Advances and Challenges in Computational Target Prediction

Advancing drug discovery with deep attention neural networks

In the dynamic field of drug discovery, deep attention neural networks are revolutionizing our approach to complex data. This review explores the attention mechanism and its extended architectures, including graph attention networks (GATs), transformers, bidirectional encoder representations from transformers (BERT), generative pre-trained transformers (GPTs) and bidirectional and auto-regressive transformers (BART). Delving into their core principles and multifaceted applications, we uncover their pivotal roles in catalyzing de novo drug design, predicting intricate molecular properties and deciphering elusive drug-target interactions. Despite challenges, these attention-based architectures hold unparalleled promise to drive transformative breakthroughs and accelerate progress in pharmaceutical research.

Polypharmacology prediction: the long road toward comprehensively anticipating small-molecule selectivity to de-risk drug discovery

INTRODUCTION

Small molecules often bind to multiple targets, a behavior termed polypharmacology. Anticipating polypharmacology is essential for drug discovery since unknown off-targets can modulate safety and efficacy - profoundly affecting drug discovery success. Unfortunately, experimental methods to assess selectivity present significant limitations and drugs still fail in the clinic due to unanticipated off-targets. Computational methods are a cost-effective, complementary approach to predict polypharmacology.

AREAS COVERED

This review aims to provide a comprehensive overview of the state of polypharmacology prediction and discuss its strengths and limitations, covering both classical cheminformatics methods and bioinformatic approaches. The authors review available data sources, paying close attention to their different coverage. The authors then discuss major algorithms grouped by the types of data that they exploit using selected examples.

EXPERT OPINION

Polypharmacology prediction has made impressive progress over the last decades and contributed to identify many off-targets. However, data incompleteness currently limits most approaches to comprehensively predict selectivity. Moreover, our limited agreement on model assessment challenges the identification of the best algorithms - which at present show modest performance in prospective real-world applications. Despite these limitations, the exponential increase of multidisciplinary Big Data and AI hold much potential to better polypharmacology prediction and de-risk drug discovery.

CKG-IMC: An inductive matrix completion method enhanced by CKG and GNN for Alzheimer's disease compound-protein interactions prediction

Alzheimer's disease (AD) is one of the most prevalent chronic neurodegenerative disorders globally, with a rapidly growing population of AD patients and currently no effective therapeutic interventions available. Consequently, the development of therapeutic anti-AD drugs and the identification of AD targets represent one of the most urgent tasks. In this study, in addition to considering known drugs and targets, we explore compound-protein interactions (CPIs) between compounds and proteins relevant to AD. We propose a deep learning model called CKG-IMC to predict Alzheimer's disease compound-protein interaction relationships. CKG-IMC comprises three modules: a collaborative knowledge graph (CKG), a principal neighborhood aggregation graph neural network (PNA), and an inductive matrix completion (IMC). The collaborative knowledge graph is used to learn semantic associations between entities, PNA is employed to extract structural features of the relationship network, and IMC is utilized for CPIs prediction. Compared with a total of 16 baseline models based on similarities, knowledge graphs, and graph neural networks, our model achieves state-of-the-art performance in experiments of 10-fold cross-validation and independent test. Furthermore, we use CKG-IMC to predict compounds interacting with two confirmed AD targets, 42-amino-acid β-amyloid (Aβ42) protein and microtubule-associated protein tau (tau protein), as well as proteins interacting with five FDA-approved anti-AD drugs. The results indicate that the majority of predictions are supported by literature, and molecular docking experiments demonstrate a strong affinity between the predicted compounds and targets.

Testing the predictive power of reverse screening to infer drug targets, with the help of machine learning

Estimating protein targets of compounds based on the similarity principle-similar molecules are likely to show comparable bioactivity-is a long-standing strategy in drug research. Having previously quantified this principle, we present here a large-scale evaluation of its predictive power for inferring macromolecular targets by reverse screening an unprecedented vast external test set of more than 300,000 active small molecules against another bioactivity set of more than 500,000 compounds. We show that machine-learning can predict the correct targets, with the highest probability among 2069 proteins, for more than 51% of the external molecules. The strong enrichment thus obtained demonstrates its usefulness in supporting phenotypic screens, polypharmacology, or repurposing. Moreover, we quantified the impact of the bioactivity knowledge available for proteins in terms of number and diversity of actives. Finally, we advise that developers of such approaches follow an application-oriented benchmarking strategy and use large, high-quality, non-overlapping datasets as provided here.

Prediction of compound-target interaction using several artificial intelligence algorithms and comparison with a consensus-based strategy

For understanding a chemical compound's mechanism of action and its side effects, as well as for drug discovery, it is crucial to predict its possible protein targets. This study examines 15 developed target-centric models (TCM) employing different molecular descriptions and machine learning algorithms. They were contrasted with 17 third-party models implemented as web tools (WTCM). In both sets of models, consensus strategies were implemented as potential improvement over individual predictions. The findings indicate that TCM reach f1-score values greater than 0.8. Comparing both approaches, the best TCM achieves values of 0.75, 0.61, 0.25 and 0.38 for true positive/negative rates (TPR, TNR) and false negative/positive rates (FNR, FPR); outperforming the best WTCM. Moreover, the consensus strategy proves to have the most relevant results in the top 20 % of target profiles. TCM consensus reach TPR and FNR values of 0.98 and 0; while on WTCM reach values of 0.75 and 0.24. The implemented computational tool with the TCM and their consensus strategy at: https://bioquimio.udla.edu.ec/tidentification01/ . Scientific Contribution: We compare and discuss the performances of 17 public compound-target interaction prediction models and 15 new constructions. We also explore a compound-target interaction prioritization strategy using a consensus approach, and we analyzed the challenging involved in interactions modeling.

Predicting binding between 55 cannabinoids and 4,799 biological targets by in silico methods

Recently, there has been an increase in cannabis-derived products being marketed as foods, dietary supplements, and other consumer products. Cannabis contains over a hundred cannabinoids, many of which have unknown physiological effects. Since there are large numbers of cannabinoids, and many are not commercially available for in vitro testing, an in silico tool (Chemotargets Clarity software) was used to predict binding between 55 cannabinoids and 4,799 biological targets (enzymes, ion channels, receptors, and transporters). This tool relied on quantitative structure activity relationships (QSAR), structural similarity, and other approaches to predict binding. From this screening, 827 cannabinoid-target binding pairs were predicted, which included 143 unique targets. Many cannabinoids sharing core structures (cannabinoid "types") had similar binding profiles, whereas most cannabinoids containing carboxylic acid groups were similar without regards to their core structure. For some of the binding predictions (43), in vitro binding data were available, and they agreed well with in silico binding data (median fourfold difference in binding concentrations). Finally, clinical adverse effects associated with 22 predicted targets were identified from an online database (Clarivate Off-X), providing important insights on potential human health hazards. Overall, in silico biological target predictions are a rapid means to identify potential hazards due to cannabinoid-target interactions, and the data can be used to prioritize subsequent in vitro and in vivo testing.

Predicting the target landscape of kinase inhibitors using 3D convolutional neural networks

Many therapies in clinical trials are based on single drug-single target relationships. To further extend this concept to multi-target approaches using multi-targeted drugs, we developed a machine learning pipeline to unravel the target landscape of kinase inhibitors. This pipeline, which we call 3D-KINEssence, uses a new type of protein fingerprints (3D FP) based on the structure of kinases generated through a 3D convolutional neural network (3D-CNN). These 3D-CNN kinase fingerprints were matched to molecular Morgan fingerprints to predict the targets of each respective kinase inhibitor based on available bioactivity data. The performance of the pipeline was evaluated on two test sets: a sparse drug-target set where each drug is matched in most cases to a single target and also on a densely-covered drug-target set where each drug is matched to most if not all targets. This latter set is more challenging to train, given its non-exclusive character. Our model's root-mean-square error (RMSE) based on the two datasets was 0.68 and 0.8, respectively. These results indicate that 3D FP can predict the target landscape of kinase inhibitors at around 0.8 log units of bioactivity. Our strategy can be utilized in proteochemometric or chemogenomic workflows by consolidating the target landscape of kinase inhibitors.

ColdDTA: Utilizing data augmentation and attention-based feature fusion for drug-target binding affinity prediction

Accurate prediction of drug-target affinity (DTA) plays a crucial role in drug discovery and development. Recently, deep learning methods have shown excellent predictive performance on randomly split public datasets. However, verifications are still required on this splitting method to reflect real-world problems in practical applications. And in a cold-start experimental setup, where drugs or proteins in the test set do not appear in the training set, the performance of deep learning models often significantly decreases. This indicates that improving the generalization ability of the models remains a challenge. To this end, in this study, we propose ColdDTA: using data augmentation and attention-based feature fusion to improve the generalization ability of predicting drug-target binding affinity. Specifically, ColdDTA generates new drug-target pairs by removing subgraphs of drugs. The attention-based feature fusion module is also used to better capture the drug-target interactions. We conduct cold-start experiments on three benchmark datasets, and the consistency index (CI) and mean square error (MSE) results on the Davis and KIBA datasets show that ColdDTA outperforms the five state-of-the-art baseline methods. Meanwhile, the results of area under the receiver operating characteristic (ROC-AUC) on the BindingDB dataset show that ColdDTA also has better performance on the classification task. Furthermore, visualizing the model weights allows for interpretable insights. Overall, ColdDTA can better solve the realistic DTA prediction problem. The code has been available to the public.

Comprehensive survey of target prediction web servers for Traditional Chinese Medicine

Traditional Chinese medicine (TCM) is characterized by multi-components, multiple targets, and complex mechanisms of action and therefore has significant advantages in treating diseases. However, the clinical application of TCM prescriptions is limited due to the difficulty in elucidating the effective substances and the lack of current scientific evidence on the mechanisms of action. In recent years, the development of network pharmacology based on drug systems research has provided a new approach for understanding the complex systems represented by TCM. The determination of drug targets is the core of TCM network pharmacology research. Over the past years, many web tools for drug targets with various features have been developed to facilitate target prediction, significantly promoting drug discovery. Therefore, this review introduces the widely used web tools for compound-target interaction prediction databases and web resources in TCM pharmacology research, and it compares and analyzes each web tool based on their basic properties, including the underlying theory, algorithms, datasets, and search results. Finally, we present the remaining challenges for the promising future of compound-target interaction prediction in TCM pharmacology research. This work may guide researchers in choosing web tools for target prediction and may also help develop more TCM tools based on these existing resources.

In-silico target prediction by ensemble chemogenomic model based on multi-scale information of chemical structures and protein sequences

Identification and validation of bioactive small-molecule targets is a significant challenge in drug discovery. In recent years, various in-silico approaches have been proposed to expedite time- and resource-consuming experiments for target detection. Herein, we developed several chemogenomic models for target prediction based on multi-scale information of chemical structures and protein sequences. By combining the information of a compound with multiple protein targets together and putting these compound-target pairs into a well-established model, the scores to indicate whether there are interactions between compounds and targets can be derived, and thus a target prediction task can be completed by sorting the outputted scores. To improve the prediction performance, we constructed several chemogenomic models using multi-scale information of chemical structures and protein sequences, and the ensemble model with the best performance was used as our final model. The model was validated by various strategies and external datasets and the promising target prediction capability of the model, i.e., the fraction of known targets identified in the top-k (1 to 10) list of the potential target candidates suggested by the model, was confirmed. Compared with multiple state-of-art target prediction methods, our model showed equivalent or better predictive ability in terms of the top-k predictions. It is expected that our method can be utilized as a powerful computational tool to narrow down the potential targets for experimental testing.

Mechanism of action deconvolution of the small-molecule pathological tau aggregation inhibitor Anle138b

BACKGROUND

A key histopathological hallmark of Alzheimer's disease (AD) is the presence of neurofibrillary tangles of aggregated microtubule-associated protein tau in neurons. Anle138b is a small molecule which has previously shown efficacy in mice in reducing tau aggregates and rescuing AD disease phenotypes.

METHODS

In this work, we employed bioinformatics analysis-including pathway enrichment and causal reasoning-of an in vitro tauopathy model. The model consisted of cultured rat cortical neurons either unseeded or seeded with tau aggregates derived from human AD patients, both of which were treated with Anle138b to generate hypotheses for its mode of action. In parallel, we used a collection of human target prediction models to predict direct targets of Anle138b based on its chemical structure.

RESULTS

Combining the different approaches, we found evidence supporting the hypothesis that the action of Anle138b involves several processes which are key to AD progression, including cholesterol homeostasis and neuroinflammation. On the pathway level, we found significantly enriched pathways related to these two processes including those entitled "Superpathway of cholesterol biosynthesis" and "Granulocyte adhesion and diapedesis". With causal reasoning, we inferred differential activity of SREBF1/2 (involved in cholesterol regulation) and mediators of the inflammatory response such as NFKB1 and RELA. Notably, our findings were also observed in Anle138b-treated unseeded neurons, meaning that the inferred processes are independent of tau pathology and thus represent the direct action of the compound in the cellular system. Through structure-based ligand-target prediction, we predicted the intracellular cholesterol carrier NPC1 as well as NF-κB subunits as potential targets of Anle138b, with structurally similar compounds in the model training set known to target the same proteins.

CONCLUSIONS

This study has generated feasible hypotheses for the potential mechanism of action of Anle138b, which will enable the development of future molecular interventions aiming to reduce tau pathology in AD patients.

Target identification by structure-based computational approaches: Recent advances and perspectives

The use of computational techniques in the early stages of drug discovery has recently experienced a boost, especially in the target identification step. Finding the biological partner(s) for new or existing synthetic and/or natural compounds by "wet" approaches may be challenging; therefore, preliminary in silico screening is even more recommended. After a brief overview of some of the most known target identification techniques, recent advances in structure-based computational approaches for target identification are reported in this digest, focusing on Inverse Virtual Screening and its recent applications. Moreover, future perspectives concerning the use of such methodologies, coupled or not with other approaches, are analyzed.

In silico activity and ADMET profiling of phytochemicals from Ethiopian indigenous aloes using pharmacophore models

In silico profiling is used in identification of active compounds and guide rational use of traditional medicines. Previous studies on Ethiopian indigenous aloes focused on documentation of phytochemical compositions and traditional uses. In this study, ADMET and drug-likeness properties of phytochemicals from Ethiopian indigenous aloes were evaluated, and pharmacophore-based profiling was done using Discovery Studio to predict therapeutic targets. The targets were examined using KEGG pathway, gene ontology and network analysis. Using random-walk with restart algorithm, network propagation was performed in CODA network to find diseases associated with the targets. As a result, 82 human targets were predicted and found to be involved in several molecular functions and biological processes. The targets also were linked to various cancers and diseases of immune system, metabolism, neurological system, musculoskeletal system, digestive system, hematologic, infectious, mouth and dental, and congenital disorder of metabolism. 207 KEGG pathways were enriched with the targets, and the main pathways were metabolism of steroid hormone biosynthesis, lipid and atherosclerosis, chemical carcinogenesis, and pathways in cancer. In conclusion, in silico target fishing and network analysis revealed therapeutic activities of the phytochemicals, demonstrating that Ethiopian indigenous aloes exhibit polypharmacology effects on numerous genes and signaling pathways linked to many diseases.

Advances in Computational Polypharmacology

In drug discovery, polypharmacology encompasses the use of small molecules with defined multi-target activity and in vivo effects resulting from multi-target engagement. Multi-target compounds are often efficacious in the treatment of complex diseases involving target and pathway networks, but might also elicit unwanted side effects. Computational approaches such as target prediction or multi-target ligand design have been used to support polypharmacological drug discovery. In addition to efforts directed at the identification or design of new multi-target compounds, other computational investigations have aimed to differentiate such compounds from potential false-positives or explore the molecular basis of multi-target activities. Herein, a concise overview of the field is provided and recent advances in computational polypharmacology through machine learning are discussed.

MHADTI: predicting drug-target interactions via multiview heterogeneous information network embedding with hierarchical attention mechanisms

MOTIVATION

Discovering the drug-target interactions (DTIs) is a crucial step in drug development such as the identification of drug side effects and drug repositioning. Since identifying DTIs by web-biological experiments is time-consuming and costly, many computational-based approaches have been proposed and have become an efficient manner to infer the potential interactions. Although extensive effort is invested to solve this task, the prediction accuracy still needs to be improved. More especially, heterogeneous network-based approaches do not fully consider the complex structure and rich semantic information in these heterogeneous networks. Therefore, it is still a challenge to predict DTIs efficiently.

RESULTS

In this study, we develop a novel method via Multiview heterogeneous information network embedding with Hierarchical Attention mechanisms to discover potential Drug-Target Interactions (MHADTI). Firstly, MHADTI constructs different similarity networks for drugs and targets by utilizing their multisource information. Combined with the known DTI network, three drug-target heterogeneous information networks (HINs) with different views are established. Secondly, MHADTI learns embeddings of drugs and targets from multiview HINs with hierarchical attention mechanisms, which include the node-level, semantic-level and graph-level attentions. Lastly, MHADTI employs the multilayer perceptron to predict DTIs with the learned deep feature representations. The hierarchical attention mechanisms could fully consider the importance of nodes, meta-paths and graphs in learning the feature representations of drugs and targets, which makes their embeddings more comprehensively. Extensive experimental results demonstrate that MHADTI performs better than other SOTA prediction models. Moreover, analysis of prediction results for some interested drugs and targets further indicates that MHADTI has advantages in discovering DTIs.

AVAILABILITY AND IMPLEMENTATION

https://github.com/pxystudy/MHADTI.

Systematic Analysis and Prediction of the Target Space of Bioactive Food Compounds: Filling the Chemobiological Gaps

Food compounds and their molecular interactions are crucial for health and provide new chemotypes and targets for drug and nutraceutic design. Here, we retrieve and analyze the complete set of published interactions of food compounds with human proteins using the FooDB as a compound set and ChEMBL as a source of interactions. The data are analyzed in terms of 19 target classes and 19 compound classes, showing a small fraction of target assignment for the compounds (1.6%) and unraveling multiple gaps in the chemobiological space for these molecules. By using well-established cheminformatic approaches [similarity ensemble approach (SEA) combined with the maximum Tanimoto coefficient to the nearest bioactive, "SEA + TC"], we achieve a much enhanced target assignment (64.2%), filling many of the gaps with target hypothesis for fast focused testing. By publishing these data sets and analyses, we expect to provide a set of resources to speed up the full clarification of the chemobiological space of food compounds, opening new opportunities for drug and nutraceutic design.

Benzothiazole Derivatives Endowed with Antiproliferative Activity in Paraganglioma and Pancreatic Cancer Cells: Structure–Activity Relationship Studies and Target Prediction Analysis

The antiproliferative effects played by benzothiazoles in different cancers have aroused the interest for these molecules as promising antitumor agents. In this work, a library of phenylacetamide derivatives containing the benzothiazole nucleus was synthesized and compounds were tested for their antiproliferative activity in paraganglioma and pancreatic cancer cell lines. The novel synthesized compounds induced a marked viability reduction at low micromolar concentrations both in paraganglioma and pancreatic cancer cells. Derivative 4l showed a greater antiproliferative effect and higher selectivity index against cancer cells, as compared to other compounds. Notably, combinations of derivative 4l with gemcitabine at low concentrations induced enhanced and synergistic effects on pancreatic cancer cell viability, thus supporting the relevance of compound 4l in the perspective of clinical translation. A target prediction analysis was also carried out on 4l by using multiple computational tools, identifying cannabinoid receptors and sentrin-specific proteases as putative targets contributing to the observed antiproliferative activity.

The Role of Ingenane Diterpenes in Cancer Therapy: From Bioactive Secondary Compounds to Small Molecules

Diterpenes are a class of critical taxonomic markers of the Euphorbiaceae family, representing small compounds (eg, molecules) with a wide range of biological activities and multi-target therapeutic potential. Diterpenes can exert different activities, including antitumor and multi-drug resistance-reversing activities, and antiviral, immunomodulatory, and anti-inflammatory effects, mainly due to their great structural diversity. In particular, one polycyclic skeleton has been highlighted: ingenane. Besides this natural diterpene, promising polycyclic skeletons may be submitted to chemical modification—by in silico approaches, chemical reactions, or biotransformation—putatively providing more active analogs (eg, ingenol derivatives), which are currently under pre-clinical investigation. This review outlines the current mechanisms of action and potential therapeutic implications of ingenol diterpenes as small cancer molecules.

Oncological drug discovery: AI meets structure-based computational research

The integration of machine learning and structure-based methods has proven valuable in the past as a way to prioritize targets and compounds in early drug discovery. In oncological research, these methods can be highly beneficial in addressing the diversity of neoplastic diseases portrayed by the different hallmarks of cancer. Here, we review six use case scenarios for integrated computational methods, namely driver prediction, computational mutagenesis, (off)-target prediction, binding site prediction, virtual screening, and allosteric modulation analysis. We address the heterogeneity of integration approaches and individual methods, while acknowledging their current limitations and highlighting their potential to bring drugs for personalized oncological therapies to the market faster.

EMBER-Embedding Multiple Molecular Fingerprints for Virtual Screening

In recent years, the debate in the field of applications of Deep Learning to Virtual Screening has focused on the use of neural embeddings with respect to classical descriptors in order to encode both structural and physical properties of ligands and/or targets. The attention on embeddings with the increasing use of Graph Neural Networks aimed at overcoming molecular fingerprints that are short range embeddings for atomic neighborhoods. Here, we present EMBER, a novel molecular embedding made by seven molecular fingerprints arranged as different “spectra” to describe the same molecule, and we prove its effectiveness by using deep convolutional architecture that assesses ligands’ bioactivity on a data set containing twenty protein kinases with similar binding sites to CDK1. The data set itself is presented, and the architecture is explained in detail along with its training procedure. We report experimental results and an explainability analysis to assess the contribution of each fingerprint to different targets.

Computer-Aided Drug Design (CADD) to De-Orphanize Marine Molecules: Finding Potential Therapeutic Agents for Neurodegenerative and Cardiovascular Diseases

Computer-aided drug design (CADD) techniques allow the identification of compounds capable of modulating protein functions in pathogenesis-related pathways, which is a promising line on drug discovery. Marine natural products (MNPs) are considered a rich source of bioactive compounds, as the oceans are home to much of the planet's biodiversity. Biodiversity is directly related to chemodiversity, which can inspire new drug discoveries. Therefore, natural products (NPs) in general, and MNPs in particular, have been used for decades as a source of inspiration for the design of new drugs. However, NPs present both opportunities and challenges. These difficulties can be technical, such as the need to dive or trawl to collect the organisms possessing the compounds, or biological, due to their particular marine habitats and the fact that they can be uncultivable in the laboratory. For all these difficulties, the contributions of CADD can play a very relevant role in simplifying their study, since, for example, no biological sample is needed to carry out an in-silico analysis. Therefore, the amount of natural product that needs to be used in the entire preclinical and clinical study is significantly reduced. Here, we exemplify how this combination between CADD and MNPs can help unlock their therapeutic potential. In this study, using a set of marine invertebrate molecules, we elucidate their possible molecular targets and associated therapeutic potential, establishing a pipeline that can be replicated in future studies.

Machine Learning Enables Accurate and Rapid Prediction of Active Molecules Against Breast Cancer Cells

Breast cancer (BC) has surpassed lung cancer as the most frequently occurring cancer, and it is the leading cause of cancer-related death in women. Therefore, there is an urgent need to discover or design new drug candidates for BC treatment. In this study, we first collected a series of structurally diverse datasets consisting of 33,757 active and 21,152 inactive compounds for 13 breast cancer cell lines and one normal breast cell line commonly used in in vitro antiproliferative assays. Predictive models were then developed using five conventional machine learning algorithms, including naïve Bayesian, support vector machine, k-Nearest Neighbors, random forest, and extreme gradient boosting, as well as five deep learning algorithms, including deep neural networks, graph convolutional networks, graph attention network, message passing neural networks, and Attentive FP. A total of 476 single models and 112 fusion models were constructed based on three types of molecular representations including molecular descriptors, fingerprints, and graphs. The evaluation results demonstrate that the best model for each BC cell subtype can achieve high predictive accuracy for the test sets with AUC values of 0.689–0.993. Moreover, important structural fragments related to BC cell inhibition were identified and interpreted. To facilitate the use of the model, an online webserver called ChemBC (http://chembc.idruglab.cn/) and its local version software (https://github.com/idruglab/ChemBC) were developed to predict whether compounds have potential inhibitory activity against BC cells.

Antifungal Activity of N-(4-Halobenzyl)amides against Candida spp. and Molecular Modeling Studies

Fungal infections remain a high-incidence worldwide health problem that is aggravated by limited therapeutic options and the emergence of drug-resistant strains. Cinnamic and benzoic acid amides have previously shown bioactivity against different species belonging to the Candida genus. Here, 20 cinnamic and benzoic acid amides were synthesized and tested for inhibition of C. krusei ATCC 14243 and C. parapsilosis ATCC 22019. Five compounds inhibited the Candida strains tested, with compound 16 (MIC = 7.8 µg/mL) producing stronger antifungal activity than fluconazole (MIC = 16 µg/mL) against C. krusei ATCC 14243. It was also tested against eight Candida strains, including five clinical strains resistant to fluconazole, and showed an inhibitory effect against all strains tested (MIC = 85.3–341.3 µg/mL). The MIC value against C. krusei ATCC 6258 was 85.3 mcg/mL, while against C. krusei ATCC 14243, it was 10.9 times smaller. This strain had greater sensitivity to the antifungal action of compound 16. The inhibition of C. krusei ATCC 14243 and C. parapsilosis ATCC 22019 was also achieved by compounds 2, 9, 12, 14 and 15. Computational experiments combining target fishing, molecular docking and molecular dynamics simulations were performed to study the potential mechanism of action of compound 16 against C. krusei. From these, a multi-target mechanism of action is proposed for this compound that involves proteins related to critical cellular processes such as the redox balance, kinases-mediated signaling, protein folding and cell wall synthesis. The modeling results might guide future experiments focusing on the wet-lab investigation of the mechanism of action of this series of compounds, as well as on the optimization of their inhibitory potency.

A unified drug-target interaction prediction framework based on knowledge graph and recommendation system

Prediction of drug-target interactions (DTI) plays a vital role in drug development in various areas, such as virtual screening, drug repurposing and identification of potential drug side effects. Despite extensive efforts have been invested in perfecting DTI prediction, existing methods still suffer from the high sparsity of DTI datasets and the cold start problem. Here, we develop KGE_NFM, a unified framework for DTI prediction by combining knowledge graph (KG) and recommendation system. This framework firstly learns a low-dimensional representation for various entities in the KG, and then integrates the multimodal information via neural factorization machine (NFM). KGE_NFM is evaluated under three realistic scenarios, and achieves accurate and robust predictions on four benchmark datasets, especially in the scenario of the cold start for proteins. Our results indicate that KGE_NFM provides valuable insight to integrate KG and recommendation system-based techniques into a unified framework for novel DTI discovery.

Challenging Reverse Screening: A Benchmark Study for Comprehensive Evaluation

As an efficient way of computational target prediction, reverse docking can find not only potential targets but also binding modes for a query ligand. Though the number of available docking tools keeps expanding, there is still not a comprehensive evaluation study which can uncover the advantages and limitations of these strategies in the research field of computational target-fishing. In this study, we propose a brand-new evaluation dataset tailor-made for reverse docking, which is composed of a true positive set (the core set) and two negative sets (the similar decoy set and the dissimilar decoy set). The proposed evaluation dataset can assess the prediction performance of docking tools as various values affected by varying degrees of inter-target ranking bias. The performance of four classical docking programs (AutoDock, AutoDock Vina, Glide and GOLD) was evaluated utilizing our dataset, and a biased prediction performance was observed regarding binding site properties. The results demonstrated that Glide (SP) and Glide(XP) had the best capacity to find true targets whether there was inter-target ranking bias or not.

Artificial intelligence in drug discovery: applications and techniques

Artificial intelligence (AI) has been transforming the practice of drug discovery in the past decade. Various AI techniques have been used in many drug discovery applications, such as virtual screening and drug design. In this survey, we first give an overview on drug discovery and discuss related applications, which can be reduced to two major tasks, i.e. molecular property prediction and molecule generation. We then present common data resources, molecule representations and benchmark platforms. As a major part of the survey, AI techniques are dissected into model architectures and learning paradigms. To reflect the technical development of AI in drug discovery over the years, the surveyed works are organized chronologically. We expect that this survey provides a comprehensive review on AI in drug discovery. We also provide a GitHub repository with a collection of papers (and codes, if applicable) as a learning resource, which is regularly updated.

Drug target inference by mining transcriptional data using a novel graph convolutional network framework

A fundamental challenge that arises in biomedicine is the need to characterize compounds in a relevant cellular context in order to reveal potential on-target or off-target effects. Recently, the fast accumulation of gene transcriptional profiling data provides us an unprecedented opportunity to explore the protein targets of chemical compounds from the perspective of cell transcriptomics and RNA biology. Here, we propose a novel Siamese spectral-based graph convolutional network (SSGCN) model for inferring the protein targets of chemical compounds from gene transcriptional profiles. Although the gene signature of a compound perturbation only provides indirect clues of the interacting targets, and the biological networks under different experiment conditions further complicate the situation, the SSGCN model was successfully trained to learn from known compound-target pairs by uncovering the hidden correlations between compound perturbation profiles and gene knockdown profiles. On a benchmark set and a large time-split validation dataset, the model achieved higher target inference accuracy as compared to previous methods such as Connectivity Map. Further experimental validations of prediction results highlight the practical usefulness of SSGCN in either inferring the interacting targets of compound, or reversely, in finding novel inhibitors of a given target of interest.

Current trends in computer aided drug design and a highlight of drugs discovered via computational techniques: A review

Computer-aided drug design (CADD) is one of the pivotal approaches to contemporary pre-clinical drug discovery, and various computational techniques and software programs are typically used in combination, in a bid to achieve the desired outcome. Several approved drugs have been developed with the aid of CADD. On SciFinder®, we evaluated more than 600 publications through systematic searching and refining, using the terms, virtual screening; software methods; computational studies and publication year, in order to obtain data concerning particular aspects of CADD. The primary focus of this review was on the databases screened, virtual screening and/or molecular docking software program used. Furthermore, we evaluated the studies that subsequently performed molecular dynamics (MD) simulations and we reviewed the software programs applied, the application of density functional theory (DFT) calculations and experimental assays. To represent the latest trends, the most recent data obtained was between 2015 and 2020, consequently the most frequently employed techniques and software programs were recorded. Among these, the ZINC database was the most widely preferred with an average use of 31.2%. Structure-based virtual screening (SBVS) was the most prominently used type of virtual screening and it accounted for an average of 57.6%, with AutoDock being the preferred virtual screening/molecular docking program with 41.8% usage. Following the screening process, 38.5% of the studies performed MD simulations to complement the virtual screening and GROMACS with 39.3% usage, was the popular MD software program. Among the computational techniques, DFT was the least applied whereby it only accounts for 0.02% average use. An average of 36.5% of the studies included reports on experimental evaluations following virtual screening. Ultimately, since the inception and application of CADD in pre-clinical drug discovery, more than 70 approved drugs have been discovered, and this number is steadily increasing over time.

Angucyclines containing β-ᴅ-glucuronic acid from Streptomyces sp. KCB15JA151

Two angucyclines, pseudonocardones D (1) and E (2), were isolated from Streptomyces sp. KCB15JA151. The planar structure was elucidated by comprehensive spectroscopic analysis. The absolute configuration of the sugar unit was determined based on the basis of coupling constants, ROESY, chemical derivatization and HPLC analysis. The biological activities of compounds 1 and 2 were examined by performing a computational target prediction, which led to tests of the antiestrogenic activity. The result suggested that compound 1 might be an ERα antagonist.

A comprehensive comparative assessment of 3D molecular similarity tools in ligand-based virtual screening

Three-dimensional (3D) molecular similarity, one major ligand-based virtual screening (VS) method, has been widely used in the drug discovery process. A variety of 3D molecular similarity tools have been developed in recent decades. In this study, we assessed a panel of 15 3D molecular similarity programs against the DUD-E and LIT-PCBA datasets, including commercial ROCS and Phase, in terms of screening power and scaffold-hopping power. The results revealed that (1) SHAFTS, LS-align, Phase Shape_Pharm and LIGSIFT showed the best VS capability in terms of screening power. Some 3D similarity tools available to academia can yield relatively better VS performance than commercial ROCS and Phase software. (2) Current 3D similarity VS tools exhibit a considerable ability to capture actives with new chemotypes in terms of scaffold hopping. (3) Multiple conformers relative to single conformations will generally improve VS performance for most 3D similarity tools, with marginal improvement observed in area under the receiving operator characteristic curve values, enrichment factor in the top 1% and hit rate in the top 1% values showed larger improvement. Moreover, redundancy and complementarity analyses of hit lists from different query seeds and different 3D similarity VS tools showed that the combination of different query seeds and/or different 3D similarity tools in VS campaigns retrieved more (and more diverse) active molecules. These findings provide useful information for guiding choices of the optimal 3D molecular similarity tools for VS practices and designing possible combination strategies to discover more diverse active compounds.

LigTMap: ligand and structure-based target identification and activity prediction for small molecular compounds

Target prediction is a crucial step in modern drug discovery. However, existing experimental approaches to target prediction are time-consuming and costly. Here, we introduce LigTMap, an online server with a fully automated workflow that can identify protein targets of chemical compounds among 17 classes of therapeutic proteins extracted from the PDBbind database. It combines ligand similarity search with docking and binding similarity analysis to predict putative targets. In the validation experiment of 1251 compounds, targets were successfully predicted for more than 70% of the compounds within the top-10 list. The performance of LigTMap is comparable to the current best servers SwissTargetPrediction and SEA. When testing with our newly compiled compounds from recent literature, we get improved top 10 success rate (66% ours vs. 60% SwissTargetPrediction and 64% SEA) and similar top 1 success rate (45% ours vs. 51% SwissTargetPrediction and 41% SEA). LigTMap directly provides ligand docking structures in PDB format, so that the results are ready for further structural studies in computer-aided drug design and drug repurposing projects. The LigTMap web server is freely accessible at https://cbbio.online/LigTMap. The source code is released on GitHub (https://github.com/ShirleyWISiu/LigTMap) under the BSD 3-Clause License to encourage re-use and further developments.

Machine learning for perturbational single-cell omics

Cell biology is fundamentally limited in its ability to collect complete data on cellular phenotypes and the wide range of responses to perturbation. Areas such as computer vision and speech recognition have addressed this problem of characterizing unseen or unlabeled conditions with the combined advances of big data, deep learning, and computing resources in the past 5 years. Similarly, recent advances in machine learning approaches enabled by single-cell data start to address prediction tasks in perturbation response modeling. We first define objectives in learning perturbation response in single-cell omics; survey existing approaches, resources, and datasets (https://github.com/theislab/sc-pert); and discuss how a perturbation atlas can enable deep learning models to construct an informative perturbation latent space. We then examine future avenues toward more powerful and explainable modeling using deep neural networks, which enable the integration of disparate information sources and an understanding of heterogeneous, complex, and unseen systems.

Resources and computational strategies to advance small molecule SARS-CoV-2 discovery: Lessons from the pandemic and preparing for future health crises

There is an urgent need to identify new therapies that prevent SARS-CoV-2 infection and improve the outcome of COVID-19 patients. This pandemic has thus spurred intensive research in most scientific areas and in a short period of time, several vaccines have been developed. But, while the race to find vaccines for COVID-19 has dominated the headlines, other types of therapeutic agents are being developed. In this mini-review, we report several databases and online tools that could assist the discovery of anti-SARS-CoV-2 small chemical compounds and peptides. We then give examples of studies that combined in silico and in vitro screening, either for drug repositioning purposes or to search for novel bioactive compounds. Finally, we question the overall lack of discussion and plan observed in academic research in many countries during this crisis and suggest that there is room for improvement.

Deep Learning in Virtual Screening: Recent Applications and Developments

Drug discovery is a cost and time-intensive process that is often assisted by computational methods, such as virtual screening, to speed up and guide the design of new compounds. For many years, machine learning methods have been successfully applied in the context of computer-aided drug discovery. Recently, thanks to the rise of novel technologies as well as the increasing amount of available chemical and bioactivity data, deep learning has gained a tremendous impact in rational active compound discovery. Herein, recent applications and developments of machine learning, with a focus on deep learning, in virtual screening for active compound design are reviewed. This includes introducing different compound and protein encodings, deep learning techniques as well as frequently used bioactivity and benchmark data sets for model training and testing. Finally, the present state-of-the-art, including the current challenges and emerging problems, are examined and discussed.

Comparison of Chemical Structure and Cell Morphology Information for Multitask Bioactivity Predictions

The understanding of the mechanism-of-action (MoA) of compounds and the prediction of potential drug targets play an important role in small-molecule drug discovery. The aim of this work was to compare chemical and cell morphology information for bioactivity prediction. The comparison was performed using bioactivity data from the ExCAPE database, image data (in the form of CellProfiler features) from the Cell Painting data set (the largest publicly available data set of cell images with ∼30,000 compound perturbations), and extended connectivity fingerprints (ECFPs) using the multitask Bayesian matrix factorization (BMF) approach Macau. We found that the BMF Macau and random forest (RF) performance were overall similar when ECFPs were used as compound descriptors. However, BMF Macau outperformed RF in 159 out of 224 targets (71%) when image data were used as compound information. Using BMF Macau, 100 (corresponding to about 45%) and 90 (about 40%) of the 224 targets were predicted with high predictive performance (AUC > 0.8) with ECFP data and image data as side information, respectively. There were targets better predicted by image data as side information, such as β-catenin, and others better predicted by fingerprint-based side information, such as proteins belonging to the G-protein-Coupled Receptor 1 family, which could be rationalized from the underlying data distributions in each descriptor domain. In conclusion, both cell morphology changes and chemical structure information contain information about compound bioactivity, which is also partially complementary, and can hence contribute to in silico MoA analysis.

Comprehensive computational target fishing approach to identify Xanthorrhizol putative targets

Xanthorrhizol (XNT), is a bioactive compound found in Curcuma xanthorrhiza Roxb. This study aimed to determine the potential targets of the XNT via computational target fishing method. This compound obeyed Lipinski's and Veber's rules where it has a molecular weight (MW) of 218.37 gmol^-1, TPSA of 20.23, rotatable bonds (RBN) of 4, hydrogen acceptor and donor ability is 1 respectively. Besides, it also has half-life (HL) values 3.5 h, drug-likeness (DL) value of 0.07, oral bioavailability (OB) of 32.10, and blood-brain barrier permeability (BBB) value of 1.64 indicating its potential as therapeutic drug. Further, 20 potential targets were screened out through PharmMapper and DRAR-CPI servers. Co-expression results derived from GeneMANIA revealed that these targets made connection with a total of 40 genes and have 744 different links. Four genes which were RXRA, RBP4, HSD11B1 and AKR1C1 showed remarkable co-expression and predominantly involved in steroid metabolic process. Furthermore, among these 20 genes, 13 highly expressed genes associated with xenobiotics by cytochrome P450, chemical carcinogenesis and steroid metabolic pathways were identified through gene ontology (GO) and KEGG pathway analysis. In conclusion, XNT is targeting multiple proteins and pathways which may be exploited to shape a network that exerts systematic pharmacological effects.

Accuracy or novelty: what can we gain from target-specific machine-learning-based scoring functions in virtual screening?

Machine-learning (ML)-based scoring functions (MLSFs) have gradually emerged as a promising alternative for protein-ligand binding affinity prediction and structure-based virtual screening. However, clouds of doubts have still been raised against the benefits of this novel type of scoring functions (SFs). In this study, to benchmark the performance of target-specific MLSFs on a relatively unbiased dataset, the MLSFs trained from three representative protein-ligand interaction representations were assessed on the LIT-PCBA dataset, and the classical Glide SP SF and three types of ligand-based quantitative structure-activity relationship (QSAR) models were also utilized for comparison. Two major aspects in virtual screening campaigns, including prediction accuracy and hit novelty, were systematically explored. The calculation results illustrate that the tested target-specific MLSFs yielded generally superior performance over the classical Glide SP SF, but they could hardly outperform the 2D fingerprint-based QSAR models. Although substantial improvements could be achieved by integrating multiple types of protein-ligand interaction features, the MLSFs were still not sufficient to exceed MACCS-based QSAR models. In terms of the correlations between the hit ranks or the structures of the top-ranked hits, the MLSFs developed by different featurization strategies would have the ability to identify quite different hits. Nevertheless, it seems that target-specific MLSFs do not have the intrinsic attributes of a traditional SF and may not be a substitute for classical SFs. In contrast, MLSFs can be regarded as a new derivative of ligand-based QSAR models. It is expected that our study may provide valuable guidance for the assessment and further development of target-specific MLSFs.

Machine learning approaches for elucidating the biological effects of natural products

Covering: 2000 to 2020 Machine learning (ML) is an efficient tool for the prediction of bioactivity and the study of structure-activity relationships. Over the past decade, an emerging trend for combining these approaches with the study of natural products (NPs) has developed in order to manage the challenge of the discovery of bioactive NPs. In the present review, we will introduce the basic principles and protocols for using the ML approach to investigate the bioactivity of NPs, citing a series of practical examples regarding the study of anti-microbial, anti-cancer, and anti-inflammatory NPs, etc. ML algorithms manage a variety of classification and regression problems associated with bioactive NPs, from those that are linear to non-linear and from pure compounds to plant extracts. Inspired by cases reported in the literature and our own experience, a number of key points have been emphasized for reducing modeling errors, including dataset preparation and applicability domain analysis.

Cheminformatics in Natural Product-based Drug Discovery

This review seeks to provide a timely survey of the scope and limitations of cheminformatics methods in natural product-based drug discovery. Following an overview of data resources of chemical, biological and structural information on natural products, we discuss, among other aspects, in silico methods for (i) data curation and natural products dereplication, (ii) analysis, visualization, navigation and comparison of the chemical space, (iii) quantification of natural product-likeness, (iv) prediction of the bioactivities (virtual screening, target prediction), ADME and safety profiles (toxicity) of natural products, (v) natural products-inspired de novo design and (vi) prediction of natural products prone to cause interference with biological assays. Among the many methods discussed are rule-based, similarity-based, shape-based, pharmacophore-based and network-based approaches, docking and machine learning methods.

Adding Stochastic Negative Examples into Machine Learning Improves Molecular Bioactivity Prediction

Multitask deep neural networks learn to predict ligand-target binding by example, yet public pharmacological data sets are sparse, imbalanced, and approximate. We constructed two hold-out benchmarks to approximate temporal and drug-screening test scenarios, whose characteristics differ from a random split of conventional training data sets. We developed a pharmacological data set augmentation procedure, Stochastic Negative Addition (SNA), which randomly assigns untested molecule-target pairs as transient negative examples during training. Under the SNA procedure, drug-screening benchmark performance increases from R² = 0.1926 ± 0.0186 to 0.4269 ± 0.0272 (122%). This gain was accompanied by a modest decrease in the temporal benchmark (13%). SNA increases in drug-screening performance were consistent for classification and regression tasks and outperformed y-randomized controls. Our results highlight where data and feature uncertainty may be problematic and how leveraging uncertainty into training improves predictions of drug-target relationships.

Uncertainty quantification in drug design

Machine learning and artificial intelligence are increasingly being applied to the drug-design process as a result of the development of novel algorithms, growing access, the falling cost of computation and the development of novel technologies for generating chemically and biologically relevant data. There has been recent progress in fields such as molecular de novo generation, synthetic route prediction and, to some extent, property predictions. Despite this, most research in these fields has focused on improving the accuracy of the technologies, rather than on quantifying the uncertainty in the predictions. Uncertainty quantification will become a key component in autonomous decision making and will be crucial for integrating machine learning and chemistry automation to create an autonomous design-make-test-analyse cycle. This review covers the empirical, frequentist and Bayesian approaches to uncertainty quantification, and outlines how they can be used for drug design. We also outline the impact of uncertainty quantification on decision making.

Predicting target profiles with confidence as a service using docking scores

Background

Identifying and assessing ligand-target binding is a core component in early drug discovery as one or more unwanted interactions may be associated with safety issues.

Contributions

We present an open-source, extendable web service for predicting target profiles with confidence using machine learning for a panel of 7 targets, where models are trained on molecular docking scores from a large virtual library. The method uses conformal prediction to produce valid measures of prediction efficiency for a particular confidence level. The service also offers the possibility to dock chemical structures to the panel of targets with QuickVina on individual compound basis.

Results

The docking procedure and resulting models were validated by docking well-known inhibitors for each of the 7 targets using QuickVina. The model predictions showed comparable performance to molecular docking scores against an external validation set. The implementation as publicly available microservices on Kubernetes ensures resilience, scalability, and extensibility.

Finding New Molecular Targets of Familiar Natural Products Using In Silico Target Prediction

Natural products comprise a rich reservoir for innovative drug leads and are a constant source of bioactive compounds. To find pharmacological targets for new or already known natural products using modern computer-aided methods is a current endeavor in drug discovery. Nature's treasures, however, could be used more effectively. Yet, reliable pipelines for the large-scale target prediction of natural products are still rare. We developed an in silico workflow consisting of four independent, stand-alone target prediction tools and evaluated its performance on dihydrochalcones (DHCs)-a well-known class of natural products. Thereby, we revealed four previously unreported protein targets for DHCs, namely 5-lipoxygenase, cyclooxygenase-1, 17β-hydroxysteroid dehydrogenase 3, and aldo-keto reductase 1C3. Moreover, we provide a thorough strategy on how to perform computational target predictions and guidance on using the respective tools.

Utilizing drug-target-event relationships to unveil safety patterns in pharmacovigilance

INTRODUCTION

Signal detection is the most pivotal activity of signal management to guarantee that drugs maintain a positive risk-benefit ratio during their lifetime on the market. Signal detection is based on the systematic evaluation of available data sources, which have recently been extended in order to improve timely and comprehensive signal detection of drug safety problems.

AREAS COVERED

In recent years, attempts have been made to incorporate pharmacological data for the prediction of safety signals. Previous studies have shown that data on the pharmacological targets of drugs are predictive of post-marketing adverse events. However, current approaches limit such predictions to adverse events expected from the interaction of a drug with the main pharmacological target and do not take off-target interactions into consideration.

EXPERT OPINION

The authors propose the application of predictive modeling techniques utilizing pharmacological data from public databases for predicting drug-target-event relationships deriving from main- and off-target binding and from which potential safety signals can be deduced. Additionally, they provide an operative procedure for the identification of clinically relevant subgroups for predicted safety signals.

Similarity-Based Methods and Machine Learning Approaches for Target Prediction in Early Drug Discovery: Performance and Scope

Computational methods for predicting the macromolecular targets of drugs and drug-like compounds have evolved as a key technology in drug discovery. However, the established validation protocols leave several key questions regarding the performance and scope of methods unaddressed. For example, prediction success rates are commonly reported as averages over all compounds of a test set and do not consider the structural relationship between the individual test compounds and the training instances. In order to obtain a better understanding of the value of ligand-based methods for target prediction, we benchmarked a similarity-based method and a random forest based machine learning approach (both employing 2D molecular fingerprints) under three testing scenarios: a standard testing scenario with external data, a standard time-split scenario, and a scenario that is designed to most closely resemble real-world conditions. In addition, we deconvoluted the results based on the distances of the individual test molecules from the training data. We found that, surprisingly, the similarity-based approach generally outperformed the machine learning approach in all testing scenarios, even in cases where queries were structurally clearly distinct from the instances in the training (or reference) data, and despite a much higher coverage of the known target space.

Scope of 3D Shape-Based Approaches in Predicting the Macromolecular Targets of Structurally Complex Small Molecules Including Natural Products and Macrocyclic Ligands

A plethora of similarity-based, network-based, machine learning, docking and hybrid approaches for predicting the macromolecular targets of small molecules are available today and recognized as valuable tools for providing guidance in early drug discovery. With the increasing maturity of target prediction methods, researchers have started to explore ways to expand their scope to more challenging molecules such as structurally complex natural products and macrocyclic small molecules. In this work, we systematically explore the capacity of an alignment-based approach to identify the targets of structurally complex small molecules (including large and flexible natural products and macrocyclic compounds) based on the similarity of their 3D molecular shape to noncomplex molecules (i.e., more conventional, “drug-like”, synthetic compounds). For this analysis, query sets of 10 representative, structurally complex molecules were compiled for each of the 28 pharmaceutically relevant proteins. Subsequently, ROCS, a leading shape-based screening engine, was utilized to generate rank-ordered lists of the potential targets of the 28 × 10 queries according to the similarity of their 3D molecular shapes with those of compounds from a knowledge base of 272 640 noncomplex small molecules active on a total of 3642 different proteins. Four of the scores implemented in ROCS were explored for target ranking, with the TanimotoCombo score consistently outperforming all others. The score successfully recovered the targets of 30% and 41% of the 280 queries among the top-5 and top-20 positions, respectively. For 24 out of the 28 investigated targets (86%), the method correctly assigned the first rank (out of 3642) to the target of interest for at least one of the 10 queries. The shape-based target prediction approach showed remarkable robustness, with good success rates obtained even for compounds that are clearly distinct from any of the ligands present in the knowledge base. However, complex natural products and macrocyclic compounds proved to be challenging even with this approach, although cases of complete failure were recorded only for a small number of targets.

Industry-scale application and evaluation of deep learning for drug target prediction

Artificial intelligence (AI) is undergoing a revolution thanks to the breakthroughs of machine learning algorithms in computer vision, speech recognition, natural language processing and generative modelling. Recent works on publicly available pharmaceutical data showed that AI methods are highly promising for Drug Target prediction. However, the quality of public data might be different than that of industry data due to different labs reporting measurements, different measurement techniques, fewer samples and less diverse and specialized assays. As part of a European funded project (ExCAPE), that brought together expertise from pharmaceutical industry, machine learning, and high-performance computing, we investigated how well machine learning models obtained from public data can be transferred to internal pharmaceutical industry data. Our results show that machine learning models trained on public data can indeed maintain their predictive power to a large degree when applied to industry data. Moreover, we observed that deep learning derived machine learning models outperformed comparable models, which were trained by other machine learning algorithms, when applied to internal pharmaceutical company datasets. To our knowledge, this is the first large-scale study evaluating the potential of machine learning and especially deep learning directly at the level of industry-scale settings and moreover investigating the transferability of publicly learned target prediction models towards industrial bioactivity prediction pipelines.