HaCTang's Group

唐浩程课题组

HaCTang's CV

E-mail: hat170@pitt.edu | 2316301466@qq.com

——————

Brief Intro

I'm Haocheng (Douglas) Tang, an unknown cyber-ricer, a moderate dialectical materialist and pure fun-seeker. My lifelong interest lies on making little tricks and exploring new edges, especially those associated with Computer Science, Biophysics, Sports, Deep Learning and Video Games. I hate repetitive labor, mindless work, bureaucracy, hierarchy and protectionism. So, whether you're here for a dose of wit, a sprinkle of wisdom, or just a good time, welcome aboard! Together, let's navigate the seas of curiosity and whimsy. After all, life's too short not to enjoy the ride!

——————

EDUCATION

School of Pharmacy, University of Pittsburgh
University of Pittsburgh, PA, Pittsburgh

Master of Science
Sept. 2024 – Jul. 2026

College of Chemistry and Molecular Engineering, Peking University
Beijing, China

Bachelor of Chemistry
Sept. 2020 – Jul. 2024

Department of Chemistry, Scripps Research
San Diego, CA, USA

Summer Intern
Jul. 2023 – Sept. 2023

——————

CURRENT INTEREST

1. Deep learning and drug design

The born of AlphaFold push CADD into the deep learning era. I'm trying to use the latest techniques in deep learning to develop advanced tools for drug discovery. I've explored RNN, GAN (SeqGAN) and Diffusion (DiT), and is exploring GPT-2, BART and Flow Matching (Frame Flow and RFM) in generation conformation as well as new moleules

There are 3 main scientific problems I'm extremely interested in this field:

a. Rational design of allosteric drugs.

b. Generative models for small molecular drugs, peptides and aptamers.

c. Generating MD ensembles of biomolecules.

2. High-performance computing (HPC) in computational biophysics

Atomistic simulations of biomolecules provide a detailed view of the structure and dynamics that complement experiments. Increased conformational sampling, enabled by new algorithms and growth in computer power, now allows a much broader range of events to be observed, providing critical insights largely inaccessible to experiments. Over long enough periods of time, MD tools like AMBER are still more accurate than AI tools like BioEmu. Another important thing is that, with the development of AI, especially for LLM and generative models used in science, HPC is becoming more and more important in accelerating drug discovery.

I used and am using MPI, openMP and CUDA (deepspeed and lightning) to do project on physical simulation and deep learnig projects.

3. Large language models

Large language models are powerful. Retrieval-augmented generation (RAG) actually is already widely used in AlphaFold (known as MSA module) and literature retrieval based reaction design and anything else. I'm interested in developing agents for chemistry software and a RAG for chemical compounds.

4. Machine learning potential

Machine learning potential is faster than QM/MM and more accurate than classical MM. I'm developing relative models for chemical reation.

5. Powerlifting

I'm a powerlifter, and my goal is to become the strongest man both mentally and physically!

3

with Teacher Liu Qi during the first PKUfitness May 4th Power Game

——————

PUBLICATIONS

Haocheng, Tang.; Junmei, Wang. Accurate Site-specific Folding via Conditional Diffusion Based on Alphafold3. BioAxiv, 2025, 10.1101/2025.07.06.663385.

Haocheng, Tang.; Jing, Long; Junmei, Wang. Auxiliary Discrminator Sequence Generative Adversarial Networks (ADSeqGAN) for Few Sample Molecule Generation. arXiv, 2025, 10.1101/2025.07.06.663385.

Zhai, Jingchen.; Xiguang, Qi.; Lianjin, Cai.; Yue, Liu.; Haocheng, Tang.; Lei, Xie.; Junmei, Wang. NNKcat: deep neural network to predict catalytic constants (Kcat) by integrating protein sequence and substrate structure with enhanced data imbalance handling. Briefings in Bioinformatics, 2025, 26 (3): bbaf212.

Yu, Liu.; Haocheng, Tang.; Tianchi, Song.; Mengxin, Xu.; Junyi, Chen.; Xi-Yang, Cui.; Yuxiang, Han.; Zhu, Li.; Zhibo, Liu. Organotrifluoroborate Enhances Tumour Targeting of Fibroblast Activation Protein Inhibitors for Targeted Radionuclide Therapy. Eur J Nucl Med Mol Imaging, 2023, 10.1007/s00259-023-06230–06233.

Cui, Xi-Yang.; Liu, Yu.; Wang, Changlun.; Wen, Zihao.; Li, Yichen.; Tang, Haocheng.; Diwu, Juan.; Yang, Yuchuan.; Cui, Mengchao.; Liu, Zhibo. China’s radiopharmaceuticals on expressway: 2014–2021. Radiochimica Acta, vol. 110, no. 6-9, 2022, pp. 765-784.

——————

AWARDS AND HONORS

Qin Wanshun-Jin Yunhui Scholarship for Outstanding Academic Performance, Peking University (top 10%) 2023

Merit Student Award, Peking University (top 10%) 2023

Principal’s Fund (Science) for Undergraduate Research, Peking University 2023

Third Prize, “New Synthesis” Popular Science Article Contest 2021

Silver Medal, 33th Chinese Chemistry Olympiad 2019

0%