Deep Transferable Compound Representation across Domains and Tasks for Low Data Drug Discovery

Current strategies to address data scarcity in artificial intelligence-based drug discovery: A comprehensive review

Artificial intelligence (AI) has played a vital role in computer-aided drug design (CADD). This development has been further accelerated with the increasing use of machine learning (ML), mainly deep learning (DL), and computing hardware and software advancements. As a result, initial doubts about the application of AI in drug discovery have been dispelled, leading to significant benefits in medicinal chemistry. At the same time, it is crucial to recognize that AI is still in its infancy and faces a few limitations that need to be addressed to harness its full potential in drug discovery. Some notable limitations are insufficient, unlabeled, and non-uniform data, the resemblance of some AI-generated molecules with existing molecules, unavailability of inadequate benchmarks, intellectual property rights (IPRs) related hurdles in data sharing, poor understanding of biology, focus on proxy data and ligands, lack of holistic methods to represent input (molecular structures) to prevent pre-processing of input molecules (feature engineering), etc. The major component in AI infrastructure is input data, as most of the successes of AI-driven efforts to improve drug discovery depend on the quality and quantity of data, used to train and test AI algorithms, besides a few other factors. Additionally, data-gulping DL approaches, without sufficient data, may collapse to live up to their promise. Current literature suggests a few methods, to certain extent, effectively handle low data for better output from the AI models in the context of drug discovery. These are transferring learning (TL), active learning (AL), single or one-shot learning (OSL), multi-task learning (MTL), data augmentation (DA), data synthesis (DS), etc. One different method, which enables sharing of proprietary data on a common platform (without compromising data privacy) to train ML model, is federated learning (FL). In this review, we compare and discuss these methods, their recent applications, and limitations while modeling small molecule data to get the improved output of AI methods in drug discovery. Article also sums up some other novel methods to handle inadequate data.

Attribute-guided prototype network for few-shot molecular property prediction

The molecular property prediction (MPP) plays a crucial role in the drug discovery process, providing valuable insights for molecule evaluation and screening. Although deep learning has achieved numerous advances in this area, its success often depends on the availability of substantial labeled data. The few-shot MPP is a more challenging scenario, which aims to identify unseen property with only few available molecules. In this paper, we propose an attribute-guided prototype network (APN) to address the challenge. APN first introduces an molecular attribute extractor, which can not only extract three different types of fingerprint attributes (single fingerprint attributes, dual fingerprint attributes, triplet fingerprint attributes) by considering seven circular-based, five path-based, and two substructure-based fingerprints, but also automatically extract deep attributes from self-supervised learning methods. Furthermore, APN designs the Attribute-Guided Dual-channel Attention module to learn the relationship between the molecular graphs and attributes and refine the local and global representation of the molecules. Compared with existing works, APN leverages high-level human-defined attributes and helps the model to explicitly generalize knowledge in molecular graphs. Experiments on benchmark datasets show that APN can achieve state-of-the-art performance in most cases and demonstrate that the attributes are effective for improving few-shot MPP performance. In addition, the strong generalization ability of APN is verified by conducting experiments on data from different domains.

CFSSynergy: Combining Feature-Based and Similarity-Based Methods for Drug Synergy Prediction

Drug synergy prediction plays a vital role in cancer treatment. Because experimental approaches are labor-intensive and expensive, computational-based approaches get more attention. There are two types of computational methods for drug synergy prediction: feature-based and similarity-based. In feature-based methods, the main focus is to extract more discriminative features from drug pairs and cell lines to pass to the task predictor. In similarity-based methods, the similarities among all drugs and cell lines are utilized as features and fed into the task predictor. In this work, a novel approach, called CFSSynergy, that combines these two viewpoints is proposed. First, a discriminative representation is extracted for paired drugs and cell lines as input. We have utilized transformer-based architecture for drugs. For cell lines, we have created a similarity matrix between proteins using the Node2Vec algorithm. Then, the new cell line representation is computed by multiplying the protein-protein similarity matrix and the initial cell line representation. Next, we compute the similarity between unique drugs and unique cells using the learned representation for paired drugs and cell lines. Then, we compute a new representation for paired drugs and cell lines based on the similarity-based features and the learned features. Finally, these features are fed to XGBoost as a task predictor. Two well-known data sets were used to evaluate the performance of our proposed method: DrugCombDB and OncologyScreen. The CFSSynergy approach consistently outperformed existing methods in comparative evaluations. This substantiates the efficacy of our approach in capturing complex synergistic interactions between drugs and cell lines, setting it apart from conventional similarity-based or feature-based methods.

Adapting Deep Learning QSPR Models to Specific Drug Discovery Projects

Medicinal chemistry and drug design efforts can be assisted by machine learning (ML) models that relate the molecular structure to compound properties. Such quantitative structure-property relationship models are generally trained on large data sets that include diverse chemical series (global models). In the pharmaceutical industry, these ML global models are available across discovery projects as an "out-of-the-box" solution to assist in drug design, synthesis prioritization, and experiment selection. However, drug discovery projects typically focus on confined parts of the chemical space (e.g., chemical series), where global models might not be applicable. Local ML models are sometimes generated to focus on specific projects or series. Herein, ML-based global models, local models, and hybrid global-local strategies were benchmarked. Analyses were done for more than 300 drug discovery projects at Novartis and ten absorption, distribution, metabolism, and excretion (ADME) assays. In this work, hybrid global-local strategies based on transfer learning approaches were proposed to leverage both historical ADME data (global) and project-specific data (local) to adapt model predictions. Fine-tuning a pretrained global ML model (used for weights' initialization, WI) was the top-performing method. Average improvements of mean absolute errors across all assays were 16% and 27% compared with global and local models, respectively. Interestingly, when the effect of training set size was analyzed, WI fine-tuning was found to be successful even in low-data scenarios (e.g., ∼10 molecules per project). Taken together, this work highlights the potential of domain adaptation in the field of molecular property predictions to refine existing pretrained models on a new compound data distribution.

Development of a standardized methodology for transfer learning with QSAR models: a purely data-driven approach for source task selection

Transfer learning is a machine learning technique that works well with chemical endpoints, with several papers confirming its efficiency. Although effective, because the choice of source/assistant tasks is non-trivial, the application of this technique is severely limited by the domain knowledge of the modeller. Considering this limitation, we developed a purely data-driven approach for source task selection that abstracts the need for domain knowledge. To achieve this, we created a supervised learning setting in which transfer outcome (positive/negative) is the variable to be predicted, and a set of six transferability metrics, calculated based on information from target and source datasets, are the features for prediction. We used the ChEMBL database to generate 100,000 transfers using random pairing, and with these transfers, we trained and evaluated our transferability prediction model (TP-Model). Our TP-Model achieved a 135-fold increase in precision while achieving a sensitivity of 92%, demonstrating a clear superiority against random search. In addition, we observed that transfer learning could provide considerable performance increases when applicable, with an average Matthews Correlation Coefficient (MCC) increase of 0.19 when using a single source and an average MCC increase of 0.44 when using multiple sources.

DeepTraSynergy: drug combinations using multimodal deep learning with transformers

MOTIVATION

Screening bioactive compounds in cancer cell lines receive more attention. Multidisciplinary drugs or drug combinations have a more effective role in treatments and selectively inhibit the growth of cancer cells.

RESULTS

Hence, we propose a new deep learning-based approach for drug combination synergy prediction called DeepTraSynergy. Our proposed approach utilizes multimodal input including drug-target interaction, protein-protein interaction, and cell-target interaction to predict drug combination synergy. To learn the feature representation of drugs, we have utilized transformers. It is worth noting that our approach is a multitask approach that predicts three outputs including the drug-target interaction, its toxic effect, and drug combination synergy. In our approach, drug combination synergy is the main task and the two other ones are the auxiliary tasks that help the approach to learn a better model. In the proposed approach three loss functions are defined: synergy loss, toxic loss, and drug-protein interaction loss. The last two loss functions are designed as auxiliary losses to help learn a better solution. DeepTraSynergy outperforms the classic and state-of-the-art models in predicting synergistic drug combinations on the two latest drug combination datasets. The DeepTraSynergy algorithm achieves accuracy values of 0.7715 and 0.8052 (an improvement over other approaches) on the DrugCombDB and Oncology-Screen datasets, respectively. Also, we evaluate the contribution of each component of DeepTraSynergy to show its effectiveness in the proposed method. The introduction of the relation between proteins (PPI networks) and drug-protein interaction significantly improves the prediction of synergistic drug combinations.

AVAILABILITY AND IMPLEMENTATION

The source code and data are available at https://github.com/fatemeh-rafiei/DeepTraSynergy.

Enhancing drug property prediction with dual-channel transfer learning based on molecular fragment

BACKGROUND

Accurate prediction of molecular property holds significance in contemporary drug discovery and medical research. Recent advances in AI-driven molecular property prediction have shown promising results. Due to the costly annotation of in vitro and in vivo experiments, transfer learning paradigm has been gaining momentum in extracting general self-supervised information to facilitate neural network learning. However, prior pretraining strategies have overlooked the necessity of explicitly incorporating domain knowledge, especially the molecular fragments, into model design, resulting in the under-exploration of the molecular semantic space.

RESULTS

We propose an effective model with FRagment-based dual-channEL pretraining (FREL). Equipped with molecular fragments, FREL comprehensively employs masked autoencoder and contrastive learning to learn intra- and inter-molecule agreement, respectively. We further conduct extensive experiments on ten public datasets to demonstrate its superiority over state-of-the-art models. Further investigations and interpretations manifest the underlying relationship between molecular representations and molecular properties.

CONCLUSIONS

Our proposed model FREL achieves state-of-the-art performance on the benchmark datasets, emphasizing the importance of incorporating molecular fragments into model design. The expressiveness of learned molecular representations is also investigated by visualization and correlation analysis. Case studies indicate that the learned molecular representations better capture the drug property variation and fragment semantics.

A voting-based machine learning approach for classifying biological and clinical datasets

BACKGROUND

Different machine learning techniques have been proposed to classify a wide range of biological/clinical data. Given the practicability of these approaches accordingly, various software packages have been also designed and developed. However, the existing methods suffer from several limitations such as overfitting on a specific dataset, ignoring the feature selection concept in the preprocessing step, and losing their performance on large-size datasets. To tackle the mentioned restrictions, in this study, we introduced a machine learning framework consisting of two main steps. First, our previously suggested optimization algorithm (Trader) was extended to select a near-optimal subset of features/genes. Second, a voting-based framework was proposed to classify the biological/clinical data with high accuracy. To evaluate the efficiency of the proposed method, it was applied to 13 biological/clinical datasets, and the outcomes were comprehensively compared with the prior methods.

RESULTS

The results demonstrated that the Trader algorithm could select a near-optimal subset of features with a significant level of p-value < 0.01 relative to the compared algorithms. Additionally, on the large-sie datasets, the proposed machine learning framework improved prior studies by ~ 10% in terms of the mean values associated with fivefold cross-validation of accuracy, precision, recall, specificity, and F-measure.

CONCLUSION

Based on the obtained results, it can be concluded that a proper configuration of efficient algorithms and methods can increase the prediction power of machine learning approaches and help researchers in designing practical diagnosis health care systems and offering effective treatment plans.

Few-shot learning via graph embeddings with convolutional networks for low-data molecular property prediction

Graph neural networks and convolutional architectures have proven to be pivotal in improving the prediction of molecular properties in drug discovery. However, this is fundamentally a low data problem that is incompatible with regular deep learning approaches. Contemporary deep networks require large amounts of training data, which severely limits the prediction of new molecular entities from limited available data. In this paper, we address the challenge of low data in molecular property prediction by: (1) defining a set of deep learning architectures that accept compound chemical structures in the form of molecular graphs, (2) creating a few-shot learning strategy across graph neural networks and convolutional neural networks to leverage the rich information of graph embeddings, and (3) proposing a two-module meta-learning framework to learn from task-transferable knowledge and predict molecular properties on few-shot data. Furthermore, we conduct multiple experiments on two benchmark multiproperty datasets to demonstrate a superior performance over conventional graph-based baselines. ROC-AUC results for 10-shot experiments show an average improvement of $$+11.37\%$$ + 11.37 % on Tox21 and $$+0.53\%$$ + 0.53 % on SIDER, which are representative small-sized biological datasets for molecular property prediction.

NSCGCN: A novel deep GCN model to diagnosis COVID-19

AIM

Corona Virus Disease 2019 (COVID-19) was a lung disease with high mortality and was highly contagious. Early diagnosis of COVID-19 and distinguishing it from pneumonia was beneficial for subsequent treatment.

OBJECTIVES

Recently, Graph Convolutional Network (GCN) has driven a significant contribution to disease diagnosis. However, limited by the nature of the graph convolution algorithm, deep GCN has an over-smoothing problem. Most of the current GCN models are shallow neural networks, which do not exceed five layers. Furthermore, the objective of this study is to develop a novel deep GCN model based on the DenseGCN and the pre-trained model of deep Convolutional Neural Network (CNN) to complete the diagnosis of chest X-ray (CXR) images.

METHODS

We apply the pre-trained model of deep CNN to perform feature extraction on the data to complete the extraction of pixel-level features in the image. And then, to extract the potential relationship between the obtained features, we propose Neighbourhood Feature Reconstruction Algorithm to reconstruct them into graph-structured data. Finally, we design a deep GCN model that exploits the graph-structured data to diagnose COVID-19 effectively. In the deep GCN model, we propose a Node-Self Convolution Algorithm (NSC) based on feature fusion to construct a deep GCN model called NSCGCN (Node-Self Convolution Graph Convolutional Network).

RESULTS

Experiments were carried out on the Computed Tomography (CT) and CXR datasets. The results on the CT dataset confirmed that: compared with the six state-of-the-art (SOTA) shallow GCN models, the accuracy and sensitivity of the proposed NSCGCN had improve 8% as sensitivity (Sen.) = 87.50%, F1 score = 97.37%, precision (Pre.) = 89.10%, accuracy (Acc.) = 97.50%, area under the ROC curve (AUC) = 97.09%. Moreover, the results on the CXR dataset confirmed that: compared with the fourteen SOTA GCN models, sixteen SOTA CNN transfer learning models and eight SOTA COVID-19 diagnosis methods on the COVID-19 dataset. Our proposed method had best performances as Sen. = 96.45%, F1 score = 96.45%, Pre. = 96.61%, Acc. = 96.45%, AUC = 99.22%.

CONCLUSION

Our proposed NSCGCN model is effective and performed better than the thirty-eight SOTA methods. Thus, the proposed NSC could help build deep GCN models. Our proposed COVID-19 diagnosis method based on the NSCGCN model could help radiologists detect pneumonia from CXR images and distinguish COVID-19 from Ordinary Pneumonia (OPN). The source code of this work will be publicly available at https://github.com/TangChaosheng/NSCGCN.

BayeshERG: a robust, reliable and interpretable deep learning model for predicting hERG channel blockers

Unintended inhibition of the human ether-à-go-go-related gene (hERG) ion channel by small molecules leads to severe cardiotoxicity. Thus, hERG channel blockage is a significant concern in the development of new drugs. Several computational models have been developed to predict hERG channel blockage, including deep learning models; however, they lack robustness, reliability and interpretability. Here, we developed a graph-based Bayesian deep learning model for hERG channel blocker prediction, named BayeshERG, which has robust predictive power, high reliability and high resolution of interpretability. First, we applied transfer learning with 300 000 large data in initial pre-training to increase the predictive performance. Second, we implemented a Bayesian neural network with Monte Carlo dropout to calibrate the uncertainty of the prediction. Third, we utilized global multihead attentive pooling to augment the high resolution of structural interpretability for the hERG channel blockers and nonblockers. We conducted both internal and external validations for stringent evaluation; in particular, we benchmarked most of the publicly available hERG channel blocker prediction models. We showed that our proposed model outperformed predictive performance and uncertainty calibration performance. Furthermore, we found that our model learned to focus on the essential substructures of hERG channel blockers via an attention mechanism. Finally, we validated the prediction results of our model by conducting in vitro experiments and confirmed its high validity. In summary, BayeshERG could serve as a versatile tool for discovering hERG channel blockers and helping maximize the possibility of successful drug discovery. The data and source code are available at our GitHub repository (https://github.com/GIST-CSBL/BayeshERG).

OptNCMiner: a deep learning approach for the discovery of natural compounds modulating disease-specific multi-targets

Background

Due to their diverse bioactivity, natural product (NP)s have been developed as commercial products in the pharmaceutical, food and cosmetic sectors as natural compound (NC)s and in the form of extracts. Following administration, NCs typically interact with multiple target proteins to elicit their effects. Various machine learning models have been developed to predict multi-target modulating NCs with desired physiological effects. However, due to deficiencies with existing chemical-protein interaction datasets, which are mostly single-labeled and limited, the existing models struggle to predict new chemical-protein interactions. New techniques are needed to overcome these limitations.

Results

We propose a novel NC discovery model called OptNCMiner that offers various advantages. The model is trained via end-to-end learning with a feature extraction step implemented, and it predicts multi-target modulating NCs through multi-label learning. In addition, it offers a few-shot learning approach to predict NC-protein interactions using a small training dataset. OptNCMiner achieved better prediction performance in terms of recall than conventional classification models. It was tested for the prediction of NC-protein interactions using small datasets and for a use case scenario to identify multi-target modulating NCs for type 2 diabetes mellitus complications.

Conclusions

OptNCMiner identifies NCs that modulate multiple target proteins, which facilitates the discovery and the understanding of biological activity of novel NCs with desirable health benefits.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-022-04752-5.

Improving Compound Activity Classification via Deep Transfer and Representation Learning

Recent advances in molecular machine learning, especially deep neural networks such as graph neural networks (GNNs), for predicting structure-activity relationships (SAR) have shown tremendous potential in computer-aided drug discovery. However, the applicability of such deep neural networks is limited by the requirement of large amounts of training data. In order to cope with limited training data for a target task, transfer learning for SAR modeling has been recently adopted to leverage information from data of related tasks. In this work, in contrast to the popular parameter-based transfer learning such as pretraining, we develop novel deep transfer learning methods TAc and TAc-fc to leverage source domain data and transfer useful information to the target domain. TAc learns to generate effective molecular features that can generalize well from one domain to another and increase the classification performance in the target domain. Additionally, TAc-fc extends TAc by incorporating novel components to selectively learn feature-wise and compound-wise transferability. We used the bioassay screening data from PubChem and identified 120 pairs of bioassays such that the active compounds in each pair are more similar to each other compared to their inactive compounds. Overall, TAc achieves the best performance with an average ROC-AUC of 0.801; it significantly improves the ROC-AUC of 83% of target tasks with an average task-wise performance improvement of 7.102%, compared to the best baseline dmpna. Our experiments clearly demonstrate that TAc achieves significant improvement over all baselines across a large number of target tasks. Furthermore, although TAc-fc achieves slightly worse ROC-AUC on average compared to TAc (0.798 vs 0.801), TAc-fc still achieves the best performance on more tasks in terms of PR-AUC and F1 compared to other methods. In summary, TAc-fc is also found to be a strong model with competitive or even better performance than TAc on a notable number of target tasks.

A fuzzy logic-based computational method for the repurposing of drugs against COVID-19

Introduction: COVID-19 has spread out all around the world and seriously interrupted human activities. Being a newfound disease, not only many aspects of the disease are unknown, but also there is not an effective medication to cure the disease. Besides, designing a drug is a time-consuming process and needs large investment. Hence, drug repurposing techniques, employed to discover the hidden benefits of the existing drugs, maybe a useful option for treating COVID-19. Methods: The present study exploits the drug repositioning concepts and introduces some candidate drugs which may be effective in controlling COVID-19. The suggested method consists of three main steps. First, the required data such as the amino acid sequences of targets and drug-target interactions are extracted from the public databases. Second, the similarity score between the targets (protein/enzymes) and genome of SARS-COV-2 is computed using the proposed fuzzy logic-based method. Since the classical approaches yield outcomes which may not be useful for the real-world applications, the fuzzy technique can address the issue. Third, after ranking targets based on the obtained scores, the usefulness of drugs affecting them is examined for managing COVID-19. Results: The results indicate that antiviral medicines, designed for curing hepatitis C, may also cure COVID-19. According to the findings, ribavirin, simeprevir, danoprevir, and XTL-6865 may be helpful in controlling the disease. Conclusion: It can be concluded that the similarity-based drug repurposing techniques may be the most suitable option for managing emerging diseases such as COVID-19 and can be applied to a wide range of data. Also, fuzzy logic-based scoring methods can produce outcomes which are more consistent with the real-world biological applications than others.

Uncertainty-Informed Deep Transfer Learning of Perfluoroalkyl and Polyfluoroalkyl Substance Toxicity

Perfluoroalkyl and polyfluoroalkyl substances (PFAS) pose a significant hazard because of their widespread industrial uses, environmental persistence, and bioaccumulation. A growing, increasingly diverse inventory of PFAS, including 8163 chemicals, has recently been updated by the U.S. Environmental Protection Agency. However, with the exception of a handful of well-studied examples, little is known about their human toxicity potential because of the substantial resources required for in vivo toxicity experiments. We tackle the problem of expensive in vivo experiments by evaluating multiple machine learning (ML) methods, including random forests, deep neural networks (DNN), graph convolutional networks, and Gaussian processes, for predicting acute toxicity (e.g., median lethal dose, or LD₅₀) of PFAS compounds. To address the scarcity of toxicity information for PFAS, publicly available datasets of oral rat LD₅₀ for all organic compounds are aggregated and used to develop state-of-the-art ML source models for transfer learning. A total of 519 fluorinated compounds containing two or more C-F bonds with known toxicity are used for knowledge transfer to ensembles of the best-performing source model, DNN, to generate the target models for the PFAS domain with access to uncertainty. This study predicts toxicity for PFAS with a defined chemical structure. To further inform prediction confidence, the transfer-learned model is embedded within a SelectiveNet architecture, where the model is allowed to identify regions of prediction with greater confidence and abstain from those with high uncertainty using a calibrated cutoff rate.

CRNNTL: Convolutional Recurrent Neural Network and Transfer Learning for QSAR Modeling in Organic Drug and Material Discovery

Molecular latent representations, derived from autoencoders (AEs), have been widely used for drug or material discovery over the past couple of years. In particular, a variety of machine learning methods based on latent representations have shown excellent performance on quantitative structure–activity relationship (QSAR) modeling. However, the sequence feature of them has not been considered in most cases. In addition, data scarcity is still the main obstacle for deep learning strategies, especially for bioactivity datasets. In this study, we propose the convolutional recurrent neural network and transfer learning (CRNNTL) method inspired by the applications of polyphonic sound detection and electrocardiogram classification. Our model takes advantage of both convolutional and recurrent neural networks for feature extraction, as well as the data augmentation method. According to QSAR modeling on 27 datasets, CRNNTL can outperform or compete with state-of-art methods in both drug and material properties. In addition, the performances on one isomers-based dataset indicate that its excellent performance results from the improved ability in global feature extraction when the ability of the local one is maintained. Then, the transfer learning results show that CRNNTL can overcome data scarcity when choosing relative source datasets. Finally, the high versatility of our model is shown by using different latent representations as inputs from other types of AEs.

Multitask CapsNet: An Imbalanced Data Deep Learning Method for Predicting Toxicants

Drug development has a high failure rate, with safety properties constituting a considerable challenge. To reduce risk, in silico tools, including various machine learning methods, have been applied for toxicity prediction. However, these approaches often confront a serious problem: the training data sets are usually biased (imbalanced positive and negative samples), which would result in model training difficulty and unsatisfactory prediction accuracy. Multitask networks obtained significantly better predictive accuracies than single-task methods, and capsule neural networks showed excellent performance in sparse data sets in previous studies. In this study, we developed a new multitask framework based on a capsule neural network (multitask CapsNet) to measure 12 different toxic effects simultaneously. We found that multitask CapsNet excelled in toxicity prediction and outperformed many other computational approaches using the multitask strategy. Only after training on biased data sets did multitask CapsNet achieve significantly improved prediction accuracy on the Tox21 Data Challenge, which gave the largest ratio of highest accuracy (8/12) among compared models. Our model gave a prediction accuracy of 96.6% for the target NR.PPAR.gamma, whose ratio of negative to positive samples was up to 36:1. These results suggested that multitask CapsNet could overcome the bias problems and would provide a novel, accurate, and efficient approach for predicting the toxicities of compounds.

Disrupting 3D printing of medicines with machine learning

3D printing (3DP) is a progressive technology capable of transforming pharmaceutical development. However, despite its promising advantages, its transition into clinical settings remains slow. To make the vital leap to mainstream clinical practice and improve patient care, 3DP must harness modern technologies. Machine learning (ML), an influential branch of artificial intelligence, may be a key partner for 3DP. Together, 3DP and ML can utilise intelligence based on human learning to accelerate drug product development, ensure stringent quality control (QC), and inspire innovative dosage-form design. With ML's capabilities, streamlined 3DP drug delivery could mark the next era of personalised medicine. This review details how ML can be applied to elevate the 3DP of pharmaceuticals and importantly, how it can expedite 3DP's integration into mainstream healthcare.

Deep Learning in Drug Target Interaction Prediction: Current and Future Perspectives

Drug-target Interactions (DTIs) prediction plays a central role in drug discovery. Computational methods in DTIs prediction have gained more attention because carrying out in vitro and in vivo experiments on a large scale is costly and time-consuming. Machine learning methods, especially deep learning, are widely applied to DTIs prediction. In this study, the main goal is to provide a comprehensive overview of deep learning-based DTIs prediction approaches. Here, we investigate the existing approaches from multiple perspectives. We explore these approaches to find out which deep network architectures are utilized to extract features from drug compound and protein sequences. Also, the advantages and limitations of each architecture are analyzed and compared. Moreover, we explore the process of how to combine descriptors for drug and protein features. Likewise, a list of datasets that are commonly used in DTIs prediction is investigated. Finally, current challenges are discussed and a short future outlook of deep learning in DTI prediction is given.

Data science in unveiling COVID-19 pathogenesis and diagnosis: evolutionary origin to drug repurposing

MOTIVATION

The outbreak of novel severe acute respiratory syndrome coronavirus (SARS-CoV-2, also known as COVID-19) in Wuhan has attracted worldwide attention. SARS-CoV-2 causes severe inflammation, which can be fatal. Consequently, there has been a massive and rapid growth in research aimed at throwing light on the mechanisms of infection and the progression of the disease. With regard to this data science is playing a pivotal role in in silico analysis to gain insights into SARS-CoV-2 and the outbreak of COVID-19 in order to forecast, diagnose and come up with a drug to tackle the virus. The availability of large multiomics, radiological, bio-molecular and medical datasets requires the development of novel exploratory and predictive models, or the customisation of existing ones in order to fit the current problem. The high number of approaches generates the need for surveys to guide data scientists and medical practitioners in selecting the right tools to manage their clinical data.

RESULTS

Focusing on data science methodologies, we conduct a detailed study on the state-of-the-art of works tackling the current pandemic scenario. We consider various current COVID-19 data analytic domains such as phylogenetic analysis, SARS-CoV-2 genome identification, protein structure prediction, host-viral protein interactomics, clinical imaging, epidemiological research and drug discovery. We highlight data types and instances, their generation pipelines and the data science models currently in use. The current study should give a detailed sketch of the road map towards handling COVID-19 like situations by leveraging data science experts in choosing the right tools. We also summarise our review focusing on prime challenges and possible future research directions.

CONTACT

hguzzi@unicz.it, sroy01@cus.ac.in.

The challenges of generalizability in artificial intelligence for ADME/Tox endpoint and activity prediction

INTRODUCTION

Artificial intelligence (AI) has seen a massive resurgence in recent years with wide successes in computer vision, natural language processing, and games. The similar creation of robust and accurate AI models for ADME/Tox endpoint and activity prediction would be revolutionary to drug discovery pipelines. There have been numerous demonstrations of successful applications, but a key challenge remains: how generalizable are these predictive models?

AREAS COVERED

The authors present a summary of current promising components of AI models in the context of early drug discovery where ADME/Tox endpoint and activity prediction is the main driver of the iterative drug design process. Following that is a review of applicability domains and dataset construction considerations which determine generalizability bottlenecks for AI deployment. Further reviewed is the role of promising learning frameworks - multitask, transfer, and meta learning - which leverage auxiliary data to overcome issues of generalizability.

EXPERT OPINION

The authors conclude that the most promising direction toward integrating reliable and informative AI models into the drug discovery pipeline is a conjunction of learned feature representations, deep learning, and novel learning frameworks. Such a solution would address the sparse and incomplete datasets that are available for key endpoints related to drug discovery.

DeepCDA: deep cross-domain compound-protein affinity prediction through LSTM and convolutional neural networks

MOTIVATION

An essential part of drug discovery is the accurate prediction of the binding affinity of new compound-protein pairs. Most of the standard computational methods assume that compounds or proteins of the test data are observed during the training phase. However, in real-world situations, the test and training data are sampled from different domains with different distributions. To cope with this challenge, we propose a deep learning-based approach that consists of three steps. In the first step, the training encoder network learns a novel representation of compounds and proteins. To this end, we combine convolutional layers and long-short-term memory layers so that the occurrence patterns of local substructures through a protein and a compound sequence are learned. Also, to encode the interaction strength of the protein and compound substructures, we propose a two-sided attention mechanism. In the second phase, to deal with the different distributions of the training and test domains, a feature encoder network is learned for the test domain by utilizing an adversarial domain adaptation approach. In the third phase, the learned test encoder network is applied to new compound-protein pairs to predict their binding affinity.

RESULTS

To evaluate the proposed approach, we applied it to KIBA, Davis and BindingDB datasets. The results show that the proposed method learns a more reliable model for the test domain in more challenging situations.

AVAILABILITY AND IMPLEMENTATION

https://github.com/LBBSoft/DeepCDA.

Artificial Intelligence in Drug Discovery: A Comprehensive Review of Data-driven and Machine Learning Approaches

As expenditure on drug development increases exponentially, the overall drug discovery process requires a sustainable revolution. Since artificial intelligence (AI) is leading the fourth industrial revolution, AI can be considered as a viable solution for unstable drug research and development. Generally, AI is applied to fields with sufficient data such as computer vision and natural language processing, but there are many efforts to revolutionize the existing drug discovery process by applying AI. This review provides a comprehensive, organized summary of the recent research trends in AI-guided drug discovery process including target identification, hit identification, ADMET prediction, lead optimization, and drug repositioning. The main data sources in each field are also summarized in this review. In addition, an in-depth analysis of the remaining challenges and limitations will be provided, and proposals for promising future directions in each of the aforementioned areas.

Transfer Learning for Drug Discovery

The data sets available to train models for in silico drug discovery efforts are often small. Indeed, the sparse availability of labeled data is a major barrier to artificial-intelligence-assisted drug discovery. One solution to this problem is to develop algorithms that can cope with relatively heterogeneous and scarce data. Transfer learning is a type of machine learning that can leverage existing, generalizable knowledge from other related tasks to enable learning of a separate task with a small set of data. Deep transfer learning is the most commonly used type of transfer learning in the field of drug discovery. This Perspective provides an overview of transfer learning and related applications to drug discovery to date. Furthermore, it provides outlooks on the future development of transfer learning for drug discovery.

Synthetic repurposing of drugs against hypertension: a datamining method based on association rules and a novel discrete algorithm

BACKGROUND

Drug repurposing aims to detect the new therapeutic benefits of the existing drugs and reduce the spent time and cost of the drug development projects. The synthetic repurposing of drugs may prove to be more useful than the single repurposing in terms of reducing toxicity and enhancing efficacy. However, the researchers have not given it serious consideration. To address the issue, a novel datamining method is introduced and applied to repositioning of drugs for hypertension (HT) which is a serious medical condition and needs some improved treatment plans to help treat it.

RESULTS

A novel two-step data mining method, which is based on the If-Then association rules as well as a novel discrete optimization algorithm, was introduced and applied to the synthetic repurposing of drugs for HT. The required data were also extracted from DrugBank, KEGG, and DrugR+ databases. The findings indicated that based on the different statistical criteria, the proposed method outperformed the other state-of-the-art approaches. In contrast to the previously proposed methods which had failed to discover a list on some datasets, our method could find a combination list for all of them.

CONCLUSION

Since the proposed synthetic method uses medications in small dosages, it might revive some failed drug development projects and put forward a suitable plan for treating different diseases such as COVID-19 and HT. It is also worth noting that applying efficient computational methods helps to produce better results.