/images/avatar.png

Xiaopeng Xu, Ph.D.

Research Scientist @ KAUST · Agentic AI for scientific discovery, protein design & synthetic biology

Recent News

  • Sep 23, 2026, my Co-I Shaheen III Grand Challenge Project proposal on “Multi-Scale AI-MD-QM/MM Platform for Next-Generation Biologics Design” was appproved on Shaheen III GPU! Cheers!
  • Aug 2, 2026, my Co-I Translational Research Grants (TRG2026) on AI-based protein design solutions for industrial biologics and medical applications was funded by KAUST! ~1 million USD fund to support our research! Cheers!
  • Jun 23, 2026, started as a Research Scientist at SFB@KAUST.
  • Jun 8, 2026, Mater-trends — to track researches on material science — up and alive.
  • Jun 3, 2026, AI-trends — to track research trends on artificial intelligence — and Bio-trends — to track researches on bioscience — up and alive.
  • Mar 25, 2026, the first tool buddle in MacromNex, ProteinMCP — an agentic AI framework for autonomous protein engineering, published in Protein Science!
  • Mar 24, 2026, SegDesign — a framework for protein segment engineering — published in Protein Science.
  • Jan 22, 2025, AggNet — a Deep Learning method for protein aggregation prediction — published in Protein Science.
  • Oct 3, 2024, AutoBA — for multi-omics analysis with Agentic AI — published in Advanced Science.
  • Jul 18, 2024, SANTO — a method for alignment and stitching in spatial omics — published in Nature Communications.
  • Jun 12, 2024, HELM-GPT — de novo macrocyclic peptide design — published in Bioinformatics!
  • Jun 23, 2024, started as a Postdoctorate Research Fellow at SFB@KAUST.
  • May 13, 2024, my Co-I Shaheen III proposal on “Molecular dynamics simulations-enhanced AI for enzyme design and optimization” was appproved on Shaheen III CPU! Cheers!
  • May 5, 2024, defended my Ph.D Dissertation — “A ChatGPT-like solution for protein design: combining generative and predictive AI to design functional proteins”! Cheers!
  • Jun 28, 2023, SGPT-RL — for chemical drug design with GPT and RL — published in F1000Research!
  • Feb 20, 2023, AB-Gen — for antibody with GPT and RL — published in Genomics, Proteomics & Bioinformatics!
  • Nov 11, 2021, an AI guided review of 17 000 studies in COVID-19 computational research published in Briefings in Bioinformatics

Recent Notes

GROMACS 分子动力学模拟

MD simulation (Gromacs)

相关代码库见 https://github.com/charlesxu90/enzyme-md。

请求 Shaheen 资源并运行

srun --time=4:00:00 --nodes=1 --cpus-per-task=8 --ntasks=1 --mem=20G --pty bash -c '/bin/bash'

MD结构预处理

AF2 预测的结构无需特殊处理,直接按照上述步骤执行即可.

Google Sites 网站开发

Google Sites Web 开发

Google Sites 域名配置

在 https://sites.google.com/ 上开发个人主页.在腾讯云上购买域名.

购买域名后,在 https://sites.google.com/ 网站下的设置功能中,输入自己的域名,点击下一步获得域名解析的配置信息.

研究生科研训练

研究生的科研训练

摘要

科研训练是个长期积累的过程。每个学生的资质不同、经历不同、兴趣也各有偏好,真实体验会有所不同。

这里将研究生所需要提升的知识和技能做统一的整理,供攻读研究生学位的学生参考。

可视化工具

常用的可视化工具包括 Python、OmniGraffle、Adobe Illustrator、以及 PowerPoint 等。

Python 数据可视化

Python 是开源工具,其中包含了很多数据可视化包,可以画出比较优美的数据图表。

扩展GPT

LoRA 轻量 finetune

https://github.com/microsoft/LoRA

LoRA 在预训练大模型,如 GPT, 的主结构外,增加了 adaptor 层,可以用较小的 memory 来 finetune 大模型。如下图,只训练 A 和 B 的参数。

https://xux-zotero-img.oss-cn-beijing.aliyuncs.com/img/20260612231420290.png

安装

pip install loralib

使用

定义模型

LoRA 目前只支持几种类型的 layer:nn.Linear, nn.Embedding 和 nn.Conv2d。同时,支持MergedLinear 来替换 nn.Linear 表示多层 MLP 的情况。

基金申请意向书写作

写作说明

参考资料

Writing a Letter of Intent

来源:https://writingcenter.uagc.edu/writing-letter-intent

What is a letter of intent?

A letter of intent is a proposal describing and explaining your intentions. The letter is a formal and professional document, focusing on a specific audience and purpose. The letter of intent is an important step in a project, as it typically must get approval before any work can begin.