A dataset for predicting protein-protein interactions in humans

Protein-protein interactions (PPIs) are fundamental to biological function. While recent advances in coevolutionary analysis and deep learning (DL)-based structure prediction have enabled large-scale PPI identification in bacterial and yeast proteomes, their application to the more complex human proteome has remained limited. To address this challenge, we 1) enhanced coevolutionary signals by generating 7-fold deeper multiple sequence alignments (MSAs) from 30 petabytes of unassembled genomic data, and 2) developed a new DL model trained on augmented datasets of domain-domain interactions derived from 200 million predicted protein structures. These improvements led to a 4-fold increase in the performance of our de novo PPI prediction pipeline for human proteins. We systematically screened around 190 million human protein pairs and predicted 17,849 high-confidence PPIs at an estimated precision of 90%, including 3,631 interactions not previously detected by experimental methods. The resu..., , # A dataset for predicting protein-protein interactions in humans

Dataset DOI: [10.5061/dryad.15dv41p84](10.5061/dryad.15dv41p84)

## Description of the data and file structure

### **protein_omicMSAs.tar.gz (17 GB)**

These MSAs are in an A3M-like format. Compared to the standard A3M format, we inserted an additional sequence at the beginning, named “mask,” to indicate the alignment quality at each position. In this “mask,” an asterisk (*) indicates high-quality positions, and a dash (-) indicates low-quality positions (these are poorly conserved and thus cannot be reliably assembled from genomic data). We recommend using only the high-quality positions (marked with *), as we did in our work. Insertions relative to the human (query) sequence are represented by lowercase letters. Each sequence corresponds to one draft genome or genomic dataset, and the NCBI accession number of the genome or dataset is used to name the sequence in the header. We also include the taxonomic information of...,

蛋白质相互作用（Protein-protein interactions, PPIs）是生物功能的核心基础。近年来，共进化分析与基于深度学习（deep learning, DL）的结构预测技术虽已实现细菌与酵母蛋白质组的大规模PPI鉴定，但在更为复杂的人类蛋白质组中的应用仍存在显著局限。为破解这一研究难题，本研究开展了两项改进：其一，通过从30拍字节的未组装基因组数据中生成7倍深度的多重序列比对（multiple sequence alignments, MSAs）以增强共进化信号；其二，开发了一款全新的深度学习模型，该模型基于由2亿个预测蛋白质结构衍生的结构域-结构域相互作用增强数据集完成训练。上述优化使我们针对人类蛋白质的从头PPI预测流程的性能提升了4倍。我们系统性筛选了约1.9亿个人类蛋白质对，并以90%的估计精确率预测得到17849个高可信度PPIs，其中包含3631个此前未被实验方法检测到的相互作用。研究结果……，# 人类蛋白质相互作用预测数据集
数据集DOI: [10.5061/dryad.15dv41p84](10.5061/dryad.15dv41p84)

## 数据与文件结构说明

### protein_omicMSAs.tar.gz（17 GB）
此类多重序列比对采用类A3M格式。相较于标准A3M格式，我们在序列起始位置插入了一条名为"mask"的额外序列，用于标注每个比对位点的质量：其中星号（*）代表高质量位点，短横线（-）代表低质量位点（此类位点保守性较差，无法从基因组数据中可靠组装）。本研究建议仅使用标记为*的高质量位点，与我们的研究实践一致。相对于人类（查询）序列的插入片段以小写字母表示。每条序列对应一个草图基因组或基因组数据集，序列头部的名称采用该基因组或数据集的NCBI登录号。我们还补充了分类学信息……