arXiv subjects

Adrienne Hoarfrost

Publications and source records attributed to Adrienne Hoarfrost.

6 recordsLinked to original sources

arXiv2026

An Active Learning Framework for Data-Efficient, Human-in-the-Loop Enzyme Function Prediction

Generalizable protein function prediction is increasingly constrained by the growing mismatch between exponentially expanding sequences of environmental proteins and the comparatively slow accumulation of experimentally verified functional data. Active learning offers a promising path forward for accelerating biological function prediction, by selecting the most informative proteins to experimentally annotate for data-efficient training, yet its potential remains largely unexplored. We introduce HATTER (Human-in-the-loop Adaptive Toolkit for Transferable Enzyme Representations), a modular framework that integrates multiple active learning strategies with human-in-the-loop experimental annotation to efficiently fine tune function prediction models. We compare active learning training to standard supervised training for biological enzyme function prediction, demonstrating that active learning achieves performance comparable to standard training across diverse protein sequence evaluation datasets while requiring fewer model updates, processing less data, and substantially reducing computational cost.

q-bio.QM↗

arXiv2026

GRIMM: Genetic stRatification for Inference in Molecular Modeling

The vast majority of biological sequences encode unknown functions and bear little resemblance to experimentally characterized proteins, limiting both our understanding of biology and our ability to harness functional potential for the bioeconomy. Predicting enzyme function from sequence remains a central challenge in computational biology, complicated by low sequence diversity and imbalanced label support in publicly available datasets. Models trained on these data can overestimate performance and fail to generalize. To address this, we introduce GRIMM (Genetic stRatification for Inference in Molecular Modeling), a benchmark for enzyme function prediction that employs genetic stratification: sequences are clustered by similarity and clusters are assigned exclusively to training, validation, or test sets. This ensures that sequences from the same cluster do not appear in multiple partitions. GRIMM produces multiple test sets: a closed-set test with the same label distribution as training (Test-1) and an open-set test containing novel labels (Test-2), serving as a realistic out-of-distribution proxy for discovering novel enzyme functions. While demonstrated on enzymes, this approach is generalizable to any sequence-based classification task where inputs can be clustered by similarity. By formalizing a splitting strategy often used implicitly, GRIMM provides a unified and reproducible framework for closed- and open-set evaluation. The method is lightweight, requiring only sequence clustering and label annotations, and can be adapted to different similarity thresholds, data scales, and biological tasks. GRIMM enables more realistic evaluation of functional prediction models on both familiar and unseen classes and establishes a benchmark that more faithfully assesses model performance and generalizability.

q-bio.QM↗

arXiv2025

Foundation Models for Astrobiology: Paper I -- Workshop and Overview

Advances in machine learning over the past decade have resulted in a proliferation of algorithmic applications for encoding, characterizing, and acting on complex data that may contain many high dimensional features. Recently, the emergence of deep-learning models trained across very large datasets has created a new paradigm for machine learning in the form of Foundation Models. Foundation Models are programs trained on very large and broad datasets with an extensive number of parameters. Once built, these powerful, and flexible, models can be utilized in less resource-intensive ways to build many different, downstream applications that can integrate previously disparate, multimodal data. The development of these applications can be done rapidly and with a much lower demand for machine learning expertise. And the necessary infrastructure and models themselves are already being established within agencies such as NASA and ESA. At NASA this work is across several divisions of the Science Mission Directorate including the NASA Goddard and INDUS Large Language Models and the Prithvi Geospatial Foundation Model. And ESA initiatives to bring Foundation Models to Earth observations has led to the development of TerraMind. A workshop was held by the NASA Ames Research Center and the SETI Institute, in February 2025, to investigate the potential of Foundation Models for astrobiological research and to determine what steps would be needed to build and utilize such a model or models. This paper shares the findings and recommendations of that workshop, and describes clear near-term, and future opportunities in the development of a Foundation Model (or Models) for astrobiology applications. These applications would include a biosignature, or life characterization, task, a mission development and operations task, and a natural language task for integrating and supporting astrobiology research needs.

astro-ph.IM↗

arXiv2024

A Benchmark Dataset for Multimodal Prediction of Enzymatic Function Coupling DNA Sequences and Natural Language

Predicting gene function from its DNA sequence is a fundamental challenge in biology. Many deep learning models have been proposed to embed DNA sequences and predict their enzymatic function, leveraging information in public databases linking DNA sequences to an enzymatic function label. However, much of the scientific community's knowledge of biological function is not represented in these categorical labels, and is instead captured in unstructured text descriptions of mechanisms, reactions, and enzyme behavior. These descriptions are often captured alongside DNA sequences in biological databases, albeit in an unstructured manner. Deep learning of models predicting enzymatic function are likely to benefit from incorporating this multi-modal data encoding scientific knowledge of biological function. There is, however, no dataset designed for machine learning algorithms to leverage this multi-modal information. Here we propose a novel dataset and benchmark suite that enables the exploration and development of large multi-modal neural network models on gene DNA sequences and natural language descriptions of gene function. We present baseline performance on benchmarks for both unsupervised and supervised tasks that demonstrate the difficulty of this modeling objective, while demonstrating the potential benefit of incorporating multi-modal data types in function prediction compared to DNA sequences alone. Our dataset is at: https://hoarfrost-lab.github.io/BioTalk/.

q-bio.GN↗

arXiv2023

Explainable machine learning identifies multi-omics signatures of muscle response to spaceflight in mice

The adverse effects of microgravity exposure on mammalian physiology during spaceflight necessitate a deep understanding of the underlying mechanisms to develop effective countermeasures. One such concern is muscle atrophy, which is partly attributed to the dysregulation of calcium levels due to abnormalities in SERCA pump functioning. To identify potential biomarkers for this condition, multi-omics data and physiological data available on the NASA Open Science Data Repository (osdr.nasa.gov) were used, and machine learning methods were employed. Specifically, we used multi-omics (transcriptomic, proteomic, and DNA methylation) data and calcium reuptake data collected from C57BL/6J mouse soleus and tibialis anterior tissues during several 30+ day-long missions on the international space station. The QLattice symbolic regression algorithm was introduced to generate highly explainable models that predict either experimental conditions or calcium reuptake levels based on multi-omics features. The list of candidate models established by QLattice was used to identify key features contributing to the predictive capability of these models, with Acyp1 and Rps7 proteins found to be the most predictive biomarkers related to the resilience of the tibialis anterior muscle in space. These findings could serve as targets for future interventions aiming to reduce the extent of muscle atrophy during space travel.

q-bio.QM↗

arXiv2022

Invariant Risk Minimisation for Cross-Organism Inference: Substituting Mouse Data for Human Data in Human Risk Factor Discovery

Human medical data can be challenging to obtain due to data privacy concerns, difficulties conducting certain types of experiments, or prohibitive associated costs. In many settings, data from animal models or in-vitro cell lines are available to help augment our understanding of human data. However, this data is known for having low etiological validity in comparison to human data. In this work, we augment small human medical datasets with in-vitro data and animal models. We use Invariant Risk Minimisation (IRM) to elucidate invariant features by considering cross-organism data as belonging to different data-generating environments. Our models identify genes of relevance to human cancer development. We observe a degree of consistency between varying the amounts of human and mouse data used, however, further work is required to obtain conclusive insights. As a secondary contribution, we enhance existing open source datasets and provide two uniformly processed, cross-organism, homologue gene-matched datasets to the community.

cs.LG↗