Biology subjects

Stylianou, E.

Publications and source records attributed to Stylianou, E..

3 recordsLinked to original sources

bioRxiv2024

A Framework for Autonomous AI-Driven Drug Discovery

The exponential increase in biomedical data offers unprecedented opportunities for drug discovery, yet overwhelms traditional data analysis methods, limiting the pace of new drug development. Here we introduce a framework for autonomous artificial intelligence (AI)-driven drug discovery that integrates knowledge graphs with large language models (LLMs). It is capable of planning and carrying out automated drug discovery programs at a massive scale while providing details of its research strategy, progress, and all supporting data. At the heart of this framework lies the focal graph - a novel construct that harnesses centrality algorithms to distill vast, noisy datasets into concise, transparent, data-driven hypotheses. We demonstrate that even small-scale applications of this highly scalable approach can yield novel, transparent insights relevant to multiple stages of the drug discovery process, including chemical structure-based target prediction, and present the implementation of a system which autonomously plans and executes a multi-step target discovery workflow. Graphical Abstract O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=65 SRC="FIGDIR/small/629024v3_ufig1.gif" ALT="Figure 1"> View larger version (18K): org.highwire.dtl.DTLVardef@9d7d7dorg.highwire.dtl.DTLVardef@199d768org.highwire.dtl.DTLVardef@10d0335org.highwire.dtl.DTLVardef@14d8d1c_HPS_FORMAT_FIGEXP M_FIG C_FIG

bioinformatics↗

bioRxiv2021

Assessment of the reproducibility and inter-site transferability of the murine direct splenocyte mycobacterial growth inhibition assay (MGIA)

Tuberculosis (TB) vaccine candidates must be tested for safety and efficacy using preclinical challenge models prior to advancement to human trials, because of the lack of a validated immune correlate or biomarker of protection. New, unbiased tools are urgently needed to expedite the selection of vaccine candidates at an early stage of development and reduce the number of animals experimentally infected with virulent Mycobacterium tuberculosis (M.tb). In recent years, there has been a concerted effort to develop standardised functional ex vivo mycobacterial growth inhibition assays (MGIAs) as a potential surrogate read-out of vaccine efficacy. We have previously described a direct MGIA for use with mouse splenocytes. In the current study, we set out to systematically compare co-culture conditions for the murine direct splenocyte MGIA with respect to both intra-assay repeatability and inter-site reproducibility. Common sample sets were shared between laboratory sites and reproducibility and sensitivity to detect a BCG-vaccine induced response were assessed. Co-culturing 5x106 splenocytes in 48-well plates resulted in improved reproducibility and superior sensitivity to detect a vaccine response compared with standing or rotating sealed 2ml screw-cap tubes. As the difference between naive and BCG vaccinated mice was not consistently detected across both sample sets at both sites, we sought to further improve assay sensitivity by altering the multiplicity of infection (MOI). Cell viability at the end of the co-culture period was improved when splenocyte input number was reduced, with the highest viability for the condition of 3x106 splenocytes in 48-well plates. This cell input was also associated with the greatest sensitivity to detect a BCG vaccine-mediated MGIA response using an M.tb inoculum. Based on our findings, we recommend optimal co-culture conditions in a move towards aligning direct MGIA protocols and generating a cross-species consensus for early evaluation of TB vaccine candidates and biomarker studies.

immunology↗

bioRxiv2017

Cytomegalovirus infection is a risk factor for TB disease in Infants

Immune activation is associated with increased risk of tuberculosis (TB) disease in infants. We performed a case-control analysis to identify drivers of immune activation and disease risk. Among 49 infants who developed TB disease over the first two years of life, and 129 matched controls who remained healthy, we found the cytomegalovirus (CMV) stimulated IFN-{gamma} response at age 4-6 months to be associated with CD8+ T-cell activation (Spearmans rho, p=6x10-8). A CMV specific IFN-{gamma} response was also associated with increased risk of developing TB disease (Conditional Logistic Regression, p=0.043, OR 2.2, 95% CI 1.02-4.83), and shorter time to TB diagnosis (Log Rank Mantel-Cox p=0.037). CMV positive infants who developed TB disease had lower expression of natural killer cell associated gene signatures and a lower frequency of CD3-CD4-CD8-lymphocytes. We identified transcriptional signatures predictive of risk of TB disease among CMV ELISpot positive (AUROC 0.98, accuracy 92.57%) and negative (AUROC 0.9, accuracy 79.3%) infants; the CMV negative signature validated in an independent infant study (AUROC 0.71, accuracy 63.9%). Understanding and controlling the microbial drivers of T cell activation, such as CMV, could guide new strategies for prevention of TB disease in infants.

immunology↗