This paper from CCDC asks if your docking tool needs a binding site as input, and you don’t have one, is cavity prediction actually good enough to bridge that gap? They ran four cavity predictors (PUResNet-2.0, LVPocket, CAVIAR, Fpocket) on 486 curated protein-ligand structures and fed the best predicted cavity into GOLD, using four different ways of translating a cavity into a binding site definition (atom-vicinity vs. residue-vicinity, at 10 and 12 Å). Fpocket and CAVIAR come out ahead on cavity centroid accuracy (means of 3.5 and 4.2 Å vs. 6.6-6.9 Å for LVPocket/PUResNet-2.0), and centroid-based cavity definitions consistently beat residue-based ones for GOLD, likely because residue expansion drags in false-positive atoms that GOLD’s scoring can reward. The more interesting result is correlation between cavity accuracy and final pose accuracy drops to 0.49 when restricted to the two best cavity methods, meaning close-enough cavities don’t reliably translate to correct poses, and conversely some docking runs succeeded even with cavity centroids >9 Å off. They also benchmark against DiffDock and Boltz-1 blind docking, where GOLD+Fpocket/CAVIAR wins on mean distance but DiffDock has a lower median with heavier-tailed outliers (quite not the usual “AI blind docking dominates” narrative you see elsewhere). Good read !
Kurczab’s group keeps pushing the “spectra as descriptors” line, and this one tests the question that actually matters: is NMR redundant if one uses ECFP4, or does it add something ? They built SpectraPRINTS which is concatenation of binned predicted ¹H/¹³C shifts (400-dim, HOSE-code/nmrshiftdb2-derived) with ECFP4. They ran the identical CNN regression pipeline across logP, logS, logD at three pH values, and both macroscopic pKa endpoints, so any difference in RMSE is due to representation and not architecture. They observed that lipophilicity/solubility endpoints get consistent gains (16–39% RMSE reduction, largest at logD pH 10.5), while pKa shows no systematic improvement which interestingly they attribute to macroscopic pKa collapsing multiple protonation microstates/tautomers into one number, which makes sense. They also shipped it as a live webapp (link here: NMR-AI).
Docking benchmarks have long leaned on the Astex diverse set and its ~2 Å RMSD success criterion, but this paper points out that criterion quietly assumes there’s one right answer to find. Kubincová et al. instead curate 60 PDB structures with alternate locations for the same ligand. These are crystallographically resolved binding-mode pairs, split into ring flips, ring puckers, and other rearrangements. They ask four templated docking protocols (RDKit/smina, rDock, PLANTS, AutoDock-GPU) to recover the non-input pose when given the other as a starting point. Success drops to 30–50% after pose selection, versus 70–90% on Astex (!!) even though the docking is templated and should have been easier. Worth reading if you rely on docking to generate starting poses for RBFE. The paper argues (and I think reasonably) that the 2 Å criterion from virtual-screening benchmarks doesn’t transfer to the pose-curation use case, where getting the wrong binding mode can cost you several kcal/mol downstream.
EvoDiffMol: evolutionary diffusion framework for 3D molecular design with optimized properties
Multi-omics network reconstruction with collaborative graphical lasso
Cross-domain transfer learning from peptides to metabolites using a multi-property fine-tuned LLM
From data to scent: validating an ensemble AI model that predicts novel insect odourant interactions
EDEL: enhancing dense retrievers for curation of biomedical knowledge bases
Bayesian Uncertainty-Guided Fidelity Fusion for Bioactivity Prediction
Iterative Interaction Fingerprints-Guided Multiobjective Molecular Generation
Gradient-Guided Graph Contrastive Learning for Mass Spectrometry-Based Proteomics Clustering
HELM-BERT: Topology-Aware Representations for Chemically Modified Peptides
BenzDB, an Exhaustive Database of Benzenoids up to Nine 6-Membered Rings
Unveiling the KRAS Relationship between Affinity and Dynamics: A Molecular Simulations Study
Familywise Feature Importance Stability in Chemical and Materials Machine Learning
Assessing Molecular Contacts Using Atom Environments Described by Ranked Lists
HELMify: A Hybrid Rule- and LLM-Based Generator of Peptide Monomer HELM Names
CatIF-RL: Activity-Oriented Enzyme Sequence Design by Steered Inverse Protein Folding
I made an app for Garmin watches with gentle reminders to be present in the moment, might be of interest to some : https://github.com/Manas02/HereAndNow
Miss Sentient@0xsachi
He didn’t get the h1b lottery and got kicked out
signüll @signulll
kimi’s founder & ceo got his phd at cmu. why didn’t he stay in america?!
7:34 AM · Jul 17, 2026 · 549K Views
166 Replies · 141 Reposts · 5.32K Likes
patagucci perf papi@kenwheeler
“yeah no i’m really excited to implement agentic solutions”

12:05 AM · Jul 17, 2026 · 27.2K Views
10 Replies · 24 Reposts · 1.06K Likes
AJ Stuyvenberg@astuyve
Watching everyone open their AWS billing console this morning

12:41 PM · Jul 17, 2026 · 16.1K Views
8 Replies · 17 Reposts · 729 Likes
IroncladDev@IroncladDev
just finished learning the kubernetes course from @bootdotdev

1:56 AM · Jul 17, 2026 · 15K Views
17 Replies · 37 Reposts · 701 Likes
delyth@StasioEnjoyer
Yo who the fuck is Michael and why is he in my kernel

3:58 PM · Jul 16, 2026 · 71.2K Views
41 Replies · 64 Reposts · 1.87K Likes
dandelion georgism 🔰🏗@DolphinMossad
1995: oh cool you can buy books online now 2026: the company that owns Whole Foods and Lord of the Rings is experiencing setbacks with its space program
Jon Erlichman @JonErlichman
On this day in 1995: Amazon launched.
6:00 PM · Jul 17, 2026 · 1.03M Views
70 Replies · 3.57K Reposts · 49.1K Likes
Drew Young@DrewYoungRadio
This kid is a legend 😂 can we please make this a gif #MLS #STLCITYSC #ALLFORCITY
Ben Pfeiffer @bpfeiff24
@DrewYoungRadio If someone makes a gif of the clip they showed at the game. *chef’s kiss* Up there with this beaut:
4:45 AM · Jul 17, 2026 · 35.8M Views
557 Replies · 20.7K Reposts · 337K Likes
The Cinéprism@TheCineprism
Rare asthetics: IMAX front row seats
6:35 AM · Jul 17, 2026 · 2.01M Views
176 Replies · 3.13K Reposts · 68.4K Likes
Ash Jogalekar@curiouswavefn
German physical chemist Angela Merkel was born #OTD 1954. Here's a paper from her early research, a computational study of an organic reaction, published in J. Amer. Chem. Soc. in 1988. Merkel also served as chancellor of Germany from 2005-2021.

6:24 PM · Jul 17, 2026 · 1.89K Views
1 Reply · 5 Reposts · 53 Likes
Bharath@Bharath_uwu
I just saw $1.5 trillion on my AWS bill and my soul left my body

AWS Support @AWSSupport
📣 Service Update: AWS Billing Console We are investigating issues with Cost Explorer reflecting inaccurate estimated billing data. 📊 Track status: https://t.co/6qSnkuEzc4 #AWS #AWSSupport
9:04 AM · Jul 17, 2026 · 2.3M Views
488 Replies · 1.16K Reposts · 25.2K Likes
Sen@senbuilds
Trillion dollar company btw
8:46 AM · Jul 17, 2026 · 411K Views
301 Replies · 418 Reposts · 12.9K Likes
roxy@hendrixnroses

9:24 PM · Jul 16, 2026 · 2.81M Views
184 Replies · 19K Reposts · 233K Likes
Evan Applegate@youwillmakemaps
3:48 PM · Jun 8, 2025 · 80.5K Views
8 Replies · 21 Reposts · 301 Likes
Christopher Akiki@christopher
O'Reilly animals sorted by orientation using PCA.

Christopher Akiki @christopher
Image quilt of all @OReillyMedia book covers sorted by color. https://t.co/GJrb2SUlK8
6:57 PM · Jul 16, 2026 · 194K Views
14 Replies · 193 Reposts · 2.45K Likes
Donald Mitchell@DonaldPMitchell
IBM transistor. Conductors 15 atoms thick.

3:31 AM · Jul 17, 2026 · 2.96M Views
96 Replies · 597 Reposts · 7.78K Likes
Dmitrii Kovanikov@ChShersh
Modern C++ is basically Python with UB and a 900-page standard. The following is valid C++ (zero macros)

4:41 AM · Jul 16, 2026 · 52.6K Views
57 Replies · 32 Reposts · 930 Likes
ThePrimeagen@ThePrimeagen
Discovering what we already knew from first principals
Kr$na @krishdotdev
The new development cycle in one image.
10:17 PM · Jul 16, 2026 · 166K Views
74 Replies · 169 Reposts · 5.41K Likes
Lawrence Jang@JangLawrenceK
my biggest fantasy is becoming a reality

Andy Fang @andyfang
Today we're opening up the DoorDash CLI in limited beta. `dd-cli` lets you order DoorDash directly from your agent: search stores, find the best deals, check out, and more. Early access for US/Canadian macOS developers by waitlist. Excited to see what folks build!
7:02 AM · Jul 16, 2026 · 850K Views
22 Replies · 268 Reposts · 9.74K Likes
Havoc@Havoc_Six

11:11 PM · Jul 15, 2026 · 718K Views
61 Replies · 4.31K Reposts · 105K Likes
Wellu@Wellutwt
Watching nolan masterpiece #TheOdyssey

6:22 AM · Jul 16, 2026 · 4.94M Views
1.37K Replies · 13.7K Reposts · 260K Likes
Alex@Alex_FF
Tell Codex to open Microsoft Paint and try to draw you
2:00 PM · Jul 15, 2026 · 1.09M Views
226 Replies · 179 Reposts · 6.5K Likes
Tzo@Go__5356

5:45 AM · Jul 15, 2026 · 79.9K Views
16 Replies · 314 Reposts · 3.61K Likes
Michael Baym@baym
the people yearn for grad school
Oscar Hong @oscrhong
a “gym for your mind” will be the next breakout product / movement everyone reaches this conclusion after their ai honeymoon phase. yes you got the result you wanted—work done, app built, revenues up—but not the *feeling* of doing great work aka mastery idk what shape this
3:25 AM · Jul 16, 2026 · 20.8K Views
7 Replies · 30 Reposts · 507 Likes
techbimbo@jameygannon
irony is you couldn't recreate this now if you tried
Riley Hennigh @rileycx
honestly the will smith spaghetti was peak ai
8:05 PM · Jul 14, 2026 · 14.2M Views
510 Replies · 6.25K Reposts · 200K Likes
ThePrimeagen@ThePrimeagen
@camiinthisthang jokes on you, i had no value before chatgpt 3.5 came out
4:35 PM · Jul 6, 2026 · 5.79K Views
7 Replies · 154 Likes
no context memes@nocontextmemes

2:55 PM · Jul 13, 2026 · 1.38M Views
122 Replies · 4.61K Reposts · 127K Likes
Signing off one last time from PT ; )
Muito Obrigado,
Manas

Comments
Nothing yet. Say the first thing.
Sign in to join the conversation.