Biology subjects

Dogan, T.

Publications and source records attributed to Dogan, T..

15 recordsLinked to original sources

bioRxiv2026

On the state of protein function prediction: a report on the fourth CAFA challenge

BackgroundThe Critical Assessment of Functional Annotation (CAFA) is a community effort held to understand the field of computational protein function prediction. Every three years, since 2010, the organizers initiate an experiment to collect function predictions on a large set of proteins and then evaluate the performance of predicting methods on a subset of proteins that have accumulated experimental annotations between the submission deadline and the evaluation time. CAFA provides an independent and rigorous assessment of the current state of the art, thus leveling the playing field, highlighting successes, revealing bottlenecks, and offering a forum for the exchange of ideas in protein science. Here, we report the results of the fourth CAFA experiment (CAFA4). ResultsCAFA4 featured the participation of 148 methods from 70 research groups on a total of 46,205 unique proteins over a 5-year annotation accumulation phase, the longest in any CAFA. In a comparison across CAFA2-CAFA4 methods, the prediction of Gene Ontology (GO) terms has clearly improved across all three GO aspects and traditional evaluation settings. While not achieving the first rank, several CAFA2 and CAFA3 methods featured in the top ten methods in many evaluations, suggesting that earlier methods still hold relevance. The performance is weaker in the newly introduced "partial knowledge" evaluation category (proteins with experimental annotations before submission deadline that gained additional annotations in the same GO aspect during the annotation accumulation phase), highlighting the need for a new class of methods. The rankings of the methods were stable over the years in traditional evaluation settings, but less so in the new partial knowledge evaluation. Overall, the field continues to progress with some influx of new participants. Sustained efforts will be necessary to substantially advance it.

bioinformatics↗

bioRxiv2026

CROssBARv2: A Unified Computational Framework for Heterogeneous Biomedical Data Representation and LLM-Driven Exploration

Biomedical discovery is hindered by fragmented, modality-specific repositories and uneven metadata, limiting integrative analysis, accessibility, and reproducibility. To address these challenges, we present CROssBARv2, a provenance-rich biomedical data-and-knowledge integration platform that unifies heterogeneous sources into a maintainable, scalable system. By consolidating diverse data types into an extensive knowledge graph enriched with standardised ontologies, rich metadata, and deep learning-based vector embeddings, CROssBARv2 alleviates the need for researchers to navigate multiple siloed databases and can facilitate downstream tasks, including predictive modelling and mechanistic reasoning, enabling applications such as drug repurposing and protein function prediction. The platform offers interactive graph exploration and embedding-based semantic search with CROssBAR-LLM, an intuitive natural language question-answering system that grounds large language model (LLM) outputs in the underlying knowledge graph to mitigate hallucinations. We assess CROssBARv2 through (i) multiple use-case analyses to test biological coherence and relational validity; (ii) knowledge-augmented biomedical question-answering benchmarks comparing CROssBAR-LLM against generalist LLMs; and (iii) a deep learning-based predictive modelling experiment for protein function prediction leveraging the heterogeneous structure of CROssBARv2. Collectively, CROssBARv2 provides a scalable, AI-ready, and user-friendly foundation that facilitates hypothesis generation, knowledge discovery, and translational research.

bioinformatics↗

bioRxiv2026

SELFormerMM: multimodal molecular representation learning via SELFIES, structure, text, and knowledge graph integration

MotivationMolecular representation learning is central to computational drug discovery. However, most existing models rely on single-modality inputs, such as molecular sequences or graphs, which capture only limited aspects of molecular behaviour. Yet unifying these modalities with complementary resources such as textual descriptions and biological interaction networks into a coherent multimodal framework remains non-trivial, hindering more informative and biologically grounded representations. ResultsWe introduce SELFormerMM, a multimodal molecular representation learning framework that integrates SELFIES notations with structural graphs, textual descriptions, and knowledge graph- derived biological interaction data. By aligning these heterogeneous views, SELFormerMM effectively captures complementary signals that unimodal approaches often overlook. Our performance evaluation has revealed that SELFormerMM outperforms structure-, sequence-, and knowledge-based models on multiple molecular property prediction tasks. Ablation analyses further indicate that effective cross-modal alignment and modality coverage improve the models ability to exploit complementary information. Overall, integrating SELFIES with structural, textual, and biological context enables richer molecular representations and provides a promising framework for hypothesis-driven drug discovery. AvailabilitySELFormerMM is available as a programmatic tool, together with datasets, pretrained models, and precomputed embeddings at https://github.com/HUBioDataLab/SELFormerMM. Contacttuncadogan@gmail.com

bioinformatics↗

bioRxiv2025

ECLIPSE: Exploration of Complex Ligand-Protein Interactions through Learning from Systems-level Heterogeneous Biomedical Knowledge Graphs

Discovering new, efficacious molecules remains slow and costly; rigorous data science-driven systems-level approaches are therefore essential to prioritise hypotheses and de-risk drug development. In this study, we present ECLIPSE, a systems-level framework for compound/ligand-protein interaction (CPI) representation and prediction, combining heterogeneous knowledge graphs (KGs), which encode large-scale entity-relation structure, with graph neural networks that exploit relational inductive biases to perform inference on graph-structured data. ECLIPSE uses our comprehensive biomedical KG-based platform, CROssBAR, incorporating genes/proteins, drugs, compounds, pathways, diseases, and phenotypes, along with their multi-layered relationships. Each entity is assigned input features derived from language or graph representation learning models and projected via type-specific neural network layers. To process these featurized biomedical KGs for bioactivity prediction, we employed the heterogeneous graph transformer (HGT) architecture. In contrast to the majority of GNN algorithms, which are restricted to homogenous graphs, HGT can handle graph heterogeneity and maintain node-and edge-type dependent representations through its attention mechanism. ECLIPSE achieves strong performance on challenging, protein-family- specific CPI benchmarks compared with baseline and state-of-the-art methods; ablations confirm performance gains from modelling graph heterogeneity and all feature sources. Use-case analyses on a druggable kinase (PIM1) and a historically undruggable receptor (HER3) illustrate generalizability across target classes and activity ranges. By leveraging direct and indirect relationships embedded in biomedical KGs, ECLIPSE provides context-aware CPI inference that is scalable to real-world settings. Code, datasets, and trained models are released to support reproducibility and reuse.

bioinformatics↗

bioRxiv2025

Molecular Contrastive Learning with Graph Attention Network (MoCL-GAT) for Enhanced Molecular Representation

Learning the representation of molecules is crucial for drug discovery but is often hindered by the scarcity of labeled experimental data, which limits the performance of supervised machine learning models. While self-supervised learning (SSL) offers a solution by leveraging vast unlabeled chemical databases, many existing methods focus on learning from either local structural information or global molecular properties, but not both simultaneously. We introduce MoCL-GAT, a novel contrastive and transfer learning-based SSL framework that addresses this gap by simultaneously learning from two complementary objectives. It combines a local contrastive task on molecular subgraphs to capture fine-grained chemical environments with a global predictive task to learn holistic molecular descriptors. This dual-objective approach, powered by a Graph Attention Network, is designed to create more robust, versatile, and transferable molecular representations. Pre-trained on 1.9 million compounds, MoCL-GAT was fine-tuned on diverse benchmarks. It achieved state-of-the-art performance on molecular property prediction tasks, with an AUROC of 0.928 on BBBP and 0.749 on SIDER, and top-ranking RMSEs of 0.570 for ESOL and 1.818 for FreeSolv. Critically, fine-tuned models consistently and significantly outperformed models trained from scratch, confirming the value of pre-training. These results validate that MoCL-GATs dual-objective approach learns highly effective and transferable representations, enabling more accurate and data-efficient predictions for key cheminformatics challenges.

bioinformatics↗

bioRxiv2025

OmniPath: integrated knowledgebase for multi-omics analysis

Analysis and interpretation of omics data largely benefit from the use of prior knowledge. However, this knowledge is fragmented across resources and often is not directly accessible for analytical methods. We developed OmniPath (https://omnipathdb.org/), a database combining diverse molecular knowledge from 168 resources. It covers causal protein-protein, gene regulatory, miRNA, and enzyme-PTM (post-translational modification) interactions, cell-cell communication, protein complexes, and information about the function, localization, structure, and many other aspects of biomolecules. It prioritizes literature curated data, and complements it with predictions and large scale databases. To enable interactive browsing of this large corpus of knowledge, we developed OmniPath Explorer, which also includes a large language model (LLM) agent that has direct access to the database. Python and R/Bioconductor client packages and a Cytoscape plugin create easy access to customized prior knowledge for omics analysis environments, such as scverse. OmniPath can be broadly used for the analysis of bulk, single-cell and spatial multi-omics data, especially for mechanistic and causal modeling. Graphical Abstract O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=79 SRC="FIGDIR/small/675512v1_ufig1.gif" ALT="Figure 1"> View larger version (27K): org.highwire.dtl.DTLVardef@17c2b6borg.highwire.dtl.DTLVardef@1069835org.highwire.dtl.DTLVardef@1f2ce76org.highwire.dtl.DTLVardef@1d0b34f_HPS_FORMAT_FIGEXP M_FIG C_FIG

bioinformatics↗

bioRxiv2025

ProtHGT: Heterogeneous Graph Transformers for Automated Protein Function Prediction Using Biological Knowledge Graphs and Language Models

MotivationThe rapid accumulation of protein sequence data, coupled with the slow pace of experimental annotations, creates a critical need for computational methods to predict protein functions. Existing models often rely on limited data types, such as sequence-based features or protein-protein interactions (PPIs), failing to capture the complex molecular relationships in biological systems. To address this, we developed ProtHGT, a heterogeneous graph transformer-based model that integrates diverse biological datasets into a unified framework using knowledge graphs for accurate and interpretable protein function prediction. ResultsProtHGT achieves state-of-the-art performance on benchmark datasets, demonstrating its ability to outperform current graph-based and sequence-based approaches. By leveraging diverse biological entity types and highly representative protein language model embeddings at the input level, the model effectively learns complex biological relationships, enabling accurate predictions across all Gene Ontology (GO) sub-ontologies. Ablation analyses highlight the critical role of heterogeneous data integration in achieving robust predictions. Finally, our use-case study has indicated that its possible to interpret ProtHGTs predictions via exploring the related parts of our input biological knowledge graph, offering plausible explanations to build or test new hypotheses. Availability and ImplementationProtHGT is available as a programmatic tool on Github and as a web service at Hugging Face. ContactTo whom the correspondence should be addressed: Tunca Do[g]an (tuncadogan@gmail.com)

bioinformatics↗

bioRxiv2025

A Benchmarking Platform for Assessing Protein Language Models on Function-related Prediction Tasks

Proteins play a crucial role in almost all biological processes, serving as the building blocks of life and mediating various cellular functions, from enzymatic reactions to immune responses. Accurate annotation of protein functions is essential for advancing our understanding of biological systems and developing innovative biotechnological applications and therapeutic strategies. To predict protein function, researchers primarily rely on classical homology-based methods, which use evolutionary relationships, and increasingly on machine learning (ML) approaches. Lately, protein language models (PLMs) have gained prominence; these models leverage specialised deep learning architectures to effectively capture intricate relationships between sequence, structure, and function. We recently conducted a comprehensive benchmarking study to evaluate diverse protein representations (i.e., classical approaches and PLMs) and discuss their trade-offs. The current work introduces the Protein Representation Benchmark - PROBE tool, a benchmarking framework designed to evaluate protein representations on function-related prediction tasks. Here, we provide a detailed protocol for running the framework via the GitHub repository and accessing our newly developed user-friendly web service. PROBE encompasses four core tasks: semantic similarity inference, ontology-based function prediction, drug target family classification, and protein-protein binding affinity estimation. We demonstrate PROBEs usage through a new use case evaluating ESM2 and three recent multimodal PLMs--ESM3, ProstT5, and SaProt--highlighting their ability to integrate diverse data types, including sequence and structural information. This study underscores the potential of protein language models in advancing protein function prediction and serves as a valuable tool for both PLM developers and users.

bioinformatics↗

bioRxiv2022

ASCARIS: Positional Feature Annotation and Protein Structure-Based Representation of Single Amino Acid Variations

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 at https://github.com/HUBioDataLab/ASCARIS.

bioinformatics↗

bioRxiv2022

Mutual Annotation-Based Prediction of Protein Domain Functions with Domain2GO

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 at https://github.com/HUBioDataLab/Domain2GO.

bioinformatics↗

bioRxiv2022

How to Best Represent Proteins in Machine Learning-based Prediction of Drug/Compound-Target Interactions

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 protein featurization (including both conventional approaches and the novel learned embeddings), data preparation and exploration, machine learning-based modeling, and performance evaluation with the aim of achieving better data representations and more successful learning in 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 datasets into train and test folds lead to near-complete data memorization and produce highly over-optimistic results, as a result, it should be avoided, (ii) learned protein sequence embeddings work well in DTI prediction and offer high potential, even though no information related to protein structures, interactions or biochemical properties is utilized during their generation, and (iii) PCM models tend to learn from compound features and leave out protein features, mostly due to the natural bias in DTI data, indicating the requirement for new and unbiased datasets. 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.

bioinformatics↗

bioRxiv2021

Protein Domain-Based Prediction of Compound-Target Interactions and Experimental Validation on LIM Kinases

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.

bioinformatics↗

bioRxiv2020

Evaluation of Methods for Protein Representation Learning: A Quantitative Analysis

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.

bioinformatics↗

bioRxiv2020

CROssBAR: Comprehensive Resource of Biomedical Relations with Deep Learning Applications and Knowledge Graph Representations

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 at https://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.

bioinformatics↗

bioRxiv2018

DEEPScreen: High Performance Drug-Target Interaction Prediction with Convolutional Neural Networks Using 2-D Structural Compound Representations

The identification of physical interactions between drug candidate chemical substances and target biomolecules is an important step in the process of drug discovery, where the standard procedure is the systematic screening of chemical compounds against pre-selected target proteins. However, experimental screening procedures are expensive and time consuming, therefore, it is not possible to carry out comprehensive tests. Within the last decade, computational approaches have been developed with the objective of aiding experimental studies by predicting novel drug-target interactions (DTI), via the construction and application of statistical models. In this study, we propose a large-scale DTI interaction prediction system, DEEPScreen, for early stage drug discovery, using convolutional deep neural networks. One of the main advantages of DEEPScreen is employing readily available simple 2-D images of compounds at the input level instead of engineered complex feature vectors that displayed limited performance in DTI prediction tasks previously. DEEPScreen learns complex features inherently from the 2-D molecular representations, thus producing highly accurate predictions. DEEPScreen system was trained for 704 target proteins (using ChEMBL curated bioactivity data) and finalized with rigorous hyper-parameter optimization tests. We compared the performance of DEEPScreen against shallow classifiers such as the random forest, logistic regression and support vector machines, to indicate the effectiveness of the proposed deep learning approach. Additionally, we compared DEEPScreen with other deep learning based state-of-the-art DTI predictors on widely used benchmark datasets and showed that DEEPScreen produces better or comparable results to the top performers. The method proposed here can be employed to computationally scan a large portion of the recorded drug candidate compound and protein spaces to aid the experimentalists working in the field of drug discovery and repurposing by providing a preselection of interesting novel DTIs.

bioinformatics↗