Project work

Official Repo of "A clinically validated foundation model for comprehensive lung pathology interpretation"

3D Extension Library for raylib

PhysiCell: Scientist end users should use latest release! Developers please fork the development branch and submit PRs to the dev branch. Thanks!

Easy to use Python library for creating 2D arcade games.

Spec-driven development (SDD) for AI coding assistants.

Extremely fast Query Engine for DataFrames, written in Rust

Python scripts to process files within a folder in parallel, with tools like fastp

TCR Repertoire Analysis and Lung Cancer Prediction

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

收集和梳理垂直领域的开源模型、数据集及评测基准。

Train a 1B LLM with 1T tokens from scratch by personal

Summarize existing representative LLMs text datasets.

AI for Science 论文解读合集（持续更新ing），论文/数据集/教程下载：hyper.ai

Minimal reproduction of DeepSeek R1-Zero

a finite element solver based on Taichi, being parallel (CPU/GPU), portable and open-source

Easy Metagenome Pipeline

HERRO is a highly-accurate, haplotype-aware, deep-learning tool for error correction of Nanopore R10.4.1 or R9.4.1 reads (read length of >= 10 kbps is recommended).

Oxford Nanopore's Basecaller

SPAdes Genome Assembler

LLM training in simple, raw C/CUDA

Ultra-fast preprocessing and quality control for long-read sequencing data

The shiny-based app for Fragment Analysis, especially for MSI analysis

A Systematic and Dynamic Pipeline for Single-Cell RNA Sequencing Analysis

Ultra-fast Multi-threaded FASTQ Demultiplexing

Bioinformatics'2020: BioBERT: a pre-trained biomedical language representation model for biomedical text mining

Intelligent Storage Acceleration Library

Heavily optimized library for DEFLATE/zlib/gzip compression and decompression