pen(Taka)
@iwatobipen.bsky.social
📤 1158
📥 807
📝 479
Medicinal Chemist, Cheminformatician, Runner and ?
People who try to freeload and just take the best bits are really scary
3 days ago
0
2
0
Wow!
8 days ago
0
1
0
Rational Design of Degrader with AI and MS technology
#memo
#journal
Targeted Protein Degrader (TPD) is one of the attractive modality of recent drug discovery area. As most of readers know that First TPD, ER degrader gains FDA approval in this year. TPD molecule induce PPI of POI and E3 ligase…
loading . . .
Rational Design of Degrader with AI and MS technology #memo #journal
Targeted Protein Degrader (TPD) is one of the attractive modality of recent drug discovery area. As most of readers know that First TPD, ER degrader gains FDA approval in this year. TPD molecule induce PPI of POI and E3 ligase and degradation of POI. It is unique mechanism because chemical compounds can induce artificial degradation process. But the process is really complex so it's difficult to design TPD molecule rationally such as SBDD.
https://iwatobipen.wordpress.com/2026/05/30/rational-design-of-degrader-with-ai-and-ms-technology-memo-journal/
8 days ago
0
3
0
SOTA is one of the metric of performance of models but, it’s not so important at real drug discovery programs. The important thing is how the model officers new insights for the program.
11 days ago
1
1
0
Integration QM and RDKit
#cheminformatics
#orca
I'm interested in how to apply quantum chemistry for my drug discovery journy longtime. My former boss teached me details of FMO. FMO is really is really useful tool for understanding protein-ligand or protein-protein interaction form QM point of…
loading . . .
Integration QM and RDKit #cheminformatics #orca
I'm interested in how to apply quantum chemistry for my drug discovery journy longtime. My former boss teached me details of FMO. FMO is really is really useful tool for understanding protein-ligand or protein-protein interaction form QM point of veiw. I love it 🙂 But GAMESS don't have official python API. And I and kzfm developed psikit which is wrapper of psi4 using rdkit.
https://iwatobipen.wordpress.com/2026/05/10/integration-qm-and-rdkit-cheminformatics-orca/
28 days ago
2
1
0
reposted by
pen(Taka)
bioRxiv Bioinfo
about 1 month ago
Guidance for high-quality functional gene embeddings from large language models
https://www.biorxiv.org/content/10.64898/2026.04.30.721875v1
0
1
1
I'm building test environment with ollama and openclaw
about 1 month ago
0
0
0
Tool for automated protein-ligand binding site extraction
#cheminformatics
#Journal
#memo
Understanding protein-ligand interaction is important for rational drug design. We can use X-ray co crystal structures for SBDD and information of ligand binding site is essential reagion. For example QM/MM…
loading . . .
Tool for automated protein-ligand binding site extraction #cheminformatics #Journal #memo
Understanding protein-ligand interaction is important for rational drug design. We can use X-ray co crystal structures for SBDD and information of ligand binding site is essential reagion. For example QM/MM approach applies QM level calculation to around binding site and applies MM to far from binding site. QM often offer more accurate energy state but its computational cost is high. So MM is used for not critical reagion for protein-ligand binding.
https://iwatobipen.wordpress.com/2026/05/01/tool-for-automated-protein-ligand-binding-site-extraction-cheminformatics-journal-memo/
about 1 month ago
0
0
0
Ensemble Analyzer: An Open-Source Python Framework for Automated Conformer Ensemble Refinement | Journal of Chemical Information and Modeling
pubs.acs.org/doi/10.1021/...
loading . . .
Ensemble Analyzer: An Open-Source Python Framework for Automated Conformer Ensemble Refinement
Accurate prediction of molecular properties requires the refinement of the full conformational ensemble at high levels of theory, which remains computationally demanding. Existing workflows typically rely on ad-hoc scripts and manual intervention. We present Ensemble Analyzer (EnAn), an open-source Python framework that automates this workflow. EnAn’s modular and extensible architecture integrates seamlessly with widely known calculators and allows automated generation and comparison of electronic and vibronic spectra. EnAn effectively manages the reproducible exploration of conformational spaces.
https://pubs.acs.org/doi/10.1021/acs.jcim.6c00273
about 1 month ago
0
1
0
DiffDock-Glide: A Hybrid Physics-Based and Data-Driven Approach to Molecular Docking | Journal of Chemical Information and Modeling
pubs.acs.org/doi/10.1021/...
loading . . .
DiffDock-Glide: A Hybrid Physics-Based and Data-Driven Approach to Molecular Docking
Recent years have seen a rise in applications of deep learning to problems in the molecular sciences. Among them, the diffusion model DiffDock stands out as a method for docking small molecules into p...
https://pubs.acs.org/doi/10.1021/acs.jcim.5c01635
about 1 month ago
0
1
0
Dually Acting Ligands Targeting Serotonin Receptors: Implications in CNS Disorders | Journal of Medicinal Chemistry
pubs.acs.org/doi/10.1021/...
loading . . .
Dually Acting Ligands Targeting Serotonin Receptors: Implications in CNS Disorders
The serotonergic system remains a critical focus of neuropsychopharmacology due to its widespread influence on mood, cognition, and behavior. Despite the clinical success of selective serotonin reupta...
https://pubs.acs.org/doi/10.1021/acs.jmedchem.5c03094
about 1 month ago
0
1
0
ggsql
opensource.posit.co/blog/2026-04...
loading . . .
ggsql: A grammar of graphics for SQL
Introducing ggsql, a grammar of graphics for SQL that lets you describe visualizations directly inside SQL queries.
https://opensource.posit.co/blog/2026-04-20_ggsql_alpha_release/
about 2 months ago
0
0
0
One of the my favorite music group is SANOVA.
horie2.wixsite.com/sanova
loading . . .
SANOVA 公式HP - ピアノインストバンド
ピアニスト堀江沙知による和製ジャズ・ピアノインストプロジェクト。
https://horie2.wixsite.com/sanova
about 2 months ago
0
0
0
Current version of OpenFE supports SepTop protocol!
docs.openfree.energy/en/stable/tu...
Cool :)
loading . . .
Running a SepTop RBFE calculation — OpenFE documentation
https://docs.openfree.energy/en/stable/tutorials/septop_tutorial.html
about 2 months ago
0
1
0
reposted by
pen(Taka)
Rocío Mercado Oropeza
about 2 months ago
🧪 Can LLMs judge chemical synthesis plans? Excited to share new work from our industrial postdoc Varvara Voinarovska, in collaboration with Samuel Genheden and Mikhail Kabeshov at AstraZeneca's Molecular AI team! 📄 :
doi.org/10.26434/che...
loading . . .
Do humans and large language models agree on the quality of synthesis plans? | ChemRxiv
Large language models (LLMs) have seen a widespread adoption in all spheres of science including chemistry and cheminformatics. Nevertheless, our knowledge of how they operate is limited, giving rise to exploration of their capabilities in different areas ...
https://doi.org/10.26434/chemrxiv.15001730/v1
2
13
3
I can’t accept that it takes long time to open excel, pptx, word files in my office PC :(
about 2 months ago
1
0
0
ESI descriptors for scaffold hopping
#memo
#journal
#LBDD
#cheminformatics
Now there are some of Folding-AI such as AF3, Boltz and OpenFold3 is available to predict 3D structure of protein-ligand complex. So we can apply SBDD approach if we don't have experimental structures but there is still of…
loading . . .
ESI descriptors for scaffold hopping #memo #journal #LBDD #cheminformatics
Now there are some of Folding-AI such as AF3, Boltz and OpenFold3 is available to predict 3D structure of protein-ligand complex. So we can apply SBDD approach if we don't have experimental structures but there is still of improvement to do the approach. There are lots of reports for doing SBDD from the predicted structure of Folding-AI but the results depend on predicted pose, pocket structure and nature of binding site.
https://iwatobipen.wordpress.com/2026/04/11/esi-descriptors-for-scaffold-hopping-memo-journal-lbdd-cheminformatics/
about 2 months ago
0
1
0
Nanoscale Direct-to-Biology Optimization of Cdk2 Inhibitors | Journal of Medicinal Chemistry
pubs.acs.org/doi/pdf/10.1...
loading . . .
Nanoscale Direct-to-Biology Optimization of Cdk2 Inhibitors
Modern hit-to-lead optimization winnows down vast chemical spaces of virtual compounds into a selection of potent and selective compounds that can be further profiled with in vitro assays. Today, miniaturized chemical synthesis can be performed in high-throughput, shifting the bottleneck to compound purification. Direct-to-biology (D2B) approaches seek to overcome this hurdle by omitting the purification step and submitting reaction mixtures directly to bioassays. Here, we explore nanoscale hit-to-lead optimization through the multistep synthesis of a library of Cdk2/CycE inhibitors, utilizing ultrahigh-throughput experimentation (ultraHTE) in 1,536-well plates. Library performance is assessed by D2B in functional biochemical, bioaffinity, and X-ray crystallographic assays. A selection of potent lead Cdk2/CycE inhibitors identified by D2B was submitted to a phenotypic cell painting assay, which showed cell cycle arrest at G0, consistent with Cdk2 inhibition. This miniaturized workflow allows the upper tiers of a typical optimization screening cascade to be performed in a single experiment.
https://pubs.acs.org/doi/pdf/10.1021/acs.jmedchem.5c03614
about 2 months ago
0
2
0
New Life for an Old Target: Melanin Concentrating Hormone (MCH) R1 Antagonists for Obesity | Journal of Medicinal Chemistry
pubs.acs.org/doi/10.1021/...
loading . . .
New Life for an Old Target: Melanin Concentrating Hormone (MCH) R1 Antagonists for Obesity
For more than two decades, MCHR1 antagonists have been extensively investigated, but clinical progress has been hindered by toxicity and inadequate brain exposure. This Viewpoint highlights recent advances that have enabled the discovery of a novel MCHR1 antagonist with improved brain penetration and reduced toxicity, allowing it to advance into clinical trials.
https://pubs.acs.org/doi/10.1021/acs.jmedchem.6c00870
about 2 months ago
0
1
0
Use transformer model for Lead optimization
#journal
#memo
New fiscal year is stared from April. And I'm staying really busy days evenif my sum gradated his unior high school and volley ball team club 🙂 My role is changed now but still working around informatics area of drug discovery. Today I…
loading . . .
Use transformer model for Lead optimization #journal #memo
New fiscal year is stared from April. And I'm staying really busy days evenif my sum gradated his unior high school and volley ball team club 🙂 My role is changed now but still working around informatics area of drug discovery. Today I read short article which used Transformer (often called AI) for Lead Optimization from. The title and URL is below.
https://iwatobipen.wordpress.com/2026/04/05/use-transformer-model-for-lead-optimization-journal-memo/
2 months ago
0
4
0
From my running course 😊
2 months ago
0
2
0
www.pnas.org/post/podcast...
loading . . .
PNAS
Proceedings of the National Academy of Sciences (PNAS), a peer reviewed journal of the National Academy of Sciences (NAS) - an authoritative source of high-impact, original research that broadly spans...
https://www.pnas.org/post/podcast/hidden-costs-ai
2 months ago
0
0
0
reposted by
pen(Taka)
Greg Landrum
2 months ago
Free registration for the 2026
#RDKit
UGM (both in-person and online attendance) is now open:
www.eventbrite.com/e/1985889262...
loading . . .
15th RDKit UGM 2026
2026 RDKit User Group Meeting (in person and online)
https://www.eventbrite.com/e/1985889262242?aff=oddtdtcreator
0
8
8
reposted by
pen(Taka)
Greg Landrum
2 months ago
We did a new major
#RDKit
release yesterday. v2026.03.1 is out and the conda-forge builds are available. As always, especially with major releases, be sure to read the "Backwards incompatible changes" section of the release notes!
github.com/rdkit/rdkit/...
loading . . .
Release 2026_03_1 (Q1 2026) Release · rdkit/rdkit
Release_2026.03.1 (Changes relative to Release_2025.09.1) Acknowledgements (Note: I'm no longer attempting to manually curate names. If you would like to see your contribution acknowledged with you...
https://github.com/rdkit/rdkit/releases/tag/Release_2026_03_1
1
23
7
reposted by
pen(Taka)
Open Free Energy
6 months ago
OpenFE is ready for production!
chemrxiv.org/engage/chemr...
In collaboration with our industry partners, we ran benchmarking simulations of our hybrid-topology RBFE protocol on a large collection of both public and private protein-ligand binding datasets.
#compchem
loading . . .
Large-scale collaborative assessment of binding free energy calculations for drug discovery using OpenFE
Accurately measuring compound binding affinities is key to driving the pharmaceutical development process. Rigorous physics-based in silico approaches, particularly alchemical free energy methods, hav...
https://chemrxiv.org/engage/chemrxiv/article-details/6936e3bda10c9f5ca1e61f71
1
17
12
Today, my eldest son successfully graduated from middle school :)
3 months ago
0
1
0
最初の立ち上げだけぶち上げてそのまま放り投げるの良くない。
3 months ago
1
0
0
Change heterocycle to another isoster with HCIE
#memo
#cheminformatics
#RDKit
iwatobipen.wordpress.com/2026/03/08/c...
loading . . .
Change heterocycle to another isoster with HCIE #memo #cheminformatics #RDKit
Aromatic heterocycles are often used drug design as central core of molecule and they are often replaced another isosteric heterocycles for improvement of potency, ADMET or finding new IP space. Th…
https://iwatobipen.wordpress.com/2026/03/08/change-heterocycle-to-another-isoster-with-hcie-memo-cheminformatics-rdkit/
3 months ago
0
0
0
reposted by
pen(Taka)
Rocío Mercado Oropeza
3 months ago
Work led by industrial PhD student Sofia Larsson and in close collaboration with Susanne Winiwarter and
@filipmiljkovic.bsky.social
at AstraZeneca. 📄 Paper:
chemrxiv.org/doi/full/10....
💻 Code:
github.com/tsofiac/drug...
💽 Data:
zenodo.org/records/1874...
loading . . .
Systematic Computational Identification of Active Drug Metabolites Across the Human Proteome | ChemRxiv
Understanding drug metabolism helps mitigate toxicity risks and anticipate pharmacological effects beyond the parent compound. Here, we explore high-confidence in vitro human bioactivity annotations from the public domain associated with a curated dataset ...
https://chemrxiv.org/doi/full/10.26434/chemrxiv.15000361/v1
1
8
3
reposted by
pen(Taka)
Greg Landrum
3 months ago
The new
#RDKit
blog post is a guest post looking at doing Butina clustering on the GPU using nvMolKit.
greglandrum.github.io/rdkit-blog/p...
loading . . .
GPU-Accelerated Clustering with nvMolKit – RDKit blog
A guest post from NVIDIA
https://greglandrum.github.io/rdkit-blog/posts/2026-02-28-nvmolkit-clustering.html
0
14
2
iwatobipen.wordpress.com/2026/03/07/r...
loading . . .
Rendering molecular image on Dataframe and Plot with marimo #Memo #RDKit #Cheminformatics
As lots of readers know that RDKit has useful functions for coding with jupyter-lab. PandasTools and IPythonConsole is useful because by using these functions rdkit can render mol objects as SVG on…
https://iwatobipen.wordpress.com/2026/03/07/rendering-molecular-image-on-dataframe-and-plot-with-marimo-memo-rdkit-cheminformatics/
3 months ago
0
3
0
It’s really surprising that Claude code works really hard :)
3 months ago
0
2
0
Shinagawa station is extremely crowded😱
3 months ago
0
0
0
reposted by
pen(Taka)
Geoff Hutchison
3 months ago
Has
@avogadro.cc
helped your research? Teaching? As we prepare Avogadro 2.0 for release this spring, I'm hoping to feature some stories (and citations).
#compchem
#opensource
#openscience
⚗️ Let me know:
discuss.avogadro.cc/t/avogadro-s...
loading . . .
Avogadro Stories (for 2.0 Release)
As we finish up the 2.0 (final!) release, I’d like to feature some stories (and citations) about how Avogadro has shaped research and teaching. So if Avogadro has helped your research, please let me ...
https://discuss.avogadro.cc/t/avogadro-stories-for-2-0-release/7323?u=ghutchis
1
32
15
It’s really difficult to understand for me that mixing quantum chemistry and quantum computing….
3 months ago
0
0
0
www.rcsb.org/stats/growth...
loading . . .
Small Molecule Statistics: Growth of Released Small Molecules per Year
As a member of the wwPDB, the RCSB PDB curates and annotates PDB data according to agreed upon standards. The RCSB PDB also provides a variety of tools and resources. Users can perform simple and adva...
https://www.rcsb.org/stats/growth/chemcomp/growth-released-chem-comp
3 months ago
0
1
0
reposted by
pen(Taka)
Rocío Mercado Oropeza
4 months ago
Happy to share our article on the PROTAC-Splitter, an ML framework for automated identification of PROTAC substructures, is now finally online in Journal of Cheminformatics!
rdcu.be/e4Ulj
🤩 Work led by our amazing senior PhD student Stefano, together with collaborators at AstraZeneca.
#chemsky
loading . . .
PROTAC-Splitter: a machine learning framework for automated identification of PROTAC substructures
https://rdcu.be/e4Ulj
0
7
1
Blender can generate cool view of molecules :)
4 months ago
1
6
0
reposted by
pen(Taka)
Derek Lowe
4 months ago
This is no way to run a regulatory agency:
loading . . .
Moderna Reversal
https://www.science.org/content/blog-post/moderna-reversal
3
58
12
相方におすすめされて一気に読んだ。 自分的には面白かった。
www.amazon.co.jp/dp/410106141...
loading . . .
成瀬は天下を取りにいく (新潮文庫 み 73-1)
Amazon.co.jp: 成瀬は天下を取りにいく (新潮文庫 み 73-1) : 宮島未奈: Japanese Books
https://www.amazon.co.jp/dp/4101061416?tag=note0e2a-22&linkCode=ogi&th=1&psc=1
4 months ago
1
0
0
I don't think that current AI technology can find novel scaffolds which is difficult to design by medicinalchemist but I think it can find solution more efficiently. (IMHO...)
4 months ago
0
0
0
MolVE: An Open-Source Web Platform for Visualizing and Evaluating AI-Designed Molecules to Aid in Prioritization | Journal of Chemical Information and Modeling
pubs.acs.org/doi/10.1021/...
loading . . .
MolVE: An Open-Source Web Platform for Visualizing and Evaluating AI-Designed Molecules to Aid in Prioritization
Advances in artificial intelligence and deep generative models have enabled the rapid generation of novel molecular structures for advanced material science and drug discovery. However, the effective evaluation of these candidates still depends, in the end, on expert judgment, which is often fragmented and difficult to scale. This work introduces MolVE, an open-source, web-based platform designed to enable asynchronous, distributed, and collaborative evaluation of molecules by experts. The platform combines secure user authentication, data set management, and interactive 2D/3D visualizations, enabling chemists and pharmacologists to curate, annotate, and evaluate molecules efficiently. Additionally, it offers APIs for seamless integration with programming languages and provides a Python service to run machine learning and deep learning models. MolVE is a comprehensive, ready-to-deploy application built with React, Node.js, Express, and PostgreSQL, and is fully containerized using Docker. This setup enables scalable deployment in both academic and industrial settings.
https://pubs.acs.org/doi/10.1021/acs.jcim.5c02412
4 months ago
0
1
0
The model showed good correlation between data came from PROTAC DB and prediction. But showed moderate correlation between data from their experiments and prediction. Data-Driven Design of PROTAC Linkers to Improve PROTAC Cell Membrane Permeability | JACS Au
pubs.acs.org/doi/10.1021/...
loading . . .
Data-Driven Design of PROTAC Linkers to Improve PROTAC Cell Membrane Permeability
Proteolysis-targeting chimeras (PROTACs) are promising next-generation therapeutics for the degradation of disease-associated proteins. However, optimizing the physicochemical properties of PROTACs, p...
https://pubs.acs.org/doi/10.1021/jacsau.6c00033
4 months ago
0
2
0
It’s snowing here for the first time in about over 10 years.
4 months ago
1
4
1
Split PROTAC molecule to 3 compornents with protac_splitter
#RDKit
#cheminfomratics
#memo
#python
Proteolysis-targeting chimeras (PROTACs) are one of the interesting modalities in these days because the modality can engage protein of interest (POI) and E3 ubiquitin ligase and then causes…
loading . . .
Split PROTAC molecule to 3 compornents with protac_splitter #RDKit #cheminfomratics #memo #python
Proteolysis-targeting chimeras (PROTACs) are one of the interesting modalities in these days because the modality can engage protein of interest (POI) and E3 ubiquitin ligase and then causes degradation of POI. PROTAC molecules are build from 3 components, POI binder, Linker and E3 binder. So chemists and cheminformatitian would like to analyse these molecules by each compornents. However sometime it's difficult to split molecule to these components.
https://iwatobipen.wordpress.com/2026/02/07/split-protac-molecule-to-3-compornents-with-protac_splitter-rdkit-cheminfomratics-memo-python/
4 months ago
0
2
1
A Comprehensive Review of Emerging Approaches in Machine Learning for De Novo PROTAC Design
arxiv.org/abs/2406.16681
loading . . .
A Comprehensive Review of Emerging Approaches in Machine Learning for De Novo PROTAC Design
Targeted protein degradation (TPD) is a rapidly growing field in modern drug discovery that aims to regulate the intracellular levels of proteins by harnessing the cell's innate degradation pathways t...
https://arxiv.org/abs/2406.16681
4 months ago
0
2
1
Protap: A Benchmark for Protein Modeling on Realistic Downstream Applications
arxiv.org/abs/2506.02052
loading . . .
Protap: A Benchmark for Protein Modeling on Realistic Downstream Applications
Recently, extensive deep learning architectures and pretraining strategies have been explored to support downstream protein applications. Additionally, domain-specific models incorporating biological ...
https://arxiv.org/abs/2506.02052
4 months ago
0
1
0
reposted by
pen(Taka)
Noel O'Boyle
5 months ago
Blogpost that looks at how LLMs have improved at 'reasoning' over time. This is a key capability that enables many scientific workflows.
baoilleach.blogspot.com/2026/01/impr...
loading . . .
Improvement in reasoning performance of LLMs over time
If you tried using ChatGPT when it first came out and concluded it wasn't much use for a scientific reasoning task, it might be time to try ...
https://baoilleach.blogspot.com/2026/01/improvement-in-reasoning-performance-of.html
0
5
2
reposted by
pen(Taka)
Nikolai Slavov
4 months ago
A reminder that proteins are highly dynamic molecules. 🟧 We have made much progress in measuring & predicting static protein structures, but the dynamics that animate life remain challenging to measure & model.
loading . . .
2
34
10
link.springer.com/article/10.1...
loading . . .
Paths to cheminformatics: Q&A with Rajarshi Guha - Journal of Cheminformatics
Journal of Cheminformatics -
https://link.springer.com/article/10.1186/s13321-025-01133-x
4 months ago
0
3
1
Load more
feeds!
log in