Biology subjects

Butte, A.

Publications and source records attributed to Butte, A..

8 recordsLinked to original sources

bioRxiv2025

Auto-MedCalc: Automated Biomarkers Discovery and Risk Score Generation with AI Agents

Reproducible biomarker identification and transplant rejection risk prediction remain fundamental yet unsolved challenges in transplantation medicine. Traditional approaches rely on hypothesis-driven analyses and domain expertise, limiting scalability and generalizability across diverse populations. We introduce Transplant-Agents, a data-driven multi-agent AI framework integrating large language models (LLMs) with machine learning algorithms for automated biomarker identification and rejection risk prediction. Agents interact through structured, iterative dialogue governed by predefined rules and criteria, converging on optimal biomarker sets reproducible across multiple iterations. We evaluated three multicenter clinical trial transplant datasets from ImmPort, comprising 683 patients across kidney, liver, and heart transplant cohorts. Transplant-Agents achieve AUROC scores of 0.93, 0.88, and 0.88. Feature importance analysis further confirms the stability, interpretability and potential generalizability of identified biomarkers. This work demonstrates that AI-agent frameworks can reliably reproduce established transplant biomarkers while enabling transparent, validated, and standardized risk prediction pipelines.

bioinformatics↗

bioRxiv2025

ImmuneFM: Pre-training Foundation Model from Cytometry Data for Immunology Research

Immunology is an essential field in the biomedicine domain, which plays an important role in oncology, vaccines, infection, etc. With the increasing amount of data available in immunology and artificial intelligence technique development, there is a need to develop data-driven AI methods in the field. However, the data from various immunology studies is very hard to integrate into an AI-ready dataset due to the lack of a standard. Moreover, independent immunology studies data lacks enough labels to train the supervised model. Motivated by these challenges, we curated a large-scale AI-ready cytometry dataset for immunology from the publicly available ImmPort portal. We design the framework to pre-train a foundation model, ImmuneFM, on the cytometry dataset. ImmuneFM can be applied to a wide range of downstream immunology diseases with fine-tuning on a limited number of labeled samples. The experiment results on eight downstream tasks demonstrate the superior performance of ImmuneFM compared to baseline deep learning and traditional methods.

immunology↗

bioRxiv2024

Self-driving development of perfusion processes for monoclonal antibody production

The development of autonomous agents in bioporcess development is crucial for advancing biopharma innovation, as it can significantly reduce the time and resources required to transition from product to process. While robotics and machine learning have greatly accelerated drug discovery and initial screening, the later stages of development have primarily benefited from experimental automation, lacking advanced computational tools for experimental planning and execution. For example, in the development of new monoclonal antibodies, the search for optimal upstream conditions (such as feeding strategy, pH, temperature, and media composition) is often conducted using sophisticated high-throughput (HT) mini-bioreactor systems, while the integration of machine learning tools for experimental design and operation in these systems have not matured accordingly. In this work, we introduce an integrated user-friendly software framework that combines a Bayesian experimental design algorithm, a cognitive digital twin of the cultivation system, and an advanced 24-parallel mini-bioreactor perfusion experimental setup. This results in an autonomous experimental machine capable of: (1) embedding existing process knowledge, (2) learning during experimentation, utilizing information from similar processes, (4) predicting future events, and (5) autonomously operating the parallel cultivation setup to achieve challenging objectives. As proof of concept, we present experimental results from 27-day-long cultivations operated by the autonomous software agent, which successfully achieved challenging goals such as increasing the viable cell volume (VCV) and maximizing the viability throughout the experiment.

bioengineering↗

bioRxiv2023

DeepHeme: A generalizable, bone marrow classifierwith hematopathologist-level performance

Morphology-based classification of cells in the bone marrow aspirate (BMA) is a key step in the diagnosis and management of hematologic malignancies. However, it is time-intensive and must be performed by expert hematopathologists and laboratory professionals. We curated a large, high-quality dataset of 41,595 hematopathologist consensus-annotated single-cell images extracted from BMA whole slide images (WSIs) containing 23 morphologic classes from the clinical archives of the University of California, San Francisco. We trained a convolutional neural network, DeepHeme, to classify images in this dataset, achieving a mean area under the curve (AUC) of 0.99. DeepHeme was then externally validated on WSIs from Memorial Sloan Kettering Cancer Center, with a similar AUC of 0.98, demonstrating robust generalization. When compared to individual hematopathologists from three different top academic medical centers, the algorithm outperformed all three. Finally, DeepHeme reliably identified cell states such as mitosis, paving the way for image-based quantification of mitotic index in a cell-specific manner, which may have important clinical applications.

bioinformatics↗

bioRxiv2021

Hybrid Gaussian Process Models for continuous time series in bolus fed-batch cultures

Hybrid modeling, meaning the integration of data-driven and knowledge-based methods, is quickly gaining popularity among many research fields, including bioprocess engineering and development. Recently, the data-driven part of hybrid methods have been largely extended with machine learning algorithms (e.g., artificial neural network, support vector regression), while the mechanistic part is typically using differential equations to describe the dynamics of the process based on its current state. In this work we present an alternative hybrid model formulation that merges the advantages of Gaussian Process State Space Models and the numerical approximation of differential equation systems through full discretization. The use of Gaussian Process Models to describe complex bioprocesses in batch, fed-batch, has been reported in several applications. Nevertheless, handling the dynamics of the states of the system, known to have a continuous time-dependent evolution governed by implicit dynamics, has proven to be a major challenge. Discretization of the process on the sampling steps is a source of several complications, as are: 1) not being able to handle multi-rate date sets, 2) the step-size of the derivative approximation is defined by the sampling frequency, and 3) a high sensitivity to sampling and addition errors. We present a coupling of polynomial regression with Gaussian Process Models as representation of the right-hand side of the ordinary differential equation system and demonstrate the advantages in a typical fed-batch cultivation for monoclonal antibody production.

bioengineering↗

bioRxiv2021

Functional-Hybrid Modeling through automated adaptive symbolic regression for interpretable mathematical expressions

Mathematical models used for the representation of (bio)-chemical processes can be grouped into two broad paradigms: white-box or mechanistic models, completely based on knowledge or black-box data-driven models based on patterns observed in data. However, in the past two-decade, hybrid modeling that explores the synergy between the two paradigms has emerged as a pragmatic compromise. The data-driven part of these have been largely based on conventional machine learning algorithm (e.g., artificial neural network, support vector regression), which prevents interpretability of the finally learnt model by the domain-experts. In this work we present a novel hybrid modeling framework, the Functional-Hybrid model, that uses the ranked domain-specific functional beliefs together with symbolic regression to develop dynamic models. We demonstrate the successful implementation of these hybrid models for four benchmark systems and a microbial fermentation reactor, all of which are systems of (bio)chemical relevance. We also demonstrate that compared to a similar implementation with the conventional ANN, the performance of Functional-Hybrid model is at least two times better in interpolation and extrapolation. Additionally, the proposed framework can learn the dynamics in 50% lower number of experiments. This improved performance can be attributed to the structure imposed by the functional transformations introduced in the Functional-Hybrid model.

bioengineering↗

bioRxiv2020

Learning epistatic polygenic phenotypes with Boolean interactions

Detecting epistatic drivers of human phenotypes is a considerable challenge. Traditional approaches use regression to sequentially test multiplicative interaction terms involving pairs of genetic variants. For higher-order interactions and genome-wide large-scale data, this strategy is computationally intractable. Moreover, multiplicative terms used in regression modeling may not capture the form of biological interactions. Building on the Predictability, Computability, Stability (PCS) framework, we introduce the epiTree pipeline to extract higher-order interactions from genomic data using tree-based models. The epiTree pipeline first selects a set of variants derived from tissue-specific estimates of gene expression. Next, it uses iterative random forests (iRF) to search training data for candidate Boolean interactions (pairwise and higher-order). We derive significance tests for interactions, based on a stabilized likelihood ratio test, by simulating Boolean tree-structured null (no epistasis) and alternative (epistasis) distributions on hold-out test data. Finally, our pipeline computes PCS epistasis p-values that probabilisticly quantify improvement in prediction accuracy via bootstrap sampling on the test set. We validate the epiTree pipeline in two case studies using data from the UK Biobank: predicting red hair and multiple sclerosis (MS). In the case of predicting red hair, epiTree recovers known epistatic interactions surrounding MC1R and novel interactions, representing non-linearities not captured by logistic regression models. In the case of predicting MS, a more complex phenotype than red hair, epiTree rankings prioritize novel interactions surrounding HLA-DRB1, a variant previously associated with MS in several populations. Taken together, these results highlight the potential for epiTree rankings to help reduce the design space for follow up experiments.

bioinformatics↗

bioRxiv2019

Integrating Biomedical Research and Electronic Health Records to Create Knowledge Based Biologically Meaningful Machine Readable Embeddings

In order to advance precision medicine, detailed clinical features ought to be described in a way that leverages current knowledge. Although data collected from biomedical research is expanding at an almost exponential rate, our ability to transform that information into patient care has not kept at pace. A major barrier preventing this transformation is that multi-dimensional data collection and analysis is usually carried out without much understanding of the underlying knowledge structure. In an effort to bridge this gap, Electronic Health Records (EHRs) of individual patients were connected to a heterogeneous knowledge network called Scalable Precision Medicine Oriented Knowledge Engine (SPOKE). Then an unsupervised machine-learning algorithm was used to create Propagated SPOKE Entry Vectors (PSEVs) that encode the importance of each SPOKE node for any code in the EHRs. We argue that these results, alongside the natural integration of PSEVs into any EHR machine-learning platform, provide a key step toward precision medicine.

systems biology↗