Biology subjects

MacMahon, M.

Publications and source records attributed to MacMahon, M..

4 recordsLinked to original sources

bioRxiv2025

Utilising multi-modal data-driven network analysis to identify monotherapy and combinational therapy targets in SOX2-dependent squamous cell lung cancer

Drug discovery requires a deep understanding of disease mechanisms, making the integration and analysis of diverse, multi-modal data types essential. These data types, spanning omics types, disease- associated, and biological pathway information, often originate from disparate sources and must be combined to uncover critical insights. We have developed iPANDDA (in-silico Pipeline for Agnostic Network-based Drug Discovery Analysis), a computational pipeline that integrates multi-modal data through a network-based approach to predict candidate drug target proteins for specific diseases. We applied iPANDDA to lung squamous cell carcinoma (LUSC), a subtype of non-small cell lung cancer (NSCLC) that accounts for approximately 25% of all lung cancer cases globally. Despite advances in cancer therapeutics, targeted therapies specifically approved for LUSC remain lacking, exacerbated by the shortage of robust models for studying LUSC carcinogenesis and therapeutic responses. The SOX2 gene, amplified in about 50% of LUSC patients, plays a critical role in driving and maintaining the cancer phenotype. Using iPANDDA, we identified relevant therapeutic targets for SOX2-dependent LUSC. Selected candidate drug targets were validated in vitro using cell-based models. We conducted target inhibition studies in both SOX2-dependent and non-SOX2-dependent cell lines, evaluating the effects of inhibition and knockout through cell viability assays. Our findings confirmed key monotherapy and combination therapy targets for SOX2-focused models. Specifically, we validated the AKT and mTOR complexes as promising therapeutic targets for LUSC. Additionally, we identified potential pathways for developing novel combination therapies targeting SOX2-dependent LUSC. iPANDDA offers a robust approach to refining and focusing therapeutic strategies for diseases with unmet clinical needs.

bioinformatics↗

bioRxiv2022

dialogi: Utilising NLP with chemical and disease similarities to drive the identification of Drug-Induced Liver Injury literature

Drug-Induced Liver Injury (DILI), despite its low occurrence rate, can cause severe side effects or even lead to death. Thus, it is one of the leading causes for terminating the development of new, and restricting the use of already-circulating, drugs. Moreover, its multifactorial nature, combined with a clinical presentation that often mimics other liver diseases, complicate the identification of DILI-related literature, which remains the main medium for sourcing results from the clinical practice and experimental studies. In this work- contributing to the Literature AI for DILI Challenge of the Critical Assessment of Massive Data Analysis (CAMDA) 2021- we present an automated pipeline for distinguishing between DILI-positive and negative papers. We used Natural Language Processing (NLP) to filter out the uninformative parts of a text, and identify and extract mentions of chemicals and diseases. We combined that information with small-molecule and disease embeddings, which are capable of capturing chemical and disease similarities, to improve classification performance. The former are directly sourced from the Chemical Checker (CC). For the latter, we collected data that encode different aspects of disease similarity from the National Library of Medicines (NLM) Medical Subject Headings (MeSH) thesaurus and the Comparative Toxicogenomics Database (CTD). Following a similar procedure as the one used in the CC, vector representations for diseases were learnt and evaluated. Two Neural Network (NN) classifiers were developed: one that only accepts texts as input (baseline model) and an augmented classifier that also utilises chemical and disease embeddings (extended model). We trained, validated, and tested the models through a Nested Cross-Validation (NCV) scheme with 10 outer and 5 inner folds. During this, the baseline and extended models performed virtually identically, with macro F1-scores of 95.04 {+/-} 0.61% and 94.80 {+/-} 0.41%, respectively. Upon validation on an external, withheld, dataset, representing imbalanced data, the extended model achieved an F1-score of 91.14 {+/-} 1.62%, outperforming its baseline counterpart, which got a lower score of 88.30 {+/-} 2.44%. We make further comparisons between the classifiers and discuss future improvements and directions, including utilising chemical and disease embeddings for visualisation and exploratory analysis of the DILI-positive literature.

bioinformatics↗

bioRxiv2022

DILIc: An AI-based classifier to search for Drug-Induced Liver Injury literature

Drug-Induced Liver Injury (DILI) is a class of Adverse Drug Reactions (ADR) which causes problems in both clinical and research settings. It is the most frequent cause of acute liver failure in the majority of western countries and is a major cause of attrition of novel drug candidates. Manual trawling of literature for is the main route of deriving information on DILI from research studies. This makes it an inefficient process prone to human error. Therefore, an automatized AI model capable of retrieving DILI-related papers from the huge ocean of literature could be invaluable for the drug discovery community. In this project, we built an artificial intelligence (AI) model combining the power of Natural Language Processing (NLP) and Machine Learning (ML) to address this problem. This model uses NLP to filter out meaningless text (e.g. stopwords) and uses customized functions to extract relevant keywords as singleton, pair, triplet and so on. These keywords are processed by apriori pattern mining algorithm to extract relevant patterns which are used to estimate initial weightings for a ML classifier. Along with pattern importance and frequency, an FDA-approved drug list mentioning DILI adds extra confidence in classification. The combined power of these methods build a DILI classifier (DILIC) with 94.91% cross-validation and 94.14% external validation accuracy. To make DILIC as accessible as possible, including to researchers without coding experience, an R Shiny App capable of classifing single or multiple entries for DILI is developed to enhance ease of user experience and made available at https://researchmind.co.uk/diliclassifier/).

bioinformatics↗

bioRxiv2020

Identification of SARS-CoV-2 induced pathways reveal drug repurposing strategies

The global outbreak of SARS-CoV-2 necessitates the rapid development of new therapies against COVID-19 infection. Here, we present the identification of 200 approved drugs, appropriate for repurposing against COVID-19. We constructed a SARS-CoV-2-induced protein (SIP) network, based on disease signatures defined by COVID-19 multi-omic datasets(Bojkova et al., 2020; Gordon et al., 2020), and cross-examined these pathways against approved drugs. This analysis identified 200 drugs predicted to target SARS-CoV-2-induced pathways, 40 of which are already in COVID-19 clinical trials(Clinicaltrials.gov, 2020) testifying to the validity of the approach. Using artificial neural network analysis we classified these 200 drugs into 9 distinct pathways, within two overarching mechanisms of action (MoAs): viral replication (130) and immune response (70). A subset of drugs implicated in viral replication were tested in cellular assays and two (proguanil and sulfasalazine) were shown to inhibit replication. This unbiased and validated analysis opens new avenues for the rapid repurposing of approved drugs into clinical trials.

pharmacology and toxicology↗