Annotation Categories Research Articles

Convolutional Neural Networks for Semantic Segmentation as a Tool for Multiclass Face Analysis in Thermal Infrared

Convolutional neural networks were used for multiclass segmentation in thermal infrared face analysis. The principle is based on existing image-to-image translation approaches, where each pixel in an image is assigned to a class label. We show that established networks architectures can be trained for the task of multiclass face analysis in thermal infrared. Created class annotations consisted of pixel-accurate locations of different face classes. Subsequently, the trained network can segment an acquired unknown infrared face image into the defined classes. Furthermore, face classification in live image acquisition is shown, in order to be able to display the relative temperature in real-time from the learned areas. This allows a pixel-accurate temperature face analysis e.g. for infection detection like Covid-19. At the same time our approach offers the advantage of concentrating on the relevant areas of the face. Areas of the face irrelevant for the relative temperature calculation or accessories such as glasses, masks and jewelry are not considered. A custom database was created to train the network. The results were quantitatively evaluated with the intersection over union (IoU) metric. The methodology shown can be transferred to similar problems for more quantitative thermography tasks like in materials characterization or quality control in production.

Explainability Metrics of Deep Convolutional Networks for Photoplethysmography Quality Assessment.

Photoplethysmography (PPG) is a noninvasive way to monitor various aspects of the circulatory system, and is becoming more and more widespread in biomedical processing. Recently, deep learning methods for analyzing PPG have also become prevalent, achieving state of the art results on heart rate estimation, atrial fibrillation detection, and motion artifact identification. Consequently, a need for interpretable deep learning has arisen within the field of biomedical signal processing. In this paper, we pioneer novel explanatory metrics which leverage domain-expert knowledge to validate a deep learning model. We visualize model attention over a whole testset using saliency methods and compare it to human expert annotations. Congruence, our first metric, measures the proportion of model attention within expert-annotated regions. Our second metric, Annotation Classification, measures how much of the expert annotations our deep learning model pays attention to. Finally, we apply our metrics to compare between a signal based model and an image based model for PPG signal quality classification. Both models are deep convolutional networks based on the ResNet architectures. We show that our signal-based one dimensional model acts in a more explainable manner than our image based model; on average 50.78% of the one dimensional model’s attention are within expert annotations, whereas 36.03% of the two dimensional model’s attention are within expert annotations. Similarly, when thresholding the one dimensional model attention, one can more accurately predict if each pixel of the PPG is annotated as artifactual by an expert. Through this testcase, we demonstrate how our metrics can provide a quantitative and dataset-wide analysis of how explainable the model is.

Annotation Tool and Urban Dataset for 3D Point Cloud Semantic Segmentation

Accurate semantic segmentation of unstructured 3D point clouds requires large amount of annotated training data for deep learning. However, there is currently no free specialized software available that can efficiently annotate large 3D point clouds. We fill this gap by introducing PC-Annotate - a public annotation tool for 3D point cloud research. The proposed tool not only enables systematic annotation with a variety of fundamental volumetric shapes, but also provides useful functionalities of point cloud registration and the generation of volumetric samples that can be readily consumed by contemporary deep learning point cloud models. We also introduce a large outdoor public dataset for 3D semantic segmentation. The proposed dataset, PC-Urban is collected in a civic setup with Ouster LiDAR and labeled with PC-Annotate. It has over 4.3 billion points covering 66K frames and 25 annotated classes. Finally, we provide baseline semantic segmentation results on PC-Urban for popular recent techniques.

Comprehensive proteomic analysis of arsenic induced toxicity reveals the mechanism of multilevel coordination of efficient defense and energy metabolism in two Brassica napus cultivars

Arsenic (As) a non-essential element is of particular concern with respect to harmful effects on plant metabolism. While extensive studies have been conducted on the physiological responses of plants to increase As concentrations, however, molecular differences elucidating species-specific changes remain largely unknown. In the present experiment, two oilseed Brassica napus (B. napus) cultivars, ZS758 and ZD622, were treated by elevated As concentration. Their responses to the As stress have been investigated through pulse amplitude modulated fluorometer and isobaric tags based proteomic (iTRAQ) analysis. The chlorophyll fluorescence attributes showed that As stress significantly decrease the photochemical efficiency of photosystem II (PSII) and photosystem I (PSI) as well as the comparatively closed stomata observed under scanning electron microscopy (SEM). In this study, 65 proteins displayed increased abundance and 52 down-regulated were found in the control vs As comparison in cultivar ZS758, while 44 up and 67 down-regulated proteins were found in the control vs As comparison in ZD622. Metabolic pathways, followed by ribosome and biosynthesis of secondary metabolites were the dominant functional annotation categories among the differentially expressed protein (DEPs). Many genes involved in primary metabolism, stress and defense were found to be As-responsive DEPs and/or DEPs between these two cultivars. Based on these results, a schematic description of key processes involved in As tolerance in ZS758 and ZD622 is proposed, which suggests that higher tolerance in ZS758 depends on a multilevel coordination of efficient defense and energy metabolism. Real-time quantitative PCR supported the expression patterns of several genes encoding a protein similar to their corresponding DEPs. In addition, these findings could shed light in unraveling the molecular mechanisms of B. napus exposed to As stress and provide or improve essential understandings in the development of advanced B. napus cultivars against As resistance.

Systematic classification of unknown metabolites using high-resolution fragmentation mass spectra.

Metabolomics using nontargeted tandem mass spectrometry can detect thousands of molecules in a biological sample. However, structural molecule annotation is limited to structures present in libraries or databases, restricting analysis and interpretation of experimental data. Here we describe CANOPUS (class assignment and ontology prediction using mass spectrometry), a computational tool for systematic compound class annotation. CANOPUS uses a deep neural network to predict 2,497 compound classes from fragmentation spectra, including all biologically relevant classes. CANOPUS explicitly targets compounds for which neither spectral nor structural reference data are available and predicts classes lacking tandem mass spectrometry training data. In evaluation using reference data, CANOPUS reached very high prediction performance (average accuracy of 99.7% in cross-validation) and outperformed four baseline methods. We demonstrate the broad utility of CANOPUS by investigating the effect of microbial colonization in the mouse digestive system, through analysis of the chemodiversity of different Euphorbia plants and regarding the discovery of a marine natural product, revealing biological insights at the compound class level.

The Potential of IFLA LRM and RDA Key Entities for Identification of Entities in Textual Documents of Cultural Heritage: The RunA Collection

This paper addresses the potential to employ IFLA Library Reference Model (LRM) and Resource Description and Access (RDA) key entity classes in annotating textual documents of cultural heritage (RunA collection). It describes methods (comparison and analysis) and procedures (identification of entity classes and annotation classes in unstructured data with a special annotation tool) for the evaluation of international data models based on the need to develop a cross-sectoral linked data collection. The article identifies key entities – works, agents (persons, institutions), concepts, places, timespans, and events – for reflecting simple or hierarchical relationships between different objects, which can be used as nodal points for semantic connection and networking in digital collections, including unstructured data sets, e.g., correspondence. The article concludes with a discussion of the challenges of correctly applying LRM’s WEMI structured entities to free-form textual data.

Classifying heuristic textual practices in academic discourse

Abstract In this paper, we investigate how deep learning techniques can be applied to discourse pragmatics. As a testcase we analyse heuristic textual practices, defined as linguistic implementations of decision routines in research processes in academic discourse. We develop a complex annotation scheme of pragmalinguistic categories on different levels of granularity and manually annotate a corpus of texts across various scientific disciplines. This is the basis for training recurrent neural networks to classify heuristic textual practices. Our experiments show that the annotation categories are robust enough to be recognised by our models which learn similarities of the sentence-surfaces represented as word embeddings. Our study aims at an iterative human-in-the-loop process in which manual-hermeneutic and algorithmic procedures mutually advance the insight process. It underlines the fact that the interaction between manual and automated methods opens up a promising field for further research, allowing interpretative analyses of complex pragmatic phenomena in large corpora.

Putative ratios of facial attractiveness in a deep neural network

Empirical evidence has shown that there is an ideal arrangement of facial features (ideal ratios) that can optimize the attractiveness of a person’s face. These putative ratios define facial attractiveness in terms of spatial relations and provide important rules for measuring the attractiveness of a face. In this paper, we show that a deep neural network (DNN) model can learn putative ratios from face images based only on categorical annotation when no annotated facial features for attractiveness are explicitly given. To this end, we conducted three experiments. In Experiment 1, we trained a DNN model to recognize the attractiveness (female/male × high/low attractiveness) of face in the images using four category-specific neurons (CSNs). In Experiment 2, face-like images were generated by reversing the DNN model (e.g., deconvolution). These images depict the intuitive attributes encoded in CSNs of the four categories of facial attractiveness and reveal certain consistencies with reported evidence on the putative ratios. In Experiment 3, simulated psychophysical experiments on face images with varying putative ratios reveal changes in the activity of the CSNs that are remarkably similar to those of human judgements reported in a previous study. These results show that the trained DNN model can learn putative ratios as key features for the representation of facial attractiveness. This finding advances our understanding of facial attractiveness via DNN-based perspective approaches.

Maternal adiposity alters the human milk metabolome: associations between nonglucose monosaccharides and infant adiposity

Human milk composition is altered by maternal obesity. The association between milk metabolites and infant outcomes has not been thoroughly investigated. This study aimed to quantify maternal adiposity-related differences in the human milk metabolome and to identify metabolites associated with infant adiposity during the first 6 mo postpartum using untargeted metabolomics. Maternal anthropometrics were assessed≤14 weeks of gestation. Human milk samples were collected at 0.5 mo (n=159), 2 mo (n=131), and 6 mo (n=94) postpartum from normal weight (NW, BMI=18.5-24.9 kg/m2) and obese (OB, BMI>30 kg/m2) mothers. GC-time-of-flight-MS was used to identify metabolic signatures that discriminate NW and OB women. Partial least squared (PLS)-discriminant analysis, and PLS-regression models were assessed to examine relations between metabolites and maternal BMI and fat mass. Metabolites altered by maternal obesity were used in linear mixed effect models to predict infant adiposity. Multivariate modeling identified 23, 17, and 10 metabolites that described maternal adiposity indices at 0.5 mo, 2 mo, and 6 mo postpartum, respectively. Monosaccharides and sugar alcohols were the most representative annotated metabolite classes that were increased in milk from OB women and included: mannose, ribose, lyxose, lyxitol (0.5 mo); mannose, ribitol, glycerol, isothreonic acid, lyxitol (2 mo); lyxitol and isothreonic acid (6 mo). Other discriminant metabolites included: 1-monostearin, xylonolactone, shikimic acid, pseudo uridine, and dodecanol (0.5 mo); N-acetyl-D-hexosamine and fumaric acid (2 mo); uric acid and tyrosine (6 mo). Mannose, lyxitol, and shikimic acid predicted higher infant adiposity over the first 6 mo of life. This study reports on 1 of the largest cohorts to date examining the metabolic profiles in human milk comparing NW and OB women. Maternal adiposity was associated with increased amounts of milk nonglucose monosaccharides. Human milk metabolomics may be useful in predicting infant adiposity. These trials were registered at www.clinicaltrials.gov as NCT01131117 and NCT02125149.

VARAdb: a comprehensive variation annotation database for human.

With the study of human diseases and biological processes increasing, a large number of non-coding variants have been identified and facilitated. The rapid accumulation of genetic and epigenomic information has resulted in an urgent need to collect and process data to explore the regulation of non-coding variants. Here, we developed a comprehensive variation annotation database for human (VARAdb, http://www.licpathway.net/VARAdb/), which specifically considers non-coding variants. VARAdb provides annotation information for 577,283,813 variations and novel variants, prioritizes variations based on scores using nine annotation categories, and supports pathway downstream analysis. Importantly, VARAdb integrates a large amount of genetic and epigenomic data into five annotation sections, which include ‘Variation information’, ‘Regulatory information’, ‘Related genes’, ‘Chromatin accessibility’ and ‘Chromatin interaction’. The detailed annotation information consists of motif changes, risk SNPs, LD SNPs, eQTLs, clinical variant-drug-gene pairs, sequence conservation, somatic mutations, enhancers, super enhancers, promoters, transcription factors, chromatin states, histone modifications, chromatin accessibility regions and chromatin interactions. This database is a user-friendly interface to query, browse and visualize variations and related annotation information. VARAdb is a useful resource for selecting potential functional variations and interpreting their effects on human diseases and biological processes.

Fiji plugins for qualitative image annotations: routine analysis and application to image classification

Quantitative measurements and qualitative description of scientific images are both important to describe the complexity of digital image data. While various software solutions for quantitative measurements in images exist, there is a lack of simple tools for the qualitative description of images in common user-oriented image analysis software. To address this issue, we developed a set of Fiji plugins that facilitate the systematic manual annotation of images or image-regions. From a list of user-defined keywords, these plugins generate an easy-to-use graphical interface with buttons or checkboxes for the assignment of single or multiple pre-defined categories to full images or individual regions of interest. In addition to qualitative annotations, any quantitative measurement from the standard Fiji options can also be automatically reported. Besides the interactive user interface, keyboard shortcuts are available to speed-up the annotation process for larger datasets. The annotations are reported in a Fiji result table that can be exported as a pre-formatted csv file, for further analysis with common spreadsheet software or custom automated pipelines. To facilitate and spread the usage of analysis tools, we provide examples of such pipelines, including a complete workflow for training and application of a deep learning model for image classification in KNIME. Ultimately, the plugins enable standardized routine sample evaluation, classification, or ground-truth category annotation of any digital image data compatible with Fiji.

Fast and Easy Access to Central European Biodiversity Data with BIOfid

The storage of data in public repositories such as the Global Biodiversity Information Facility (GBIF) or the National Center for Biotechnology Information (NCBI) is nowadays stipulated in the policies of many publishers in order to facilitate data replication or proliferation. Species occurrence records contained in legacy printed literature are no exception to this. The extent of their digital and machine-readable availability, however, is still far from matching the existing data volume (Thessen and Parr 2014). But precisely these data are becoming more and more relevant to the investigation of ongoing loss of biodiversity. In order to extract species occurrence records at a larger scale from available publications, one has to apply specialised text mining tools. However, such tools are in short supply especially for scientific literature in the German language. The Specialised Information Service Biodiversity Research*1 BIOfid (Koch et al. 2017) aims at reducing this desideratum, inter alia, by preparing a searchable text corpus semantically enriched by a new kind of multi-label annotation. For this purpose, we feed manual annotations into automatic, machine-learning annotators. This mixture of automatic and manual methods is needed, because BIOfid approaches a new application area with respect to language (mainly German of the 19th century), text type (biological reports), and linguistic focus (technical and everyday language). We will present current results of the performance of BIOfid’s semantic search engine and the application of independent natural language processing (NLP) tools. Most of these are freely available online, such as TextImager (Hemati et al. 2016). We will show how TextImager is tied into the BIOfid pipeline and how it is made scalable (e.g. extendible by further modules) and usable on different systems (docker containers). Further, we will provide a short introduction to generating machine-learning training data using TextAnnotator (Abrami et al. 2019) for multi-label annotation. Annotation reproducibility can be assessed by the implementation of inter-annotator agreement methods (Abrami et al. 2020). Beyond taxon recognition and entity linking, we place particular emphasis on location and time information. For this purpose, our annotation tag-set combines general categories and biology-specific categories (including taxonomic names) with location and time ontologies. The application of the annotation categories is regimented by annotation guidelines (Lücking et al. 2020). Within the next years, our work deliverable will be a semantically accessible and data-extractable text corpus of around two million pages. In this way, BIOfid is creating a new valuable resource that expands our knowledge of biodiversity and its determinants.

Multi-Path Deep CNNs for Fine-Grained Car Recognition

Along with the growing demands of intelligent traffic system, how to recognize the category information of a car from surveillance cameras has been an important task. Fine-grained car recognition is facing challenges mainly due to similar appearance of inter-class car images. Moreover, unlike other forms of object recognition, there are a large quantity of car models, that most other objects do not have, which causes fine-grained car recognition to be of vital importance but challenging. Recent research focuses on training a deep convolution neural network (DCNN) on a large dataset. Typically these methods largely rely on the holistic appearance of cars and may fail to train an optimal DCNN to comprehend information from multiple parts of a car. To address this issue, we carefully measure the effectiveness of different parts of a car and highlight the importance of car fronts for fine-grained car recognition. Then, considering multiple important parts from cars, we propose a novel multi-path DCNN model which is equipped with a 3-branch deep convolutional network to better exploit holistic as well as part information for fine-grained car recognition. Multiple parts from cars provide complementary information to boost performance. To further facilitate research on fine-grained car recognition, we also collect a large-scale dataset named “Multiple Parts from Cars” (MPF-Cars) which contains category annotation as well as car part information. We evaluate our proposed multi-path DCNN on MPF-Cars and another benchmark dataset CarFlag-563. Experiments demonstrate the effectiveness of our proposed method.

Speech Personality Recognition Based on Annotation Classification Using Log-Likelihood Distance and Extraction of Essential Audio Features

Speech personality recognition relies on training models that require an excessive number of features and are, in most cases, designed specifically for certain databases. As a result, when tested on different datasets, overfitted classifier models are not always reliable because their accuracy changes with changes in the domain of speakers. Moreover, personality annotations are often subjective, which creates variability in raters perception during labeling. These problems inhibit the effectiveness of speech personality recognition applications. To reduce the unexplained variance caused by unknown differences in raters perception, a structure that uses Balanced Iterative Reducing and Clustering using Hierarchies (BIRCH) algorithm is proposed. Furthermore, a feature extraction method is proposed to filter out undesirable adulterations be it noise, silence, or uncertain pitch segments, while extracting essential audio features, i.e., signal power roll-off, pitch, and pause rate. Experiments on the standard SSPNet dataset records a relative 4% increase in overall accuracy when log-likelihood based annotations are used. Moreover, improved consistency in accuracy is observed when this method is tested on male and female subsets.

Unsupervised Visual–Textual Correlation Learning With Fine-Grained Semantic Alignment

With the rapid growth of multimedia data on the Internet, there has been a rapid rise in the demand for visual-textual cross-media retrieval between images and sentences. However, the heterogeneous property of visual and textual data brings huge challenges to measure the cross-media similarity for retrieval. Although existing methods have achieved great progress with the strong learning ability of the deep neural network, they rely heavily on the scale of training data with manual annotation, that is, either pairwise image-sentence annotation or category annotation as supervised information for visual-textual correlation learning, which are extremely labor and time consuming to collect. Without any pairwise or category annotation, it is highly challenging to construct a correlation between images and sentences due to their inconsistent distributions and representations. But people can naturally understand the correlation between visual and textual data in high-level semantic, and those images and sentences containing the same group of semantic concepts can be easily matched in human brain. Inspired by the above human cognitive process, this article proposes an unsupervised visual-textual correlation learning (UVCL) approach to construct correlations without any manual annotation. The contributions are summarized as follows: 1) unsupervised semantic-guided cross-media correlation mining is proposed to bridge the heterogeneous gap between visual and textual data. We measure the semantic matching degree between images and sentences, and generate descriptive sentences according to the concepts extracted from images to further augment the training data in an unsupervised manner. Therefore, the approach can exploit the semantic knowledge within both visual and textual data to reduce the gap between them for further correlation learning and 2) unsupervised visual-textual fine-grained semantic alignment is proposed to learn cross-media correlation by aligning the fine-grained visual local patches and textual keywords with fine-grained soft attention as well as semantic-guided hard attention, and the results can effectively highlight the fine-grained semantic information within both images and sentences to boost visual-textual alignment. Extensive experiments are conducted to perform visual-textual cross-media retrieval in unsupervised setting without any manual annotation on two widely used datasets, namely, Flickr-30K and MS-COCO, which verify the effectiveness of our proposed UVCL approach.

Transcription response of Tetranychus cinnabarinus to plant-mediated short-term and long -term selenium treatment

Selenium is a trace element necessary for living organisms. It exists mainly in the form of selenite in nature. In plants, selenium can enhance defenses against pests. In this study, transcriptome sequencing technology was used to analyze the response mechanism of Tetranychus cinnabarinus to plant-mediated selenium treatment. We tested four sodium selenite treatments (5, 20, 50, and 200 μM) that were the same for short (2 d) and long (30 d) treatment durations. The results showed that the number of differentially expressed genes (DEGs) in the short-term treatment was greater than in the long-term treatment. This indicated that the gene expression of spider mites gradually stabilized during the selenium treatment. Regardless of the long-term and short-term conditions, spider mites had the largest response to the 20 μM sodium selenite treatment. The functional annotation classification of DEGs showed no significant difference under different concentrations and treatment durations. A total of 25 genes were differentially expressed in all eight treatments, including four down-regulated cytochrome P450 genes and one up-regulated chitinase gene. We speculate that selenium may have the potential to enhance the activity of chemical acaricides. Transcriptome sequencing of sodium selenite treatment at different concentrations and different times revealed the response mechanism of spider mites under plant-mediated selenium treatment. At the same time, it also provides new clues for the development of methods for preventing and controlling spider mites with selenium.

Weakly Supervised Fine-Grained Image Classification via Salient Region Localization and Different Layer Feature Fusion

The fine-grained image classification task is about differentiating between different object classes. The difficulties of the task are large intra-class variance and small inter-class variance. For this reason, improving models’ accuracies on the task heavily relies on discriminative parts’ annotations and regional parts’ annotations. Such delicate annotations’ dependency causes the restriction on models’ practicability. To tackle this issue, a saliency module based on a weakly supervised fine-grained image classification model is proposed by this article. Through our salient region localization module, the proposed model can localize essential regional parts with the use of saliency maps, while only image class annotations are provided. Besides, the bilinear attention module can improve the performance on feature extraction by using higher- and lower-level layers of the network to fuse regional features with global features. With the application of the bilinear attention architecture, we propose the different layer feature fusion module to improve the expression ability of model features. We tested and verified our model on public datasets released specifically for fine-grained image classification. The results of our test show that our proposed model can achieve close to state-of-the-art classification performance on various datasets, while only the least training data are provided. Such a result indicates that the practicality of our model is incredibly improved since fine-grained image datasets are expensive.

A substrate-based ontology for human solute carriers.

Solute carriers (SLCs) are the largest family of transmembrane transporters in the human genome with more than 400 members. Despite the fact that SLCs mediate critical biological functions and several are important pharmacological targets, a large proportion of them is poorly characterized and present no assigned substrate. A major limitation to systems‐level de‐orphanization campaigns is the absence of a structured, language‐controlled chemical annotation. Here we describe a thorough manual annotation of SLCs based on literature. The annotation of substrates, transport mechanism, coupled ions, and subcellular localization for 446 human SLCs confirmed that ~30% of these were still functionally orphan and lacked known substrates. Application of a substrate‐based ontology to transcriptomic datasets identified SLC‐specific responses to external perturbations, while a machine‐learning approach based on the annotation allowed us to identify potential substrates for several orphan SLCs. The annotation is available at https://opendata.cemm.at/gsflab/slcontology/. Given the increasing availability of large biological datasets and the growing interest in transporters, we expect that the effort presented here will be critical to provide novel insights into the functions of SLCs.

IncDet: In Defense of Elastic Weight Consolidation for Incremental Object Detection.

Elastic weight consolidation (EWC) has been successfully applied for general incremental learning to overcome the catastrophic forgetting issue. It adaptively constrains each parameter of the new model not to deviate much from its counterpart in the old model during fine-tuning on new class data sets, according to its importance weight for old tasks. However, the previous study demonstrates that it still suffers from catastrophic forgetting when directly used in object detection. In this article, we show EWC is effective for incremental object detection if with critical adaptations. First, we conduct controlled experiments to identify two core issues why EWC fails if trivially applied to incremental detection: 1) the absence of old class annotations in new class images makes EWC misclassify objects of old classes in these images as background and 2) the quadratic regularization loss in EWC easily leads to gradient explosion when balancing old and new classes. Then, based on the abovementioned findings, we propose the corresponding solutions to tackle these issues: 1) utilize pseudobounding box annotations of old classes on new data sets to compensate for the absence of old class annotations and 2) adopt a novel Huber regularization instead of the original quadratic loss to prevent from unstable training. Finally, we propose a general EWC-based incremental object detection framework and implement it under both Fast R-CNN and Faster R-CNN, showing its flexibility and versatility. In terms of either the final performance or the performance drop with respect to the upper bound of joint training on all seen classes, evaluations on the PASCAL VOC and COCO data sets show that our method achieves a new state of the art.

Phenotype-specific differences in polygenicity and effect size distribution across functional annotation categories revealed by AI-MiXeR.

MotivationDetermining the relative contributions of functional genetic categories is fundamental to understanding the genetic etiology of complex human traits and diseases. Here, we present Annotation Informed-MiXeR, a likelihood-based method for estimating the number of variants influencing a phenotype and their effect sizes across different functional annotation categories of the genome using summary statistics from genome-wide association studies.ResultsExtensive simulations demonstrate that the model is valid for a broad range of genetic architectures. The model suggests that complex human phenotypes substantially differ in the number of causal variants, their localization in the genome and their effect sizes. Specifically, the exons of protein-coding genes harbor more than 90% of variants influencing type 2 diabetes and inflammatory bowel disease, making them good candidates for whole-exome studies. In contrast, <10% of the causal variants for schizophrenia, bipolar disorder and attention-deficit/hyperactivity disorder are located in protein-coding exons, indicating a more substantial role of regulatory mechanisms in the pathogenesis of these disorders.Availability and implementationThe software is available at: https://github.com/precimed/mixer.Supplementary information Supplementary data are available at Bioinformatics online.