This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

The genome of a eukaryotic cell is often vulnerable to both intrinsic and extrinsic threats due to its constant exposure to a myriad of heterogeneous compounds.Despite the availability of innate DNA damage response pathways, some genomic lesions trigger cells for malignant transformation. Accurate prediction of carcinogens is an ever-challenging task due to the limited information about bona fide (non)carcinogens. We developed Metabokiller, an ensemble classifier that accurately recognizes carcinogens by quantitatively assessing their electrophilicity as well as their potential to induce proliferation, oxidative stress, genomic instability, alterations in the epigenome, and anti-apoptotic response. Concomitant with the carcinogenicity prediction, Metabokiller is fully interpretable since it reveals the contribution of the aforementioned biochemical properties in imparting carcinogenicity. Metabokiller outperforms existing best-practice methods for carcinogenicity prediction. We used Metabokiller to unravel cells' endogenous metabolic threats by screening a large pool of human metabolites and predicted a subset of these metabolites that could potentially trigger malignancy in normal cells. To cross-validate Metabokiller predictions, we performed a range of functional assays using Saccharomyces cerevisiae and human cells with two Metabokiller-flagged human metabolites namely 4-Nitrocatechol and 3,4-Dihydroxyphenylacetic acid and observed high synergy between Metabokiller predictions and experimental validations.

Artificial intelligence (AI)-based computational techniques allow rapid exploration of the chemical space. However, representation of the compounds into computational-compatible and detailed features is one of the crucial steps for quantitative structure–activity relationship (QSAR) analysis. Recently, graph-based methods are emerging as a powerful alternative to chemistry-restricted fingerprints or descriptors for modeling. Although graph-based modeling offers multiple advantages, its implementation demands in-depth domain knowledge and programming skills. Here we introduce deepGraphh, an end-to-end web service featuring a conglomerate of established graph-based methods for model generation for classification or regression tasks. The graphical user interface of deepGraphh supports highly configurable parameter support for model parameter tuning, model generation, cross-validation and testing of the user-supplied query molecules. deepGraphh supports four widely adopted methods for QSAR analysis, namely, graph convolution network, graph attention network, directed acyclic graph and Attentive FP. Comparative analysis revealed that deepGraphh supported methods are comparable to the descriptors-based machine learning techniques. Finally, we used deepGraphh models to predict the blood–brain barrier permeability of human and microbiome-generated metabolites. In summary, deepGraphh offers a one-stop web service for graph-based methods for chemoinformatics.