Search

Bronchoalveolar lavage of the epithelial lining fluid (BALF) can sample the profound changes in the airway lumen milieu prevalent in chronic obstructive pulmonary disease (COPD). We compared the BALF proteome of ex-smokers with moderate COPD who are not in exacerbation status to non-smoking healthy control subjects and applied proteome-scale translational bioinformatics approaches to identify potential therapeutic protein targets and drugs that modulate these proteins for the treatment of COPD. Proteomic profiles of BALF were obtained from (1) never-smoker control subjects with normal lung function (n = 10) or (2) individuals with stable moderate (GOLD stage 2, FEV1 50–80% predicted, FEV1/FVC < 0.70) COPD who were ex-smokers for at least 1 year (n = 10). After identifying potential crucial hub proteins, drug–proteome interaction signatures were ranked by the computational analysis of novel drug opportunities (CANDO) platform for multiscale therapeutic discovery to identify potentially repurposable drugs. Subsequently, a literature-based knowledge graph was utilized to rank combinations of drugs that most likely ameliorate inflammatory processes. Proteomic network analysis demonstrated that 233 of the >1800 proteins identified in the BALF were significantly differentially expressed in COPD versus control. Functional annotation of the differentially expressed proteins was used to detail canonical pathways containing the differential expressed proteins. Topological network analysis demonstrated that four putative proteins act as central node proteins in COPD. The drugs with the most similar interaction signatures to approved COPD drugs were extracted with the CANDO platform. The drugs identified using CANDO were subsequently analyzed using a knowledge-based technique to determine an optimal two-drug combination that had the most appropriate effect on the central node proteins. Network analysis of the BALF proteome identified critical targets that have critical roles in modulating COPD pathogenesis, for which we identified several drugs that could be repurposed to treat COPD using a multiscale shotgun drug discovery approach.

Humans are exposed to numerous compounds daily, some of which have adverse effects on health. Computational approaches for modeling toxicological data in conjunction with machine learning algorithms have gained popularity over the last few years. Machine learning approaches have been used to predict toxicity-related biological activities using chemical structure descriptors. However, toxicity-related proteomic features have not been fully investigated. In this study, we construct a computational pipeline using machine learning models for predicting the most important protein features responsible for the toxicity of compounds taken from the Tox21 dataset that is implemented within the multiscale Computational Analysis of Novel Drug Opportunities (CANDO) therapeutic discovery platform. Tox21 is a highly imbalanced dataset consisting of twelve in vitro assays, seven from the nuclear receptor (NR) signaling pathway and five from the stress response (SR) pathway, for more than 10,000 compounds. For the machine learning model, we employed a random forest with the combination of Synthetic Minority Oversampling Technique (SMOTE) and the Edited Nearest Neighbor (ENN) method (SMOTE+ENN), which is a resampling method to balance the activity class distribution. Within the NR and SR pathways, the activity of the aryl hydrocarbon receptor (NR-AhR) and the mitochondrial membrane potential (SR-MMP) were two of the top-performing twelve toxicity endpoints with AUCROCs of 0.90 and 0.92, respectively. The top extracted features for evaluating compound toxicity were analyzed for enrichment to highlight the implicated biological pathways and proteins. We validated our enrichment results for the activity of the AhR using a thorough literature search. Our case study showed that the selected enriched pathways and proteins from our computational pipeline are not only correlated with AhR toxicity but also form a cascading upstream/downstream arrangement. Our work elucidates significant relationships between protein and compound interactions computed using CANDO and the associated biological pathways to which the proteins belong for twelve toxicity endpoints. This novel study uses machine learning not only to predict and understand toxicity but also elucidates therapeutic mechanisms at a proteomic level for a variety of toxicity endpoints.

Computational approaches have accelerated novel therapeutic discovery in recent decades. The Computational Analysis of Novel Drug Opportunities (CANDO) platform for shotgun multitarget therapeutic discovery, repurposing, and design aims to improve their efficacy and safety by employing a holistic approach that computes interaction signatures between every drug/compound and a large library of non-redundant protein structures corresponding to the human proteome fold space. These signatures are compared and analyzed to determine if a given drug/compound is efficacious and safe for a given indication/disease. In this study, we used a deep learning-based autoencoder to first reduce the dimensionality of CANDO-computed drug–proteome interaction signatures. We then employed a reduced conditional variational autoencoder to generate novel drug-like compounds when given a target encoded “objective” signature. Using this approach, we designed compounds to recreate the interaction signatures for twenty approved and experimental drugs and showed that 16/20 designed compounds were predicted to be significantly (p-value ≤ 0.05) more behaviorally similar relative to all corresponding controls, and 20/20 were predicted to be more behaviorally similar relative to a random control. We further observed that redesigns of objectives developed via rational drug design performed significantly better than those derived from natural sources (p-value ≤ 0.05), suggesting that the model learned an abstraction of rational drug design. We also show that the designed compounds are structurally diverse and synthetically feasible when compared to their respective objective drugs despite consistently high predicted behavioral similarity. Finally, we generated new designs that enhanced thirteen drugs/compounds associated with non-small cell lung cancer and anti-aging properties using their predicted proteomic interaction signatures. his study represents a significant step forward in automating holistic therapeutic design with machine learning, enabling the rapid generation of novel, effective, and safe drug leads for any indication.