Thomas Desautels
YOU?
Author Swipe
View article: Design of cross-reactive antigens with machine learning and high-throughput experimental evaluation
Design of cross-reactive antigens with machine learning and high-throughput experimental evaluation Open
Selecting an optimal antigen is a crucial step in vaccine development, significantly influencing both the vaccine’s effectiveness and the breadth of protection it provides. High antigen sequence variability, as seen in pathogens like rhino…
View article: Deep Symbolic Optimization: Reinforcement Learning for Symbolic Mathematics
Deep Symbolic Optimization: Reinforcement Learning for Symbolic Mathematics Open
Deep Symbolic Optimization (DSO) is a novel computational framework that enables symbolic optimization for scientific discovery, particularly in applications involving the search for intricate symbolic structures. One notable example is eq…
View article: Preemptive optimization of a clinical antibody for broad neutralization of SARS-CoV-2 variants and robustness against viral escape
Preemptive optimization of a clinical antibody for broad neutralization of SARS-CoV-2 variants and robustness against viral escape Open
Most previously authorized clinical antibodies against severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) have lost neutralizing activity to recent variants due to rapid viral evolution. To mitigate such escape, we preemptively e…
View article: Robust Multi-fidelity Bayesian Optimization with Deep Kernel and Partition
Robust Multi-fidelity Bayesian Optimization with Deep Kernel and Partition Open
View article: Practical Bayesian Algorithm Execution via Posterior Sampling
Practical Bayesian Algorithm Execution via Posterior Sampling Open
We consider Bayesian algorithm execution (BAX), a framework for efficiently selecting evaluation points of an expensive function to infer a property of interest encoded as the output of a base algorithm. Since the base algorithm typically …
View article: Computationally restoring the potency of a clinical antibody against Omicron
Computationally restoring the potency of a clinical antibody against Omicron Open
View article: Learning Regions of Interest for Bayesian Optimization with Adaptive Level-Set Estimation
Learning Regions of Interest for Bayesian Optimization with Adaptive Level-Set Estimation Open
We study Bayesian optimization (BO) in high-dimensional and non-stationary scenarios. Existing algorithms for such scenarios typically require extensive hyperparameter tuning, which limits their practical effectiveness. We propose a framew…
View article: Language model-accelerated deep symbolic optimization
Language model-accelerated deep symbolic optimization Open
View article: Improv Dynamic Workflows
Improv Dynamic Workflows Open
A workflow is a series of dependent computations which are executed to yield an experimental result, much like sheet music describes a musical performance. Dynamic workflows are like improvisational jazz, in which the musicians create uniq…
View article: Review materials for Computationally Restoring the Potency of a Clinical Antibody
Review materials for Computationally Restoring the Potency of a Clinical Antibody Open
Train and use machine learning models; select protein sequences for simulation and laboratory testing. Code implements key decision steps in this process. Provided for review purposes and public release.
View article: Computationally restoring the potency of a clinical antibody against SARS-CoV-2 Omicron subvariants
Computationally restoring the potency of a clinical antibody against SARS-CoV-2 Omicron subvariants Open
The COVID-19 pandemic underscored the promise of monoclonal antibody-based prophylactic and therapeutic drugs 1–3 , but also revealed how quickly viral escape can curtail effective options 4, 5 . With the emergence of the SARS-CoV-2 Omicro…
View article: Learning Region of Interest for Bayesian Optimization with Adaptive Level-Set Estimation
Learning Region of Interest for Bayesian Optimization with Adaptive Level-Set Estimation Open
View article: AbBERT: Learning Antibody Humanness via Masked Language Modeling
AbBERT: Learning Antibody Humanness via Masked Language Modeling Open
Understanding the degree of humanness of antibody sequences is critical to the therapeutic antibody development process to reduce the risk of failure modes like immunogenicity or poor manufacturability. We introduce AbBERT, a transformer-b…
View article: Large-scale application of free energy perturbation calculations for antibody design
Large-scale application of free energy perturbation calculations for antibody design Open
View article: Fluorescence correlation spectroscopy measurements of proteins expressed inside microcapsules
Fluorescence correlation spectroscopy measurements of proteins expressed inside microcapsules Open
View article: SARS-COV-2 Omicron variant predicted to exhibit higher affinity to ACE-2 receptor and lower affinity to a large range of neutralizing antibodies, using a rapid computational platform
SARS-COV-2 Omicron variant predicted to exhibit higher affinity to ACE-2 receptor and lower affinity to a large range of neutralizing antibodies, using a rapid computational platform Open
Summary Rapid assessment of whether a pandemic pathogen may have increased transmissibility or be capable of evading existing vaccines and therapeutics is critical to mounting an effective public health response. Over the period of seven d…
View article: Deep Kernel Bayesian Optimization
Deep Kernel Bayesian Optimization Open
View article: Rapid<i>in silico</i>design of antibodies targeting SARS-CoV-2 using machine learning and supercomputing
Rapid<i>in silico</i>design of antibodies targeting SARS-CoV-2 using machine learning and supercomputing Open
Summary Rapidly responding to novel pathogens, such as SARS-CoV-2, represents an extremely challenging and complex endeavor. Numerous promising therapeutic and vaccine research efforts to mitigate the catastrophic effects of COVID-19 pande…
View article: Pediatric Severe Sepsis Prediction Using Machine Learning
Pediatric Severe Sepsis Prediction Using Machine Learning Open
Early detection of pediatric severe sepsis is necessary in order to administer effective treatment. In this study, we assessed the efficacy of a machine-learning-based prediction algorithm applied to electronic healthcare record (EHR) data…
View article: Prediction of early unplanned intensive care unit readmission in a UK tertiary care hospital: a cross-sectional machine learning approach
Prediction of early unplanned intensive care unit readmission in a UK tertiary care hospital: a cross-sectional machine learning approach Open
Objectives Unplanned readmissions to the intensive care unit (ICU) are highly undesirable, increasing variance in care, making resource planning difficult and potentially increasing length of stay and mortality in some settings. Identifyin…
View article: Using Transfer Learning for Improved Mortality Prediction in a Data-Scarce Hospital Setting
Using Transfer Learning for Improved Mortality Prediction in a Data-Scarce Hospital Setting Open
Algorithm-based clinical decision support (CDS) systems associate patient-derived health data with outcomes of interest, such as in-hospital mortality. However, the quality of such associations often depends on the availability of site-spe…
View article: Prediction of Sepsis in the Intensive Care Unit With Minimal Electronic Health Record Data: A Machine Learning Approach
Prediction of Sepsis in the Intensive Care Unit With Minimal Electronic Health Record Data: A Machine Learning Approach Open
Despite using little more than vitals, InSight is an effective tool for predicting sepsis onset and performs well even with randomly missing data.
View article: Using electronic health record collected clinical variables to predict medical intensive care unit mortality
Using electronic health record collected clinical variables to predict medical intensive care unit mortality Open
Through the multidimensional analysis of the correlations between eight common clinical variables, AutoTriage provides an improvement in the specificity and sensitivity of patient mortality prediction over existing prediction method…
View article: High-performance detection and early prediction of septic shock for alcohol-use disorder patients
High-performance detection and early prediction of septic shock for alcohol-use disorder patients Open
Analysis of the higher order correlations and trends between relevant clinical measurements using the InSight algorithm leads to more accurate detection and prediction of septic shock, even in cases where diagnosis may be confounded by AUD.