Top Tweets for #RetroSynthesis
Join us for our webinar on Oct. 22 and experience how science-smart #AI is bringing search result #summarization to CAS @SciFinder and see the next evolution of the solution's #retrosynthesis tool. Register now: https://t.co/4zaoju7Fy5
We’re proud to announce that our team has won the $1M #standardinnovationchallenge for our world-leading M1 RetroScore platform. Big thanks to #standardindustries and @WRGraceCo #retrosynthesis #AI #medchem #HTE #drugdiscovery
Proud to be part of @MoleculeOne! We’re offering free trial of our world-leading M1 RetroScore retrosynthesis platform. DM or comment to get access #retrosynthesis #AI #drugdiscovery #standardinnovationchallenge
@MoleculeOne has won the $1M AI Challenge focused on leveraging artificial intelligence to revolutionize fine chemical manufacturing.
The challenge was hosted by Standard Industries, a global industrial powerhouse with $11B in annual revenue, over 20,000 employees, and operations in 50 countries.
You can check out the press release in the first comment.
Going to ACS? Concerned you’re behind the curve on what AI can do for you? Drop by Booth 3255 and speak with Reaxys customer success experts to see how #Reaxys combines high-quality reaction data with AI. #retrosynthesis #ACSSpring2025
https://t.co/4Rk5LkZvQm
📈 The quality of your data is crucial for successful model training! #ScienceofSynthesis provides chemical reaction and structure data carefully curated by expert data scientists.
These datasets are perfect for:
💡 Reaction prediction
💡 #Retrosynthesis training
💡 Reliable, synthetically applicable reactions
🔑 Unlock endless possibilities: https://t.co/dSs2INcas1
#MachineLearning #DataScience
The new stereoselective labeling capability in the CAS SciFinder #retrosynthesis tool empowers research scientists to design molecules with higher precision, safety, and efficacy. Learn more from our news release: https://t.co/0dSYzwf1Eu
🤖🧪“RLSynC: Offline-Online Reinforcement Learning for Synthon Completion”was just accepted at #JCIM @JCIM_JCTC.
RLSynC is a novel approach to synthon completion in single-step #retrosynthesis. RLSynC uses online-offline #RL to predict diverse reactions that are realistic based on an independent forward synthesis model.
🤖Offline-Online: Our agents start learning from offline data derived on real reactions. Once training converges, we augment the offline data with predicted reactions from the agents, with rewards determined by an independent forward synthesis model. This cycle of self-improvement balances our exploitation of existing knowledge with exploration of new possibilities.
🎨Diverse: RLSynC completes synthons by adding single atoms, allowing it a lot of flexibility to explore new ways of completing synthons. Additionally, RLSynC is optimized to satisfy a forward synthesis model, which can encourage diverse predictions not found in the ground-truth training data.
⚗️Realistic: An independent forward synthesis reward function guides the agents’ learning, encouraging ones which it predicts can produce the desired product. On average, the top 10 predictions from RLSynC contain significantly more reactions which satisfy this condition than the baselines.
📄Preprint: https://t.co/jpLOZ2sQBF
🧑💻Code: https://t.co/VnViTeKhJ5
Keep an eye out for a follow-up announcement when the paper is released by #JCIM.
Authors: @FrazierBaker, @ziqiChen123, @AduAmpratw82108, @ningx005
@OhioState @OhioStateCSE @OSUbigdata @OSUengineering @osu_pharmacy @OhioStateMed @OhioStateERIK
#AI #AI4Science #reinforcementlearning #synthesis #chemistry #multiagent #cheminformatics
📢Very excited to announce that my paper was accepted at #JCIM @JCIM_JCTC. Follow @TheNingLab for more related research.
A special thanks to my coauthors for making this paper possible. It was a great team!
#retrosynthesis #AI #RL #AI4Science #researchpaper
🤖🧪“RLSynC: Offline-Online Reinforcement Learning for Synthon Completion”was just accepted at #JCIM @JCIM_JCTC.
RLSynC is a novel approach to synthon completion in single-step #retrosynthesis. RLSynC uses online-offline #RL to predict diverse reactions that are realistic based on an independent forward synthesis model.
🤖Offline-Online: Our agents start learning from offline data derived on real reactions. Once training converges, we augment the offline data with predicted reactions from the agents, with rewards determined by an independent forward synthesis model. This cycle of self-improvement balances our exploitation of existing knowledge with exploration of new possibilities.
🎨Diverse: RLSynC completes synthons by adding single atoms, allowing it a lot of flexibility to explore new ways of completing synthons. Additionally, RLSynC is optimized to satisfy a forward synthesis model, which can encourage diverse predictions not found in the ground-truth training data.
⚗️Realistic: An independent forward synthesis reward function guides the agents’ learning, encouraging ones which it predicts can produce the desired product. On average, the top 10 predictions from RLSynC contain significantly more reactions which satisfy this condition than the baselines.
📄Preprint: https://t.co/jpLOZ2sQBF
🧑💻Code: https://t.co/VnViTeKhJ5
Keep an eye out for a follow-up announcement when the paper is released by #JCIM.
Authors: @FrazierBaker, @ziqiChen123, @AduAmpratwum82108, @ningx005
@OhioState @OhioStateCSE @OSUbigdata @OSUengineering @osu_pharmacy @OhioStateMed @OhioStateERIK
#AI #AI4Science #reinforcementlearning #synthesis #chemistry #multiagent #cheminformatics
🤖🧪“RLSynC: Offline-Online Reinforcement Learning for Synthon Completion”was just accepted at #JCIM @JCIM_JCTC.
RLSynC is a novel approach to synthon completion in single-step #retrosynthesis. RLSynC uses online-offline #RL to predict diverse reactions that are realistic based on an independent forward synthesis model.
🤖Offline-Online: Our agents start learning from offline data derived on real reactions. Once training converges, we augment the offline data with predicted reactions from the agents, with rewards determined by an independent forward synthesis model. This cycle of self-improvement balances our exploitation of existing knowledge with exploration of new possibilities.
🎨Diverse: RLSynC completes synthons by adding single atoms, allowing it a lot of flexibility to explore new ways of completing synthons. Additionally, RLSynC is optimized to satisfy a forward synthesis model, which can encourage diverse predictions not found in the ground-truth training data.
⚗️Realistic: An independent forward synthesis reward function guides the agents’ learning, encouraging ones which it predicts can produce the desired product. On average, the top 10 predictions from RLSynC contain significantly more reactions which satisfy this condition than the baselines.
📄Preprint: https://t.co/jpLOZ2sQBF
🧑💻Code: https://t.co/VnViTeKhJ5
Keep an eye out for a follow-up announcement when the paper is released by #JCIM.
Authors: @FrazierBaker, @ziqiChen123, @AduAmpratwum82108, @ningx005
@OhioState @OhioStateCSE @OSUbigdata @OSUengineering @osu_pharmacy @OhioStateMed @OhioStateERIK
#AI #AI4Science #reinforcementlearning #synthesis #chemistry #multiagent #cheminformatics
Artificial Intelligence for Retrosynthetic Planning Needs Both Data and Expert Knowledge | JACS #JACSPerspective @GloriusFrank @GloriusGroup @uni_muenster @TotalSyntheses @GrzybowskiLabPL #AI #Retrosynthesis #Expert #Knowledge https://t.co/C8VaFXvK5S
Sunday must-read: one of our top downloaded #Synlett articles from 2023:
Retrosynthetic simplicity by Mark Levin @LevinChem
#skeletalediting #retrosynthesis #simplicity #heterocycles
Read 👉 https://t.co/Bnfr69n4Ha
Retrosynthesis week in #LCSOSynthesisProblem! Duncan challenged us to find pathways for the synthesis of key intermediates in total syntheses starting from Carvone derivatives in @angew_chem @J_A_C_S @JOC_OL #Retrosynthesis
Take a look: https://t.co/LFw4iMBxaI
"How do we think about molecules?" Barbara Terlouw and David Meijer are teaching #Cheminformatics during the @MAGicMOLFUN #workshop #spring #school #Wageningen @WUR 😎 #retrosynthesis #SMILES #SMARTS and do you spot the #CineMol drawing? 😁
#LCSOSynthesisProblem of the week! @EmmaGabRobert challenged us with three MedChem retrosynthesis in @ACSBioMed ! #Retrosynthesis #Chemistry @NovartisScience @AstraZeneca @Merck
Take a look: https://t.co/nwdl1V5gsM
Group member Friedrich Hastedt presenting his poster on #ML-based #retrosynthesis frameworks at the 6th Machine Learning & AI in (Bio)Chemical Engineering Conference @cebcambridge. It’s been a great event so far! #chemistry #MachineLearning
Chemical Science
Computer-assisted multistep chemoenzymatic retrosynthesis using a chemical synthesis planner
@ChemicalScience #Chemistry #Chemoenzymatic #Retrosynthesis
https://t.co/tvBE7CtdEM
G2Retro can better predict the reactants for one-step #retrosynthesis, in the collaboration of @OSUengineering, @OhioStateMed, @osu_pharmacy, @OSUbigdata and @OhioState.
https://t.co/RY0PoXhWRV
Weekly thread of #compchem articles published in the Materials science and inorganic, nanoscale & physical chemistry team @NatureComms! Three papers, three different #machinelearning applications: #retrosynthesis, #electrochemisty, and #solidstate phases #compMSINPC 1/5
Moritz Classen, a PhD candidate at ETH Zurich, gives an overview of predictive retrosynthesis in this customer presentation series from Reaxys User Day: https://t.co/YXDuDlZDQh
#Reaxys #retrosynthesis #chemistry
Most Popular Users
Elon Musk 
@elonmusk
240.4M followers
Barack Obama
@barackobama
119.3M followers
Donald J. Trump
@realdonaldtrump
111.7M followers
Cristiano Ronaldo
@cristiano
110M followers
Narendra Modi
@narendramodi
107M followers
Rihanna
@rihanna
97.5M followers
NASA
@nasa
92.1M followers
Justin Bieber
@justinbieber
90.8M followers
KATY PERRY
@katyperry
87.4M followers
Taylor Swift
@taylorswift13
81.2M followers
Lady Gaga
@ladygaga
72.7M followers
Kim Kardashian
@kimkardashian
69.6M followers
Virat Kohli
@imvkohli
69.4M followers
YouTube
@youtube
68.6M followers
Bill Gates
@billgates
63.7M followers
The Ellen Show
@theellenshow
62.5M followers
Neymar Jr
@neymarjr
62.1M followers
CNN
@cnn
61.9M followers
X
@x
60.8M followers
Selena Gomez
@selenagomez
60.5M followers