Search

As the number of protein sequences increases in biological databases, computational methods are required to provide accurate functional annotation with high coverage. Although several machine learning methods have been proposed for this purpose, there are still two main issues: (i) construction of reliable positive and negative training and validation datasets, and (ii) fair evaluation of their performances based on predefined experimental settings. To address these issues, we have developed ProFAB: Open Protein Functional Annotation Benchmark, which is a platform providing an infrastructure for a fair comparison of protein function prediction methods. ProFAB provides filtered and preprocessed protein annotation datasets and enables the training and evaluation of function prediction methods via several options. We believe that ProFAB will be useful for both computational and experimental researchers by enabling the utilization of ready-to-use datasets and machine learning algorithms for protein function prediction based on Gene Ontology terms and Enzyme Commission numbers. ProFAB is available at https://github.com/kansil/ProFAB and https://profab.kansil.org.

Computational approaches have been used at different stages of drug development with the purpose of decreasing the time and cost of conventional experimental procedures. Lately, techniques mainly developed and applied in the field of artificial intelligence (AI), have been transferred to different application domains such as biomedicine.In this study, we conducted an investigative analysis via data-driven evaluation of potential hepatocellular carcinoma (HCC) therapeutics in the context of AI-assisted drug discovery/repurposing. First, we discussed basic concepts, computational approaches, databases, modeling approaches, and featurization techniques in drug discovery/repurposing. In the analysis part, we automatically integrated HCC-related biological entities such as genes/proteins, pathways, phenotypes, drugs/compounds, and other diseases with similar implications, and represented these heterogeneous relationships via a knowledge graph using the CROssBAR system.Following the system-level evaluation and selection of critical genes/proteins and pathways to target, our deep learning-based drug/compound-target protein interaction predictors DEEPScreen and MDeePred have been employed for predicting new bioactive drugs and compounds for these critical targets. Finally, we embedded ligands of selected HCC-associated proteins which had a significant enrichment with the CROssBAR system into a 2-D space to identify and repurpose small molecule inhibitors as potential drug candidates based on their molecular similarities to known HCC drugs.We expect that these series of data-driven analyses can be used as a roadmap to propose early-stage potential inhibitors (from database-scale sets of compounds) to both HCC and other complex diseases, which may subsequently be analyzed with more targeted in silico and experimental approaches.

MotivationGenomic variations may cause deleterious effects on protein functionality and perturb biological processes. Elucidating the effects of variations is critical for developing novel treatment strategies for diseases of genetic origin. Computational approaches have been aiding the work in this field by modeling and analyzing the mutational landscape. However, new approaches are required, especially for accurate and comprehensive representation and data-centric analysis of sequence variations.ResultsIn this study, we propose ASCARIS (Annotation and StruCture-bAsed RepresentatIon of Single amino acid variations - SAVs), a method for the featurization (i.e., quantitative representation) of SAVs, which could be used for a variety of purposes, such as predicting their functional effects or building multi-omics-based integrative models. In ASCARIS representations, we incorporated the correspondence between the location of the SAV on the sequence and 30 different types of positional feature annotations (e.g., active/lipidation/glycosylation sites; calcium/metal/DNA binding, inter/transmembrane regions, etc.) from UniProt, along with structural features such as protein domains, the location of variation (e.g., core/interface/surface), and the change in physico-chemical properties using models from PDB and AlphaFold-DB. We also mapped the mutated and annotated residues to the 3-D plane and calculated the spatial distances between them in order to account for the functional changes caused by variations in positions close to the functionally essential ones. Finally, we constructed a 74-dimensional feature set to represent each SAV in a dataset composed of ∼100,000 data points.We statistically analyzed the relationship between each of these features and the consequences of variations, and found that each of them carries information in this regard. To investigate potential applications of ASCARIS, we trained variant effect predictor models that utilize our SAV representations as input. We carried out both an ablation study and a comparison against the state-of-the-art methods over well-known benchmark datasets. We observed that our method displays a competing performance against widely-used predictors. Also, our predictions were complementary to these methods which is probably due to fact that ASCARIS has a rather unique focus in modeling variations. ASCARIS can be used either alone or in combination with other approaches, to universally represent SAVs from a functional perspective.Availability and implementationThe source code, datasets, results, and user instructions of ASCARIS are available athttps://github.com/HUBioDataLab/ASCARIS.

MotivationIdentifying unknown functional properties of proteins is an important task for understanding their roles in both health and disease states. The domain composition of a protein can reveal critical information in this context, as domains are structural and functional units that dictate how the protein should act at the molecular level. The expensive and time-consuming nature of wet-lab experimental approaches prompted researchers to develop computational strategies for predicting biomolecular functions. Biological ontologies, such as the Gene Ontology (GO), which provide a standardized vocabulary of information about biological entities, are frequently employed in protein function prediction.ResultsIn this study, we proposed a new method called Domain2GO that predicts associations between protein domains and GO terms, thus redefining the problem as domain function prediction, using documented protein-level GO annotations together with proteins’ domain content. To obtain reliable associations, co-annotation patterns of domains and GO terms in the same proteins are examined using statistical resampling. An ablation study was conducted to compare the predictive performance of various implementations of Domain2GO, differing from each other by the utilized statistical measure (e.g., information theory inspired similarity measures and the ones calculated by the expectation-maximization algorithm). As a use-case study, examples selected from the finalized domain-GO term mappings were evaluated for their biological relevance via a literature review. Then, we applied the proposed method to predict presently unknown protein functions by propagating domain-associated GO terms to proteins annotated with these domains. For protein function prediction performance evaluation and comparison against other methods, we employed Critical Assessment of Function Annotation 3 (CAFA3) challenge datasets. The results demonstrated the high potential of Domain2GO, particularly for predicting molecular function and biological process terms, along with advantages such as producing interpretable results and having exceptionally low computational costs. The approach presented here can be extended to other ontologies and biological entities in order to investigate unknown relationships in complex and large-scale biological data.Availability and implementationThe source code, datasets, results, and user instructions for Domain2GO are available athttps://github.com/HUBioDataLab/Domain2GO.

The identification of drug/compound-target interactions (DTIs) constitutes the basis of drug discovery, for which computational predictive approaches have been applied. As a relatively new data-driven paradigm, proteochemometric (PCM) modeling utilizes both protein and compound properties as a pair at the input level and processes them via statistical/machine learning. The representation of input samples (i.e., proteins and their ligands) in the form of quantitative feature vectors is crucial for the extraction of interaction-related properties during the artificial learning and subsequent prediction of DTIs. Lately, the representation learning approach, in which input samples are automatically featurized via training and applying a machine/deep learning model, has been utilized in biomedical sciences. In this study, we performed a comprehensive investigation of different computational approaches/techniques for data preparation and protein featurization, including both conventional approaches and the novel learned embeddings, with the aim of achieving better data representations and more successful learning in PCM-based DTI prediction. For this, we first constructed realistic and challenging benchmark datasets on small, medium, and large scales to be used as reliable gold standards for specific DTI modeling tasks. We developed and applied a network analysis-based splitting strategy to divide datasets into structurally different training and test folds. Using these datasets together with various featurization methods, we trained and tested DTI prediction models and evaluated their performance from different angles. Our main findings can be summarized under 3 items: (i) random splitting of the dataset into train and test folds leads to near-complete data memorization and produce highly over-optimistic results, as a result, it should be avoided; (ii) learned protein sequence embeddings works well in DTI prediction, even though no information related to protein structures, interactions or biochemical properties is utilized during the training of these models; and (iii) PCM models tends to learn from compound features and leave out protein features, mostly due to the natural bias in DTI data. We hope this study will aid researchers in designing robust and high-performing data-driven DTI prediction systems that have real-world translational value in drug discovery.

Summary Accurate prediction of the subcellular locations (SLs) of proteins is a critical topic in protein science. In this study, we present SLPred, an ensemble-based multi-view and multi-label protein subcellular localization prediction tool. For a query protein sequence, SLPred provides predictions for nine main SLs using independent machine-learning models trained for each location. We used UniProtKB/Swiss-Prot human protein entries and their curated SL annotations as our source data. We connected all disjoint terms in the UniProt SL hierarchy based on the corresponding term relationships in the cellular component category of Gene Ontology and constructed a training dataset that is both reliable and large scale using the re-organized hierarchy. We tested SLPred on multiple benchmarking datasets including our-in house sets and compared its performance against six state-of-the-art methods. Results indicated that SLPred outperforms other tools in the majority of cases. Availability and implementation SLPred is available both as an open-access and user-friendly web-server (https://slpred.kansil.org) and a stand-alone tool (https://github.com/kansil/SLPred). All datasets used in this study are also available at https://slpred.kansil.org. Supplementary information Supplementary data are available at Bioinformatics online.

Predictive approaches such as virtual screening have been used in drug discovery with the objective of reducing developmental time and costs. Current machine learning and network-based approaches have issues related to generalization, usability, or model interpretability, especially due to the complexity of target proteins’ structure/function, and bias in system training datasets. Here, we propose a new method “DRUIDom” (DRUg Interacting Domain prediction) to identify bio-interactions between drug candidate compounds and targets by utilizing the domain modularity of proteins, to overcome problems associated with current approaches. DRUIDom is composed of two methodological steps. First, ligands/compounds are statistically mapped to structural domains of their target proteins, with the aim of identifying their interactions. As such, other proteins containing the same mapped domain or domain pair become new candidate targets for the corresponding compounds. Next, a million-scale dataset of small molecule compounds, including those mapped to domains in the previous step, are clustered based on their molecular similarities, and their domain associations are propagated to other compounds within the same clusters. Experimentally verified bioactivity data points, obtained from public databases, are meticulously filtered to construct datasets of active/interacting and inactive/non-interacting drug/compound–target pairs (~2.9M data points), and used as training data for calculating parameters of compound–domain mappings, which led to 27,032 high-confidence associations between 250 domains and 8,165 compounds, and a finalized output of ~5 million new compound–protein interactions. DRUIDom is experimentally validated by syntheses and bioactivity analyses of compounds predicted to target LIM-kinase proteins, which play critical roles in the regulation of cell motility, cell cycle progression, and differentiation through actin filament dynamics. We showed that LIMK-inhibitor-2 and its derivatives significantly block the cancer cell migration through inhibition of LIMK phosphorylation and the downstream protein cofilin. One of the derivative compounds (LIMKi-2d) was identified as a promising candidate due to its action on resistant Mahlavu liver cancer cells. The results demonstrated that DRUIDom can be exploited to identify drug candidate compounds for intended targets and to predict new target proteins based on the defined compound–domain relationships. Datasets, results, and the source code of DRUIDom are fully-available at: https://github.com/cansyl/DRUIDom., Author summary Drug development comprises several interlinked steps from designing drug candidate molecules to running clinical trials, with the aim to bring a new drug to market. A critical yet costly and labor-intensive stage is drug discovery, in which drug candidate molecules that specifically interact with the intended biomolecular target (mostly proteins) are identified. Lately, data-centric computational methods have been proposed to aid experimental procedures in drug discovery. These methods have the ability to rapidly assess large molecule libraries and reduce the time and cost of the process; however, most of them suffer from problems related to producing reliable biologically relevant results, preventing them from gaining real-world usage. Herein, we have developed a new method called DRUIDom (DRUg Interacting Domain prediction) to identify unknown interactions between drugs/drug candidate compounds and biological targets by utilizing the modular structure of proteins. For this, we identify the domains, i.e., the evolutionary and functional building blocks of proteins, where these potential drug compounds can bind, and utilize this information along with protein domain annotations to predict new drug targets. We have tested the biological relevance of DRUIDom on selected proteins that play critical roles in the progression of numerous types of cancer. Cell-based experimental results indicated that predicted inhibitors are effective even on drug-resistant cancer cells. Our results suggest DRUIDom produces novel and biologically relevant results that can be directly used in the early steps of the drug discovery process.

Predictive approaches such as virtual screening have been used in drug discovery with the objective of reducing developmental time and costs. Current machine learning and network- based approaches have issues related to generalization, usability, or model interpretability, especially due to the complexity of target proteins’ structure/function, and bias in system training datasets. Here, we propose a new computational method “DRUIDom” to predict bio- interactions between drug candidate compounds and target proteins by utilizing the domain modularity of proteins, to overcome problems associated with current approaches. DRUIDom is composed of two methodological steps. First, ligands/compounds are statistically mapped to structural domains of their target proteins, with the aim of identifying physical or functional interactions. As such, other proteins containing the mapped domain or domain pair become new candidate targets for the corresponding compounds. Next, a million-scale dataset of small molecule compounds, including the ones mapped to domains in the previous step, are clustered based on their molecular similarities, and their domain associations are propagated to other compounds within the same clusters. Experimentally verified bioactivity data points, obtained from public databases, are meticulously filtered to construct datasets of active/interacting and inactive/non-interacting compound–target pairs (∼2.9M data points), and used as training data for calculating parameters of compound– domain mappings, which led to 27,032 high-confidence associations between 250 domains and 8,165 compounds, and a finalized output of ∼5 million new compound–protein interactions. DRUIDom is experimentally validated by syntheses and bioactivity analyses of compounds predicted to target LIM-kinase proteins, which play critical roles in the regulation of cell motility, cell cycle progression, and differentiation through actin filament dynamics. We showed that LIMK-inhibitor-2 and its derivatives significantly block the cancer cell migration through inhibition of LIMK phosphorylation and the downstream protein cofilin. One of the derivative compounds (LIMKi-2d) was identified as a promising candidate due to its action on resistant Mahlavu liver cancer cells. The results demonstrated that DRUIDom can be exploited to identify drug candidate compounds for intended targets and to predict new target proteins based on the defined compound–domain relationships. The datasets, results, and the source code of DRUIDom are fully-available at: https://github.com/cansyl/DRUIDom.Author SummaryDrug development comprises several interlinked steps from designing drug candidate molecules to running clinical trials, with the aim to bring a new drug to market. A critical yet costly and labor-intensive stage is drug discovery, in which drug candidate molecules that specifically interact with the intended biomolecular target (mostly proteins) are identified. Lately, data-centric computational methods have been proposed to aid experimental procedures in drug discovery. These methods have the ability to rapidly assess large molecule libraries and reduce the time and cost of the process; however, most of them suffer from problems related to producing reliable biologically relevant results, preventing them from gaining real-world usage. Here, we have developed a new method called DRUIDom to predict unknown interactions between drugs/drug candidate compounds and biological targets by utilizing the modular structure of proteins. For this, we identify the domains, i.e., the evolutionary and functional building blocks of proteins, where these potential drug compounds can bind, and utilize this information along with protein domain annotations to predict new drug targets. We have tested the biological relevance of DRUIDom on selected proteins that play critical roles in the progression of numerous types of cancer. Cell-based experimental results indicated that predicted inhibitors are effective even on drug-resistant cancer cells. Our results suggest that DRUIDom produces novel and biologically relevant results that can be directly used in the early steps of the drug discovery process.

WOS: 000467839800015, 31089211, Automated protein function prediction is critical for the annotation of uncharacterized protein sequences, where accurate prediction methods are still required. Recently, deep learning based methods have outperformed conventional algorithms in computer vision and natural language processing due to the prevention of overfitting and efficient training. Here, we propose DEEPred, a hierarchical stack of multi-task feed-forward deep neural networks, as a solution to Gene Ontology (GO) based protein function prediction. DEEPred was optimized through rigorous hyper-parameter tests, and benchmarked using three types of protein descriptors, training datasets with varying sizes and GO terms form different levels. Furthermore, in order to explore how training with larger but potentially noisy data would change the performance, electronically made GO annotations were also included in the training process. The overall predictive performance of DEEPred was assessed using CAFA2 and CAFA3 challenge datasets, in comparison with the state-of-the-art protein function prediction methods. Finally, we evaluated selected novel annotations produced by DEEPred with a literature-based case study considering the 'biofilm formation process' in Pseudomonas aeruginosa. This study reports that deep learning algorithms have significant potential in protein function prediction; particularly when the source data is large. The neural network architecture of DEEPred can also be applied to the prediction of the other types of ontological associations. The source code and all datasets used in this study are available at: https://github.com/cansyl/DEEPred., YOK OYP scholarship, The authors would like to thank Andrew Nightingale for the critical reading of the manuscript. ASR was supported by YOK OYP scholarship.

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.

Systemic analysis of available large-scale biological/biomedical data is critical for studying biological mechanisms, and developing novel and effective treatment approaches against diseases. However, different layers of the available data are produced using different technologies and scattered across individual computational resources without any explicit connections to each other, which hinders extensive and integrative multi-omics-based analysis. We aimed to address this issue by developing a new data integration/representation methodology and its application by constructing a biological data resource. CROssBAR is a comprehensive system that integrates large-scale biological/biomedical data from various resources and stores them in a NoSQL database. CROssBAR is enriched with the deep-learning-based prediction of relationships between numerous data entries, which is followed by the rigorous analysis of the enriched data to obtain biologically meaningful modules. These complex sets of entities and relationships are displayed to users via easy-to-interpret, interactive knowledge graphs within an open-access service. CROssBAR knowledge graphs incorporate relevant genes-proteins, molecular interactions, pathways, phenotypes, diseases, as well as known/predicted drugs and bioactive compounds, and they are constructed on-the-fly based on simple non-programmatic user queries. These intensely processed heterogeneous networks are expected to aid systems-level research, especially to infer biological mechanisms in relation to genes, proteins, their ligands, and diseases.

Data-centric approaches have been utilized to develop predictive methods for elucidating uncharacterized aspects of proteins such as their functions, biophysical properties, subcellular locations and interactions. However, studies indicate that the performance of these methods should be further improved to effectively solve complex problems in biomedicine and biotechnology. A data representation method can be defined as an algorithm that calculates numerical feature vectors for samples in a dataset, to be later used in quantitative modelling tasks. Data representation learning methods do this by training and using a model that employs statistical and machine/deep learning algorithms. These novel methods mostly take inspiration from the data-driven language models that have yielded ground-breaking improvements in the field of natural language processing. Lately, these learned data representations have been applied to the field of protein informatics and have displayed highly promising results in terms of extracting complex traits of proteins regarding sequence-structure-function relations. In this study, we conducted a detailed investigation over protein representation learning methods, by first categorizing and explaining each approach, and then conducting benchmark analyses on;(i)inferring semantic similarities between proteins,(ii)predicting ontology-based protein functions, and(iii)classifying drug target protein families. We examine the advantages and disadvantages of each representation approach over the benchmark results. Finally, we discuss current challenges and suggest future directions. We believe the conclusions of this study will help researchers in applying machine/deep learning-based representation techniques on protein data for various types of predictive tasks. Furthermore, we hope it will demonstrate the potential of machine learning-based data representations for protein science and inspire the development of novel methods/tools to be utilized in the fields of biomedicine and biotechnology.

Systemic analysis of available large-scale biological and biomedical data is critical for developing novel and effective treatment approaches against both complex and infectious diseases. Owing to the fact that different sections of the biomedical data is produced by different organizations/institutions using various types of technologies, the data are scattered across individual computational resources, without any explicit relations/connections to each other, which greatly hinders the comprehensive multi-omics-based analysis of data. We aimed to address this issue by constructing a new biological and biomedical data resource, CROssBAR, a comprehensive system that integrates large-scale biomedical data from various resources and store them in a new NoSQL database, enrich these data with deep-learning-based prediction of relations between numerous biomedical entities, rigorously analyse the enriched data to obtain biologically meaningful modules and display them to users via easy-to-interpret, interactive and heterogenous knowledge graph (KG) representations within an open access, user-friendly and online web-service athttps://crossbar.kansil.org. As a use-case study, we constructed CROssBAR COVID-19 KGs (available at:https://crossbar.kansil.org/covid_main.php) that incorporate relevant virus and host genes/proteins, interactions, pathways, phenotypes and other diseases, as well as known and completely new predicted drugs/compounds. Our COVID-19 graphs can be utilized for a systems-level evaluation of relevant virus-host protein interactions, mechanisms, phenotypic implications and potential interventions.

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 vatalay@metu.edu.tr Supplementary information Supplementary data are available at Bioinformatics online.

The aim of the UniProt Knowledgebase is to provide users with a comprehensive, high-quality and freely accessible set of protein sequences annotated with functional information. In this article, we describe significant updates that we have made over the last two years to the resource. The number of sequences in UniProtKB has risen to approximately 190 million, despite continued work to reduce sequence redundancy at the proteome level. We have adopted new methods of assessing proteome completeness and quality. We continue to extract detailed annotations from the literature to add to reviewed entries and supplement these in unreviewed entries with annotations provided by automated systems such as the newly implemented Association-Rule-Based Annotator (ARBA). We have developed a credit-based publication submission interface to allow the community to contribute publications and annotations to UniProt entries. We describe how UniProtKB responded to the COVID-19 pandemic through expert curation of relevant entries that were rapidly made available to the research community through a dedicated portal. UniProt resources are available under a CC-BY (4.0) license via the web at https://www.uniprot.org/.

Rifaioglu, Ahmet Sureyya/0000-0001-6717-4767; Dogan, Tunca/0000-0002-1298-9763; Martin, Maria-Jesus/0000-0001-5454-2815, WOS: 000509119800021, PubMed ID: 30084866, 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., Turkish Ministry of Development, KanSiL project [KanSil_2016K121540]; Newton/Katip Celebi Institutional Links program by TUBITAK, TurkeyTurkiye Bilimsel ve Teknolojik Arastirma Kurumu (TUBITAK); British Council, UK [116E930]; European Molecular Biology Laboratory core funds, This work was supported by the Turkish Ministry of Development, KanSiL project (KanSil_2016K121540); the Newton/Katip Celebi Institutional Links program by TUBITAK, Turkey and British Council, UK (project no: 116E930); and the European Molecular Biology Laboratory core funds.

The Critical Assessment of Functional Annotation (CAFA) is an ongoing, global, community-driven effort to evaluate and improve the computational annotation of protein function. Here we report on the results of the third CAFA challenge, CAFA3, that featured an expanded analysis over the previous CAFA rounds, both in terms of volume of data analyzed and the types of analysis performed. In a novel and major new development, computational predictions and assessment goals drove some of the experimental assays, resulting in new functional annotations for more than 1000 genes. Specifically, we performed experimental whole-genome mutation screening in Candida albicans and Pseudomonas aureginosa genomes, which provided us with genome-wide experimental data for genes associated with biofilm formation and motility (P. aureginosa only). We further performed targeted assays on selected genes in Drosophila melanogaster, which we suspected of being involved in long-term memory. We conclude that, while predictions of the molecular function and biological process annotations have slightly improved over time, those of the cellular component have not. Term-centric prediction of experimental annotations remains equally challenging; although the performance of the top methods is significantly better than expectations set by baseline methods in C. albicans and D. melanogaster, it leaves considerable room and need for improvement. We finally report that the CAFA community now involves a broad range of participants with expertise in bioinformatics, biological experimentation, biocuration, and bioontologies, working together to improve functional annotation, computational function prediction, and our ability to manage big data in the era of large experimental screens.

`Gebze'de Âşıklık Geleneği` adlı bu yüksek lisans tezinde, öncelikle Gebze'nin tarihî geçmişi, coğrafî özellikleri, nüfus ve ekonomik yapısı, sosyokültürel yapısı üzerinde durulmuştur. Âşıklığın tanımı ve içeriği, oluşumundan günümüze âşıklık geleneği açıklanmıştır. Tarihî süreçte Gebze'ye yapılan göçler ve geleneğin taşınması, Gebze'de âşıklık geleneğinin oluşumunu sağlayan Kars, Erzurum ve Ardahan'daki geleneğin Gebze'deki icra biçimleri, âşıkların Gebze'deki icra ortamları, elektronik kültür ortamlarından faydalanma süreçleri ve geleneğin elektronik kültür ortamına bağlı yaşadığı değişim ele alınmıştır. Ayrıca geleneğin unsurlarının geleceğe ne şekilde ve ne derece taşındığı, Gebze'ye göçlerin nedenleri ve bunun geleneğe olan etkileri Gebze Âşıklar, Şairler, Ozanlar ve Edebiyatçılar Derneği ve Gedikler Kültür Evinden âşıkların ne derece yararlandığı ile alakalı veriler yapılan derlemeler sonucu elde edilmiştir. Elde edilen sonuçlar, halk bilimsel açıdan ele alınmıştır. In this postgraduate thesis named `Minstrelsy Tradition in Gebze`, the historical background, demographic and economic structure and socio-cultural status of Gebze is stressed. The definition and content, since its origin and its path to today, Minstrelsy tradition is expressed. Throughout the historical period, the migrations and the transfer of this tradition to Gebze along with the Minstrels' various performing forms and atmospheres, which emerged in Kars, Erzurum and Ardahan, their utilization processes from electronical platforms along with the evolutionary period of this tradition related to electronical culture context are covered in this thesis. In addition, the extent and way of transferring the elements of this tradition to the future, the reasons of migration to Gebze, how Minstrels benefit from `Minstrels, Poets and Men of Letters Society` and `Gedik Culture House` are concluded thanks to the compilations gathered during this study. The collected outcomes are handled in terms of social sciences. 119

Tosatto, Silvio/0000-0003-4525-7793; Zhang, Feng/0000-0003-3447-897X; Gonzalez, Jose Maria Fernandez/0000-0002-4806-5140; Devignes, Marie-Dominique/0000-0002-0399-8713; Wass, Mark/0000-0001-5428-6479; Falda, Marco/0000-0003-2642-519X; Thurlby, Natalie/0000-0002-1007-0286; Zosa, Elaine/0000-0003-2482-0663; Dessimoz, Christophe/0000-0002-2170-853X; Yunes, Jeffrey/0000-0003-1869-3231; Hamid, Md Nafiz/0000-0001-8681-6526; Hoehndorf, Robert/0000-0001-8149-5890; Dogan, Tunca/0000-0002-1298-9763; NOTARO, MARCO/0000-0003-4309-2200; Cozzetto, Domenico/0000-0001-6752-5432; Lewis, Kimberley/0000-0003-3010-8453; Roche, Daniel/0000-0002-9204-1840; Martin, Maria-Jesus/0000-0001-5454-2815; Tress, Michael/0000-0001-9046-6370; Tolvanen, Martti/0000-0003-3434-7646; Cheng, Jianlin/0000-0003-0305-2853; Rose, Peter/0000-0001-9981-9750; Renaux, Alexandre/0000-0002-4339-2791; Kacsoh, Balint/0000-0001-9171-0611; O'Donovan, Claire/0000-0001-8051-7429; Kulmanov, Maxat/0000-0003-1710-1820; Friedberg, Iddo/0000-0002-1789-8000; Zhou, Naihui/0000-0001-6268-6149, WOS: 000498615000001, PubMed ID: 31744546, Background The Critical Assessment of Functional Annotation (CAFA) is an ongoing, global, community-driven effort to evaluate and improve the computational annotation of protein function. Results Here, we report on the results of the third CAFA challenge, CAFA3, that featured an expanded analysis over the previous CAFA rounds, both in terms of volume of data analyzed and the types of analysis performed. In a novel and major new development, computational predictions and assessment goals drove some of the experimental assays, resulting in new functional annotations for more than 1000 genes. Specifically, we performed experimental whole-genome mutation screening in Candida albicans and Pseudomonas aureginosa genomes, which provided us with genome-wide experimental data for genes associated with biofilm formation and motility. We further performed targeted assays on selected genes in Drosophila melanogaster, which we suspected of being involved in long-term memory. Conclusion We conclude that while predictions of the molecular function and biological process annotations have slightly improved over time, those of the cellular component have not. Term-centric prediction of experimental annotations remains equally challenging; although the performance of the top methods is significantly better than the expectations set by baseline methods in C. albicans and D. melanogaster, it leaves considerable room and need for improvement. Finally, we report that the CAFA community now involves a broad range of participants with expertise in bioinformatics, biological experimentation, biocuration, and bio-ontologies, working together to improve functional annotation, computational function prediction, and our ability to manage big data in the era of large experimental screens., National Science FoundationNational Science Foundation (NSF) [DBI1564756, DBI-1458359, DBI-1458390, DMS1614777, CMMI1825941, NSF 1458390]; Gordon and Betty Moore FoundationGordon and Betty Moore Foundation [GBMF 4552]; National Institutes of Health NIGMSUnited States Department of Health & Human ServicesNational Institutes of Health (NIH) - USANIH National Institute of General Medical Sciences (NIGMS) [P20 GM113132]; Cystic Fibrosis Foundation [CFRDP STANTO19R0]; BBSRCBiotechnology and Biological Sciences Research Council (BBSRC) [BB/K004131/1, BB/F00964X/1, BB/M025047/1, BB/M015009/1]; Consejo Nacional de Ciencia y Tecnologia Paraguay (CONACyT)Consejo Nacional de Ciencia y Tecnologia (CONACyT) [14-INV-088, PINV15-315]; NSFNational Science Foundation (NSF) [1660648, DBI 1759934, IIS1763246, DBI-1458477, 0965768, DMR-1420073, DBI-1458443]; NIHUnited States Department of Health & Human ServicesNational Institutes of Health (NIH) - USA [R01GM093123, DP1MH110234, UL1 TR002319, U24 TR002306]; Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany's Excellence Strategy-EXC 2155 "RESIST"German Research Foundation (DFG) [39087428]; National Institutes of HealthUnited States Department of Health & Human ServicesNational Institutes of Health (NIH) - USA [R01GM123055, R01GM60595, R15GM120650, GM083107, GM116960, AI134678, NIH R35-GM128637, R00-GM097033]; ERCEuropean Research Council (ERC) [StG 757700]; Spanish Ministry of Science, Innovation and Universities [BFU2017-89833-P]; Severo Ochoa award; Centre of Excellence project "BioProspecting of Adriatic Sea"; Croatian Government; European Regional Development FundEuropean Union (EU) [KK.01.1.1.01.0002]; ATT Tieto kayttoon grant; Academy of FinlandAcademy of Finland; University of Turku; CSC-IT Center for Science Ltd.; University of Miami; National Cancer Institute of the National Institutes of HealthUnited States Department of Health & Human ServicesNational Institutes of Health (NIH) - USANIH National Cancer Institute (NCI) [U01CA198942]; Helsinki Institute for Life Sciences; Academy of FinlandAcademy of Finland [292589]; National Natural Science Foundation of ChinaNational Natural Science Foundation of China [31671367, 31471245, 91631301, 61872094, 61572139]; National Key Research and Development Program of China [2016YFC1000505, 2017YFC0908402]; Italian Ministry of Education, University and Research (MIUR) PRIN 2017 projectMinistry of Education, Universities and Research (MIUR) [2017483NH8]; Shanghai Municipal Science and Technology Major Project [2017SHZDZX01, 2018SHZDZX01]; UK Biotechnology and Biological Sciences Research CouncilBiotechnology and Biological Sciences Research Council (BBSRC) [BB/N019431/1, BB/L020505/1, BB/L002817/1]; Elsevier; Extreme Science and Engineering Discovery Environment (XSEDE) award [MCB160101, MCB160124]; Ministry of Education, Science and Technological Development of the Republic of Serbia [173001]; Taiwan Ministry of Science and Technology [106-2221-E-004-011-MY2]; Montana State University; Bavarian Ministry for Education; Simons Foundation; NIH NINDSUnited States Department of Health & Human ServicesNational Institutes of Health (NIH) - USANIH National Institute of Neurological Disorders & Stroke (NINDS) [1R21NS103831-01]; University of Illinois at Chicago (UIC) Cancer Center award; UIC College of Liberal Arts and Sciences Faculty Award; UIC International Development Award; Yad Hanadiv [9660/2019]; National Institute of General Medical Science of the National Institute of Health [GM066099, GM079656]; Research Supporting Plan (PSR) of University of Milan [PSR2018-DIP-010-MFRAS]; Swiss National Science FoundationSwiss National Science Foundation (SNSF) [150654]; EMBL-European Bioinformatics Institute core funds; CAFA BBSRC [BB/N004876/1]; European Union's Horizon 2020 research and innovation program under the Marie Sklodowska-Curie grantEuropean Union (EU) [778247]; COST ActionEuropean Cooperation in Science and Technology (COST) [BM1405]; NIH/NIGMSUnited States Department of Health & Human ServicesNational Institutes of Health (NIH) - USANIH National Institute of General Medical Sciences (NIGMS) [R01 GM071749]; National Human Genome Research Institute of the National of Health [U41 HG007234]; INB Grant (ISCIII-SGEFI/ERDF) [PT17/0009/0001]; TUBITAKTurkiye Bilimsel ve Teknolojik Arastirma Kurumu (TUBITAK) [EEEAG-116E930]; KanSil [2016K121540]; Universita degli Studi di Milano; 111 ProjectMinistry of Education, China - 111 Project [B18015]; key project of Shanghai Science Technology [16JC1420402]; ZJLab; project Ribes Network POR-FESR 3S4H [TOPP-ALFREVE18-01]; PRID/SID of University of Padova [TOPP-SID19-01]; NIGMSUnited States Department of Health & Human ServicesNational Institutes of Health (NIH) - USANIH National Institute of General Medical Sciences (NIGMS) [R15GM120650]; King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR) [URF/1/3454-01-01, URF/1/3790-01-01]; "the Human Project from Mind, Brain and Learning" of the NCCU Higher Education Sprout Project by the Taiwan Ministry of Education; National Center for High-performance ComputingIstanbul Technical University, The work of IF was funded, in part, by the National Science Foundation award DBI-1458359. The work of CSG and AJL was funded, in part, by the National Science Foundation award DBI-1458390 and GBMF 4552 from the Gordon and Betty Moore Foundation. The work of DAH and KAL was funded, in part, by the National Science Foundation award DBI-1458390, National Institutes of Health NIGMS P20 GM113132, and the Cystic Fibrosis Foundation CFRDP STANTO19R0. The work of AP, HY, AR, and MT was funded by BBSRC grants BB/K004131/1, BB/F00964X/1 and BB/M025047/1, Consejo Nacional de Ciencia y Tecnologia Paraguay (CONACyT) grants 14-INV-088 and PINV15-315, and NSF Advances in BioInformatics grant 1660648. The work of JC was partially supported by an NIH grant (R01GM093123) and two NSF grants (DBI 1759934 and IIS1763246). ACM acknowledges the support by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany's Excellence Strategy -EXC 2155 "RESIST" - Project ID 39087428. DK acknowledges the support from the National Institutes of Health (R01GM123055) and the National Science Foundation (DMS1614777, CMMI1825941). PB acknowledges the support from the National Institutes of Health (R01GM60595). GB and BZK acknowledge the support from the National Science Foundation (NSF 1458390) and NIH DP1MH110234. FS was funded by the ERC StG 757700 "HYPER-INSIGHT" and by the Spanish Ministry of Science, Innovation and Universities grant BFU2017-89833-P. FS further acknowledges the funding from the Severo Ochoa award to the IRB Barcelona. TS was funded by the Centre of Excellence project "BioProspecting of Adriatic Sea", co-financed by the Croatian Government and the European Regional Development Fund (KK.01.1.1.01.0002). The work of SK was funded by ATT Tieto kayttoon grant and Academy of Finland. JB and HM acknowledge the support of the University of Turku, the Academy of Finland and CSC -IT Center for Science Ltd. TB and SM were funded by the NIH awards UL1 TR002319 and U24 TR002306. The work of CZ and ZW was funded by the National Institutes of Health R15GM120650 to ZW and start-up funding from the University of Miami to ZW. The work of PWR was supported by the National Cancer Institute of the National Institutes of Health under Award Number U01CA198942. PR acknowledges NSF grant DBI-1458477. PT acknowledges the support from Helsinki Institute for Life Sciences. The work of AJM was funded by the Academy of Finland (No. 292589). The work of FZ and WT was funded by the National Natural Science Foundation of China (31671367, 31471245, 91631301) and the National Key Research and Development Program of China (2016YFC1000505, 2017YFC0908402]. CS acknowledges the support by the Italian Ministry of Education, University and Research (MIUR) PRIN 2017 project 2017483NH8. SZ is supported by the National Natural Science Foundation of China (No. 61872094 and No. 61572139) and Shanghai Municipal Science and Technology Major Project (No. 2017SHZDZX01). PLF and RLH were supported by the National Institutes of Health NIH R35-GM128637 and R00-GM097033. JG, DTJ, CW, DC, and RF were supported by the UK Biotechnology and Biological Sciences Research Council (BB/N019431/1, BB/L020505/1, and BB/L002817/1) and Elsevier. The work of YZ and CZ was funded in part by the National Institutes of Health award GM083107, GM116960, and AI134678; the National Science Foundation award DBI1564756; and the Extreme Science and Engineering Discovery Environment (XSEDE) award MCB160101 and MCB160124.; The work of BG, VP, RD, NS, and NV was funded by the Ministry of Education, Science and Technological Development of the Republic of Serbia, Project No. 173001. The work of YWL, WHL, and JMC was funded by the Taiwan Ministry of Science and Technology (106-2221-E-004-011-MY2). YWL, WHL, and JMC further acknowledge the support from "the Human Project from Mind, Brain and Learning" of the NCCU Higher Education Sprout Project by the Taiwan Ministry of Education and the National Center for High-performance Computing for computer time and facilities. The work of IK and AB was funded by Montana State University and NSF Advances in Biological Informatics program through grant number 0965768. BR, TG, and JR are supported by the Bavarian Ministry for Education through funding to the TUM. The work of RB, VG, MB, and DCEK was supported by the Simons Foundation, NIH NINDS grant number 1R21NS103831-01 and NSF award number DMR-1420073. CJJ acknowledges the funding from a University of Illinois at Chicago (UIC) Cancer Center award, a UIC College of Liberal Arts and Sciences Faculty Award, and a UIC International Development Award. The work of ML was funded by Yad Hanadiv (grant number 9660/2019). The work of OL and IN was funded by the National Institute of General Medical Science of the National Institute of Health through GM066099 and GM079656. Research Supporting Plan (PSR) of University of Milan number PSR2018-DIP-010-MFRAS. AWV acknowledges the funding from the BBSRC (CASE studentship BB/M015009/1). CD acknowledges the support from the Swiss National Science Foundation (150654). CO and MJM are supported by the EMBL-European Bioinformatics Institute core funds and the CAFA BBSRC BB/N004876/1. GG is supported by CAFA BBSRC BB/N004876/1. SCET acknowledges funding from the European Union's Horizon 2020 research and innovation program under the Marie Sklodowska-Curie grant agreement No 778247 (IDPfun) and from COST Action BM1405 (NGP-net). SEB was supported by NIH/NIGMS grant R01 GM071749. The work of MLT, JMR, and JMF was supported by the National Human Genome Research Institute of the National of Health, grant numbers U41 HG007234. The work of JMF and JMR was also supported by INB Grant (PT17/0009/0001 - ISCIII-SGEFI/ERDF). VA acknowledges the funding from TUBITAK EEEAG-116E930. RCA acknowledges the funding from KanSil 2016K121540. GV acknowledges the funding from Universita degli Studi di Milano - Project "Discovering Patterns in Multi-Dimensional Data" and Project "Machine Learning and Big Data Analysis for Bioinformatics". SZ is supported by the National Natural Science Foundation of China (No. 61872094 and No. 61572139) and Shanghai Municipal Science and Technology Major Project (No. 2017SHZDZX01). RY and SY are supported by the 111 Project (NO. B18015), the key project of Shanghai Science & Technology (No. 16JC1420402), Shanghai Municipal Science and Technology Major Project (No. 2018SHZDZX01), and ZJLab. ST was supported by project Ribes Network POR-FESR 3S4H (No. TOPP-ALFREVE18-01) and PRID/SID of University of Padova (No. TOPP-SID19-01). CZ and ZW were supported by the NIGMS grant R15GM120650 to ZW and start-up funding from the University of Miami to ZW. The work of MK and RH was supported by the funding from King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR) under Award No. URF/1/3454-01-01 and URF/1/3790-01-01. The work of SDM is funded, in part, by NSF award DBI-1458443.

“Gebze’de Âşıklık Geleneği” adlı bu yüksek lisans tezinde, öncelikle Gebze’nin tarihî geçmişi, coğrafî özellikleri, nüfus ve ekonomik yapısı, sosyokültürel yapısı üzerinde durulmuştur. Âşıklığın tanımı ve içeriği, oluşumundan günümüze âşıklık geleneği açıklanmıştır. Tarihî süreçte Gebze’ye yapılan göçler ve geleneğin taşınması, Gebze'de âşıklık geleneğinin oluşumunu sağlayan Kars, Erzurum ve Ardahan’daki geleneğin Gebze’deki icra biçimleri, âşıkların Gebze'deki icra ortamları, elektronik kültür ortamlarından faydalanma süreçleri ve geleneğin elektronik kültür ortamına bağlı yaşadığı değişim ele alınmıştır. Ayrıca geleneğin unsurlarının geleceğe ne şekilde ve ne derece taşındığı, Gebze’ye göçlerin nedenleri ve bunun geleneğe olan etkileri Gebze Âşıklar, Şairler, Ozanlar ve Edebiyatçılar Derneği ve Gedikler Kültür Evinden âşıkların ne derece yararlandığı ile alakalı veriler yapılan derlemeler sonucu elde edilmiştir. Elde edilen sonuçlar, halk bilimsel açıdan ele alınmıştır. In this postgraduate thesis named “Minstrelsy Tradition in Gebze”, the historical background, demographic and economic structure and socio-cultural status of Gebze is stressed. The definition and content, since its origin and its path to today, Minstrelsy tradition is expressed. Throughout the historical period, the migrations and the transfer of this tradition to Gebze along with the Minstrels’ various performing forms and atmospheres, which emerged in Kars, Erzurum and Ardahan, their utilization processes from electronical platforms along with the evolutionary period of this tradition related to electronical culture context are covered in this thesis. In addition, the extent and way of transferring the elements of this tradition to the future, the reasons of migration to Gebze, how Minstrels benefit from “Minstrels, Poets and Men of Letters Society” and “Gedik Culture House” are concluded thanks to the compilations gathered during this study. The collected outcomes are handled in terms of social sciences.

WOS: 000519240000025, The identification of physical interactions between drug candidate compounds and target biomolecules is an important process in drug discovery. Since conventional screening procedures are expensive and time consuming, computational approaches are employed to provide aid by automatically predicting novel drug-target interactions (DTIs). In this study, we propose a large-scale DTI prediction system, DEEPScreen, for early stage drug discovery, using deep convolutional neural networks. One of the main advantages of DEEPScreen is employing readily available 2-D structural representations of compounds at the input level instead of conventional descriptors that display limited performance. DEEPScreen learns complex features inherently from the 2-D representations, thus producing highly accurate predictions. The DEEPScreen system was trained for 704 target proteins (using curated bioactivity data) and finalized with rigorous hyper-parameter optimization tests. We compared the performance of DEEPScreen against the state-of-the-art on multiple benchmark datasets to indicate the effectiveness of the proposed approach and verified selected novel predictions through molecular docking analysis and literature-based validation. Finally, JAK proteins that were predicted by DEEPScreen as new targets of a well-known drug cladribine were experimentally demonstrated in vitro on cancer cells through STAT3 phosphorylation, which is the downstream effector protein. The DEEPScreen system can be exploited in the fields of drug discovery and repurposing for in silico screening of the chemogenomic space, to provide novel DTIs which can be experimentally pursued. The source code, trained "ready-to-use" prediction models, all datasets and the results of this study are available at ; https://github.com/cansyl/DEEPscreen., TUBITAK, TurkeyTurkiye Bilimsel ve Teknolojik Arastirma Kurumu (TUBITAK); British Council, UK [116E930]; European Molecular Biology Laboratory core funds, This work was supported by the Newton/Katip Celebi Institutional Links program by TUBITAK, Turkey and British Council, UK (project no: 116E930, project acronym: CROssBAR), and the European Molecular Biology Laboratory core funds.

Motivation: Similarity-based methods have been widely used in order to infer the properties of genes and gene products containing little or no experimental annotation. New approaches that overcome the limitations of methods that rely solely upon sequence similarity are attracting increased attention. One of these novel approaches is to use the organization of the structural domains in proteins. Results: We propose a method for the automatic annotation of protein sequences in the UniProt Knowledgebase (UniProtKB) by comparing their domain architectures, classifying proteins based on the similarities and propagating functional annotation. The performance of this method was measured through a cross-validation analysis using the Gene Ontology (GO) annotation of a sub-set of UniProtKB/Swiss-Prot. The results demonstrate the effectiveness of this approach in detecting functional similarity with an average F-score: 0.85. We applied the method on nearly 55.3 million uncharacterized proteins in UniProtKB/TrEMBL resulted in 44 818 178 GO term predictions for 12 172 114 proteins. 22% of these predictions were for 2 812 016 previously non-annotated protein entries indicating the significance of the value added by this approach. Availability and implementation: The results of the method are available at: ftp://ftp.ebi.ac.uk/pub/contrib/martin/DAAC/. Contact: tdogan@ebi.ac.uk Supplementary information: Supplementary data are available at Bioinformatics online.

Computational methods are more commonly employed for our understanding of cellular signaling mechanisms with the aim to develop cures for diseases including cancer. Identification of disease specific targeted drugs requires systems level analysis of cellular networks. Our research group developed a comprehensive resource, called CROssBAR, which connects various biological data sources in order to provide a well-connected resource with a focus on drug discovery and precision medicine. CROssBAR aims to predict and reveal novel drug-target interactions using deep learning algorithms. CROssBAR predictions were validated on hepatocellular carcinoma cells which is the 5th most prevalent and 3th deadliest cancer worldwide. We have selected 2 new small molecule kinase inhibitors Lenvatinib, Sunitinib along with Sorafenib and Regorafenib which are currently used in clinics. CROssBAR identifies novel and known gene targets for Lenvatinib, Sunitinib in comparison with Sorafenib and Regorafenib. Genes from SAPK/JNK and PI3K/Akt pathway that were not previously associated with hepatocellular carcinoma therapeutics were determined. All selected small molecules were bioactive on Huh7 and Mahlavu cells by SRB assay. Cell death was characterized by Annexin V which was due to G1/S cell cycle arrest. Further analysis of proteins involved in the SAPK/JNK, PI3K/Akt pathways and apoptotic markers such as PARP and Caspases were examined with immunoblotting upon treatment. As a result, cellular stress mechanisms activated PI3K/Akt and SAPK/JNK pathways which caused programmed cell death in HCC. With our deep learning approach, we were able to demonstrate a correlation between Lenvatinib and Sunitinib and their novel targets in HCC. Our validation results have illustrated that the comprehensive CROssBAR tool developed by our research group achieved in vitro significant predictions of new drugs and their targets against HCC that were not previously reported. Hence with this study we were able to demonstrate the use and validity of the CROssBAR tool along with new targets for primary liver cancer therapeutics. Citation Format: Esra Nalbat, Ahmet Sureyya Rifaioglu, Tunca Dogan, Maria Jesus Martin, Rengul Cetin-Atalay, Volkan Atalay. In vitro validation of drug-target interactions revealed in silico by Comprehensive Resource of Biomedical Relations with Network Representations and Deep Learning (CROssBAR) in HCC [abstract]. In: Proceedings of the Annual Meeting of the American Association for Cancer Research 2020; 2020 Apr 27-28 and Jun 22-24. Philadelphia (PA): AACR; Cancer Res 2020;80(16 Suppl):Abstract nr 5235.

WOS: 000445215600004, 30241466, Science Citation Index Expanded, 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., YOK OYP scholarships, AD and ASR were supported by YOK OYP scholarships. The funding body did not play any role in the design of the study and collection, analysis, and interpretation of data and in writing the manuscript.

Analysing the relationships between biomolecules and the genetic diseases is a highly active area of research, where the aim is to identify the genes and their products that cause a particular disease due to functional changes originated from mutations. Biological ontologies are frequently employed in these studies, which provided researchers with extensive opportunities for knowledge discovery through computational data analysis. In this study, a novel approach is proposed for the identification of relationships between biomedical entities by automatically mapping phenotypic abnormality defining HPO terms with biomolecular function defining GO terms, where each association indicates the occurrence of the abnormality due to the loss of the biomolecular function expressed by the corresponding GO term. The proposed HPO2GO mappings were extracted by calculating the frequency of the co-annotations of the terms on the same genes/proteins, using already existing curated HPO and GO annotation sets. This was followed by the filtering of the unreliable mappings that could be observed due to chance, by statistical resampling of the co-occurrence similarity distributions. Furthermore, the biological relevance of the finalized mappings were discussed over selected cases, using the literature. The resulting HPO2GO mappings can be employed in different settings to predict and to analyse novel gene/protein - ontology term - disease relations. As an application of the proposed approach, HPO term - protein associations (i.e., HPO2protein) are predicted. In order to test the predictive performance of the method on a quantitative basis, and to compare it with the state-of-the-art, CAFA2 challenge HPO prediction target protein set was employed. The results of the benchmark indicated the potential of the proposed approach, as HPO2GO beat all models from 38 participating groups (with Fmax=0.402), by a margin of 12.6% compared to the top performer. It is important to note that, HPO2GO was not proposed to replace, but to complement the conventional approaches used in the field of biomedical relation discovery. The automated cross ontology mapping approach developed in this work can easily be extended to other ontologies as well, to identify unexplored relation patterns at the systemic level. The proposed approach will be more effective when combined with powerful techniques such as text/literature mining. The datasets, results and the source code of HPO2GO are available for download at: https://github.com/cansyl/HPO2GO.

Proteins use their functional regions to exploit various activities, including binding to other proteins, nucleic acids, or drugs. Functional sites of the proteins have a tendency to be more conserved than the rest of the protein surface. Therefore, detection of the conserved residues using phylogenetic analysis is a general approach to predict functionally critical residues. In this chapter, we describe some of the available methods to predict functional sites and demonstrate a complete pipeline with tool alternatives at several steps. We explain the standard procedure and all intermediate stages including homology detection with BLAST search, multiple sequence alignment (MSA) and the construction of a phylogenetic tree for a given query sequence. Additionally, we demonstrate the prediction results of these methods on a case study. Finally, we discuss the possible challenges and bottlenecks throughout the pipeline. Our step-by-step description about the functional site prediction could be a helpful resource for the researchers interested in finding protein functional sites, to be used in drug discovery research.

Proteins use their functional regions to exploit various activities, including binding to other proteins, nucleic acids, or drugs. Functional sites of the proteins have a tendency to be more conserved than the rest of the protein surface. Therefore, detection of the conserved residues using phylogenetic analysis is a general approach to predict functionally critical residues. In this chapter, we describe some of the available methods to predict functional sites and demonstrate a complete pipeline with tool alternatives at several steps. We explain the standard procedure and all intermediate stages including homology detection with BLAST search, multiple sequence alignment (MSA) and the construction of a phylogenetic tree for a given query sequence. Additionally, we demonstrate the prediction results of these methods on a case study. Finally, we discuss the possible challenges and bottlenecks throughout the pipeline. Our step-by-step description about the functional site prediction could be a helpful resource for the researchers interested in finding protein functional sites, to be used in drug discovery research.

Protein-Protein Interactions (PPIs) are the key components in many cellular processes including signaling pathways, enzymatic reactions and epigenetic regulation. Abnormal interactions of some proteins may be pathogenic and cause various disorders including cancer and neurodegenerative diseases. Although inhibiting PPIs with small molecules is a challenging task, it gained an increasing interest because of its strong potential for drug discovery and design. The knowledge of the interface as well as the structural and chemical characteristics of the PPIs and their roles in the cellular pathways is necessary for a rational design of small molecules to modulate PPIs. In this study, we review the recent progress in the field and detail the physicochemical properties of PPIs including binding hot spots with a focus on structural methods. Then, we review recent approaches for structural prediction of PPIs. Finally, we revisit the concept of targeting PPIs from a systems biology perspective and we refer to approaches that are usually employed when the structural information is not present.

WOS: 000419819500001, 29098713, Recent advances in computing power and machine learning empower functional annotation of protein sequences and their transcript variations. Here, we present an automated prediction system UniGOPred, for GO annotations and a database of GO term predictions for proteomes of several organisms in UniProt Knowledgebase (UniProtKB). UniGOPred provides function predictions for 514 molecular function (MF), 2909 biological process (BP), and 438 cellular component (CC) GO terms for each protein sequence. UniGOPred covers nearly the whole functionality spectrum in Gene Ontology system and it can predict both generic and specific GO terms. UniGOPred was run on CAFA2 challenge target protein sequences and it is categorized within the top 10 best performing methods for the molecular function category. In addition, the performance of UniGOPred is higher compared to the baseline BLAST classifier in all categories of GO. UniGOPred predictions are compared with UniProtKB/TrEMBL database annotations as well. Furthermore, the proposed tool's ability to predict negatively associated GO terms that defines the functions that a protein does not possess, is discussed. UniGOPred annotations were also validated by case studies on PTEN protein variants experimentally and on CHD8 protein variants with literature. UniGOPred protein functional annotation system is available as an open access tool at ., TUBITAK 1001 Grants [110S388, 105E035]; KanSiL project, TR Ministry of Development; YOK OYP scholarships, We thank Dr. Bill Pearson for UniGOPred predictions related discussion and Dr. Evan E. Eichler for CHD8 and Autism related discussions. This work was supported by TUBITAK 1001 Grants 110S388 and 105E035 and by KanSiL project, TR Ministry of Development. A.S.R. was supported by YOK OYP scholarships.

The mission of the Universal Protein Resource (UniProt) (http://www.uniprot.org) is to provide the scientific community with a comprehensive, high-quality and freely accessible resource of protein sequences and functional annotation. It integrates, interprets and standardizes data from literature and numerous resources to achieve the most comprehensive catalog possible of protein information. The central activities are the biocuration of the UniProt Knowledgebase and the dissemination of these data through our Web site and web services. UniProt is produced by the UniProt Consortium, which consists of groups from the European Bioinformatics Institute (EBI), the SIB Swiss Institute of Bioinformatics (SIB) and the Protein Information Resource (PIR). UniProt is updated and distributed every 4 weeks and can be accessed online for searches or downloads.

InterPro is a widely used database that integrates functional signatures provided by different protein sequence annotation databases with manual curation; in order to present a comprehensive database of functional sequence annotation. However, the integration of the signatures causes inconsistent and/or redundant annotations in some cases. In this study, we proposed an unsupervised method for the automatic detection of inconsistent and redundant entries in the InterPro database. Two clustering methods: Markov Cluster Algorithm (MCL) and hierarchical clustering are employed in order to investigate to what extent these signatures can be detected. Results show that a considerable amount of (~75%) redundant entries can be identified. The future goal is to develop a system that does the identification of redundant and inconsistent signatures with very high performance using machine learning techniques in a supervised fashion. The findings of the study may aid InterPro curators to fix the problematic entries. It may also be used by curators as a road map before the integration of new signatures.

UniProt is an important collection of protein sequences and their annotations, which has doubled in size to 80 million sequences during the past year. This growth in sequences has prompted an extension of UniProt accession number space from 6 to 10 characters. An increasing fraction of new sequences are identical to a sequence that already exists in the database with the majority of sequences coming from genome sequencing projects. We have created a new proteome identifier that uniquely identifies a particular assembly of a species and strain or subspecies to help users track the provenance of sequences. We present a new website that has been designed using a user-experience design process. We have introduced an annotation score for all entries in UniProt to represent the relative amount of knowledge known about each protein. These scores will be helpful in identifying which proteins are the best characterized and most informative for comparative analysis. All UniProt data is provided freely and is available on the web at http://www.uniprot.org/.

10th IASTED International Conference on Biomedical Engineering, BioMed 2013; Innsbruck; Austria; 13 February 2013 through 15 February 2013, Multiple sequence alignment (MSA) is a widely used method to uncover the relationships between the biomolecular sequences. One essential prerequisite to apply this procedure is to have a considerable amount of similarity between the test sequences. It's usually not possible to obtain reliable results from the multiple alignments of large and diverse datasets. Here we propose a method to obtain sequence clusters of significant intragroup similarities and make sense out of the multiple alignments containing remote sequences. This is achieved by thresholding the pairwise connectivity map over 2 parameters. The first one is the inferred pairwise evolutionary distances and the second parameter is the number of gapless positions on the pairwise comparisons of the alignment. Threshold curves are generated regarding the statistical parameter values obtained from a shuffled dataset and probability distribution techniques are employed to select an optimum threshold curve that eliminate as much of the unreliable connectivities while keeping the reliable ones. We applied the method on a large and diverse dataset composed of nearly 18000 human proteins and measured the biological relevance of the recovered connectivities. Our precision measure (0.981) was nearly 20% higher than the one for the connectivities left after a classical thresholding procedure displaying a significant improvement. Finally we employed the method for the functional clustering of protein sequences in a gold standard dataset. We have also measured the performance, obtaining a higher F-measure (0.882) compared to a conventional clustering operation (0.827).

Contains fulltext : 171819.pdf (Publisher’s version ) (Open Access) Life sciences are yielding huge data sets that underpin scientific discoveries fundamental to improvement in human health, agriculture and the environment. In support of these discoveries, a plethora of databases and tools are deployed, in technically complex and diverse implementations, across a spectrum of scientific disciplines. The corpus of documentation of these resources is fragmented across the Web, with much redundancy, and has lacked a common standard of information. The outcome is that scientists must often struggle to find, understand, compare and use the best resources for the task at hand.Here we present a community-driven curation effort, supported by ELIXIR-the European infrastructure for biological information-that aspires to a comprehensive and consistent registry of information about bioinformatics resources. The sustainable upkeep of this Tools and Data Services Registry is assured by a curation effort driven by and tailored to local needs, and shared amongst a network of engaged partners.As of November 2015, the registry includes 1785 resources, with depositions from 126 individual registrations including 52 institutional providers and 74 individuals. With community support, the registry can become a standard for dissemination of information about bioinformatics resources: we welcome everyone to join us in this common endeavour. The registry is freely available at https://bio.tools.