Abstract This study explores the application of deep learning in forecasting electricity consumption. Initially, we assess the performance of standard neural networks, such as convolutional neural networks (CNN) and long short‐term memory (LSTM), along with basic methods like ARIMA and random forest, on a univariate electricity consumption data set. Subsequently, we develop hybrid models for a comprehensive multivariate data set created by merging weather and electricity data. These hybrid models demonstrate superior performance compared to individual models on the univariate data set. Our main contribution is the introduction of a novel hybrid data fusion model. This model integrates a single‐model approach for univariate data, a hybrid model for multivariate data, and a linear regression model that processes the outputs from both. Our hybrid fusion model achieved an RMSE value of 0.0871 on the Chicago data set, outperforming other models such as Random Forest (0.2351), ARIMA (0.2184), CNN (0.1802), LSTM + LSTM (0.1496), and CNN + LSTM (0.1587). Additionally, our model surpassed the performance of our base transformer model. Furthermore, combining the best‐performing transformer model, with a Gaussian Process model resulted in further improvement in performance. The Transformer + Gaussian model achieved an RMSE of 0.0768, compared with 0.0781 for the single transformer model. Similar trends were observed in the Pittsburgh and IHEC data sets.

MOTIVATION: Utilizing AI-driven approaches for drug-target interaction (DTI) prediction require large volumes of training data which are not available for the majority of target proteins. In this study, we investigate the use of deep transfer learning for the prediction of interactions between drug candidate compounds and understudied target proteins with scarce training data. The idea here is to first train a deep neural network classifier with a generalized source training dataset of large size and then to reuse this pre-trained neural network as an initial configuration for re-training/fine-tuning purposes with a small-sized specialized target training dataset. To explore this idea, we selected six protein families that have critical importance in biomedicine: kinases, G-protein-coupled receptors (GPCRs), ion channels, nuclear receptors, proteases, and transporters. In two independent experiments, the protein families of transporters and nuclear receptors were individually set as the target datasets, while the remaining five families were used as the source datasets. Several size-based target family training datasets were formed in a controlled manner to assess the benefit provided by the transfer learning approach. RESULTS: Here, we present a systematic evaluation of our approach by pre-training a feed-forward neural network with source training datasets and applying different modes of transfer learning from the pre-trained source network to a target dataset. The performance of deep transfer learning is evaluated and compared with that of training the same deep neural network from scratch. We found that when the training dataset contains fewer than 100 compounds, transfer learning outperforms the conventional strategy of training the system from scratch, suggesting that transfer learning is advantageous for predicting binders to under-studied targets. AVAILABILITY AND IMPLEMENTATION: The source code and datasets are available at https://github.com/cansyl/TransferLearning4DTI. Our web-based service containing the ready-to-use pre-trained models is accessible at https://tl4dti.kansil.org.

MOTIVATION: Identification of interactions between bioactive small molecules and target proteins is crucial for novel drug discovery, drug repurposing and uncovering off-target effects. Due to the tremendous size of the chemical space, experimental bioactivity screening efforts require the aid of computational approaches. Although deep learning models have been successful in predicting bioactive compounds, effective and comprehensive featurization of proteins, to be given as input to deep neural networks, remains a challenge. RESULTS: Here, we present a novel protein featurization approach to be used in deep learning-based compound-target protein binding affinity prediction. In the proposed method, multiple types of protein features such as sequence, structural, evolutionary and physicochemical properties are incorporated within multiple 2D vectors, which is then fed to state-of-the-art pairwise input hybrid deep neural networks to predict the real-valued compound-target protein interactions. The method adopts the proteochemometric approach, where both the compound and target protein features are used at the input level to model their interaction. The whole system is called MDeePred and it is a new method to be used for the purposes of computational drug discovery and repositioning. We evaluated MDeePred on well-known benchmark datasets and compared its performance with the state-of-the-art methods. We also performed in vitro comparative analysis of MDeePred predictions with selected kinase inhibitors' action on cancer cells. MDeePred is a scalable method with sufficiently high predictive performance. The featurization approach proposed here can also be utilized for other protein-related predictive tasks. AVAILABILITY AND IMPLEMENTATION: The source code, datasets, additional information and user instructions of MDeePred are available at https://github.com/cansyl/MDeePred. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Bioinformatics (2010) doi: 10.1093/bioinformatics/btaa496 Co-author Tunca Doğan’s name was initially misspelled as Tunca Doğana. This has been corrected online.

SUMMARY: iBioProVis is an interactive tool for visual analysis of the compound bioactivity space in the context of target proteins, drugs and drug candidate compounds. iBioProVis tool takes target protein identifiers and, optionally, compound SMILES as input, and uses the state-of-the-art non-linear dimensionality reduction method t-Distributed Stochastic Neighbor Embedding (t-SNE) to plot the distribution of compounds embedded in a 2D map, based on the similarity of structural properties of compounds and in the context of compounds' cognate targets. Similar compounds, which are embedded to proximate points on the 2D map, may bind the same or similar target proteins. Thus, iBioProVis can be used to easily observe the structural distribution of one or two target proteins' known ligands on the 2D compound space, and to infer new binders to the same protein, or to infer new potential target(s) for a compound of interest, based on this distribution. Principal component analysis (PCA) projection of the input compounds is also provided, Hence the user can interactively observe the same compound or a group of selected compounds which is projected by both PCA and embedded by t-SNE. iBioProVis also provides detailed information about drugs and drug candidate compounds through cross-references to widely used and well-known databases, in the form of linked table views. Two use-case studies were demonstrated, one being on angiotensin-converting enzyme 2 (ACE2) protein which is Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) Spike protein receptor. ACE2 binding compounds and seven antiviral drugs were closely embedded in which two of them have been under clinical trial for Coronavirus disease 19 (COVID-19). AVAILABILITY AND IMPLEMENTATION: iBioProVis and its carefully filtered dataset are available at https://ibpv.kansil.org/ for public use. CONTACT: [email protected]. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

The identification of interactions between drugs/compounds and their targets is crucial for the development of new drugs. In vitro screening experiments (i.e. bioassays) are frequently used for this purpose; however, experimental approaches are insufficient to explore novel drug-target interactions, mainly because of feasibility problems, as they are labour intensive, costly and time consuming. A computational field known as 'virtual screening' (VS) has emerged in the past decades to aid experimental drug discovery studies by statistically estimating unknown bio-interactions between compounds and biological targets. These methods use the physico-chemical and structural properties of compounds and/or target proteins along with the experimentally verified bio-interaction information to generate predictive models. Lately, sophisticated machine learning techniques are applied in VS to elevate the predictive performance. The objective of this study is to examine and discuss the recent applications of machine learning techniques in VS, including deep learning, which became highly popular after giving rise to epochal developments in the fields of computer vision and natural language processing. The past 3 years have witnessed an unprecedented amount of research studies considering the application of deep learning in biomedicine, including computational drug discovery. In this review, we first describe the main instruments of VS methods, including compound and protein features (i.e. representations and descriptors), frequently used libraries and toolkits for VS, bioactivity databases and gold-standard data sets for system training and benchmarking. We subsequently review recent VS studies with a strong emphasis on deep learning applications. Finally, we discuss the present state of the field, including the current challenges and suggest future directions. We believe that this survey will provide insight to the researchers working in the field of computational drug discovery in terms of comprehending and developing novel bio-prediction methods.

BACKGROUND: The automated prediction of the enzymatic functions of uncharacterized proteins is a crucial topic in bioinformatics. Although several methods and tools have been proposed to classify enzymes, most of these studies are limited to specific functional classes and levels of the Enzyme Commission (EC) number hierarchy. Besides, most of the previous methods incorporated only a single input feature type, which limits the applicability to the wide functional space. Here, we proposed a novel enzymatic function prediction tool, ECPred, based on ensemble of machine learning classifiers. RESULTS: In ECPred, each EC number constituted an individual class and therefore, had an independent learning model. Enzyme vs. non-enzyme classification is incorporated into ECPred along with a hierarchical prediction approach exploiting the tree structure of the EC nomenclature. ECPred provides predictions for 858 EC numbers in total including 6 main classes, 55 subclass classes, 163 sub-subclass classes and 634 substrate classes. The proposed method is tested and compared with the state-of-the-art enzyme function prediction tools by using independent temporal hold-out and no-Pfam datasets constructed during this study. CONCLUSIONS: ECPred is presented both as a stand-alone and a web based tool to provide probabilistic enzymatic function predictions (at all five levels of EC) for uncharacterized protein sequences. Also, the datasets of this study will be a valuable resource for future benchmarking studies. ECPred is available for download, together with all of the datasets used in this study, at: https://github.com/cansyl/ECPred . ECPred webserver can be accessed through http://cansyl.metu.edu.tr/ECPred.html .

This study obtains projective reconstructions of an object or a scene from its image pair and measures relative consistency of these projective reconstructions. 3D points are estimated from an image pair using projective and epipolar geometry. Two measures are presented for verification of projective reconstructions with each other. These measures are based on the equality of ratios between the x-, y- and z-coordinates of 3D reconstructed points which are obtained from the same corresponding points. This information is used for measuring the relative consistency of projective reconstructions obtained from the same image pair.

MOTIVATION: We designed a general computational kernel for classification problems that require specific motif extraction and search from sequences. Instead of searching for explicit motifs, our approach finds the distribution of implicit motifs and uses as a feature for classification. Implicit motif distribution approach may be used as modus operandi for bioinformatics problems that require specific motif extraction and search, which is otherwise computationally prohibitive. RESULTS: A system named P2SL that infer protein subcellular targeting was developed through this computational kernel. Targeting-signal was modeled by the distribution of subsequence occurrences (implicit motifs) using self-organizing maps. The boundaries among the classes were then determined with a set of support vector machines. P2SL hybrid computational system achieved approximately 81% of prediction accuracy rate over ER targeted, cytosolic, mitochondrial and nuclear protein localization classes. P2SL additionally offers the distribution potential of proteins among localization classes, which is particularly important for proteins, shuttle between nucleus and cytosol. AVAILABILITY: http://staff.vbi.vt.edu/volkan/p2sl and http://www.i-cancer.fen.bilkent.edu.tr/p2sl CONTACT: [email protected].

This paper presents particularly a contextual post processing subsystem for a Turkish machine printed character recognition system. The contextual post processing subsystem is based on positional binary 3-gram statistics for Turkish language, an error corrector parser and a lexicon, which contains root words and the inflected forms of the root words. Error corrector parser is used for correcting CR alternatives using Turkish Morphology. 1.

In this paper, a unistroke keyboard based on computer vision is described for the handicapped. The keyboard can be made of paper or fabric containing an image of a keyboard, which has an upside down U-shape. It can even be displayed on a computer screen. Each character is represented by a non-overlapping rectangular region on the keyboard image and the user enters a character by illuminating a character region with a laser pointer. The keyboard image is monitored by a camera and illuminated key locations are recognized. During the text entry process the user neither have to turn the laser light off nor raise the laser light from the keyboard. A disabled person who has difficulty using his/her hands may attach the laser pointer to an eyeglass and easily enter text by moving his/her head to point the laser beam on a character location. In addition, a mouse-like device can be developed based on the same principle. The user can move the cursor by moving the laser light on the computer screen which is monitored by a camera.

The goal of this study is to investigate the reconstruction of three-dimensional (3-D) graphical models of real objects in a controlled imaging environment and present the work done in our group based on silhouette-based reconstruction. Although many parts of the whole system have been well-known in the literature and in practice, the main contribution of the paper is that it describes a complete, end-to-end system explained in detail. Based on a multi-image calibration method, an algorithm to extract the rotation axis of a turn-table has been developed. Furthermore, this can be extended to estimate robustly the initial bounding volume of the object to be modeled. The disadvantages of the silhouette-based reconstruction can be removed by an algorithm using photoconsistency. This algorithm has a simpler visibility check, and it eliminates the selection of threshold existing in similar algorithms. Besides, in order to construct the appearance, we use the concept of particles. The reconstruction results are shown both on real world and synthetic objects.

We describe a computer vision based mouse, which can control and command the cursor of a computer or a computerized system using a camera. In order to move the cursor on the computer screen the user simply moves the mouse shaped passive device placed on a surface within the viewing area of the camera. The video generated by the camera is analyzed using computer vision techniques and the computer moves the cursor according to mouse movements. The computer vision based mouse has regions corresponding to buttons for clicking. To click a button the user simply covers one of these regions with his/her finger.

Proposes a viewer for visual reconstruction and retrieval of form documents. The structure of the form document and the filled-in data are stored in an SGML (Standard Generalised Markup Language) instance. A DSSSL (Document Style Semantics and Specification Language) instance holds style properties of the data. Filled-in data is kept in a relational database. The viewer uses SGML and DSSSL instances as input and visually reconstructs a form document image by retrieving the corresponding filled-in data from the database.

In this work, a subband domain textual image compression method is developed. The document image is first decomposed into subimages using binary subband decompositions. Next, the character locations in the subbands and the symbol library consisting of the character images are encoded. The method is suitable for keyword search in the compressed data. It is observed that very high compression ratios are obtained with this method. Simulation studies are presented.

In this paper our aim is to develop a logical representation for form documents. We propose a hierarchical structure to represent the logical layout of a form by using lines. The approach is top-down and no domain knowledge such as the preprinted data or filled-in data is used. Logically same but physically different forms are associated to the same hierarchical tree. This representation can handle geometrical modifications and slight variations.

Unsupervised segmentation of images which are composed of various textures is investigated. A coarse segmentation is achieved through a hierarchical self organizing map. This initial segmentation result is fed into a simulated annealing algorithm in which region and texture parameters are estimated using a maximum likelihood technique. Region geometries are modeled as Potts model while textures are modeled as Markov random fields. Tests are performed on artificial textured images.

This paper describes a new framework, called repulsive attractive (RA) network for baseline extraction on document images. The RA network is a self organizing feature detector which interacts with the document text image through the attractive and repulsive forces defined among the network components and the document image. Experimental results indicate that the network can successfully extract the baselines under heavy noise and with overlaps between the ascending and descending portions of the characters of adjacent lines. The proposed method is also applicable to a wide range of image processing applications, such as curve fitting, segmentation and thinning.

Segmentation of gray level images into regions of uniform texture is investigated. An unsupervised approach through the use of Kohonen's self organizing map (SOM) and a multilayer version of it, the hierarchical self organizing map (HSOM), is employed to find the regions in an image composed of textures from different classes. For testing, gray level artificial textured images modeled as Markov random fields are used as the input. No parameter estimation is done. The size and the topology of SOM and HSOM are independent from the size of the input image. The segmentation results are very promising.

We propose a parallel algorithm for the generation of colour textures based upon the non-linear equations of the "multiple class random neural network model". A neuron is used to obtain the texture value of each pixel in the bit-map plane. Each neuron interacts with its immediate planar neighbours in order to obtain the texture for the whole plane. A model which uses at most 4(C2 + C) parameters for the whole network, where C is the number of colours, is proposed. Numerical iterations of the non-linear field equations of the neural network model, starting with a randomly generated image, are shown to produce textures having different desirable features such as granularity, inclination and randomness. The experimental evaluation shows that the random network provides good results, at a computational cost which is considerably less than that of other approaches such as Markov random fields.

The generation of artifical textures is a useful function in image synthesis systems. The purpose of this paper is to describe the use of the random neural network (RN) model developed by Gelenbe to generate various textures having different characteristics. An eight parameter model, based on a choice of the local interaction parameters between neighbouring neurons in the plane, is proposed. Numerical iterations of the field equations of the neural network model, starting with a randomly generated gray-level image, are shown to produce textures having different desirable features such as granularity, inclination, and randomness. The experimental evaluation shows that the random network provides good results, at a computational cost less than that of other approaches such as Markov random fields. Various examples of textures generated by our method are presented.