Biology subjects

Ellington, C.

Publications and source records attributed to Ellington, C..

5 recordsLinked to original sources

bioRxiv2026

Large Language Model Agent Enables Autonomous Machine Learning Model Building for Biomedicine

Machine learning accelerates biomedical discovery, but creating effective predictive models requires specialized human expertise and demanding manual effort. Researchers must iteratively design pipelines, select architectures, and debug code. This challenge is particularly severe in biomedicine because of the heterogeneous datasets, sparse annotations, and complex evaluation protocols that are common in the domain. We present AIDO.Builder, an agentic artificial intelligence system that fully automates the entire life-cycle of biomedical model development. Provided only with a natural language task description and a target metric, AIDO.Builder autonomously constructs executable training and evaluation pipelines. The system selects suitable modeling strategies, executes experiments, and uses automated feedback-loop to iteratively revise its own code, configurations, and training procedures. It flexibly adapts to new tasks by training specialized models de novo or by using pretrained foundation models to build predictive models through task-appropriate adaptation. We show that across diverse biomedical benchmarks, AIDO. Builder produces highly competitive solutions against human alternatives, while eliminating the manual iteration previously required for robust model development. By automating the translation of raw data into reliable AI models, AIDO.Builder demonstrates how AI itself can be used to accelerate AI for biomedical research.

bioinformatics↗

bioRxiv2026

Foundation Models Improve Perturbation Response Prediction

Predicting cellular responses to genetic or chemical perturbations has been a long-standing goal in biology. Recent applications of foundation models to this task have yielded contradictory results regarding their superiority over simple baselines. We conducted an extensive analysis of over 600 different models across various prediction tasks and evaluation metrics, demonstrating that while some foundation models fail to outperform simple baselines, others significantly improve predictions for both genetic and chemical perturbations. Furthermore, we developed and evaluated methods for integrating multiple foundation models for perturbation prediction. Our results show that with sufficient data, these models approach fundamental performance limits, confirming that foundation models can improve cellular response simulations. Code and Data: https://github.com/genbio-ai/foundation-models-perturbation

bioinformatics↗

bioRxiv2025

Interpretable adenylation domain specificity prediction using protein language models

Natural products have long been a rich source of diverse and clinically effective drug candidates. Non-ribosomal peptides (NRPs), polyketides (PKs), and NRP-PK hybrids are three classes of natural products that display a broad range of bioactivities, including antibiotic, antifungal, anticancer, and immunosuppressant activities. However, discovering these compounds through traditional bioactivity-guided techniques is costly and time-consuming, often resulting in the rediscovery of known molecules. Consequently, genome mining has emerged as a high-throughput strategy to screen hundreds of thousands of microbial genomes to identify their potential to produce novel natural products. Adenylation domains play a key role in the biosynthesis of NRPs and NRP-PKs by recruiting substrates to incrementally build the final structure. We propose MASPR, a machine learning method that leverages protein language models for accurate and interpretable predictions of A-domain substrate specificities. MASPR demonstrates superior accuracy and generalization over existing methods and is capable of predicting substrates not present in its training data, or zero-shot classification. We use MASPR to develop Seq2Hybrid, an efficient algorithm to predict the structure of hybrid NRP-PK natural products from microbial genomes. Using Seq2Hybrid, we propose putative biosynthetic gene clusters for the orphan natural products Octaminomycin A, Dityromycin, SW-163B, and JBIR-39.

bioinformatics↗

bioRxiv2024

AttentionPert: Accurately Modeling Multiplexed Genetic Perturbations with Multi-scale Effects

Genetic perturbations (i.e. knockouts, variants) have laid the foundation for our understanding of many diseases, implicating pathogenic mechanisms and indicating therapeutic targets. However, experimental assays are fundamentally limited in the number of perturbation conditions they can measure. Computational methods can fill this gap by predicting perturbation effects under unseen conditions, but accurately predicting the transcriptional responses of cells to unseen perturbations remains a significant challenge. We address this by developing a novel attention-based neural network, AttentionPert, which accurately predicts gene expression under multiplexed perturbations and generalizes to unseen conditions. AttentionPert integrates global and local effects in a multi-scale model, representing both the non-uniform system-wide impact of the genetic perturbation and the localized disturbance in a network of gene-gene similarities, enhancing its ability to predict nuanced transcriptional responses to both single and multi-gene perturbations. In comprehensive experiments, AttentionPert demonstrates superior performance across multiple datasets outperforming the state-of-theart method in predicting differential gene expressions and revealing novel gene regulations. AttentionPert marks a significant improvement over current methods, particularly in handling the diversity of gene perturbations and in predicting out-of-distribution scenarios.

bioinformatics↗

bioRxiv2020

Vectorchip: Microfluidic platform for highly parallel bite by bite profiling of mosquito-borne pathogen transmission

Mosquito bites transmit a number of human pathogens resulting in potentially fatal diseases including malaria, dengue, chikungunya, West Nile encephalitis, and Zika. Although female mosquitoes transmit pathogens via salivary droplets deposited during blood feeding on a host, very little is known about the genomic content of these nanoliter scale droplets, including the transmission dynamics of live pathogens. Here we introduce Vectorchip, a low-cost, scalable microfluidic platform for molecular interrogation of individual mosquito bites in a high-throughput fashion. An ultra-thin PDMS membrane coupled to a microfluidic chip acts as a biting interface, through which freely-behaving mosquitoes deposit saliva droplets by biting into isolated arrayed micro-wells enabling molecular interrogation of individual bites. By modulating membrane thickness, the device enables on-chip comparison of biting capacity and provides a mechanical filter allowing selection of a specific mosquito species. Utilizing Vectorchip, we show on-chip simultaneous detection of mosquito DNA as well as viral RNA from Zika infected Aedes aegypti mosquitoes - demonstrating multiplexed high-throughput screening of vectors and pathogens. Focus-forming assays performed on-chip quantify number of infectious viral particles transmitted during mosquito bites, enabling assessment of active virus transmission. The platform presents a promising approach for single-bite-resolution laboratory and field characterization of vector pathogen communities, to reveal the intricate dynamics of pathogen transmission, and could serve as powerful early warning artificial "sentinel" for mosquito-borne diseases.

bioengineering↗