Maicol Bissaro
@_Maicol_
Followers
280
Following
2K
Media
27
Statuses
586
Computational Chemist @Evotec 🇬🇧 Former PhD student @UniPadova 🇮🇹
Oxford, England
Joined July 2009
Nice overview of our recent research at @Evotec showing how we can encode oligonucleotide sequences as chemical entities (not just as strings) enabling the training of ML models also for chemically-modified ones. Check out the preprint 🧬💻 https://t.co/JBB64pKKkH
Encode oligos as chemistry, not just strings. HELM→SMILES→MAP4 seems to match sequence-only approaches to predict siRNA efficacy. But, it generalizes to chemically modified oligonucleotides, where sequence-only baselines don’t work.
0
1
6
135
3K
14K
A must read for anyone trying to predict binding affinities by @rinikerlab and @dr_greg_landrum
pubs.acs.org
As part of the ongoing quest to find or construct large data sets for use in validating new machine learning (ML) approaches for bioactivity prediction, it has become distressingly common for...
0
32
141
New post at Practical Cheminformatics, “Some Thoughts on Biotech vs Pharma for Computational Chemists”.
0
18
75
8
207
2K
Wow! From @Dereklowe: “This is by far the most believable shot at room-temperature-and-pressure superconductivity the world has seen so far, and the coming days and weeks are going to be extremely damned interesting.”
science.org
A Room-Temperature Superconductor? New Developments
19
230
1K
And we’re off! First up it’s Christoffer Lind from @Evotec with his talk: “Combining FEP with QM interaction energies for ligand affinity prediction and optimisation” #MDinPharma
1
2
8
Great view from here for the first talk of #MDinPharma by Christoffer Lind giving us insights on combining FEP with QM interaction energies.
0
1
21
We’re very happy to announce that our RFdiffusion manuscript is now on bioRxiv! A lot can change in a week - we’ve now tested over a thousand designs and there’s so much exciting new data! 🧵
26
246
1K
Excited to share our preprint on using unsupervised learning to find inhibitors from fragments hits. The idea is learning a distance distribution of pharmacophores from fragment hits, and then scoring a large purchasable library using that. (1/3) https://t.co/0kTSXtHwOa
14
33
168
Thrilled to be at the @RSC_CICAG “AI in Chemistry” conference - lots of interesting talks, come along to hear about my work on”unsupervised learning of fragment-protein complexes”! #AIChem22
0
6
27
Happy to share my first publication! Thanks to all that participated in this tough challenge! Special thanks to my supervisors @philbiggin and @FrankvonDelft! Also thank you @DiamondLightSou, @davidlmobley, @jchodera and @_Mehtap_Isik_! https://t.co/K5Wq3Yr4tM
link.springer.com
Journal of Computer-Aided Molecular Design - A novel crystallographic fragment screening data set was generated and used in the SAMPL7 challenge for protein-ligands. The SAMPL challenges...
4
10
52
Evotec SE – EVO -is proud to announce that today we have joined the Nasdaq Family | Watch the virtual ringing of the Nasdaq Digital Opening Bell https://t.co/kN3LN9VztD | #researchneverstops
0
8
27