Using deep neural networks to evaluate object vision tasks in rats

In the last two decades rodents have been on the rise as a dominant model for visual neuroscience. This is particularly true for earlier levels of information processing, but a number of studies have suggested that also higher levels of processing such as invariant object recognition occur in rodents. Here we provide a quantitative and comprehensive assessment of this claim by comparing a wide range of rodent behavioral and neural data with convolutional deep neural networks. These networks have been shown to capture hallmark properties of information processing in primates through a succession of convolutional and fully connected layers. We find that performance on rodent object vision tasks can be captured using low to mid-level convolutional layers only, without any convincing evidence for the need of higher layers known to simulate complex object recognition in primates. Our approach also reveals surprising insights on assumptions made before, for example, that the best performing animals would be the ones using the most abstract representations–which we show to likely be incorrect. Our findings suggest a road ahead for further studies aiming at quantifying and establishing the richness of representations underlying information processing in animal models at large.     

Using deep neural networks to model similarity between visual patterns: Application to fish sexual signals

The evolution of visual patterns is a frontier in the theory of sexual selection as we seek to understand the function of complex visual patterning in courtship. Recently, the sensory drive and sensory bias models of sexual selection have been applied to higher-level visual processing. One prediction of this application is that animals' sexual signals will mimic the visual statistics of their habitats. An enduring difficulty of testing predictions of visual pattern evolution is in developing quantitative methods for comparing patterns. Advances in artificial neural networks address this challenge by allowing for the direct comparison of images using both simple and complex features. Here, we use VGG19, an industry‑leading image classification network to test predictions of sensory drive, by comparing visual patterns in darter fish (Etheostoma spp.) to images of their habitats. We find that images of female darters are significantly more similar to images of their habitat than are images of males, supporting a role of camouflage in female patterning. We do not find direct evidence for sensory drive shaping the design of male patterns; however, this work demonstrates the utility of network methods for pattern analysis and suggests future directions for visual pattern research.     

Bifluorophoric molecules as fluorescent beacons for antibody-antigen binding

The quenching of fluorescence (up to 98%) by anti-fluorescein antibodies is well documented in the literature. Here we report a system where, instead of quenching, bifluorophoric molecules are designed to increase in fluorescence upon binding by an anti-fluorescein antibody. Bifluorophoric molecules are made of fluorescein (F) linked to tetramethylrhodamine (T) via varying numbers of methylene units, denoted as F-(CH(2))(n)-T. These F-(CH(2))(n)-T conjugates are almost nonfluorescent when free in solution due to intramolecular dimerization and stacking. Upon binding to an anti-fluorescein antibody, however, up to 110-fold increase in fluorescence was observed from the rhodamine moiety. This increase is believed to result from intramolecular dimer dissociation that dequenches the rhodamine fluorescence. Fluorescein fluorescence, on the other hand, remains quenched due to binding and intramolecular resonance energy transfer. Moreover, the excitation wavelength was at the absorption maxima of fluorescein, giving a Stoke's shift of about 90 nm. This system couples directly molecular recognition with a concurrent increase in fluorescence emission, obviating wash and incubation steps required by most assays. It is an important molecular reporter system for developing homogeneous assays.     

Application of artificial neural networks for yeast cells classification

The present paper describes a method for automatic classification of yeast cells in four groups: active with oval form, budding, weakened and dead. This method can be used in the previously developed structural mathematical model of the yeast cultivation process described in [1].     

Predicting enhancers with deep convolutional neural networks

Background

With the rapid development of deep sequencing techniques in the recent years, enhancers have been systematically identified in such projects as FANTOM and ENCODE, forming genome-wide landscapes in a series of human cell lines. Nevertheless, experimental approaches are still costly and time consuming for large scale identification of enhancers across a variety of tissues under different disease status, making computational identification of enhancers indispensable.

Results

To facilitate the identification of enhancers, we propose a computational framework, named DeepEnhancer, to distinguish enhancers from background genomic sequences. Our method purely relies on DNA sequences to predict enhancers in an end-to-end manner by using a deep convolutional neural network (CNN). We train our deep learning model on permissive enhancers and then adopt a transfer learning strategy to fine-tune the model on enhancers specific to a cell line. Results demonstrate the effectiveness and efficiency of our method in the classification of enhancers against random sequences, exhibiting advantages of deep learning over traditional sequence-based classifiers. We then construct a variety of neural networks with different architectures and show the usefulness of such techniques as max-pooling and batch normalization in our method. To gain the interpretability of our approach, we further visualize convolutional kernels as sequence logos and successfully identify similar motifs in the JASPAR database.

Conclusions

DeepEnhancer enables the identification of novel enhancers using only DNA sequences via a highly accurate deep learning model. The proposed computational framework can also be applied to similar problems, thereby prompting the use of machine learning methods in life sciences.

     

Motion vectors and deep neural networks for video camera traps

Commercial camera traps are usually triggered by a Passive Infra-Red (PIR) motion sensor necessitating a delay between triggering and the image being captured. This often seriously limits the ability to record images of small and fast moving animals. It also results in many “empty” images, e.g., owing to moving foliage against a background of different temperature. In this paper we detail a new triggering mechanism based solely on the camera sensor. This is intended for use by citizen scientists and for deployment on an affordable, compact, low-power Raspberry Pi computer (RPi). Our system introduces a video frame filtering pipeline consisting of movement and image-based processing. This makes use of Machine Learning (ML) feasible on a live camera stream on an RPi. We describe our free and open-source software implementation of the system; introduce a suitable ecology efficiency measure that mediates between specificity and recall; provide ground-truth for a video clip collection from camera traps; and evaluate the effectiveness of our system thoroughly. Overall, our video camera trap turns out to be robust and effective.     

Application of neural networks to the classification of pancreatic intraductal proliferative lesions.

The aim of the study was to test applycability of neural networks to classification of pancreatic intraductal proliferative lesions basing on nuclear features, especially chromatin texture. Material for the study was obtained from patients operated on for pancreatic cancer, chronic pancreatitis and other tumours requiring pancreatic resection. Intraductal lesions were classified as low and high grade as previously described. The image analysis system consisted of a microscope, CCD camera combined with a PC and AnalySIS v. 2.11 software. The following texture characteristics were measured: variance of grey levels, features extracted from the grey levels correlation matrix and mean values, variance and standard deviation of the energy obtained from Laws matrices. Furthermore we used moments derived invariants and basic geometric data such as surface area, the minimum and maximum diameter and shape factor. The sets of data were randomly divided into training and testing groups. The training of the network using the back-propagation algorithm, and the final classification of data was carried out with a neural network simulator SNNS v. 4.1. We studied the efficacy of networks containing from one to three hidden layers. Using the best network, containing three hidden layers, the rate of correct classification of nuclei was 73%, and the rate of misdiagnosis was 3%; in 24% the network response was ambiguous. The present findings may serve as a starting point in search for methods facilitating early diagnosis of ductal pancreatic carcinoma.     

Motif-based protein sequence classification using neural networks.

We present a system for multi-class protein classification based on neural networks. The basic issue concerning the construction of neural network systems for protein classification is the sequence encoding scheme that must be used in order to feed the neural network. To deal with this problem we propose a method that maps a protein sequence into a numerical feature space using the matching scores of the sequence to groups of conserved patterns (called motifs) into protein families. We consider two alternative ways for identifying the motifs to be used for feature generation and provide a comparative evaluation of the two schemes. We also evaluate the impact of the incorporation of background features (2-grams) on the performance of the neural system. Experimental results on real datasets indicate that the proposed method is highly efficient and is superior to other well-known methods for protein classification.     

Using weighted fixed neural networks for unsupervised fuzzy clustering

A novel algorithm for unsupervised fuzzy clustering is introduced. The algorithm uses a so-called Weighted Fixed Neural Network (WFNN) to store important and useful information about the topological relations in a given data set. The algorithm produces a weighted connected net, of weighted nodes connected by weighted edges, which reflects and preserves the topology of the input data set. The weights of the nodes and the edges in the resulting net are proportional to the local densities of data samples in input space. The connectedness of the net can be changed, and the higher the connectedness of the net is chosen, the fuzzier the system becomes. The new algorithm is computationally efficient when compared to other existing methods for clustering multi-dimensional data, such as color images.     

Evaluating the performance of artificial neural networks for the classification of freshwater benthic macroinvertebrates

Macroinvertebrates form an important functional component of aquatic ecosystems. Their ability to indicate various types of anthropogenic stressors is widely recognized which has made them an integral component of freshwater biomonitoring. The use of macroinvertebrates in biomonitoring is dependent on manual taxa identification which is currently a time-consuming and cost-intensive process conducted by highly trained taxonomical experts. Automated taxa identification of macroinvertebrates is a relatively recent research development. Previous studies have displayed great potential for solutions to this demanding data mining application. In this research we have a collection of 1350 images from eight different macroinvertebrate taxa and the aim is to examine the suitability of artificial neural networks (ANNs) for automated taxa identification of macroinvertebrates. More specifically, the focus is drawn on different training algorithms of Multi-Layer Perceptron (MLP), probabilistic neural network (PNN) and Radial Basis Function network (RBFN). We performed thorough experimental tests and we tested altogether 13 training algorithms for MLPs. The best classification accuracy of MLPs, 95.3%, was obtained by two conjugate gradient backpropagation variations and scaled conjugate gradient backpropagation. For PNN 92.8% and for RBFN 95.7% accuracies were achieved. The results show how important a proper choice of ANN is in order to obtain high accuracy in the automated taxa identification of macroinvertebrates and the obtained model can outperform the level of identification which is made by a taxonomist.     

Unveiling functions of the visual cortex using task-specific deep neural networks

The human visual cortex enables visual perception through a cascade of hierarchical computations in cortical regions with distinct functionalities. Here, we introduce an AI-driven approach to discover the functional mapping of the visual cortex. We related human brain responses to scene images measured with functional MRI (fMRI) systematically to a diverse set of deep neural networks (DNNs) optimized to perform different scene perception tasks. We found a structured mapping between DNN tasks and brain regions along the ventral and dorsal visual streams. Low-level visual tasks mapped onto early brain regions, 3-dimensional scene perception tasks mapped onto the dorsal stream, and semantic tasks mapped onto the ventral stream. This mapping was of high fidelity, with more than 60% of the explainable variance in nine key regions being explained. Together, our results provide a novel functional mapping of the human visual cortex and demonstrate the power of the computational approach.     

Using neural networks for prediction of the subcellular location of proteins.

Neural networks have been trained to predict the subcellular location of proteins in prokaryotic or eukaryotic cells from their amino acid composition. For three possible subcellular locations in prokaryotic organisms a prediction accuracy of 81% can be achieved. Assigning a reliability index, 33% of the predictions can be made with an accuracy of 91%. For eukaryotic proteins (excluding plant sequences) an overall prediction accuracy of 66% for four locations was achieved, with 33% of the sequences being predicted with an accuracy of 82% or better. With the subcellular location restricting a protein's possible function, this method should be a useful tool for the systematic analysis of genome data and is available via a server on the world wide web.     

Affinity electrophoresis used for determination of binding constants for antibody-antigen reactions.

The use of affinity electrophoresis in agarose gels for determination of binding constants for the interaction of antigens with monoclonal antibodies is exemplified for monoclonal anti-human serum albumin and anti-alpha 1-fetoprotein antibodies. The calculated binding constants are verified by independent binding assays. The electrophoretic separation of antigen-antibody complexes of different stoichiometry is also demonstrated. Thus, affinity electrophoresis represents an alternative method for both qualitative and quantitative assessment of antigen-antibody interactions.     

A strategy to identify linker-based modules for the allosteric regulation of antibody-antigen binding affinities of different scFvs

Antibody single-chain variable fragments (scFvs) are used in a variety of applications, such as for research, diagnosis and therapy. Essential for these applications is the extraordinary specificity, selectivity and affinity of antibody paratopes, which can also be used for efficient protein purification. However, this use is hampered by the high affinity for the protein to be purified because harsh elution conditions, which may impair folding, integrity or viability of the eluted biomaterials, are typically required. In this study, we developed a strategy to obtain structural elements that provide allosteric modulation of the affinities of different antibody scFvs for their antigen. To identify suitable allosteric modules, a complete set of cyclic permutations of calmodulin variants was generated and tested for modulation of the affinity when substituting the linker between VH and VL. Modulation of affinity induced by addition of different calmodulin-binding peptides at physiologic conditions was demonstrated for 5 of 6 tested scFvs of different specificities and antigens ranging from cell surface proteins to haptens. In addition, a variety of different modulator peptides were tested. Different structural solutions were found in respect of the optimal calmodulin permutation, the optimal peptide and the allosteric effect for scFvs binding to different antigen structures. Significantly, effective linker modules were identified for scFvs with both VH-VL and VL-VH architecture. The results suggest that this approach may offer a rapid, paratope-independent strategy to provide allosteric regulation of affinity for many other antibody scFvs.     

Sleep classification in infants based on artificial neural networks.

The study reports on the possibility of classifying sleep stages in infants using an artificial neural network. The polygraphic data from 4 babies aged 6 weeks, 6 months and 1 year recorded over 8 hours were available for classification. From each baby 22 signals were recorded, digitized and stored on an optical disc. Subsets of these signals and additional calculated parameters were used to obtain data vectors, each of which represents an interval of 30 sec. For classification, two types of neural networks were used, a Multilayer Perceptron and a Learning Vector Quantizer. The teaching input for both networks was provided by a human expert. For the 6 sleep classes in babies aged 6 months, a 65% to 80% rate of correct classification (4 babies) was obtained for the testing data not previously seen.