Discover and read the best of Twitter Threads about #drugdiscovery

Most recents (19)

"Looking to fuel your knowledge this summer, students? Check out these #Coursera courses

#ScientificWriting: coursera.org/learn/sciwrite
#DrugDiscovery: coursera.org/learn/drug-dis…
Understanding #Cancer: coursera.org/learn/cancer Image
"هل تبحث عن تعزيز معرفتك هذا الصيف، ؟ تعرف على هذه الدورات والتخصصات من #Coursera. 🎓🔬💻

#الكتابة_العلمية: coursera.org/learn/sciwrite
#اكتشاف_الأدوية: coursera.org/learn/drug-dis…
فهم #السرطان: coursera.org/learn/cancer
Read 4 tweets
1/ The impact of #Covid on $PVCT’s R&D, #DrugDiscovery, and clinical development of our #HalogenatedXanthene (#HX) medical science platform and #RoseBengalSodium (#RBS) investigational drug & drug formulation pipeline. A #THREAD.
2/ This $PVCT #thread will be an ongoing one for some time. Please check back to read it again (and again), and learn more about our medical scientific history and our lead molecule #RoseBengalSodium’s journey to becoming a multi-disease, broad-spectrum, therapeutic compound.
3/ #Covid has been a deeply painful experience, to say the least, for the U.S. and the world. It also marked a turning point in the advancement and expansion of our #HX medical science platform, as well as our lead molecule #RoseBengalSodium and the investigational drugs and drug… twitter.com/i/web/status/1…
Read 63 tweets
Our team working on ML for chemistry/drug discovery was unfortunately affected by the recent layoffs at Google.

I’m still very much interested in how new technologies can accelerate research in the life and natural sciences.

#ml #ai #compchem #drugdiscovery #googlelayoffs
If you know of open roles for which expertise in ML, simulation, or modelling as applied to drug/protein/materials design is sought, please feel free to reach out -- any pointer will be much appreciated!
As an opportunity for change, I’m also open to roles that may stretch my skills and expertise. Due to personal constraints, I’ll be looking for positions primarily in the SF Bay and Boston areas.
Read 4 tweets
🧵#Bioinformatics in #drug #discovery and development, a THREAD🧵🧵:
#Bioinformatics is playing an increasingly important role in the discovery and development of new #drugs. In this thread, we'll explore how #bioinformatics is being used to identify new targets for drug intervention and optimize drug design.
One key aspect of #bioinformatics in drug discovery is the identification of potential #drug #targets.
Read 12 tweets
Our recent paper "Exposing the Limitations of Molecular Machine Learning with Activity Cliffs" is now online!
doi.org/10.1021/acs.jc…

@korney34 @fra_grisoni @molecularML #AI #ML #drugdiscovery #Chemistry

By going to the limits of molecular property prediction ... 👇
with activity cliffs -- molecules that have highly similar structures, but large differences in bioactivity -- we see that deep learning still lacks behind of traditional machine learning for bioactivity prediction.
We showed that evaluating your models performance activity cliffs is crucial for prospective applications, especially in low data scenarios. To do this we developed a cool tool called MoleculeACE github.com/molML/Molecule…
Read 3 tweets
Excited to share our new paper in Nature Chemical Biology @nchembio

AI is poised to transform #therapeutic #science

The Commons is an initiative to access and evaluate #AI capability across therapeutic modalities and stages of discovery 1/4

nature.com/articles/s4158… Image
@nchembio @KexinHuang5 @TianfanFu @WenhaoGao1 @marinkazitnik @HarvardDBMI @yzhao062 @jure @jimeng @cwcoley @yusufroohani The Commons establishes a foundation for understanding which AI methods are most suitable for drug discovery and why

It provides a robust foundation and modern AI infrastructure to support predictive modeling and data-driven design 2/4 Image
@nchembio @KexinHuang5 @TianfanFu @WenhaoGao1 @marinkazitnik @HarvardDBMI @yzhao062 @jure @jimeng @cwcoley @yusufroohani Researchers across disciplines can use the Commons for numerous #drugdiscovery applications 3/4 Image
Read 4 tweets
Thrilled to share our preprint on structure-based discovery and optimization of SARS-CoV-2 macrodomain (Mac1) inhibitors. We present several low- to sub-micromolar inhibitors and atomic SAR thanks to >150 crystal structures!
biorxiv.org/content/10.110…
Super proud and grateful to be part of an amazing team including scientists from the @BShoichet @fraser_lab @IvanAhelLab @Ashworth_SF @GestwickiLab @adamrenslo @chem4biology and @FrankvonDelft labs!
BIG shoutout to Galen (@fraser_lab) for soaking roughly 300 molecules and determining many many many many crystal structures at 1 Å resolution. All of which are about to be released in the PDB @buildmodels and fragalysis.diamond.ac.uk (Thanks @Darenfearon)
Read 10 tweets
Really excited to announce that AntiBERTa is now published in @Patterns_CP! Here we describe a transformer model that demonstrates understanding of antibody sequences 🧵 (1/6)

#machinelearning #antibodies #drugdiscovery
cell.com/patterns/fullt…
We pre-train a transformer model based on RoBERTa. We exclusively use full-length antibody/B-cell receptor sequences using the MLM objective. Other similar transformers FYI include BioPhi (@prihodad), ABLang (@HegelundOlsen), AntiBERTy (@jeffruffolo) (2/6)
We show that the embeddings pick up nuanced features of BCR/antibody sequences. For example, V gene usage mutational load, and remarkably, B cell provenance. This is all done in a zero-shot setting, i.e. none of these labels were provided during pre-training. (3/6) Image
Read 7 tweets
🔬An international consortium, led by #IRBBarcelona & the biotech company @MerusNV, reports the discovery of MCLA-158, the first clinical candidate screened in #organoids targeting 🎯 #cancer #stemcells of solid tumors.

📰@NatureCancer

➡️bit.ly/3MLiu3h

#IRBScience Image
Named Petosemtamab, the antibody MCLA-158 prevents the onset of #metastasis (that is, the spread of #cancer to other vital organs) and slows the growth of primary tumours in experimental models of cancer. Image
The study also lays the groundwork for the use of #organoids in the #DrugDiscovery process undertaken by pharmaceutical companies.

Organoids are patient-derived samples that can be grown in the laboratory, and they reproduce certain aspects of the tumour compartment. Image
Read 6 tweets
There’s a lot of magicking and buzzwording around #AI and #MachineLearning in #drugdiscovery

I thought I’d do a thread on a concrete example of using ML to discover a drug candidate about to enter Phase 2a for a stroke disorder:

@RecursionPharma’s $RXRX REC-994
It’s in this Circulation paper from 2015 and illustrates the seed that became $RXRX “phenomics” platform with Chris Gibson (CEO, co-founder) and his former academic mentor Dean Li (board & co-founder) as first/last authors

ahajournals.org/doi/10.1161/ci…
The disease:

CCM (cerebral cavernous malformation) is a monogenic loss-of-function stroke disease affecting 1 in 200-500 in the US. 20% are due to the familial form usually due to a loss-of-function mutation in 1 of 3 genes, including the CCM2 gene
Read 20 tweets
Getting started on the Open #Bioinformatics Research Project initiative
👀🧵👇 See thread below
1. Watch the introductory video on the Open Bioinformatics Research Project initiative for:
- Intro to the initiative
- High-level overview of the dataset
- Ideas for which types of analysis to perform
2. Accessing the dataset
👉 GitHub github.com/dataprofessor/…
👉 Kaggle kaggle.com/thedataprof/be…
Read 8 tweets
Very glad to share our latest review on #geometricdeeplearning in molecular sciences, with special emphasis on drug discovery, quantum chemistry and synthesis prediction. 1/6
We put strong focus on the various existing molecular representations and their individual symmetries and advantages for different modeling applications. 2/6 Image
We discuss the major network architectures, such as RNNs, GNNs, 3D CNNs and Transformers, their applications on molecular systems, and the relevant equivariances they incorporate. 3/6 Image
Read 7 tweets
Read 259 tweets
Syngene is delighted to share that we are part of Fortune India’s Top 100 Wealth Creators list for 2021.
The criteria involved being a listed company with a 5-year CAGR of 7.5% plus in terms of market cap, revenue &profit (2017-21).
#FortuneIndia #Syngene #FortuneList #CDMO
1/5
Those incurring a net loss in any of the 5 fiscals (2016-20) were filtered out. The final 100 were based on firms having revenues of Rs 300 crores or more in FY20.
2/5
Key to our success has been our growing clientele who regard us more as a strategic partner with flexibility to work across a spectrum of clients -MNCs to start-ups. We also have a consistent client retention rate of 90%.

#strategicpartnership #clientele #USA #Europe #Japan
3/5
Read 5 tweets
Read 284 tweets
Don’t miss the latest research from #FacesOfCell. Read Nicolas Villanueva’s (@NicoVPhD) paper, “Delineating the conformational landscape of the adenosine A2A receptor during G protein coupling”: cell.com/cell/fulltext/… "My training, experiences, and opportunities have put m
Dr. Villanueva (@NicoVPhD) is #LatinXinSTEM and a senior scientist at @zentalisp. His research interests are in #StructuralBiology, #GProteins, and #GPCRs, and he hopes to be a leader of the field of structure-based #DrugDiscovery
@NicoVPhD believes transformational science arises from diversity and is committed to building diverse teams that uplift those from disadvantaged groups to pioneer novel approaches for scientific discovery
Read 4 tweets
Am I crazy? I listened to #Rutte and understand the pont for herd immunity. It allows a laisez faire approach after the pain is over.. however, for a visur with an R0 of 2.35 you need 43% of the population to be immune and been through the disease. (1/x)
So that means that some 7,493,610 people (minal) should have been through the disease. Assuming the GGD under reporting rate of 1/6th (rtlnieuws.nl/nieuws/nederla… ) that means that 1,248,935 should test positive (or at least have symptoms warranting testing) (2/x)
If we then assume a hospitalization rate of 12 % (jamanetwork.com/journals/jama/… ) (which is currently at 15% (205/1413, rivm.nl/nieuws/actuele…) this means 149,872 require hostpital care.
Read 20 tweets
1/ It's been a very busy few weeks in the Walsh group @diamondLightSou but extremely happy to announce that in collaboration with Frank von Delft group’s at Diamond we have been able to perform a full X-ray fragment based drug discovery experiment on the SARS-CoV-2 main protease
2/ We have released all data from this work here: diamond.ac.uk/covid-19/for-s… #covid19 #SARS_COV_2 #DrugDiscovery #AntiviralDrugs #structuralbiology #crystallography #cryoEM #nmr We will update data as its generated to accelerate drug development to combat #COVID19 @JeremyFarrar
3/ This has been an amazing team effort involving on the science side my group (Petra Lukacik, Claire Strain-Damerell & David Owen) and Frank von Delft's XChem Team (Primarily Alice Douangamath, Daren Fearon) and Ailsa Powell from the @DiamondILO @EJShotton team
Read 25 tweets
@cziscience consistently impresses me by doing important things that aren't incentivized by existing systems.
Speaking of which, an accessible version of this looks like it would be really useful for... everyone in #drugdiscovery and a lot of people in #academia, speeding up the search for cures. @cziscience @Eric_Fauman collaboration for Xmas 2020?
@pfizer I know this is internal, but there's a lot of karma to be had here and someone WILL replicate this. How about sharing an export of non-proprietary columns for @cziscience to implement à la bit.ly/2QLpP8R? You might even end up with a nicer UI yourselves.
Read 3 tweets

Related hashtags

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3.00/month or $30.00/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal Become our Patreon

Thank you for your support!