Jake Parker
@agenemachine.bsky.social
Protein engineer (Rosetta/ML/wet lab) working on a NewCo building targeted chemotherapy for solid tumours (esp. PDAC) using ADEPT — loops and buried polar groups are a feature, not a bug.
De novo design of a theozyme with catalytic efficiencies similar to natural ones— another milestone in computational design!
www.nature.com/articles/s41...
www.nature.com/articles/s41...
Complete computational design of high-efficiency Kemp elimination enzymes - Nature
We present a computational approach to the design of high-efficiency enzymes with catalytic parameters comparable to natural enzymes, enabling programming of stable, high-efficiency, new-to-nature Kem...
www.nature.com
June 19, 2025 at 12:30 AM
De novo design of a theozyme with catalytic efficiencies similar to natural ones— another milestone in computational design!
www.nature.com/articles/s41...
www.nature.com/articles/s41...
Does negging work on VCs?!?
March 16, 2025 at 11:57 AM
Does negging work on VCs?!?
Reposted by Jake Parker
Stabilized PvRBP2b variants - wonderful collab with Sarel Fleishman
🔥Increased yields and thermal stability
✌️Maintains human mAb recognition
🩸Sensitivity as a sero-diagnostic for P. vivax
💕 Editors Pick
👨🏻🔬First paper for PhD student Jaison
Please read & repost!
www.jbc.org/article/S002...
🔥Increased yields and thermal stability
✌️Maintains human mAb recognition
🩸Sensitivity as a sero-diagnostic for P. vivax
💕 Editors Pick
👨🏻🔬First paper for PhD student Jaison
Please read & repost!
www.jbc.org/article/S002...
Stabilized designs of the malaria adhesin protein PvRBP2b for use as a potential diagnostic for Plasmodium vivax
Plasmodium vivax is emerging as the most prevalent species causing malaria outside
Africa. Most P. vivax infections are relapses due to the reactivation of the dormant
liver stage parasites (hypnozoit...
www.jbc.org
March 6, 2025 at 4:51 AM
Stabilized PvRBP2b variants - wonderful collab with Sarel Fleishman
🔥Increased yields and thermal stability
✌️Maintains human mAb recognition
🩸Sensitivity as a sero-diagnostic for P. vivax
💕 Editors Pick
👨🏻🔬First paper for PhD student Jaison
Please read & repost!
www.jbc.org/article/S002...
🔥Increased yields and thermal stability
✌️Maintains human mAb recognition
🩸Sensitivity as a sero-diagnostic for P. vivax
💕 Editors Pick
👨🏻🔬First paper for PhD student Jaison
Please read & repost!
www.jbc.org/article/S002...
Love the masked epitope approach– lots of room for expanding on the idea.
$JANX obliterated the benchmark
- 100% (!!) PSA50, with DOR at 12weeks > 75%
- 63% PSA90
- 50% ORR
- 100% CRS with 6% Gr3+
+ 52% post-market
investors.januxrx.com/investor-med...
- 100% (!!) PSA50, with DOR at 12weeks > 75%
- 63% PSA90
- 50% ORR
- 100% CRS with 6% Gr3+
+ 52% post-market
investors.januxrx.com/investor-med...
December 3, 2024 at 1:33 AM
Love the masked epitope approach– lots of room for expanding on the idea.
Reposted by Jake Parker
dealing with the ruggedness of protein fitness landscapes is perhaps the most challenging aspect of protein design and engineering - here we have written a short perspective about it - it's complicated and not perfectly understood but very interesting!
arxiv.org/abs/2411.12957
arxiv.org/abs/2411.12957
Computational and Experimental Exploration of Protein Fitness Landscapes: Navigating Smooth and Rugged Terrains
Proteins evolve through complex sequence spaces, with fitness landscapes serving as a conceptual framework that links sequence to function. Fitness landscapes can be smooth, where multiple similarly a...
arxiv.org
November 22, 2024 at 10:21 AM
dealing with the ruggedness of protein fitness landscapes is perhaps the most challenging aspect of protein design and engineering - here we have written a short perspective about it - it's complicated and not perfectly understood but very interesting!
arxiv.org/abs/2411.12957
arxiv.org/abs/2411.12957
Another very nice database, this time of ADCs searchable by antibody, payload, linker, sequence similarity and includes preclinical and clinical data!
Second most common antigen is DLL3!
adcdb.idrblab.net
Second most common antigen is DLL3!
adcdb.idrblab.net
ADCdb: the database of antibody-drug conjugates
adcdb.idrblab.net
November 22, 2024 at 1:42 AM
Another very nice database, this time of ADCs searchable by antibody, payload, linker, sequence similarity and includes preclinical and clinical data!
Second most common antigen is DLL3!
adcdb.idrblab.net
Second most common antigen is DLL3!
adcdb.idrblab.net
November 21, 2024 at 4:34 AM
Reposted by Jake Parker
#GoodThingsComeToThoseWait Sorry it's taking us a while. Promise that the wait will be well worth it! #OpenFold3 Love all the great work that's already been done #HelixFold3 #Ligo #Chai1 #Protenix #Boltz1
November 20, 2024 at 10:34 AM
#GoodThingsComeToThoseWait Sorry it's taking us a while. Promise that the wait will be well worth it! #OpenFold3 Love all the great work that's already been done #HelixFold3 #Ligo #Chai1 #Protenix #Boltz1
Reposted by Jake Parker
The Baker lab seems serious about moving into enzyme design.
Here, they train a flow-matching model that can be conditioned by atomic coordinates and then use it to design enzymes based on active site geometry specified by density functional theory.
www.biorxiv.org/content/10.1...
Here, they train a flow-matching model that can be conditioned by atomic coordinates and then use it to design enzymes based on active site geometry specified by density functional theory.
www.biorxiv.org/content/10.1...
November 15, 2024 at 10:11 PM
The Baker lab seems serious about moving into enzyme design.
Here, they train a flow-matching model that can be conditioned by atomic coordinates and then use it to design enzymes based on active site geometry specified by density functional theory.
www.biorxiv.org/content/10.1...
Here, they train a flow-matching model that can be conditioned by atomic coordinates and then use it to design enzymes based on active site geometry specified by density functional theory.
www.biorxiv.org/content/10.1...
Reposted by Jake Parker
New GPU-based MMseqs2: 20x faster searches on a single L40S (approx. as fast as a RTX 4090) vs. a 128-core CPU. This work enables to set up a very cost-efficient ColabFold MSA GPU server. 🧵🧵
📄 www.biorxiv.org/content/10.1...
💾 mmseqs.com
🗞️ developer.nvidia.com/blog/boost-a...
📄 www.biorxiv.org/content/10.1...
💾 mmseqs.com
🗞️ developer.nvidia.com/blog/boost-a...
November 15, 2024 at 11:02 PM
New GPU-based MMseqs2: 20x faster searches on a single L40S (approx. as fast as a RTX 4090) vs. a 128-core CPU. This work enables to set up a very cost-efficient ColabFold MSA GPU server. 🧵🧵
📄 www.biorxiv.org/content/10.1...
💾 mmseqs.com
🗞️ developer.nvidia.com/blog/boost-a...
📄 www.biorxiv.org/content/10.1...
💾 mmseqs.com
🗞️ developer.nvidia.com/blog/boost-a...
Reposted by Jake Parker
Strong receptor-ligand binding affinity
#ChemistsWhoCook
#ChemistsWhoCook
November 13, 2024 at 4:59 AM
Strong receptor-ligand binding affinity
#ChemistsWhoCook
#ChemistsWhoCook
This is the one I've been waiting for! Generation of small molecule binders is a major limitation to biosensor development. This will unlock many things from research tools to diagnostics and therapeutics.
"Small-molecule binding and sensing with a designed protein family"🧪🧶🧬
www.biorxiv.org/content/10.1...
www.biorxiv.org/content/10.1...
November 3, 2023 at 1:05 PM
This is the one I've been waiting for! Generation of small molecule binders is a major limitation to biosensor development. This will unlock many things from research tools to diagnostics and therapeutics.