
PhD student 👩💻| Computational Drug Discovery @CDDLeiden Cancer research using AI and structure-based methods. A bit of 🎻🥋📕🏞 📸 in my free time.
Leiden, The Netherlands
Joined October 2011
- Tweets2.8K
- Following117
- Followers372
- Likes1.5K
Another one of my PhD chapters got published! 🎉🎉
In this chapter, @CDDLeiden we looked at the possibility of creating dynamic protein descriptors (3DDPDs) for bioactivity modeling from MD data.
jcheminf.biomedcentral.com/a…
github.com/CDDLeiden/3ddpd
Marina Gorostiola González retweeted
The highest impact factor is when your paper reaches your mom’s fridge❤️
Great to see published this great collaborative effort that I contributed to! Have a look! 🎉✨
Check out our review on #AI for #naturalproduct drug discovery! Just out in @NatRevDrugDisc 👇
A huge collaborative effort between disciplines and institutions 💪🏻
Amazing achievement by my PhD supervisor @GJPvWesten !! Stoked to be part of your group! ✨🎉
Congratulations to our @LED3hub member @GJPvWesten on receiving the very prestigious Gold Medal of @KNCVchemie #IUPACCHAINS2023 @IUPAC2023, which is awarded for groundbreaking work in chemistry under the age 40. He is awarded for his groundbreaking work on AI in drug discovery.
Marina Gorostiola González retweeted
The longer people are in academia, the more they realize that when reading papers it's best to ignore Intro, Discussion etc. and just look at Methods and Results
journals.plos.org/plosone/ar…
Marina Gorostiola González retweeted
"Chatbots in Drug Discovery: A Case Study on Anti-Cocaine Addiction Drug Development with ChatGPT"
arxiv.org/abs/2308.06920
Marina Gorostiola González retweeted
Introducing PINNACLE, a contextual graph AI model for comprehensive protein understanding
PINNACLE dynamically adjusts its outputs based on molecular contexts in which it operates
Providing outputs tailored to molecular contexts is essential for broader use of foundational models in biology and medicine
Leveraging #single-cell atlas, PINNACLE is trained on contextualized protein networks to generate context-aware representations split across 156 cell type contexts from 24 tissues
Pretrained PINNACLE protein representations can be adapted for broad array of tasks
🧪enhance 3D structural representations
💊study genomic drug effects across cell type contexts
🎯nominate #therapeutic targets
🌲zero-shot retrieval of the tissue hierarchy
Led by a superstar PhD student @_michellemli! Grateful for wonderful collaborators @harvardmed @HarvardDBMI @BrighamWomens @MassGeneralNews @MassGenBrigham @Roche @harvard_data
Y Huang @YepHuang, M Sumathipala @marissa_sumathi, MQ Liang, A Valdeolivas, A Ananthakrishnan, K Liao, and D Marbach
#AI4Science #SingleCell #AI #Proteins [1/4]
Getting started!! #shef2023
New preprint alert! Our work @CDDLeiden on dynamic protein descriptors for PCM modelling is now available on ChemRvix and all the code on our group GitHub. Looking forward to the feedback on our newly developed 3DDPDs 🥳
chemrxiv.org/engage/chemrxiv…
Marina Gorostiola González retweeted
Work by @OlivierBeqgn , @BongersBrandon , @Willemjespers , @GJPvWesten et al. :” Papyrus: a large-scale curated dataset aimed at bioactivity predictions”
Get the data here: doi.org/10.5281/zenodo.70198…
Scripts to adapt your own data: github.com/CDDLeiden/Papyrus…
jcheminf.biomedcentral.com/a…
Some pretty cool collaborative work on somatic mutations in GPCRs!
Just online: "Pan-cancer functional analysis of somatic mutations in G protein-coupled receptors" Veni of @GJPvWesten and continued by @BongersBrandon , @m_gorostiola , @Willemjespers , et al!
CC @NWO_Science , @LACDR , @LED3hub , @LeidenScience
nature.com/articles/s41598-0…
Probably the best @CDDLeiden tradition: Computational cheese day!!
Marina Gorostiola González retweeted
Too many studies that apply machine learning to science & medicine employ incorrect methodologies.
Many make very basic mistakes, such as not having separate training & test sets, using the test set (not a separate validation set) for feature selection, hyperparameter tuning, etc
There’s a reproducibility crisis brewing in almost every scientific field that has adopted machine learning. On July 28, we’re hosting an online workshop featuring a slate of expert speakers to help you diagnose and fix these problems in your own research: sites.google.com/princeton.e…
Marina Gorostiola González retweeted
College completely failed to teach me data analysis.
So I spent over 10,000 hours learning Python.
Then, I picked the 13 best libraries for machine learning and data analysis.
But unlike college, these won't cost you $120,000.
Here they are for free:
Marina Gorostiola González retweeted
The amazing #2022ICCS is over. The @cddleiden delegation also had posters from: @BournezC , @martin_sicho , @ManuelG81702324 , @sohvi_luukkonen , @DavidAraripe , @1inde1 , @BolaK_DDD , @BongersBrandon , Helle vd Maagdenberg, Rosan Kuin. CC @LeidenScienceEN , @LACDR #2022ICCS
Marina Gorostiola González retweeted
Great presence of @CDDLeiden at the @intconfchemstr. Talks by @OlivierBeqgn and @m_gorostiola. Posters by many group members. CC @sails_Leiden @LACDR #2022iccs
Today I presented our work on 3D protein dynamic descriptors (3DDPDs) at #2022ICCS . Great ideas during the Q&A session and room for collaboration with other tools presented these days!
Marina Gorostiola González retweeted
Replying to @m_gorostiola
@m_gorostiola presenting her work about 3DDPDs. Used a preliminary version of Papyrus for collecting data. Super nice presentation (though, once again, I am very biased). #2022ICCS
Marina Gorostiola González retweeted
1/5 Robust deep learning based protein sequence design using ProteinMPNN biorxiv.org/content/10.1101/… The high rate of experimental success and applicability to almost any protein sequence design problem has made it the standard approach at the @UWproteindesign github.com/dauparas/ProteinM…






























