Function Prediction

Function prediction aims to infer the biological role or purpose of a molecule (e.g., gene, RNA, protein) or a physical object based on its characteristics. Current research heavily utilizes machine learning, particularly deep learning models, incorporating diverse data types such as DNA sequences, 3D structures, natural language descriptions, and dynamic interaction networks to improve prediction accuracy. These advancements are crucial for accelerating biological discovery, enabling more efficient drug design, and facilitating the development of novel materials by allowing for better understanding and manipulation of functional properties. Furthermore, research is exploring improved model training strategies, moving beyond parameter optimization to directly estimate the most likely function itself, leading to more robust and generalizable predictions.

Papers

July 21, 2024

A Benchmark Dataset for Multimodal Prediction of Enzymatic Function Coupling DNA Sequences and Natural Language
Yuchen Zhang, Ratish Kumar Chandrakant Jha, Soumya Bharadwaj, Vatsal Sanjaykumar Thakkar, Adrienne Hoarfrost, Jin Sun
Natural Language Benchmark Dataset Multimodal Prediction Function Prediction

February 14, 2024

3D-based RNA function prediction tools in rnaglib
Carlos Oliver, Vincent Mallet, Jérôme Waldispühl
3D Structure RNA Structure RNA Design miRNA Description Function Prediction

November 27, 2023

Should We Learn Most Likely Functions or Parameters?
Shikai Qiu, Tim G. J. Rudner, Sanyam Kapoor, Andrew Gordon Wilson
Estimation Task Many Parameter Posterior Inference Better Generalization Bayesian Posterior Maximum a Posteriori Function Prediction

October 5, 2023

A 5' UTR Language Model for Decoding Untranslated Regions of mRNA and Function Predictions
Yanyi Chu, Dan Yu, Yupeng Li, Kaixuan Huang, Yue Shen, Le Cong, Jason Zhang, Mengdi Wang
Unseen Language RNA Sequence Efficient Translation Function Prediction

February 8, 2023

DDeMON: Ontology-based function prediction by Deep Learning from Dynamic Multiplex Networks
Jan Kralj, Blaž Škrlj, Živa Ramšak, Nada Lavrač, Kristina Gruden
Deep Learning Gene Expression Data Biological System Multiplex Network Dynamic Deep Protein Function Annotation Function Prediction

May 5, 2022

Fixing Malfunctional Objects With Learned Physical Simulation and Functional Prediction
Yining Hong, Kaichun Mo, Li Yi, Leonidas J. Guibas, Antonio Torralba, Joshua B. Tenenbaum, Chuang Gan
3D Object Physical Simulation Perception Module Function Prediction

Function Prediction

Papers

A Benchmark Dataset for Multimodal Prediction of Enzymatic Function Coupling DNA Sequences and Natural Language

3D-based RNA function prediction tools in rnaglib

Should We Learn Most Likely Functions or Parameters?

A 5' UTR Language Model for Decoding Untranslated Regions of mRNA and Function Predictions

DDeMON: Ontology-based function prediction by Deep Learning from Dynamic Multiplex Networks

Fixing Malfunctional Objects With Learned Physical Simulation and Functional Prediction