Anti-cancer drug design has been acknowledged as a complicated, expensive, time-consuming, and challenging task. How to reduce the research costs and speed up the development process of anti-cancer drug designs has become a challenging and urgent question for the pharmaceutical industry. Computer-aided drug design methods have played a major role in the development of cancer treatments for over three decades. Recently, artificial intelligence has emerged as a powerful and promising technology for faster, cheaper, and more effective anti-cancer drug designs. This study is a narrative review that reviews a wide range of applications of artificial intelligence-based methods in anti-cancer drug design. We further clarify the fundamental principles of these methods, along with their advantages and disadvantages. Furthermore, we collate a large number of databases, including the omics database, the epigenomics database, the chemical compound database, and drug databases. Other researchers can consider them and adapt them to their own requirements.

Gastric cancer (GC) is the third leading cause of cancer death worldwide. Its clinical course varies considerably due to the highly heterogeneous tumour microenvironment (TME). Decomposing the complex TME from histological images into its constituent parts is crucial for evaluating its patterns and enhancing GC therapies. Although various deep learning methods were developed in medical field, their applications on this task are hindered by the lack of well-annotated histological images of GC. Through this work, we seek to provide a large database of histological images of GC completely annotated for 8 tissue classes in TME. The dataset consists of nearly 31 K histological images from 300 whole slide images. Additionally, we explained two deep learning models used as validation examples using this dataset.

Drug–target interaction (DTIs) prediction plays a vital role in probing new targets for breast cancer research. Considering the multifaceted challenges associated with experimental methods identifying DTIs, the in silico prediction of such interactions merits exploration. In this study, we develop a feature-based method to infer unknown DTIs, called PsePDC-DTIs, which fuses information regarding protein sequences extracted by pseudo-position specific scoring matrix (PsePSSM), detrended cross-correlation analysis coefficient (DCCA coefficient), and an FP2 format molecular fingerprint descriptor of drug compounds. In addition, the synthetic minority oversampling technique (SMOTE) is employed for dealing with the imbalanced data after Lasso dimensionality reduction. Then, the processed feature vectors are put into a random forest classifier to perform DTIs predictions on four gold standard datasets, including nuclear receptors (NR), G-protein-coupled receptors (GPCR), ion channels (IC), and enzymes (E). Furthermore, we explore new targets for breast cancer treatment using its risk genes identified from large-scale genome-wide genetic studies using PsePDC-DTIs. Through five-fold cross-validation, the average values of accuracy in NR, GPCR, IC, and E datasets are 95.28%, 96.19%, 96.74%, and 98.22%, respectively. The PsePDC-DTIs model provides us with 10 potential DTIs for breast cancer treatment, among which erlotinib (DB00530) and FGFR2 (hsa2263), caffeine (DB00201) and KCNN4 (hsa3783), as well as afatinib (DB08916) and FGFR2 (hsa2263) are found with direct or inferred evidence. The PsePDC-DTIs model has achieved good prediction results, establishing the validity and superiority of the proposed method.

Ultrasonography (US) of thyroid nodules is often time consuming and may be inconsistent between observers, with a low positivity rate for malignancy in biopsies. Even after determining the ultrasound Thyroid Imaging Reporting and Data System (TIRADS) stage, Fine needle aspiration biopsy (FNAB) is still required to obtain a definitive diagnosis. Although various deep learning methods were developed in medical field, they tend to be trained using TI-RADS reports as image labels. Here, we present a large US dataset with pathological diagnosis annotation for each case, designed for developing deep learning algorithms to directly infer histological status from thyroid ultrasound images. The dataset was collected from two retrospective cohorts, which consists of 8508 US images from 842 cases. Additionally, we explained three deep learning models used as validation examples using this dataset.

Accurate detection of abnormal cervical cells in cervical cancer screening increases the chances of timely treatment. The vigorous development of deep learning methods has established a new ecosystem for cervical cancer screening, which has been proven to effectively improve efficiency and accuracy of cell detection in many studies. Although many contributing studies have been conducted, limited public datasets and time-consuming collection efforts may hinder the generalization performance of those advanced models and restrict further research. Through this work, we seek to provide a large dataset of cervical cytology images with exhaustive annotations of abnormal cervical cells. The dataset consists of 8,037 images derived from 129 scanned Thinprep cytologic test (TCT) slide images. Furthermore, we performed evaluation experiments to demonstrate the performance of representative models trained on our dataset in abnormal cells detection.

Detecting the unintended adverse reactions of drugs (ADRs) is a crucial concern in pharmacological research. The experimental validation of drug–ADR associations often entails expensive and time-consuming investigations. Thus, a computational model to predict ADRs from known associations is essential for enhanced efficiency and cost-effectiveness. Here, we propose BiMPADR, a novel model that integrates drug gene expression into adverse reaction features using a message passing neural network on a bipartite graph of drugs and adverse reactions, leveraging publicly available data. By combining the computed adverse reaction features with the structural fingerprints of drugs, we predict the association between drugs and adverse reactions. Our models obtained high AUC (area under the receiver operating characteristic curve) values ranging from 0.861 to 0.907 in an external drug validation dataset under differential experiment conditions. The case study on multiple BET inhibitors also demonstrated the high accuracy of our predictions, and our model’s exploration of potential adverse reactions for HWD-870 has contributed to its research and development for market approval. In summary, our method would provide a promising tool for ADR prediction and drug safety assessment in drug discovery and development.