Chris J. Maddison
@cmaddis.bsky.social
MABs and LLM-assisted coding are what blew my mind this year.
December 25, 2024 at 10:44 PM
MABs and LLM-assisted coding are what blew my mind this year.
Reposted by Chris J. Maddison
We have done a similar feat for protein sequences @martaowesyou.bsky.social @cmaddis.bsky.social : www.biorxiv.org/content/10.1...
Boosting the Predictive Power of Protein Representations with a Corpus of Text Annotations
Protein language models are trained to predict amino acid sequences from vast protein databases, while learning to represent proteins as feature vectors. These vector representations have enabled impr...
www.biorxiv.org
December 24, 2024 at 1:25 PM
We have done a similar feat for protein sequences @martaowesyou.bsky.social @cmaddis.bsky.social : www.biorxiv.org/content/10.1...
Reposted by Chris J. Maddison
@nikitadhawan.bsky.social developed NATURAL (www.cs.toronto.edu/~nikita/natu...) with @cottascience.bsky.social , Karen & @cmaddis.bsky.social. Its an end-to-end pipeline that starts from raw-text data and ends with a causal (**) effect associated with an intervention.
(**) conditions apply
🧵(6/7)
(**) conditions apply
🧵(6/7)
NATURAL
www.cs.toronto.edu
December 11, 2024 at 12:20 AM
@nikitadhawan.bsky.social developed NATURAL (www.cs.toronto.edu/~nikita/natu...) with @cottascience.bsky.social , Karen & @cmaddis.bsky.social. Its an end-to-end pipeline that starts from raw-text data and ends with a causal (**) effect associated with an intervention.
(**) conditions apply
🧵(6/7)
(**) conditions apply
🧵(6/7)
I haven't gone since 2019 because I've had very significant health challenges due to COVID19. This year the conference is near family, so it's more accessible to me.
December 2, 2024 at 2:07 PM
I haven't gone since 2019 because I've had very significant health challenges due to COVID19. This year the conference is near family, so it's more accessible to me.
At the moment the disease is defined clinically as symptoms lasting more than 3 months after COVID19.
November 28, 2024 at 4:42 AM
At the moment the disease is defined clinically as symptoms lasting more than 3 months after COVID19.
You can't be in all three, Dan.
November 23, 2024 at 9:34 PM
You can't be in all three, Dan.
Moving my work in this direction, would love to be added!
November 17, 2024 at 7:59 PM
Moving my work in this direction, would love to be added!
cmaddis is my preferred handle. an accident of history.
October 6, 2023 at 11:44 PM
cmaddis is my preferred handle. an accident of history.