Kira Radinsky
YOU?
Author Swipe
View article: Learning Protein Representations with Conformational Dynamics
Learning Protein Representations with Conformational Dynamics Open
Proteins change shape as they work, and these changing states control whether binding sites are exposed, signals are relayed, and catalysis proceeds. Most protein language models pair a sequence with a single structural snapshot, which can…
View article: AI-Validated Brain Targeted mRNA Lipid Nanoparticles with Neuronal Tropism
AI-Validated Brain Targeted mRNA Lipid Nanoparticles with Neuronal Tropism Open
Targeting therapeutic nanoparticles to the brain poses a challenge due to the restrictive nature of the blood-brain barrier (BBB). Here we report the development of mRNA-loaded lipid nanoparticles (LNPs) functionalized with BBB-interacting…
View article: FusionProt: Fusing Sequence and Structural Information for Unified Protein Representation Learning
FusionProt: Fusing Sequence and Structural Information for Unified Protein Representation Learning Open
Accurate protein representations that integrate sequence and three-dimensional (3D) struc-ture are critical to many biological and biomedical tasks. Most existing models either ignore structure or combine it with sequence through a single,…
View article: Beyond the leaderboard: leveraging predictive modeling for protein–ligand insights and discovery
Beyond the leaderboard: leveraging predictive modeling for protein–ligand insights and discovery Open
Motivation Ligands are biomolecules that bind to specific sites on target proteins, often inducing conformational changes important in the protein’s function. Knowledge about ligand interactions with proteins are fundamental to understandi…
View article: Predicting Oxidation Potentials with DFT-Driven Machine Learning
Predicting Oxidation Potentials with DFT-Driven Machine Learning Open
We introduce OxPot, a comprehensive open-access data set comprising over 15 thousand chemically diverse organic molecules. Leveraging the precision of DFT-derived highest occupied molecular orbital energies (EHOMO), OxPot serves as a robus…
View article: Beyond the Leaderboard: Leveraging Predictive Modeling for Protein-Ligand Insights and Discovery
Beyond the Leaderboard: Leveraging Predictive Modeling for Protein-Ligand Insights and Discovery Open
Motivation Ligands are biomolecules that bind to specific sites on target proteins, often inducing conformational changes important in the protein’s function. Knowledge about ligand interactions with proteins is fundamental to understandin…
View article: Docking-Aware Attention: Dynamic Protein Representations through Molecular Context Integration
Docking-Aware Attention: Dynamic Protein Representations through Molecular Context Integration Open
Computational prediction of enzymatic reactions represents a crucial challenge in sustainable chemical synthesis across various scientific domains, ranging from drug discovery to materials science and green chemistry. These syntheses rely …
View article: ReactEmbed: A Cross-Domain Framework for Protein-Molecule Representation Learning via Biochemical Reaction Networks
ReactEmbed: A Cross-Domain Framework for Protein-Molecule Representation Learning via Biochemical Reaction Networks Open
The challenge in computational biology and drug discovery lies in creating comprehensive representations of proteins and molecules that capture their intrinsic properties and interactions. Traditional methods often focus on unimodal data, …
View article: Leveraging Temporal Trends for Training Contextual Word Embeddings to Address Bias in Biomedical Applications: Development Study
Leveraging Temporal Trends for Training Contextual Word Embeddings to Address Bias in Biomedical Applications: Development Study Open
Background Women have been underrepresented in clinical trials for many years. Machine-learning models trained on clinical trial abstracts may capture and amplify biases in the data. Specifically, word embeddings are models that enable rep…
View article: Ordinary Differential Equations for Enhanced 12-Lead ECG Generation
Ordinary Differential Equations for Enhanced 12-Lead ECG Generation Open
In the realm of artificial intelligence, the generation of realistic training data for supervised learning tasks presents a significant challenge. This is particularly true in the synthesis of electrocardiograms (ECGs), where the objective…
View article: GOProteinGNN: Leveraging Protein Knowledge Graphs for Protein Representation Learning
GOProteinGNN: Leveraging Protein Knowledge Graphs for Protein Representation Learning Open
Proteins play a vital role in biological processes and are indispensable for living organisms. Accurate representation of proteins is crucial, especially in drug development. Recently, there has been a notable increase in interest in utili…
View article: Interpretable Multivariate Time Series Forecasting Using Neural Fourier Transform
Interpretable Multivariate Time Series Forecasting Using Neural Fourier Transform Open
Multivariate time series forecasting is a pivotal task in several domains, including financial planning, medical diagnostics, and climate science. This paper presents the Neural Fourier Transform (NFT) algorithm, which combines multi-dimen…
View article: Molecular Optimization Model with Patentability Constraint
Molecular Optimization Model with Patentability Constraint Open
In drug development, molecular optimization is a crucial challenge that involves generating novel molecules given a lead molecule as input. The task requires maintaining molecular similarity to the original molecule while simultaneously op…
View article: Leveraging Prototypical Representations for Mitigating Social Bias without Demographic Information
Leveraging Prototypical Representations for Mitigating Social Bias without Demographic Information Open
Mitigating social biases typically requires identifying the social groups associated with each data sample. In this paper, we present DAFair, a novel approach to address social bias in language models. Unlike traditional methods that rely …
View article: GraphERT-- Transformers-based Temporal Dynamic Graph Embedding
GraphERT-- Transformers-based Temporal Dynamic Graph Embedding Open
Dynamic temporal graphs evolve over time, adding and removing nodes and edges between time snapshots. The tasks performed on such graphs are diverse and include detecting temporal trends, finding graph-to-graph similarities, and graph visu…
View article: Shielded Representations: Protecting Sensitive Attributes Through Iterative Gradient-Based Projection
Shielded Representations: Protecting Sensitive Attributes Through Iterative Gradient-Based Projection Open
Natural language processing models tend to learn and encode social biases present in the data. One popular approach for addressing such biases is to eliminate encoded information from the model's representations. However, current methods a…
View article: Clinical Contradiction Detection
Clinical Contradiction Detection Open
Detecting contradictions in text is essential in determining the validity of the literature and sources that we consume. Medical corpora are riddled with conflicting statements. This is due to the large throughput of new studies and the di…
View article: Shielded Representations: Protecting Sensitive Attributes Through Iterative Gradient-Based Projection
Shielded Representations: Protecting Sensitive Attributes Through Iterative Gradient-Based Projection Open
Natural language processing models tend to learn and encode social biases present in the data. One popular approach for addressing such biases is to eliminate encoded information from the model’s representations. However, current methods a…
View article: Physicians and Machine-Learning Algorithm Performance in Predicting Left-Ventricular Systolic Dysfunction from a Standard 12-Lead-Electrocardiogram
Physicians and Machine-Learning Algorithm Performance in Predicting Left-Ventricular Systolic Dysfunction from a Standard 12-Lead-Electrocardiogram Open
Early detection of left ventricular systolic dysfunction (LVSD) may prompt early care and improve outcomes for asymptomatic patients. Standard 12-lead ECG may be used to predict LVSD. We aimed to compare the performance of Machine Learning…
View article: Learning to Rank Articles for Molecular Queries
Learning to Rank Articles for Molecular Queries Open
The cost of developing new drugs is estimated at billions of dollars per year. Identification of new molecules for drugs involves scanning existing bio-medical literature for relevant information. As the potential drug molecule is novel, r…
View article: EqGNN: Equalized Node Opportunity in Graphs
EqGNN: Equalized Node Opportunity in Graphs Open
Graph neural networks (GNNs), has been widely used for supervised learning tasks in graphs reaching state-of-the-art results. However, little work was dedicated to creating unbiased GNNs, i.e., where the classification is uncorrelated with…
View article: tBDFS: Temporal Graph Neural Network Leveraging DFS
tBDFS: Temporal Graph Neural Network Leveraging DFS Open
Temporal graph neural networks (temporal GNNs) have been widely researched, reaching state-of-the-art results on multiple prediction tasks. A common approach employed by most previous works is to apply a layer that aggregates information f…
View article: What If: Generating Code to Answer Simulation Questions
What If: Generating Code to Answer Simulation Questions Open
Many texts, especially in chemistry and biology, describe complex processes. We focus on texts that describe a chemical reaction process and questions that ask about the process's outcome under different environmental conditions. To answer…
View article: Leveraging World Events to Predict E-Commerce Consumer Demand under Anomaly
Leveraging World Events to Predict E-Commerce Consumer Demand under Anomaly Open
Consumer demand forecasting is of high importance for many e-commerce\napplications, including supply chain optimization, advertisement placement, and\ndelivery speed optimization. However, reliable time series sales forecasting\nfor e-com…
View article: Temporal Attention for Language Models
Temporal Attention for Language Models Open
Pretrained language models based on the transformer architecture have shown great success in NLP. Textual training data often comes from the web and is thus tagged with time-specific information, but most language models ignore this inform…
View article: Temporal Attention for Language Models
Temporal Attention for Language Models Open
Pretrained language models based on the transformer architecture have shown great success in NLP.Textual training data often comes from the web and is thus tagged with time-specific information, but most language models ignore this informa…
View article: Gender-sensitive word embeddings for healthcare
Gender-sensitive word embeddings for healthcare Open
Objective To analyze gender bias in clinical trials, to design an algorithm that mitigates the effects of biases of gender representation on natural-language (NLP) systems trained on text drawn from clinical trials, and to evaluate its per…
View article: Time Masking for Temporal Language Models
Time Masking for Temporal Language Models Open
Our world is constantly evolving, and so is the content on the web. Consequently, our languages, often said to mirror the world, are dynamic in nature. However, most current contextual language models are static and cannot adapt to changes…