Mark Gerstein Journalist Profile

Articles

Uncertainty abounds, what now?

1 month ago | science.org | Maowei Liang |Marco Uytiepo |Dov Greenbaum |Mark Gerstein

The reviewer is at the Zvi Meitar Institute for Legal Implications of Emerging TechnologiesThe reviewer is at the Harry Radzyner Law SchoolThe reviewer is at the Dina Recanati School of Medicine, Reichman University, Herzliya, IsraelThe reviewer is at the Department of Biomedical Informatics and Data Science
Uncertainty abounds, what now?

1 month ago | science.org | Maowei Liang |Marco Uytiepo |Dov Greenbaum |Mark Gerstein

Skip to main content Main content starts here Books et al. StatisticsA statistician offers insight into risk, probability, and decision-makingDov Greenbaum [email protected] and Mark GersteinAuthors Info & AffiliationsScience20 Mar 2025Vol 387, Issue 6740p. 1261 Access the full articleView all access options to continue reading this article. References and Notes1D. Spiegelhalter, The Art of Statistics: How to Learn from Data (Basic Books, 2021).
Hidden human costs of AI

Jan 2, 2025 | science.org | Dov Greenbaum |Mark Gerstein

Get Science’s award-winning newsletter with the latest news, commentary, and research, free to your inbox daily.
23andMe must secure its DNA databases immediately

Dec 14, 2024 | thehill.com | Dov Greenbaum |Mark Gerstein

23andMe, born from the techno-optimism of the Human Genome Project, revolutionized direct-to-consumer genetic testing. But with its valuation now in freefall, mounting layoffs and its board resigning en masse, 23andMe’s imminent failure raises a critical question: What will happen to the sensitive genetic data of its 15 million customers?
MolLM: A Unified Language Model for Integrating Biomedical Text with 2D and 3D Molecular Representations

Feb 9, 2024 | biorxiv.org | Xiangru Tang |Andrew Tran |Jeffrey Tan |Mark Gerstein

AbstractThe current paradigm of deep learning models for the joint representation of molecules and text primarily relies on 1D or 2D molecular formats, neglecting significant 3D structural information that offers valuable physical insight. This narrow focus inhibits the models' versatility and adaptability across a wide range of modalities. Conversely, the limited research focusing on explicit 3D representation tends to overlook textual data within the biomedical domain.
MolLM: A Unified Language Model to Integrate Biomedical Text with 2D and 3D Molecular Representations

Dec 17, 2023 | biorxiv.org | Xiangru Tang |Andrew Tran |Jeffrey Tan |Mark Gerstein

AbstractThe present paradigm of deep learning models for molecular representation relies mostly on 1D or 2D formats, neglecting significant 3D structural information that offers valuable physical insight. This narrow focus inhibits the model's versatility and adaptability across a wide range of modalities. Conversely, the smaller amount of research that focuses on explicit 3D representation tends to overlook textual data within the biomedical domain.
MolLM: Integrating 3D and 2D Molecular Representations with Biomedical Text via a Unified Pre-trained Language Model

Nov 25, 2023 | biorxiv.org | Andrew Tran |Jeffrey Tan |Mark Gerstein |Xiangru Tang

AbstractThe present paradigm of current deep learning models for molecular representation relies largely on singular 1D or 2D formats, neglecting significant 3D structural information that offers valuable physical insight. This narrow focus inhibits the model's versatility and adaptability across a wide range of modalities.
Unified views on variant impact across many diseases

Feb 27, 2023 | cell.com | Sushant Kumar |Mark Gerstein

Mutation burden and genetic-association tests]. Typically, these models include various covariates (e.g., age, sex, ancestry) to avoid confounding effects as well as a random effect term to account for genetic relatedness among individuals in a given study [].