Biology subjects

Checkley, S.

Publications and source records attributed to Checkley, S..

3 recordsLinked to original sources

bioRxiv2026

An AI-Assisted Workflow for Reconstruction, Extension, and Calibration of Quantitative Systems Pharmacology Models.

AbstractsO_ST_ABSBackgroundC_ST_ABSQuantitative systems pharmacology (QSP) models provide mechanistic insight into drug response but are limited by labor-intensive, expert-driven workflows. We developed an AI-assisted QSP (AI-QSP) framework that integrates large language models (LLMs) with SBML-based modeling to enable automated reconstruction, extension, and calibration of mechanistic models. MethodsThe framework was applied to a published CAR-T QSP model. The model was reconstructed in SBML and extended via LLM-guided prompts to incorporate key resistance mechanisms: T-cell exhaustion, PD-1/PD-L1 checkpoint regulation, and tumor antigen escape. Model development followed an iterative expert-in-the-loop workflow. The resulting model (21 reactions, 9 species) was calibrated to synthetic benchmark data using 19-parameter optimization. Model credibility was assessed using ASME V&V 40 and ICH M15 principles, including global sensitivity and profile-likelihood analyses. ResultsThe calibrated model reproduced benchmark dynamics with high accuracy (mean log-RMSE = 0.132). Sensitivity analysis identified CAR-T killing and bystander cytotoxicity as dominant drivers of tumor response. Profile-likelihood analysis showed 71% of parameters were practically identifiable, with remaining parameters prioritised for future data-driven refinement. ConclusionsAI-assisted QSP modeling enables reproducible, scalable model reconstruction and evolution while maintaining mechanistic transparency and regulatory alignment. This framework provides a foundation for accelerating model-informed drug development in cell and gene therapies.

systems biology↗

bioRxiv2026

RNA foundation models enable generalizable endometriosis disease classification and stable gene-level interpretation

Endometriosis is a chronic inflammatory condition with significant diagnostic delays impacting one in ten reproductive age women worldwide. While machine learning (ML) models trained on transcriptomic data show promise for disease prediction, limited generalizability across independent patient cohorts has hindered clinical translation. Foundations models (FMs) pretrained on large-scale transcriptomic data offer promise to learn transferrable, biologically meaningful representations that could support cross-cohort predictions. We assembled a 12-cohort bulk RNA-seq benchmark (334 samples) and developed a computationally efficient pipeline to test whether FMs improve endometriosis classification, an approach not previously applied to this disease. Using AutoXAI4Omics with cohort-aware validation, we compared embeddings derived from five state-of-the-art RNA FMs against TPM baselines. In cross-cohort prediction, FM embeddings significantly improved performance, achieving a weighted F1-score of 0.83 vs. 0.68 for the baseline. To allow gene-level interpretation of FM embedding models, we introduce classified-aligned integrated gradients (CA-IG), an interpretability approach aligning gene-level attributions to the downstream classifier without end-to-end finetuning. CA-IG revealed a conserved set of predictive genes from FM embeddings across cohort-validation regimes, contrasting with unstable baseline explainability, suggesting that FM embeddings prioritized transferable disease-related signal over cohort-specific effects. These genes include novel candidates that converge on biologically plausible pathways for endometriosis.

bioinformatics↗

bioRxiv2020

Genetic characterization of AmpC and extended-spectrum beta-lactamase (ESBL) phenotypes in Escherichia coli and Salmonella from Alberta poultry

Horizontal gene transfer is an important mechanism which facilitates bacterial populations in overcoming antimicrobial treatment. In this study, a total of 120 Escherichia coli and 62 Salmonella enterica subsp. enterica isolates were isolated from poultry farms in Alberta. Fourteen serovars were identified among Salmonella isolates. Thirty one percent of E. coli isolates were multiclass drug resistant (resistant to [≥] 3 drug classes), while only about 16% of Salmonella isolates were multiclass drug resistant. Among those, eight E. coli isolates had an AmpC-type phenotype, and one Salmonella isolate had an extended-spectrum beta-lactamase (ESBL)-type {beta}-lactamase phenotype. We identified both AmpC-type (blaCMY-2) and ESBL-type (blaTEM) genes in both E. coli and Salmonella isolates. Plasmids from eight of nine E. coli and Salmonella isolates were transferred to recipient strain E. coli J53 through conjugation. Transferable plasmids in above total eight E. coli and Salmonella isolates were also transferred into a lab-made sodium azide-resistant Salmonella recipient through conjugation. The class 1 integrase gene, int1, was detected on plasmids from two E. coli isolates. Further investigation of class 1 integron cassette regions revealed the presence of an aadA gene encoding streptomycin 3"-adenylyltransferase, an aadA1a/aadA2 gene encoding aminoglycoside 3"-O-adenyltransferase, and a putative adenylyltransferase gene. This study provides some insight into potential horizontal gene transfer events of antimicrobial resistance genes between E. coli and Salmonella in poultry production.

microbiology↗