Rohit Modee

Scientist @BII, A*STAR | Phd @iiit_hyderabad Computational chemist and machine learning researcher.

[Rohit Modee @RohitModee]

🔬Our new work introduces MolOpt: Autonomous Molecular Geometry Optimization through Multiagent 🤖#Reinforcement #Learning at The Journal of Physical Chemistry B: https://t.co/KQ8B2Eg2eY #MolecularOptimization #compchem @iiit_hyderabad

[Chada Sriharshitha @sriharshitha_29]

Continuous leakage of drainage water on Rajapushpa Provincia/ Muppa Road from the last 3 days. Causing great inconvenience to residents & workers in near by communities.

@CommissionrGHMC @GHMCOnline @gadwalvijayainc @HMWSSBOnline

[Leo Zang @LeoTZ03]

Structure prediction of alternative protein conformations | @NatureComms
- Cfold, a structure prediction model designed to predict alternative protein conformations.
- Train AF2 without the Template Track and focus on MSAs and coevolutionary signals
- Predict different conformations using Dropout and MSA Clustering
Link: https://t.co/dIBeAT5ovS

[Leo Zang @LeoTZ03]

Dynamic PDB: A New Dataset and a SE(3) Model Extension by Integrating Dynamic Behaviors and Physical Properties in Protein Structures
- Dynamic PDB contains 12.6K proteins subjected to 1 microsecond of molecular dynamics simulations with detailed physical properties such as atomic velocities, forces, and potential/kinetic energies
- Select high-resolution structures (≤ 2.0 Å) proteins with fewer than 500 AA, excluding membrane proteins and proteins with coil-loop conformations
- Use OpenMM (Amber-ff14SB force field) for MD simulation with two equilibration phases: a canonical ensemble (NVT) and an isothermal-isobaric ensemble (NPT)
- Build SE(3)-diffusion with conditional physical properties (velocity and force) and Invariant Point Attention
Preprint: https://t.co/2IodDobjWR

[Patrick Bryant @Patrick18287926]

Check out my new work with @FrankNoeBerlin where we answer if the structure of different protein conformations really can be predicted. https://t.co/CKBvPCiw1R Also try the Colab to see if your protein has different conformations: https://t.co/HPQx76BzS9

[GAMA Miguel Angel 🐦‍⬛🔑 @miangoar]

I just found a playlist with the lectures of the Rosetta Common Bootcamp (2023): PyRosetta, AlphaFold2, ProteinMPNN, Protein language models and Diffusion models🔥

Protein Modeling and Design with PyRosetta and Machine Learning
https://t.co/p2Sva6ZFOG

📝
https://t.co/hgE07e1VmF

[Machine Learning: Science and Technology @MLSTjournal]

Great new work by Jonas Elsborg and @ArghyaBhowmik5 @DTUEnergy @DTUtweet - 'ArtiSAN: navigating the complexity of material #structures with deep #reinforcementlearning' - https://t.co/UlCqTvovJv #machinelearning #materials #AI #catalysis #compchem #alloys #energy #graphs

[Jason H. Moore, PhD @moorejh]

Understatement of the year...

[Olexandr Isayev 🇺🇦🇺🇸 @olexandr]

Very exciting to share: AQuaRef- #CryoEM and XRD protein structure refinement with #MachineLearning #QM Teamwork by @MalgoBiczysko @Kavi_Dil @Zubatyuk @adrian_roitberg @waller_lab @hokru_science @PendingAI and @LBNLresearch team 💪
https://t.co/4qojxZX3Pn #compchem

[Simon Olsson @smnlssn]

Excited to share a new pre-print from the lab -- first lead by twitter-less Ross Irwin. In this paper, we present a highly and efficient E(3) equivariant architecture, scale optimal transport. Via flow matching we build an efficient mol. generator https://t.co/FFtfFMXeYY

[Jan Jensen (janhjensen.bsky.social) @janhjensen]

Overcoming the Pitfalls of Computing Reaction Selectivity from Ensembles of Transition States | ChemRxiv - https://t.co/K2nDBkdhmN

[Adolfo Poma @PomaResearch]

✔️Registration is open
✔️Great speakers @tiwarylab @drannaduncan @Matth_Chavent @tristanbereau @smnlssn @MicheleCeriotti @FergLab @XuhuiHuangChem @olexandr @gdefabritiis @Rebecca_Wade_C @KarenPalacioR @BettinaGKeller @ChengBingqing...
📍Great place @mpi_polymer
🗓️Sep 17-19,2024

[NDTV @ndtv]

#SandeshkhaliCase | "BJP forced me to sign blank papers": Woman withdraws rape complaint against TMC leaders

@MickyGupta84 reports

[Dhruv Rathee @dhruv_rathee]

Rahul Gandhi has agreed to do a 1-on-1 debate with Narendra Modi.

Will Modi accept?

[Pawan Khera 🇮🇳 @Pawankhera]

Shri Rahul Gandhi has accepted the invitation for a public debate with Shri Narendra Modi.
And the ball is now in the court of Shri Narendra Modi.

[Luigi Bonati @LuigiBonati]

Interested in catalytic simulations?
Check out our @cecamEvents workshop in Liguria (Italy) Oct. 7-9, to explore modern approaches (incl. #ML) to simulate catalytic reactivity under realistic conditions!
Apply by June 15 through CECAM
https://t.co/gdj5rCvje4
#compchem please RT

[Education, & Politics __🇮🇳 @energy_aaj]

@kshatresh Cap must be there for efficient work .. how a professor can guide 10-12 students .. IITs PhD are taking 6-7 years .. as lack of time with professor

[Mohamed Ahmed @m_0_a]

We research, build and ship some of the most exciting and challenging products in the world, with passion from Nairobi. Come join us build M365 Copilot.

We ❤️ engineers and scientists that ❤️ breaking and building things! https://t.co/pb7h390rUN
@MasakhaneNLP @DeepIndaba

[Björn Schumacher @schumacherbj]

How to start a PhD

[Ben Blaiszik @BenBlaiszik]

Stay tuned for more details on our featured speakers, judges, and in-person locations!

Save the date: May 8-9th, 2024. Together, let's unlock new frontiers in materials and chemistry research!

https://t.co/FcGfA7M1hY

[Olexandr Isayev 🇺🇦🇺🇸 @olexandr]

Hey chemtweeps #compchem and ML folks. If you work with LLMs in chemistry and related sciences please consider submitting a paper. This is going to be great focused issue