Transfer Learning for Drug Discovery.

By Chenjing Cai, Shiwei Wang, Youjun Xu, Weilin Zhang, Ke Tang, Ouyang Qi, Luhua Lai, Jianfeng Pei. Journal of Medicinal Chemistry, 2020

307 citations recorded by the source corpus.

The data volume of in silico drug discovery studies is often small. Therefore, the availability of labeled data is a major limitation in artificial intelligence-assisted drug discovery. One solution to the problem is to develop algorithms that can cope with relatively heterogeneous and scarce data. Transfer learning is a kind of machine learning that can leverage existing knowledge from other related tasks to a specific task with insufficient data. Deep transfer learning is the most commonly used method and has attained much progress in the field of drug discovery. This perspective aims to provide an overview of transfer learning and related applications in drug discovery and give outlooks as to future development and application of transfer learning for drug discovery.

Subfields: Computational Theory and Mathematics, Materials Chemistry, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/7d5d93af1518a36039b214c0b30ca2f7a5bf4e4e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Materials Chemistry

In Molecular Biology

Citations in the corpus

A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities (2022, background): “Transfer learning [63] is a classical learning paradigm, which aims to solve the challenging problem that there are only a few or even no labelled samples [64] in the FSL [65].”
Artificial Intelligence For Natural Product Drug Discovery (2023, background): “This can improve model efficiency and mitigate issues relating to low-data regimes 145 , for example, in de novo molecular design 146–148 .”