Biology subjects

Horvitz, E.

Publications and source records attributed to Horvitz, E..

8 recordsLinked to original sources

bioRxiv2026

The Limits of Sequence-Based Biosecurity Screening Tools in the Age of AI-Assisted Protein Design

Rapid advancements in AI have enabled significant progress in protein and nucleic acid design, but they also pose biosecurity challenges. We examine the vulnerabilities of biosecurity screening software (BSS) to AI-reformulated synthetic homologs of proteins of concern (POCs) that have been fragmented into smaller segments. We evaluate four BSS tools that were recently patched to enhance their AI resiliency. Without any further modification, we found that two of the four tools were capable of robustly detecting fragments as short as 50 nucleotides, demonstrating screening capabilities that exceed those requested in the U.S. Framework for Nucleic Acid Synthesis. Upgraded versions of the other two tools improved performance. Although our findings confirm the effectiveness of the tested BSS tools, at the same time, they emphasize the urgency of developing alternate BSS approaches to counter evolving AI-enabled biosecurity risks.

synthetic biology↗

bioRxiv2025

Learning Protein Representations with Conformational Dynamics

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 miss state-dependent features central to interaction, localization, and enzyme activity. Studies also indicate that many proteins assume multiple, functionally relevant shapes, motivating approaches that learn from this variability. Here we present DynamicsPLM, a protein language model conditioned on ensembles of computationally generated conformations to derive state-aware representations. DynamicsPLM improves predictive performance across protein-protein interaction, subcellular localization, enzyme classification, and metal-ion binding. On a widely used protein-protein interaction benchmark, it achieves a four-point accuracy gain over the strongest baseline. On a curated test set enriched for proteins with multiple conformational states, the margin increases to eleven points. These findings argue for a shift from static to dynamics-aware modeling, in which conformational variability is treated as informative. By elevating conformational state to a central element of machine learning in protein biology, this work advances modeling toward mechanisms that better reflect how proteins operate in cells and provides a route to actionable hypotheses about when and how binding, signaling, and catalysis occur.*

bioinformatics↗

bioRxiv2025

Experimental Evaluation of AI-Driven Protein Design Risks Using Safe Biological Proxies

Advances in machine learning are providing leaps forward for beneficial applications of protein engineering, while also raising concerns about biosecurity. Recently, Wittmann et al. described an in silico pipeline of generative AI tools to reformulate sequences of concern (SOCs) as synthetic homologs that may evade detection by biosecurity screening software (BSS) used by nucleic acid synthesis providers. Experimental testing of synthetic homologs is required to ascertain the true severity of this vulnerability. We present a generalizable framework to assess biosecurity risk consisting of testing, evaluation, validation, and verification (TEVV) of AI-assisted protein design (AIPD). We determine that common AIPD models in use at the time this study was initiated (early 2024) are not yet powerful enough to reliably rewrite the sequence of a given protein, while both maintaining activity and evading detection by BSS.

synthetic biology↗

bioRxiv2025

Beyond the Leaderboard: Leveraging Predictive Modeling for Protein-Ligand Insights and Discovery

MotivationLigands are biomolecules that bind to specific sites on target proteins, often inducing conformational changes important in the proteins function. Knowledge about ligand interactions with proteins is fundamental to understanding biological mechanisms and advancing drug discovery. Traditional protein language models focus on amino acid sequences and three-dimensional structures, overlooking the structural and functional changes induced by protein-ligand interactions. We investigate the value of integrating ligand-protein binding data in several predictive challenges and leverage findings to frame research directions and questions. ResultsWe show how the integration of protein-ligand interaction data in protein representation learning can increase predictive power. We evaluate the methodology across diverse biological tasks, demonstrating consistent improvements over state-of-the-art models. We further demonstrate how the study of the specific boosts in predictive capabilities coming with the introduction of the lig- and modality can serve to focus attention and provide insights on biological mechanisms. By leveraging large pretrained protein language models and enriching them with interaction-specific features through a tailored learning process, we capture functional and structural nuances of proteins in their biochemical context. Availability and implementationThe full code and data are freely available at https://github.com/kalifadan/ProtLigand. Contactkalifadan@cs.technion.ac.il

bioinformatics↗

bioRxiv2024

Toward AI-Resilient Screening of Nucleic Acid Synthesis Orders: Process, Results, and Recommendations

Fast-moving advances in AI-assisted protein engineering are enabling breakthroughs in the life sciences that promise numerous beneficial applications. At the same time, these new capabilities are creating potential biosecurity challenges by providing new pathways to intentional or accidental synthesis of genes that encode hazardous proteins. The synthesis of nucleic acids is a key choke point in the AI-assisted protein engineering pipeline as it is where digital designs are transformed into physical instructions that can produce potentially harmful proteins. Thus, one focus for efforts to enhance biosecurity in the face of new AI-enabled capabilities is on bolstering the screening of orders by nucleic acid synthesis providers. We describe a multistakeholder, cross-sector effort to address biosecurity challenges with uses of AI-powered biological design tools to reformulate naturally occurring proteins of concern to create synthetic homologs that have low sequence identity to the wild-type proteins. We evaluated the abilities of traditional nucleic acid biosecurity screening tools to detect these synthetic homologs and found that, of tools tested, not all could previously detect such AI-redesigned sequences reliably. However, as we report, patches were built and deployed to improve detection rates over the course of the project, resulting in a final mean detection rate over tools of 97% of the synthetic homologs that were determined, using in-silico metrics, to be more likely to retain wild-type-like function. Finally, we make recommendations on approaches for studying and addressing the rising risk of adversarial AI-assisted protein engineering attacks like the one we identified and worked to mitigate.

synthetic biology↗

bioRxiv2021

Toward More General Embeddings for Protein Design: Harnessing Joint Representations of Sequence and Structure

AO_SCPLOWBSTRACTC_SCPLOWProtein embeddings learned from aligned sequences have been leveraged in a wide array of tasks in protein understanding and engineering. The sequence embeddings are generated through semi-supervised training on millions of sequences with deep neural models defined with hundreds of millions of parameters, and they continue to increase in performance on target tasks with increasing complexity. We report a more data-efficient approach to encode protein information through joint training on protein sequence and structure in a semi-supervised manner. We show that the method is able to encode both types of information to form a rich embedding space which can be used for downstream prediction tasks. We show that the incorporation of rich structural information into the context under consideration boosts the performance of the model by predicting the effects of single-mutations. We attribute increases in accuracy to the value of leveraging proximity within the enriched representation to identify sequentially and spatially close residues that would be affected by the mutation, using experimentally validated or predicted structures.

biochemistry↗

bioRxiv2020

SciSight: Combining faceted navigation and research group detection for COVID-19 exploratory scientific search

The COVID-19 pandemic has sparked unprecedented mobilization of scientists, generating a deluge of papers that makes it hard for researchers to keep track and explore new directions. Search engines are designed for targeted queries, not for discovery of connections across a corpus. In this paper, we present SciSight, a system for exploratory search of COVID-19 research integrating two key capabilities: first, exploring associations between biomedical facets automatically extracted from papers (e.g., genes, drugs, diseases, patient outcomes); second, combining textual and network information to search and visualize groups of researchers and their ties. SciSight1 has so far served over 15K users with over 42K page views and 13% returns.

bioinformatics↗

bioRxiv2020

On Biases of Attention in Scientific Discovery

How do nuances of scientists’ attention influence what they discover? We pursue an understanding of the influences of patterns of attention on discovery with a case study about confirmations of protein-protein interactions over time. We find that modeling and accounting for attention can help us to recognize and interpret biases in databases of confirmed interactions and to better understand missing data and unknowns in our fund of knowledge.View Full Text

scientific communication and education↗