Biology subjects

Hartley, M.-A.

Publications and source records attributed to Hartley, M.-A..

3 recordsLinked to original sources

bioRxiv2026

CAPO: Compute-Aware Automated Protein-Model Optimization

Protein models such as Evolutionary Scale Modeling (ESM), AlphaFold and Boltz have transformed computational protein science, yet a pretrained model rarely transfers to a particular laboratory's assay without adaptation to its data and experimental setting, and that adaptation is technically demanding and spends real compute budget. Existing agentic systems can automate model training, yet typically treat fine-tuning as a reliable tool call: feasibility and cost are estimated rather than measured, and infeasibility is discovered only after compute has been spent. We formulate protein-model adaptation as a gated decision problem: given a task, raw data and a compute budget c_max, a system should decide whether and how to adapt a model before committing expensive computation. We introduce CAPO (Compute-Aware Automated Protein-Model Optimization), a multi-agent system built around one rule: gate before you train. CAPO measures feasibility on the target accelerator, projects cost against the available budget, runs a canary inside the actual training loop and maintains an auditable artifact trail; critically, it can decline an unaffordable adaptation and select a cheaper alternative. We evaluate CAPO, without system changes, on three protein-modeling tasks: (i) SARS-CoV-2 host-range prediction, (ii) hit-to-lead affinity ranking and (iii) temporal variant-effect reclassification. On host range, CAPO partially fine-tuned an 8-million-parameter ESM-2 model to a species-averaged MCC of 0.826, compared with 0.743 for a hand-designed expert transformer; it matched a general coding agent while using 57.4% less GPU time and reduced failed training trials from four to zero. For hit-to-lead affinity ranking, CAPO rejected Boltz-2 fine-tuning and instead trained an assay-calibrated lightweight head over frozen representations, improving ranking on 11 of 15 held-out targets in 1.68 GPU-hours. On temporally held-out ClinVar variants, rank-4 low-rank adaptation of ESM-2 reached an MCC of 0.478, compared with 0.252 for a one-hot baseline and 0.000 for the frozen zero-shot score. These results come from single runs, without a gate ablation and with one generalist-agent comparison. Within those limits, they show that measured admission control can make protein-model adaptation not only automated but selective: deciding what to compute, what not to compute and why.

bioinformatics↗

bioRxiv2019

Novel Rhabdovirus and an almost complete drain fly transcriptome recovered from two independent contaminations of clinical samples.

Metagenomic approaches enable an open exploration of microbial communities without requiring a priori knowledge of a samples composition by shotgun sequencing the total RNA or DNA of the sample. Such an approach is valuable for exploratory diagnostics of novel pathogens in clinical practice. Yet, one may also identify surprising off-target findings. Here we report a mostly complete transcriptome from a drain fly (likely Psychoda alternata) as well as a novel Rhabdovirus-like virus recovered from two independent contaminations of RNA sequencing libraries from clinical samples of cerebral spinal fluid (CSF) and serum, out of a total of 724 libraries sequenced at the same laboratory during a 2-year time span. This drain fly genome shows a considerable divergence from previously sequenced insects, which may obscure common clinical metagenomic analyses not expecting such contaminations. The classification of these contaminant sequences allowed us to identify infected drain flies as the likely origin of the novel Rhabdovirus-like sequence, which could have been erroneously linked to human pathology, had they been ignored.

bioinformatics↗

bioRxiv2018

Prognostic models for Ebola virus disease derived from data collected at five treatment units in Sierra Leone and Liberia: performance, external validation, and risk visualization

BackgroundWe created a family of prognostic models for Ebola virus disease from the largest dataset of EVD patients published to date. We incorporated these models into an app, \"Ebola Care Guidelines\", that provides access to recommended, evidence-based supportive care guidelines and highlights the signs/symptoms with the largest contribution to prognosis.\n\nMethodsWe applied multivariate logistic regression on 470 patients admitted to five Ebola treatment units in Liberia and Sierra Leone during the 2014-16 outbreak. We validated the models with two independent datasets from Sierra Leone.\n\nFindingsViral load and age were the most important predictors of death. We generated a parsimonious model including viral load, age, body temperature, bleeding, jaundice, dyspnea, dysphagia, and referral time recorded at triage. We also constructed fallback models for when variables in the parsimonious model are unavailable. The performance of the parsimonious model approached the predictive power of observational wellness assessments by experienced health workers, with Area Under the Curve (AUC) ranging from 0.7 to 0.8 and overall accuracy of 64% to 74%.\n\nInterpretationMachine-learning models and mHealth tools have the potential for improving the standard of care in low-resource settings and emergency scenarios, but data incompleteness and lack of generalizable models are major obstacles. We showed how harmonization of multiple datasets yields prognostic models that can be validated across different cohorts. Similar performance between the parsimonious model and those incorporating expert wellness assessments suggests that clinically-guided machine learning approaches can recapitulate clinical expertise, and thus be useful when such expertise is unavailable. We also demonstrated with our guidelines app how integration of those models with mobile technologies enables deployable clinical management support tools that facilitate access to comprehensive bodies of medical knowledge.\n\nFundingHoward Hughes Medical Institute, US National Institutes of Health

bioinformatics↗