Discover and read the best of Twitter Threads about #alphafold
Most recents (24)
Revolutionizing the World: 20 AI & Machine Learning Startups You Need to Know. š§µ...
1/20: In this thread i will try and explore the fascinating world of AI and machine learning startups! Discover some of the most innovative companies pushing the boundaries in this space. #AIStartups #MachineLearning
1/ In 2021, DeepMind made headlines when it announced that it had developed an algorithm called AlphaFold that could predict the 3D structure of proteins with remarkable accuracy. Here's what you need to know about this groundbreaking technology. #bioinformatics #AlphaFold #AI 
2/ Proteins are essential building blocks of life, and their structure is critical to understanding how they function. Determining the structure of a protein can be a long and complex process, but AlphaFold is changing that.
3/ AlphaFold uses deep neural networks to predict the 3D structure of a protein based on its amino acid sequence. By training on a vast database of known protein structures, AlphaFold can accurately predict the structure of a protein in a matter of days, rather than years.
Delivery of therapeutic molecules is a major bottleneck for treating a wide range of diseases. Today we describe a new modality for delivering proteins based on an engineered contractile injection system @nature nature.com/articles/s4158ā¦
1/ Inspired by the machinery used by endosymbiotic bacteria to deliver protein payloads to their host animalsā cells, we sought to engineer these systems, called contractile injection systems (CISs), for delivery to human cells.
2/ We focused on the Photorhabdus virulence cassette (PVC), a type of CIS that is secreted by Photorhabdus and known to infect insect and mouse cells. We reconstituted PVCs in E. coli and confirmed they could attach to insect cells, their native target.
š§µš§µ THREAD: #Bioinformatics and #AlphaFold š§µš§µ
1. #AlphaFold is a deep learning system developed by #DeepMind, to predict the 3D #structure of #proteins from their #aminoacid sequence.
2. #AlphaFold has been applied and tested extensively in the biennial #CASP (Critical Assessment of protein Structure Prediction) experiment, and has achieved state-of-the-art performance.
From helping transform the way we can predict wind power output to improving the performance of Document AI and giving wider access to #AlphaFold, weāre proud to partner with @GoogleCloud to bring our AI research into the real world.
Hereās how. š§µ
Hereās how. š§µ
1ļøā£ Industries aiming to use AI to read documents need lots of training data, which can be hard to find.
We helped develop machine learning models that need 50% less data to parse utility bills and purchase orders for @GoogleCloud Document AI users.
We helped develop machine learning models that need 50% less data to parse utility bills and purchase orders for @GoogleCloud Document AI users.
2ļøā£ Wind farms are crucial to building a carbon-free future - but the weather makes it hard to predict.
With @GoogleCloud, we helped produce a Custom AI tool to better predict how much wind power could be generated - trained on forecasts and a customerās historical turbine data.
With @GoogleCloud, we helped produce a Custom AI tool to better predict how much wind power could be generated - trained on forecasts and a customerās historical turbine data.
NEW: This Post Was Written By #AI: sjtylr.net/2022/10/08/thiā¦
From idea to content and published post in under 30mins, using free tools. This tech is developing *fast* and will have implications for teaching, learning and our graduates.
#EdTech
From idea to content and published post in under 30mins, using free tools. This tech is developing *fast* and will have implications for teaching, learning and our graduates.
#EdTech
āļøUsing tools from @playground_ai @peppertype_ai @AiWritesonic @copy_ai and inspired by @Suhail @kaifulee @FryRsquared @DeepMind @daniel_eckler and more. Follow them all for super-interesting news. #AI
We made #AlphaFold dream of new protein assemblies, used #ProteinMPNN to bring it back to reality, and the results were stunning! (1/5) science.org/doi/10.1126/scā¦
Using #AlphaFold hallucination, we generated protein assemblies with up to C42 symmetry and validated 10 designs (7xtal/3cryoEM) ā these structure differ significantly from anything the network has seen during training! (2/5)
What does this image and these proteins have in common? Activation maximization initially lead to adversarial sequences (insoluble), but #ProteinMPNN gave these structures a new life in the wetlab! (image: en.wikipedia.org/wiki/DeepDream) (3/5)
1/ Youāve sequenced your samples and identified variants. Great! š
Now, here's how you can use @ensembl to find out the effect of your variants on #protein structures and interactions. A thread...š§µ
#genomics #bioinformatics #tweetorial #Ensembltraining š§¬
Now, here's how you can use @ensembl to find out the effect of your variants on #protein structures and interactions. A thread...š§µ
#genomics #bioinformatics #tweetorial #Ensembltraining š§¬
2/ The Variant Effect Predictor (VEP) is what youāre going to need for this task. You can find it in the blue header from the @ensembl homepage: ensembl.org/info/docs/toolā¦
#VEP
#VEP
3/ Click the āLaunch VEPā button to open the VEP web tool and enter your input data using instructions in the documentation:
šensembl.org/info/docs/toolā¦
šensembl.org/info/docs/toolā¦
More than 100 studies citing @Google 's #AlphaFold are being released each month according to the New Scientist. The protein structures and open-source tools previously released by @DeepMind have already accelerated many areas of research.
Some perspective on #AlphaFold with the rather eye-popping announcement from @DeepMind and @emblebi (which I am Director of) of all known proteins (~200 million) having an AlphaFold prediction run.
First off at some conceptual level this is "just" about the scaleability of computational methods - if you can do 1 in a computer, you can do 200 million. But still, instantiating this resource in a systematic manner makes it real. But this instantiation is not trivial.
There are three types of engineering needed here; one is knowing, tracking and organising all known proteins - this is mission of @uniprot, a joint project of @emblebi, @sib and PIR of @Georgetown. Conceptually looks pretty simple but ... bamboozling detail, reconcilation, etc
1/6 Can #AlphaFold learn from + & - labeled data to predict peptide binding better? w/ Phil Bradley @JustasDauparas @minkbaek @Mohamad_Abedi David Baker we present joint structure prediction-classification fine-tuning of #AF2 to classify pMHC binding.@UWproteindesign @fredhutch
2/6 We developed a template-based method for accurately predicting pMHC structures & fed confidence scores to a simple classifier to fine-tune with structure+classification loss on a self-distillation set of + and - pMHC interactions & reach SOTA in Class I & II classification.
3/6 We show that our method is potentially orthogonal to NetMHCpan and can correctly label peptides where NetMHCpan fails.
In the recent years @DeepMind has been working on Protein Folding and thanks to their deep learning architecture AlphaFold they already managed to predict millions of proteins, accelerating the making of new protein-based drugs for fighting diseases. Ā š§µ
#DeepMind #AlphaFold #AI
#DeepMind #AlphaFold #AI
When mutated, normal cells might become cancerous. AlphaFold may determine how a mutation can alter the structure, and hence the function, of the proteins encoded by these genes. Understanding how mutations influence their structure can be key to developing new medical treatments
AlphaFold, is able to predict the structure of the protein in which a mutation occurs, see where that mutation is, and how the mutated protein interacts with other molecules, and ultimately get an idea about the mechanism, or why that mutation causes a problem for that cell
1/ My new home @future just turned 1 š! Some thoughts on why Iām so excited about Future, by way of sharing a few of my favorite articles weāve published so far. š§µ
2/ My colleagues share my optimistic outlook but get that building a better future wonāt be easy. Many of my favorites tap into a common theme: science is integral to creating a better world, only if we (scientists) embrace new technologies and explore radical ideas, e.g.
3/ Science is slow, but it doesnāt have to be. One of the things slowing science down is the archaic process of funding science. Begging for #grants takes huge chunks of researcher time, decisions take months, and decision-makers are often risk-averse.
Today is a BFD triumph in life scienceāsolving the 3D structure at near atomic level resolution, one of the world's hardest, giant jigsaw puzzlesāthe nuclear pore complexāthe largest molecular machine in human cells, with structure-based AI prediction
@ScienceMagazine
@ScienceMagazine
Extraordinary work and perseverance by multiple groups
science.org/doi/10.1126/scā¦
This wouldn't have happened without #AI #AlphaFold
science.org/doi/10.1126/scā¦
This wouldn't have happened without #AI #AlphaFold
A "negative" result, but phenomenal thought piece from @naturalantibody / @antibodymap. TLDR predicting antibody-antigen interactions is pretty darn hard (1/5) #antibodies #machinelearning #alphafold
naturalantibody.com/use-case/deepmā¦
naturalantibody.com/use-case/deepmā¦
Predicting Ab-Ag interactions is a sub-problem of the protein-protein interaction problem. There are many facets to consider here, including but not limited to, identifying the correct antigen (let alone the correct epitope), the correct paratope, orientation, etc (2/5)
@antibodymap's team show first that true Ab-Ag pairs (i.e. those where we know the Ab binds antigen) and false Ab-Ag pairs (i.e. Ag was randomly given to an Ab), the pIDDT scores are incomparable, suggesting score-based discrimination is HARD. (3/5)
1/ How do proteins take their shape in the cell? Insights from our article with @JackJKelly @TheYueLab @UniofOxford @v_paavilainen @HiLIFE_Helsinki @LHapponen @lunduniversity @structbiolbxl @imperialcollege @pfizer nature.com/articles/s4159ā¦ #OpenAccess š§µš
2/ #AlphaFold can predict the folded protein shape, but not the complicated folding process itself. Often cells use protein complexes called chaperonins to help other proteins to fold. Here we purified a chaperonin called TRiC from cultured human cells.
3/ Purification was possible only by using #CRISPR genetic scissors. We introduced a purification handle in one of the 8 TRiC subunits. This allowed purification of the endogenous chaperonin as opposed to an engineered version of it. Quite a TRiCK! #samplerevolution
Congratulations to @demishassabis, John Jumper, and David Baker who will be awarded the Wiley Foundation 20th annual Wiley Prize in Biomedical Sciences on April 1: dpmd.ai/Wiley-Prize š§µ 1/7
Demis and John accept the award on behalf of the @DeepMind team who worked on #AlphaFold, which was recognised as a solution to the āprotein folding problemā at CASP14 in Nov 2020: dpmd.ai/casp14_blog 2/7
From the start, we committed to giving broad access to our work and, in July 2021, we published our methods in @Nature along with the open source code.
Paper: dpmd.ai/alphafold-methā¦
Open Source: dpmd.ai/alphafold-githā¦ 3/7
Paper: dpmd.ai/alphafold-methā¦
Open Source: dpmd.ai/alphafold-githā¦ 3/7
Systematically overlaying likely pathogenic variants over @DeepMind #AlphaFold predicted structures provides a unique opportunity to dive into the mechanisms of disease.
Here, NOD2 inflammatory disease-causing variants on the experimentally unresolved structure. 1/5
Here, NOD2 inflammatory disease-causing variants on the experimentally unresolved structure. 1/5
Data-wise, the @OpenTargets Platform and Genetics Portal provide a comprehensive aggregation of disease-causing variants post-processed from other great resources like @GWASCatalog or @NCBI_Clinical ClinVar (via @evarchive) among others
platform.opentargets.org/evidence/ENSG0ā¦
2/5
platform.opentargets.org/evidence/ENSG0ā¦
2/5
Now we also make human #AlphaFold structures available as a result of the collaboration between @embl and @DeepMind. All thanks to the great protein annotation tools provided by @uniprot
See NOD2 platform profile page
platform.opentargets.org/target/ENSG000ā¦
3/5
See NOD2 platform profile page
platform.opentargets.org/target/ENSG000ā¦
3/5
Since the publication of #AlphaFold2 and #RoseTTAFold and now that the tools and models have been made accessible, there has been an avalanche of attempts to solve old crystal structures. This thread covers tips from the #PhaserTeam for doing #MR with these models. (1/...)
The first thing to be aware of is that the B-factor fields contain measures of confidence in the correctness of the prediction, not actual B-factors. This means: 1) we can use that confidence to trim the model and 2) we need to convert that to an appropriate B-factor. (2/...)
Phaser will take those B-factors and use them to weight the different parts of the model. This can improve your chances of success with the model. (3/...)
Very excited to share that our work on Protein Nonrefoldability is out today in @J_A_C_S! #AlphaFold might be great at finding proteins' native structures... but turns out many proteins themselves are not! Short š§µ1/7
pubs.acs.org/doi/full/10.10ā¦
pubs.acs.org/doi/full/10.10ā¦
We developed a mass spec approach to probe the refoldability of the proteome. First we unfold & refold E. coli extracts, then use a protease to interrogate the structures of 'refolded' proteins. The resulting peptide fragments are sequenced by LC-MS & compared to native. 2/7
We found that most simple 'model' proteins are well-behaved and can refold on their own. But lots of multi-subunit assemblies, multi-domain proteins, and certain fold-types cannot fully refold intrinsically. 3/7
Now that the #alphafold hype has completely died down (ha!), I've written a new blog post on the AF2 method paper: moalquraishi.wordpress.com/2021/07/25/theā¦. This is a technical deep-dive into aspects of AF2 that I find most surprising/innovative and of relevance to broader biomolecular modeling.
My post is _not_ a high-level summary of how AF2 works. For that I suggest @c_outeiral's blog post blopig.com/blog/2021/07/aā¦.
Should say that we will have in a couple of weeks a formal review paper out that is a high-level overview of AF2 and its implications.
Yesterday we announced early collaborations using the #AlphaFold Protein Structure Database, which offers the most complete and accurate picture of the human proteome to date. So how is AlphaFold helping these organisations with their workā¦? 1/
The Drugs for Neglected Diseases initiative (@DNDi) has advanced their research into life-saving cures for diseases that disproportionately affect the poorer parts of the world. 2/
The @CEI_UoP is using #AlphaFold's predictions to help engineer faster enzymes for recycling some of our most polluting single-use plastics. 3/
A personal view point on the #AlphaFold announcement today from the @DeepMind and @emblebi team, part of @embl. TL;DR - I am *still* pinching myself about this.
When @demishassabis and the AlphaFold team first presented the results from CASP to me last November I genuinely almost fell off my chair. I think I swore quite a bit (in a British way) in amazement.
One of the reasons was I knew how rigorous CASP was - 20 years ago people published all sorts of "solving the folding problem" which then... didn't work beyond the training set. CASP cleverly used the fact that there are genuinely unknown structures each year solved by experiment
Today with @emblebi, we're launching the #AlphaFold Protein Structure Database, which offers the most complete and accurate picture of the human proteome, doubling humanityās accumulated knowledge of high-accuracy human protein structures - for free: dpmd.ai/alphafolddb 1/
Weāre also sharing the proteomes of 20 other biologically-significant organisms, totalling over 350k structures. Soon we plan to expand to over 100 million, covering almost every sequenced protein known to science & the @uniprot reference database.
dpmd.ai/alphafold-blog 2/
dpmd.ai/alphafold-blog 2/
Weāre excited to see how this will enable and accelerate research for scientists around the world. We've already seen promising signals from early collaborators using #AlphaFold in their own work, including @DNDi, @CEI_UoP, @UCSF & @CUBoulder: dpmd.ai/alphafold-caseā¦ 3/
