Drug-induced cardiotoxicity (DICT) is a leading cause of drug trial failure and discontinuation. Current drug annotations for cardiotoxicity largely focus on individual outcomes or mechanisms. Considering the broad spectrum of adverse cardiac events, we developed Drug-Induced Cardiotoxicity Rank (DICTrank) using FDA labeling and comprehensively classified 1318 human drugs into four categories: Most-DICT-Concern (n=341), Less-DICT-Concern (n=528), No-DICT-Concern (n=343), and Ambiguous-DICT-Concern (n=106). Notably, DICTrank covers diverse therapeutic categories, of which several were enriched with Most-DICT-Concern drugs, such as antineoplastic agents, sex hormones, anti-inflammatory drugs, beta-blockers, and cardiac therapy. DICTrank currently presents the largest drug list of DICT annotation, and it could contribute to the development of new approach methods, including AI models for early identification of DICT risk during drug development and beyond.
1 January 2021 in Annals of Translational Medicine
Background: Alzheimer’s disease (AD) is an age-progressive neurodegenerative disorder that affects cognitive function. There have been several functional connectivity (FC) strengths; however, FC density needs more development in AD. Therefore, this study wanted to determine the alternations in resting-state functional connectivity density (FCD) induced by Alzheimer’s and mild cognitive impairment (MCI). Methods: One hundred and eleven AD patients, 29 MCI patients, and 73 healthy controls (age- and sex-matched) were recruited and assessed using resting-state functional magnetic resonance imaging (MRI) scanning. The ultra-fast graph theory called FCD mapping was used to calculate the voxel-wise short- and long-range FCD values of the brain. We performed voxel-based between-group comparisons of FCD values to show the cerebral regions with significant FCD alterations. We performed Pearson’s correlation analyses between aberrant functional connectivity densities and several clinical variables with adjustment for age and sex. Results: Patients with cognition decline showed significantly abnormal long-range FCD in the cerebellum crus I, right insula, left inferior frontal gyrus, left superior frontal gyrus, left inferior frontal gyrus, and right middle frontal gyrus. The short-range FCD changed in the cerebellum crus I, left inferior frontal gyrus, left superior occipital gyrus, and right middle frontal gyrus. The long- and short-range functional connectivity in the left inferior frontal gyrus was positively correlated with Mini-mental State Examination (MMSE) scores. Conclusions: FCD in the identified regions reflects mechanism and compensation for loss of cognitive function. These findings could improve the pathology of AD and MCI and supply a neuroimaging marker for AD and MCI.
Translational research in toxicology has significantly benefited from transcriptomic profiling, particularly in drug safety. However, its application has predominantly focused on limited organs, notably the liver, due to resource constraints. This paper presents TransTox, an innovative AI model using a generative adversarial network (GAN) method to facilitate the bidirectional translation of transcriptomic profiles between the liver and kidney under drug treatment. TransTox demonstrates robust performance, validated across independent datasets and laboratories. First, the concordance between real experimental data and synthetic data generated by TransTox was demonstrated in characterizing toxicity mechanisms compared to real experimental settings. Second, TransTox proved valuable in gene expression predictive models, where synthetic data could be used to develop gene expression predictive models or serve as “digital twins” for diagnostic applications. The TransTox approach holds the potential for multi-organ toxicity assessment with AI and advancing the field of precision toxicology.
Animal studies are required for the evaluation of candidate drugs to ensure patient and volunteer safety. Toxicogenomics is often applied in these studies to gain understanding of the underlying mechanisms of toxicity, which is usually focused on critical organs such as the liver or kidney in young male rats. There is a strong ethical reason to reduce, refine and replace animal use (the 3Rs), where the mapping of data between organs, sexes and ages could reduce the cost and time of drug development. Herein, we proposed a generative adversarial network (GAN)-based framework entitled TransOrGAN that allowed the molecular mapping of gene expression profiles in different rodent organ systems and across sex and age groups. We carried out a proof-of-concept study based on rat RNA-seq data from 288 samples in 9 different organs of both sexes and 4 developmental stages. First, we demonstrated that TransOrGAN could infer transcriptomic profiles between any 2 of the 9 organs studied, yielding an average cosine similarity of 0.984 between synthetic transcriptomic profiles and their corresponding real profiles. Second, we found that TransOrGAN could infer transcriptomic profiles observed in females from males, with an average cosine similarity of 0.984. Third, we found that TransOrGAN could infer transcriptomic profiles in juvenile, adult, and aged animals from adolescent animals with an average cosine similarity of 0.981, 0.983, and 0.989, respectively. Altogether, TransOrGAN is an innovative approach to infer transcriptomic profiles between ages, sexes, and organ systems, offering the opportunity to reduce animal usage and to provide an integrated assessment of toxicity in the whole organism irrespective of sex or age.
With the accomplishment of the Human Genome Project, the significance of protein structure research becomes more outstanding. The prediction of protein structure is aimed at the study of amino acid molecules, and belongs to the field of Bio-Nano research. There are two kinds of methods to study protein structure: experiment and theory. This paper adopts ab-initio prediction method which is one of theoretical methods. Based on the "thermodynamic hypothesis," there are many different models applied to the field. This paper selects 3D AB off-lattice model to solve this problem. ABC-PIO combines the characteristics of the diversity generated by artificial bee colony algorithm and the fast convergence speed of pigeon inspired optimization. At the end of this algorithm, Cauchy perturbation strategy is added to optimize the local optimum. Two functions are introduced to dynamically control two operators of the hybrid algorithm. In order to test the quality of ABC-PIO, ten real protein sequences from the Protein Data Bank have been selected. Compared with other four algorithms, the algorithm gets better result. To calculate the error between the predicted and the true protein structure RMSD is set. Comparisons are made not only in the convergence curves but also in the backbone drawings.