Christof Angermüller (@cangermueller) header
Christof Angermüller (@cangermueller) profile picture

Software Engineer at Google

Mountain View, CA
Joined November 2012
Photo by Christof Angermüller (@cangermueller)Photo by Christof Angermüller (@cangermueller)Photo by Christof Angermüller (@cangermueller)Photo by Christof Angermüller (@cangermueller)Photo by Christof Angermüller (@cangermueller)Photo by Christof Angermüller (@cangermueller)Photo by Christof Angermüller (@cangermueller)Photo by Christof Angermüller (@cangermueller)Photo by Christof Angermüller (@cangermueller)Photo by Christof Angermüller (@cangermueller)
Excited to announce our latest paper on ML-guided design of single-domain antibodies against CoV-2; A collaboration between @GoogleDeepMind, @AAlphaBio and @LumenBio.
1
13
1
94
9,533
After only 3 rounds of ML-based design and wet-lab testing, we were able to significantly improve the efficacy against multiple CoV2 strains, including Delta and Omicron. Designed Abs are diverse with up to 15 mutations, providing a therapeutic hedge against future pathogens.
1
3
923
Christof Angermüller retweeted
Nature review: Scientific discovery in the age of artificial intelligence go.nature.com/45fUazH
2
34
6
114
55,363
Christof Angermüller retweeted
"Sensitive remote homology search by local alignment of small positional embeddings from protein language models" ESM2 embeddings used " as input to the highly optimized Foldseek, HMMER3, and HH-suite search algorithms" biorxiv.org/content/10.1101/…
21
86
11,153
Contextualizing protein representations using deep learning on protein networks and single-cell data t.ly/M1iY6
2
6
733
Self-play reinforcement learning guides protein engineering t.ly/RP3RY
8
40
3,898
The Patent and Literature Antibody Database (PLAbDab): an evolving reference set of functionally diverse, literature-annotated antibody sequences and structures bit.ly/3OpR1aG
1
8
486
Christof Angermüller retweeted
“Large language models are universal biomedical simulators” Another use of GPT-4 for biomedical sciences research biorxiv.org/content/10.1101/…
24
114
24,538
Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models bit.ly/3NnnKvU
7
396
PoET: A generative model of protein families as sequences-of-sequences bit.ly/3qVm2u8
1
3
321
ProteinChat: Towards Achieving ChatGPT-Like Functionalities on Protein 3D Structures bit.ly/43rXvLp
4
30
3,612
ChatGPT-powered Conversational Drug Editing Using Retrieval and Domain Feedback arxiv.org/abs/2305.18090
1
6
721
A Multimodal Protein Representation Framework for Quantifying Transferability Across Biochemical Downstream Tasks bit.ly/3OW2hMO
3
546
Christof Angermüller retweeted
BiomedGPT, a unified biomedical generative pretrained transformer model for vision, language, and multimodal tasks. Achieves state-of-the-art performance across 5 distinct tasks with 20 public datasets spanning over 15 unique biomedical modalities. arxiv.org/abs/2305.17100
12
200
10
801
166,314
Christof Angermüller retweeted
“Self-driving laboratories to autonomously navigate the protein fitness landscape” Four independent trajectories “quickly converged on thermostable enzymes that were at least 12 C more stable than the starting sequences” biorxiv.org/content/10.1101/…
4
58
3
220
45,791
A general model to predict small molecule substrates of enzymes based on machine and deep learning go.nature.com/3OueNCU
10
1
41
2,846