Posts by Tags

Functional property learning

论文笔记(Learning functional properties of proteins with language models)

1 minute read

Published:

蛋白质数据的表征,是解决当前生物医学问题的一大关键,比较好的方法是从优秀的语言模型汲取灵感,以构建类似的生信模型,这些模型最近已经在序列-结构-功能关系提取上获得了很大的成功。这篇论文对蛋白质表征学习做了深入的调研,分类并解释每一种方法,依次在如下预测目标中对他们进行评估:

Protein Language Model

论文笔记(Learning functional properties of proteins with language models)

1 minute read

Published:

蛋白质数据的表征,是解决当前生物医学问题的一大关键,比较好的方法是从优秀的语言模型汲取灵感,以构建类似的生信模型,这些模型最近已经在序列-结构-功能关系提取上获得了很大的成功。这篇论文对蛋白质表征学习做了深入的调研,分类并解释每一种方法,依次在如下预测目标中对他们进行评估:

convolutional neural network

Geometric Vector Perceptrons

1 minute read

Published:

The geometric vector perceptron is a simple module for learning vector-valued and scalar-valued functions over geometric vectors and scalars. GVP-GNN can be applied to any problem where the input domain is a structure of a single macromolecule or of molecules bound to one another.

graph neural network

Geometric Vector Perceptrons

1 minute read

Published:

The geometric vector perceptron is a simple module for learning vector-valued and scalar-valued functions over geometric vectors and scalars. GVP-GNN can be applied to any problem where the input domain is a structure of a single macromolecule or of molecules bound to one another.

inverse folding problem

Computational Protein Design Overview

1 minute read

Published:

Computational Protein Design(CPD) has produced impressive results for engineering new proteins, resulting in a wide variety of applications. In this blog, the whole pipeline and mainstream methods of CPD will be concluded.

protein design

Computational Protein Design Overview

1 minute read

Published:

Computational Protein Design(CPD) has produced impressive results for engineering new proteins, resulting in a wide variety of applications. In this blog, the whole pipeline and mainstream methods of CPD will be concluded.

protein language models

Computational Protein Design Overview

1 minute read

Published:

Computational Protein Design(CPD) has produced impressive results for engineering new proteins, resulting in a wide variety of applications. In this blog, the whole pipeline and mainstream methods of CPD will be concluded.

structure modeling

Geometric Vector Perceptrons

1 minute read

Published:

The geometric vector perceptron is a simple module for learning vector-valued and scalar-valued functions over geometric vectors and scalars. GVP-GNN can be applied to any problem where the input domain is a structure of a single macromolecule or of molecules bound to one another.