Ben Blaiszik Profile picture
Mar 24 13 tweets 7 min read
We are less than a week from the virtual hackathon for #LLM applications in materials science and chemistry. Here is some inspiration from other's applications to drive you!

🗓️ Register and start teaming today: eventbrite.com/e/llm-march-ma…

#hackathon #openscience #ML #AI
@kmjablonka using fine tuned GPT-3 and GPT-4 (in-line prompting) as a model surrogate for various chemical modeling problems.

Have questions for Kevin? He will be giving a demo during the March 29th live session, and is a co-organizer.

ChatGPT can also be used for applications in drug discovery. Shared via @andrewwwhite01 who is also a hackathon co-organizer and judge.

@nc_frey investigated neural scaling in large chemical models with 1B+ parameters & 10M datapoints. Explored physical priors and scale interplay, plus potential for prompt engineering. #ChemGPT encoder
Paper-QA, question and answering software to answer specific questions from PDFs .

embed docs into vectors -> embed query into vector -> search for top k passages in docs

Fan Li shows Zotero QA which attaches summarization and QA capabilities to your Zotero library.
Group hackathon projects using @LangChainAI for more LLM inspiration.
ChemNLP is a new open community effort collecting chemistry datasets and exploring LLM applications in chemistry. You can join the Discord today, and start collaborating with the community.

BioNeMo by @nvidia is a cloud service for generative AI in drug discovery that leverages LLMs and other capabilities like AlphaFold.
ScholarBert, a science focused BERT model trained on 221B tokens from scientific corpus, openly available on @huggingface. @LabsGlobus

🤗 link: huggingface.co/globuslabs
Ethan Mollick shows an example using Bing to design some trendy new watches. Really, you could just scroll through @emollick's entire timeline for LLM application inspiration. 😄

💡 Let's build some amazing LLM applications in materials and chemistry together✨

Slack invite is on the event page once you register.
And here’s another application from today!

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with Ben Blaiszik

Ben Blaiszik Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @BenBlaiszik

Nov 18, 2022
Great story from @Mechanophore and colleagues @UofIllinois. From skeptic to believer: the power of models. Let's take a look at some of these journeys and what we can learn.

✨What is your story?✨

#MaterialsDataMonth #academictwitter @OpenAcademics
doi.org/10.1016/j.tet.…
@Mechanophore's story - seeing models make intriguing predictions into reaction behavior. "A key turning point for me was seeing how FEA of Frontal Ring-Opening Metathesis Polymerizations simulates autonomous curing processes by balancing reaction enthalpy with heat transport" Image
@MrBSussels Story - modeled complex reaction mechanisms using a simplified graphical abstraction to create a system of coupled linear equations and analytically solved them to provide an empirical rate law in agreement with the experimental observations. Skeptic → Believer Image
Read 4 tweets
Nov 7, 2022
Did you know you can create a Google Scholar profile for your research group?

While GS is mostly used to track individual metrics, this process allows you to track and highlight team and project metrics.

Here's 5 steps to get to this 👇 #AcademicChatter #AcademicTwitter Image
1. Create a group Google Account
2. Navigate to Google Scholar (scholar.google.com) and click "My Profile"
3. Fill in your details Image
4. Add your group's articles.
5. Be sure to select "Make my profile public" in Settings Image
Read 5 tweets
Oct 3, 2022
It's been a wild week already in #ML/#AI for science. Advancements in using diffusion models for protein folding, using learned potentials to discover new catalyst materials, a proposed battery data genome to speed energy storage material discovery, and so much more! 🧵 (1/8)
@KevinKaichuang et al use diffusion models to generate novel foldable protein structures. (2/8)
@_akhaliq presents NeuralPLexer to predict protein-ligand structures. This will help understand the interaction between small molecules and proteins. Also with diffusion models ✨ (3/8)
Read 11 tweets

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/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

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

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us on Twitter!

:(