife populations. Here we demonstrate the application ofuse an innovative combination of matching methods and hurdle-mixed models with a large-scale and long-term dataset of unprecedented coverage for Finland's large carnivore species. We show that the national PA network , at the national level, PAs does not support higher densities than non-protected habitat for 3 of the 4 species investigated. For the brown bear, PAs appear to have lower densities than non-protected areas. For some species, PA effects interact with region or time, i.e. wolverine densities decreased inside PAs over the study period and lynx densities increased inside eastern PAs. Although we show that matching approaches could and should be applied to wildlife population data, Wwe support their application of matching methods in combination of additional analytical frameworks for deeper understanding of conservation impacts on wildlife populations. These methodological advances are crucial for improving PA targets and extremely timely for preparing ambitious PA targets a post-2020 global framework for biodiversity.

opencc-zeroMay 2020View details →

Data from: From structure to function in mutualistic interaction networks: topologically important frugivores have greater potential as seed dispersers

1. Networks of mutualistic interactions between animals and plants are considered a pivotal part of ecological communities. However, mutualistic networks are rarely studied from the perspective of species-specific roles, and it remains to be established whether those animal species more relevant for network structure also contribute more to the ecological functions derived from interactions. 2. Here, we relate the contribution to seed dispersal of vertebrate species with their topological role in frugivore-plant interaction networks. For one year in two localities with remnant patches of Colombian tropical dry forest, we sampled abundance, morphology, behavior, and fruit consumption from fleshy-fruited plants of various frugivore species. 3. We assessed the network topological role of each frugivore species by integrating their degree of generalization in interactions with plants with their contributions to network nestedness and modularity. We estimated the potential contribution of each frugivore species to community-wide seed dispersal, on the basis of a set of frugivore ecological, morphological and behavioral characteristics important for seed dispersal, together with frugivore abundance and frugivory degree. 4. The various frugivore species showed strong differences in their network structural roles, with generalist species contributing the most to network modularity and nestedness. Frugivores also showed strong variability in terms of potential contribution to seed dispersal, depending on the specific combinations of frugivore abundance, frugivory degree and the different traits and behaviors. 5. For both localities, the seed dispersal potential of a frugivore species responded positively to its contribution to network structure, evidencing that the most important frugivore species in the network topology were also those making the strongest contribution as seed dispersers. Contribution to network structure was correlated with frugivore abundance, diet, and behavioral characteristics. This suggests that the species-level link between structure and function is due to the fact that the occurrence of frugivore-plant interactions depends largely on the characteristics of the frugivore involved, which also condition its ultimate role in seed dispersal. 22-May-2020

opencc-by-4.0Jun 2020View details →

Data of A recurrent neural network-accelerated multi-scale model for elasto-plastic heterogeneous materials subjected to random cyclic and non-proportional loading paths

<pre>Data related to the publication (we would be grateful if you could cite the paper in the case in which you are using the data) title = "A recurrent neural network-accelerated multi-scale model for elasto-plastic heterogeneous materials subjected to random cyclic and non-proportional loading paths", journal = "Computer Methods in Applied Mechanics and Engineering", pages = " 113234", year = "2020", issn = "0045-7825", doi = "https://doi.org/10.1016/j.cma.2020.113234", author = "Wu, Ling and Nguyen, Van Dung and Kilingar, Nanda Gopala and Noels, Ludovic"</pre>

openother-ncJun 2020View details →

CellCognize: a neural network pipeline for cell type classification from flow cytometry data

Readme file content The files stored here contain the following material as supplementary and source data for the publication Rapid detection of microbiota cell type diversity using machine-learned classification of flow cytometry data Birge D. Özel Duygan1, Noushin Hadadi1, Ambrin Farizah Bab1, Markus Seyfried2, Jan R. van der Meer1 1 Department of Fundamental Microbiology, University of Lausanne, 1015 Lausanne, Switzerland 2 Biotechnology Department, Firmenich SA, Geneva, Switzerland %%%%%%% Flow cytometry data %%%%%% FCM_files: .mat files with cleaned data as described in the supplementary methods section Ecoli_lakewater: raw FCM data (in .csv format) of E. coli cultures and E. coli cultures mixed to lakewater MIX_experiment_ACL_AJH_PVR: raw FCM data (in .csv format) of the synthetic three culture experiment with E. coli, A. johnsonii and P. veronii, as described in the main text and SI methods. PHE_OCT_enrichments: raw FCM data (in .csv format) of the phenol and 1-octanol enrichments and the 1-octanol isolates, as described in the main text and SI methods. %%%%%%% Neural network data %%%%%% NN_file_example: three ANN functions, to be used in conjunction with the SI methods section Supplementary_Methods.docx: Detailed description on the construction, usage and scripts for the ANN. To be used in conjunction with the Flow Cytometry data %%%%%%% 16S sequencing data %%%%%% raw fastq- files of the sample reads of the 1-octanol and phenol enrichments described in the paper, at t=0 and t=3d, each in triplicates, forward and reverse. Readme_16S_sequence_files.txt: sample description of the read files

opencc-by-4.0Jul 2020View details →

Crowdsourced air traffic data from The OpenSky Network 2020 [CC-BY]

Motivation The data in this dataset is derived and cleaned from the full OpenSky dataset to illustrate the development of air traffic during the COVID-19 pandemic. It spans all flights seen by the network's more than 2500 members since 1 January 2020. More data will be periodically included in the dataset until the end of the COVID-19 pandemic. License Creative Commons CC-BY The only difference with the <a href="https://zenodo.org/record/3928550">original dataset</a> comes from anonymised aircraft information. Disclaimer The data provided in the files is provided as is. Despite our best efforts at filtering out potential issues, some information could be erroneous. <ul> <li>Origin and destination airports are computed online based on the ADS-B trajectories on approach/takeoff: no crosschecking with external sources of data has been conducted. Fields origin or destination are empty when no airport could be found.</li> <li>Aircraft information come from the OpenSky aircraft database. Fields typecode and registration are empty when the aircraft is not present in the database.</li> </ul> Description of the dataset One file per month is provided as a csv file with the following features: <ul> <li>callsign: the identifier of the flight displayed on ATC screens (usually the first three letters are reserved for an airline: AFR for Air France, DLH for Lufthansa, etc.)</li> <li>number: the commercial number of the flight, when available (the matching with the callsign comes from public open API)</li> <li>aircraft_uid: a unique anonymised identifier for aircraft;</li> <li>typecode: the aircraft model type (when available);</li> <li>origin: a four letter code for the origin airport of the flight (when available);</li> <li>destination: a four letter code for the destination airport of the flight (when available);</li> <li>firstseen: the UTC timestamp of the first message received by the OpenSky Network;</li> <li>lastseen: the UTC timestamp of the last message received by the OpenSky Network;</li> <li>day: the UTC day of the last message received by the OpenSky Network;</li> <li>latitude_1, longitude_1, altitude_1: the first detected position of the aircraft;</li> <li>latitude_2, longitude_2, altitude_2: the last detected position of the aircraft.</li> </ul> Examples Possible visualisations and a more detailed description of the data are available at the following page: <<a href="https://traffic-viz.github.io/scenarios/covid19.html">https://traffic-viz.github.io/scenarios/covid19.html</a>> Credit If you use this dataset, please cite the original OpenSky paper: Matthias Schäfer, Martin Strohmeier, Vincent Lenders, Ivan Martinovic and Matthias Wilhelm. "Bringing Up OpenSky: A Large-scale ADS-B Sensor Network for Research". In Proceedings of the 13th IEEE/ACM International Symposium on Information Processing in Sensor Networks (IPSN), pages 83-94, April 2014. and the traffic library used to derive the data: Xavier Olive. "traffic, a toolbox for processing and analysing air traffic data." Journal of Open Source Software 4(39), July 2019.

opencc-by-4.0Jul 2020View details →

Classify on the Clock (CloCk) - An Entry Level Image Data Set for Neural Networks

General information This data set contains synthetic images of an analog clock. Each time point from 00:00:00 - 11:59:59 is included as a separate image. We provide three different versions of each image with an increasing number of additional information: <ul> <li>Sparse: The image includes just the hour, minute and second hand</li> <li>Reduced: Additional markings around the clock</li> <li>Full: Additional written numbers</li> </ul> The hands differ in size and color: <ul> <li>Hour: Black, short, wide</li> <li>Minute: Blue, long, medium</li> <li>Second: Red, long, slim</li> </ul> We provide the following files in this data repository: <ul> <li>RGB images with a size of 512x512 for all three versions</li> <li>A suggested training, validation and test split</li> <li>The creation script as Python file</li> </ul> The script can easily be modified to create images with a different size and color.   Clock System The movements of the hands follow a linear relationship. Their angles can be calculated by the forward system: \( \begin{bmatrix} 6^\circ & 0 & 0 \\ 0.1^\circ & 6^\circ & 0 \\ 0 & 0.5^\circ & 30^\circ \end{bmatrix} \begin{pmatrix} n_{\text{sec}} \\ n_{\text{min}} \\ n_{\text{hour}} \end{pmatrix} = \begin{pmatrix} \alpha_{\text{sec}}\\ \alpha_{\text{min}} \\ \alpha_{\text{hour}} \end{pmatrix}.\) One can also introduce rotated versions of the images. The system becomes non-linear in this case: \(\operatorname{mod}\left( \begin{bmatrix} 6^\circ & 0 & 0 \\ 0.1^\circ & 6^\circ & 0 \\ 0 & 0.5^\circ & 30^\circ \end{bmatrix} \begin{pmatrix} n_{\text{sec}} \\ n_{\text{min}} \\ n_{\text{hour}} \end{pmatrix} + \omega, \, 360^\circ \right) = \begin{pmatrix} \alpha_{\text{sec}}\\ \alpha_{\text{min}} \\ \alpha_{\text{hour}} \end{pmatrix}.\)   Use Cases This data set was originally designed for basic research on Capsule Networks. Use cases are: <ul> <li>Evalutation of classification and regression performance</li> <li>Influence of image transformations, e.g. rotations</li> <li>Detection of the hierarchy & relationship of image parts</li> <li>Concealment of objects in the image</li> <li>Interpretability of the learned model</li> <li>Solving a discrete inverse problem (sparse version)</li> <li>...</li> </ul>

opencc-zeroOct 2019View details →

Data from: Co-prescription network reveals social dynamics of opioid doctor shopping

This paper examines network prominence in a co-prescription network as an indicator of opioid doctor shopping (i.e., fraudulent solicitation of opioids from multiple prescribers). Using longitudinal data from a large commercially insured population, we construct a network where a tie between patients is weighted by the number of shared opioid prescribers. Given prior research suggesting that doctor shopping may be a social process, we hypothesize that active doctor shoppers will occupy central structural positions in this network. We show that network prominence, operationalized using PageRank, is associated with more opioid prescriptions, higher predicted risk for dangerous morphine dosage, opioid overdose, and opioid use disorder, controlling for number of prescribers and other variables. Moreover, as a patient's prominence increases over time, so does their risk for these outcomes, compared to their own average level of risk. Results highlight the importance of co-prescription networks in characterizing high-risk social dynamics.

opencc-zeroJul 2020View details →

Data from: Link prediction in real-world multiplex networks via layer reconstruction method

Networks are invaluable tools to study real biological, social and technological complex systems in which connected elements form a purposeful phenomenon. A higher resolution image of these systems shows that the connection types do not confine to one but to a variety of types. Multiplex networks encode this complexity with a set of nodes which are connected in different layers via different types of links. A large body of research on link prediction problem is devoted to finding missing links in single-layer (simplex) networks. In recent years, the problem of link prediction in multiplex networks has gained the attention of researchers from different scientific communities. Although most of these studies suggest that prediction performance can be enhanced by using the information contained in different layers of the network, the exact source of this enhancement remains obscure. Here, it is shown that similarity w.r.t. structural features (eigenvectors) is a major source of enhancements for link prediction task in multiplex networks using the proposed Layer Reconstruction Method and experiments on real-world multiplex networks from different disciplines. Moreover, we characterize how low values of similarity w.r.t. structural features result in cases where improving prediction performance is substantially hard.

Data from: Findings from an exploration of a social network intervention to promote diet quality and health behaviours in older adults with COPD: a feasibility study

Background: Diet quality in older people with Chronic Obstructive Pulmonary Disease (COPD) is associated with better health and lung function. Social factors, such as social support, social networks and participation in activities, have been linked with diet quality in older age. A social network tool – GENIE (Generating Engagement in Network Involvement) – was implemented in a COPD community care context. The study aimed to assess the feasibility of the GENIE intervention to promote diet quality and other health behaviours in COPD. Methods: Twenty-two community-dwelling older adults with COPD were recruited from a local COPD Service. Participants were offered usual care or the GENIE intervention. Process evaluation methods were used to assess intervention implementation, context and mechanisms of impact; <a name="_Hlk11247522">these included observations of patient interactions with the intervention, documented in observational field notes and in films of a patient group discussion.</a> Diet quality was assessed by food frequency questionnaire; 'prudent' diet scores were used to describe diet quality at baseline and at 3-month follow-up. Change in diet quality was expressed per month, from baseline to follow-up. Results: Feasibility data showed that the GENIE intervention could be implemented in this sample of community-living older people. The intervention was acceptable to clinicians and older people with COPD, especially for those with less severe disease, when facilitated appropriately and considering the levels of literacy of participants. There was no significant change in diet quality in the intervention group over the follow-up period (median change in prudent diet score per month, (interquartile range (IQR)): 0.03, (-0.24 – 0.07)); whereas an overall fall in diet quality was observed in the control group (-0.15, (-0.24 – 0.03)). Conclusion: The process evaluation findings suggest that this intervention is feasible and acceptable to both patients and clinicians. Although the sample size achieved in this study was small, findings suggest that the intervention may have a protective effect against declines in diet quality, and other health behaviours, in an older COPD population. Findings from this feasibility study indicate that further evaluation of the GENIE intervention is warranted in a larger study, with a longer follow-up.

opencc-by-4.0Aug 2020View details →

Predicting Phenotype from Multi-Scale Genomic and Environment Data using Neural Networks and Knowledge Graphs

Background: To mitigate the effects of climate change on public health and conservation, we need to better understand the dynamic interplay between biological processes and environmental effects. Machine learning (ML) methods in general, and Deep Learning (DL) methods in particular, are a potential way forward because they are able to cope with the nonlinearity of natural systems. However, there are several barriers that exist, including the absence of ML-ready data. We propose to develop a machine learning framework capable of predicting phenotypes based on multi-scale data about genes and environments. A critical part of this framework are data transformation methods that map the heterogeneous input data into formats that are consumable by the ML techniques. The central hypothesis of this research is that deep learning algorithms and biological knowledge graphs will predict phenotypes more accurately across more taxa and more ecosystems than do current numerical and traditional statistical modeling methods. Our long term goal is to develop predictive analytics for organismal response to environmental perturbations using innovative data science approaches. This pilot project on predicting emergent properties of complex systems and multidimensional interactions is funded by the NSF (Award # 1939945, 1940059, 1940062, 1940330).    Results: We have established shared project governance, communication channels, project timeline, and data and computing environment across four universities. We have successfully reached out to three other projects for broader collaboration.

Data from: Chromosome-scale inference of hybrid speciation and admixture with convolutional neural networks

Inferring the frequency and mode of hybridization among closely related organisms is an important step for understanding the process of speciation and can help to uncover reticulated patterns of phylogeny more generally. Phylogenomic methods to test for the presence of hybridization come in many varieties and typically operate by leveraging expected patterns of genealogical discordance in the absence of hybridization. An important assumption made by these tests is that the data (genes or SNPs) are independent given the species tree. However, when the data are closely linked, it is especially important to consider their non-independence. Recently, deep learning techniques such as convolutional neural networks (CNNs) have been used to perform population genetic inferences with linked SNPs coded as binary images. Here we use CNNs for selecting among candidate hybridization scenarios using the tree topology (((P1,P2),P3),Out) and a matrix of pairwise nucleotide divergence (dXY) calculated in windows across the genome. Using coalescent simulations to train and independently test a neural network showed that our method, HyDe-CNN, was able to accurately perform model selection for hybridization scenarios across a wide-breath of parameter space. We then used HyDe-CNN to test models of admixture in Heliconius butterflies, as well as comparing it to a random forest classifier trained on introgression-based statistics. Given the flexibility of our approach, the dropping cost of long-read sequencing, and the continued improvement of CNN architectures, we anticipate that inferences of hybridization using deep learning methods like ours will help researchers to better understand patterns of admixture in their study organisms.

Data from: Evolutionary networks from RADseq loci point to hybrid origins of Medicago carstiensis and Medicago cretacea

Premise: Although hybridization has played an important role in the evolution of many plant species, phylogenetic reconstructions that include hybridizing lineages have been historically constrained by the available models and data. RADseq has been a popular sequencing technique for the reconstruction of hybridization in the Next Generation Sequencing era. However, the utility of RADseq for the reconstruction of complex evolutionary networks has not been thoroughly investigated. Conflicting phylogenetic relationships in the genus Medicago have been mainly attributed to hybridization but the specific hybrid origins of taxa have not been yet clarified. Methods: We obtained new molecular data from diploid species of Medicago section Medicago using single-digest RADseq to reconstruct evolutionary networks from gene trees, an approach that is computationally tractable with datasets that include several species and complex hybridization patterns. Results: Our analyses revealed that assembly filters to exclusively select a small set of loci with high phylogenetic information led to the most divergent network topologies. Conversely, alternative clustering thresholds or filters on the number of samples per locus had a lower impact on networks. A strong hybridization signal was detected for M. carstiensis and M. cretacea, while less clear signals were observed for M. rugosa, M. rhodopea, M. suffruticosa, M. marina, M. scutellata and M. sativa. Conclusions: Complex network reconstructions from RADseq gene trees were not robust under variations of the assembly parameters and filters. But when most divergent networks were discarded, all remaining analyses consistently supported a hybrid origin for M. carstiensis and M. cretacea.

Data from: Dung beetle-megafauna trophic networks in Singapore's fragmented forests

We investigated trophic networks between dung beetles and megafauna species in five forest fragments in Singapore varying in size and isolation. We found that Singapore's dung beetle communities were attracted to extant and extinct dung types from different dietary groups. All forest fragment networks were similar, and displayed high generalism and high nestedness.

Data from: Seasonal dynamics of flock interaction networks across a human-modified landscape in lowland Amazonian rainforest

Although lowland tropical rainforests were once widely believed to be the archetype of stability, seasonal variation exists. In these environments, seasonality is defined by rainfall, leading to a predictable pattern of biotic and abiotic changes. Only the full annual cycle reveals niche breadth, yet most studies of tropical organisms ignore seasonality, thereby underestimating realized conditions. If human-modified habitats display more seasonal stress than intact habitats, then ignoring seasonality will have particularly important repercussions for conservation. We examined the seasonal dynamics of Amazonian mixed-species flocks—an important species interaction network—across three habitats with increasing human disturbance. We quantified seasonal space use, species richness and attendance, and four ecological network metrics for flocks in primary forest, small forest fragments, and regenerating secondary forest in central Amazonia. Our results indicate that, even in intact, lowland rainforest, mixed-species flocks exhibit seasonal differences. During the dry season, flocks included more species, generally ranged over larger areas, and displayed network structures that were less complex and less cohesive. We speculate that because most flocking species nest during the dry season—a time of reduced arthropod abundance—flocks are simultaneously constrained by these two competing pressures. Moreover, these seasonal differences were most pronounced in forest fragments and secondary forest, habitats that are less buffered from the changing seasons. Our results suggest that seasonality influences the conservation value of human-modified habitats, raising important questions about how rainforest organisms will cope with an increasingly unstable climate.

Data from: Incorporating alternative interaction modes, forbidden links and trait-based mechanisms increases the minimum trait dimensionality of ecological networks

<ol> <li>Individual-level traits mediate interaction outcomes and community structure. It is important, therefore, to identify the minimum number of traits that characterise ecological networks, i.e. their 'minimum dimensionality'. Existing methods for estimating minimum dimensionality often lack three features associated with increased trait numbers: alternative interaction modes (e.g. feeding strategies such as active vs. sit-and-wait feeding), trait-mediated 'forbidden links' and a mechanistic description of interactions. Omitting these features can underestimate the trait numbers involved, and therefore, minimum dimensionality. We develop a 'minimum mechanistic dimensionality' measure, accounting for these three features.</li> <li>The only input our method requires is the network of interaction outcomes. We assume how traits are mechanistically involved in alternative interaction modes. These unidentified traits are contrasted using pairwise performance inequalities between interacting species. For example, if a predator feeds upon a prey species via a typical predation mode, in each step of the predation sequence the predator's performance must be greater than the prey's. We construct a system of inequalities from all observed outcomes, which we attempt to solve with mixed integer linear programming. The number of traits required for a feasible system of inequalities provides our minimum dimensionality estimate.</li> <li>We applied our method to 658 published empirical ecological networks including primary consumption, predator–prey, parasitism, pollination, seed dispersal and animal dominance networks, to compare with minimum dimensionality estimates when the three focal features are missing. Minimum dimensionality was typically higher when including alternative interaction modes (54% of empirical networks), 'forbidden interactions' as trait-mediated interaction outcomes (92%), or a mechanistic perspective (81%), compared to estimates missing these features. Additionally, we tested minimum dimensionality estimates on simulated networks with known dimensionality. Our method typically estimated a higher minimum dimensionality, closer to the actual dimensionality, while avoiding the overestimation associated with a previous method.</li> <li>Our method can reduce the risk of omitting traits involved in different interaction modes, in failure outcomes, or mechanistically. More accurate estimates will allow us to parameterise models of theoretical networks with more realistic structure at the interaction outcome level. Thus, we hope our method can improve predictions of community structure and structure-dependent dynamics.</li> </ol>

Data from: Modelling the current and future biodiversity distribution in the Chilean Mediterranean Hotspot. The role of protected areas network in a warmer future

Aim: Mediterranean Chile is part of the five recognized Mediterranean-type climates in the world and harbors a very rich floral diversity. Climate change has been reported as a significant threat to its biodiversity. We used the flora of Mediterranean Chile to analyze how biodiversity patterns, as measured by Phylogenetic Diversity, genus and species richness will respond to climate change scenarios and identify the areas that will harbor the greatest evolutionary potential and biodiversity richness. We also evaluated how these spatial patterns are depicted within the current network of protected areas. Location: Chilean Mediterranean climate-type Region, South America. Methods: Biodiversity metrics were evaluated for current and future climatic scenarios. Species distribution models were done using Maxent for 1.727 species and 571 genera. Relationships between species/genera gain, loss and turnover were evaluated. For Mediterranean endemic species, loss and gain was also related to life form. Finally, variation in species gain, loss and turnover was evaluated in future climate change scenarios within and outside Mediterranean Chile state protected areas. Results: We found a general decrease in species richness in the entire Region toward future climate change scenarios. Phylogenetic Diversity is predicted to be higher than expected by richness in the north and south of the area, and lower than expected by richness in the Andes mountain. The highest average species and genus loss is predicted to occur outside the protected areas, meanwhile species and genus gain is higher within them. Main conclusions: Future biodiversity patterns are reported here for the first time in the Chilean Mediterranean Region. Our findings enhance the importance of the current protected areas to harbor this future variation, despite their reduced number and size along the region.