Hit finding & screening
28 articles
A pyrazine-2-carboxamide antimalarial that cures mice in one dose has entered phase 1
- A P. falciparum growth-inhibition screen identified a new pyrazine-2-carboxamide series for blood-stage malaria.
- Lead optimization improved anti-plasmodial potency and metabolic stability and reduced CYP2D6 inhibition risk, giving IWY357.
- A single dose was fully curative in a Pf-humanized SCID mouse model, resistance selection showed a high barrier, and the compound has progressed through GLP toxicology into phase 1.
A phenotypic hit taken all the way to the clinic with a single-dose cure in the humanized-mouse model is what the field has wanted since resistance to front-line agents began eroding. The CYP2D6 fix matters for combinations, which is where a short-course regimen would actually live. I would watch the human PK, since a single-dose claim lives or dies on exposure.
An AlphaLISA screen opens the ISG15–UBA7 interaction to inhibitor hunting
- ISG15 and its E1 enzyme UBA7 drive ISGylation, a pathway linked to treatment resistance in cancer, yet no inhibitors exist.
- The authors built an AlphaLISA assay for the ISG15–UBA7 interaction with strong robustness metrics for high-throughput use.
- A pilot screen of a small library gave a handful of hits, two of which also reduced ISGylation in cells.
This is a pilot on under a thousand compounds, so the hits are starting points, not leads. What matters is that a protein-protein interaction between a ubiquitin-like modifier and its E1 now has a screenable format. I'd run it against a real diversity set and counter-screen AlphaLISA interferers hard.
HTS framework finds small molecules that block tau binding to the LRP1 receptor
- The team built a quantitative assay set around purified LRP1 ligand-binding domain 4, using fluorescence polarization, split luciferase and TR-FRET.
- Tau, RAP and a peptide ligand competed for overlapping binding sites with nanomolar-range affinities across formats.
- A screen on this platform identified small-molecule inhibitors of the interaction, a starting point against tau uptake and spread.
Protein–protein interactions with a receptor ectodomain are tough targets, so three orthogonal assays is the right way to weed out artifacts. I'd treat the hits cautiously until they show activity in cellular tau-uptake assays and clear LRP1's many other ligands, such as ApoE and RAP, without broad liabilities.
High-Throughput Screening Identifies Small-Molecule Inhibitors of the Tau-LRP1 Interaction ↗
HTS-derived covalent inhibitors hit active, GTP-bound KRAS G12C
- Approved KRAS G12C drugs mostly trap the inactive GDP state and face resistance; this series targets the active GTP-bound state instead.
- A keto-indolizine HTS hit with an aniline-derived acrylamide binds Cys12 in the switch-II pocket; crystallography shows the warhead engaging the γ-phosphate of a GTP analogue.
- Optimization gave compound 17, orally bioavailable in preclinical species, which prolongs disruption of KRAS–cRAF binding and ERK signalling and produced complete regression in a pancreatic cancer xenograft.
Using the γ-phosphate to position the warhead is neat: GTP-state selectivity comes from the nucleotide itself, not only the pocket. The comparison I'd want is against RAS(ON) tri-complex inhibitors, which need cyclophilin A while this doesn't. Acrylamide reactivity and proteome-wide cysteine selectivity also matter more here than for GDP-state binders.
In silico building-block selection widens the diversity of a 403,200-member peptide-like DEL
- A three-cycle, peptide-like DEL of 403,200 compounds was built, with a chemical space model of 4,774 commercial amino acids used to find under-represented building blocks.
- Affinity selections were run against three targets to compare library performance.
- Selection against carbonic anhydrase II recovered the known sulfonamide pharmacophore, supporting the computational design approach.
Recovering the sulfonamide on CA II is the expected sanity check, not proof of lead-like coverage. Peptide-like DELs often return big, polar hits, so what I'd judge is how many selected compounds sit in usable property space off-DNA, and how the two other targets behaved.
Screening under 0.1% of a library yields new QPCT/L inhibitor tool BI-3614
- QPCT and Golgi-bound QPCTL convert N-terminal glutamines to pyroglutamate, affecting Aβ oligomerization, chemokine stability and CD47–SIRPα signaling.
- A virtual screen selecting under 0.1% of an in-house library, based on similarity to bioactive conformations of known inhibitors, delivered new chemotypes and sped up hit discovery.
- Structure-guided optimization of a quinazolidinone series gave the cellular tool compound BI-3614, with improved activity over earlier inhibitors.
Screening under a tenth of a percent and still finding fresh chemotypes is the efficiency argument for conformation-based similarity searching. The old QPCT inhibitors leaned on metal-binding groups, so a new cell-active series is welcome for CD47 pyroglutamate biology. QPCT versus QPCTL selectivity is what I'd check first.
Scope library: a chemical space between fragments and full molecules for tractable hits
- Scope defines a chemical space between fragments and elaborated low-molecular-weight library compounds, emphasizing compound quality, ligand efficiency and selected property ranges to keep hits tractable for medicinal chemistry.
- Scope ring systems (ring-X-ring) organize the space and guide intentional functionalization toward low- to mid-micromolar potency; a roughly 10k-compound set suits medium-throughput SPR, native MS, DSF and biochemical screens.
- Case studies on trypanosomal CLK1, a 14-3-3/ERα molecular glue project and SARS-CoV-2 Mpro show comparable primary hit rates to diversity sets, with better ligand efficiency after counter-screening.
Honestly, the pitch I like here is hits you can actually start working on: a library sitting between fragments and full-size compounds, built around ligand efficiency, with ring-X-ring cores that tell you where to functionalize next. A 10k set fits SPR, native MS and DSF, so a smaller group can run it. The open question is whether primary hit rates on par with diversity sets, with better LE after counter-screening, hold up beyond three targets, and how much the scaffold constraint narrows novelty.
Open Screening Dataset Maps Small-Molecule Inhibitors Across Nine Human DNA Glycosylases
- A Scandinavian consortium built a high-throughput biochemical assay platform for human DNA glycosylases, the eleven enzymes that initiate base excision repair.
- A chemogenomic library was screened against nine glycosylases with assays good enough for hit calling, yielding primary and concentration-response data and several previously unreported inhibitors.
- All data, protocols and metadata are publicly available.
Glycosylases have been chemically neglected, so an open, annotated screen across nine of them is starting material a hit-finding team can mine directly. Chemogenomic libraries carry target annotations, which helps with mechanism and selectivity reads. I'd immediately cross-check the hits for assay interference and DNA-binder artifacts, since nucleic-acid enzyme screens are notorious for them.
A high-throughput screening dataset of small-molecule inhibitors across human DNA glycosylases ↗
Automated Ligand-Detected NMR Platform Speeds Hit Triage in Drug Discovery
- An automated, high-throughput ligand-detected NMR method targets hit triage in medicinal chemistry screening campaigns.
- The approach is framed as enabling rapid, qualitative binding assessment of screening hits at scale.
- Reads as a platform/methodology contribution focused on throughput and workflow automation rather than a single target or chemical series.
NMR gives you binding mode, not just 'yes it binds' — that's the filter SPR and TSA can't offer, especially for the promiscuous frequent-hitters that eat up your week. If the automation actually holds up at HTS volumes, this slots in as a fast confidence check before compounds go into a co-crystal queue, not a replacement for it.
New ACS Platform Streamlines Drug Discovery by Screening Crude Reaction Mixtures Directly
- A direct-to-biology (D2B) platform synthesizes candidate compounds at small scale and evaluates the crude reaction mixtures directly in biological assays, bypassing conventional purification.
- The approach couples miniaturized, automation-compatible chemistry with rapid biological readout to shorten the design-make-test cycle typical of early hit-finding and library exploration.
- Positioned within a broader wave of D2B methodology in medicinal chemistry, applicable to accelerating hit identification across diverse chemotypes.
Skipping purification is the real win—cuts days off the DMT cycle when you're triaging hundreds of analogs. But I want hard numbers on false-positive rates from residual catalyst/byproducts before trusting crude-mixture hits blind; great for rapid SAR triage, not for anything feeding a confirmatory dose-response.
Two-Step Route Expands Warhead Diversity in Covalent Genetically-Encoded Macrocycle Libraries
- A two-step route builds covalent genetically-encoded macrocycle libraries (cGELs): cysteines form the macrocycle via a diketone linchpin, then a separate Knorr-pyrazole step adds the electrophilic warhead.
- Separating cyclization (basic pH) from warhead installation (acidic pH) avoids the regioisomer mixtures that limited earlier one-pot chemical modification methods.
- This lets more diverse, reactive electrophiles be used safely, broadening covalent chemotypes accessible for selections against protein targets in DEL-style screens.
Regioisomer scrambling in one-pot warhead installation is exactly what kills confidence when you're deconvoluting covalent DEL hits — you can't tell if a signal is real or an artifact of a messy electrophile mixture. Decoupling cyclization from Knorr-pyrazole warhead chemistry means finally screening exotic, more reactive electrophiles beyond the usual acrylamide/chloroacetamide workhorses without second-guessing every hit's identity.
TrmD as an Antibacterial Target: A Review of Small-Molecule Inhibitor Discovery Strategies
- TrmD, a SPOUT-family bacterial tRNA methyltransferase without a human counterpart, is highlighted as a validated antibacterial target amid rising antimicrobial resistance.
- The review catalogs strategies used to discover small-molecule TrmD inhibitors—fragment-based design, high-throughput and virtual screening, click-chemistry-enabled direct-to-biology methods, molecular hybridization, and prodrug approaches.
- It synthesizes structural features and structure-activity relationships across these diverse chemical scaffolds to inform future inhibitor optimization.
TrmD's lack of a human ortholog is the real selling point here — a wide therapeutic window without the usual off-target liability, which is rare enough in antibacterial discovery to justify the review's existence. The click-chemistry/direct-to-biology entries jump out as the underexploited lane: fast SAR turnaround without carrying every analog through full synthesis, exactly what a fragmented, scaffold-diverse target like this needs before someone finally nails spectrum and PK.
TrmD: A Promising Antibacterial Target and Its Small-Molecule Inhibitors ↗
Machine Learning and Docking Methods Show Uneven Generalization on DNA-Encoded Library Screens
- The study benchmarks machine learning, physics-based docking, and cofolding methods for predicting protein-ligand binding using DNA-encoded library (DEL) screening data.
- Methods compared include state-of-the-art ML models alongside physics-based docking tools (Schrodinger Glide, Rosetta GALigandDock) and the cofolding method Boltz-2.
- Ground-truth binding data came from ultralarge DEL selection experiments across three biologically diverse protein targets and multiple DEL synthesis formats.
- The work follows a NeurIPS competition in which even top-performing ML models trained on DEL data failed to generalize to out-of-distribution (OOD) chemical space.
- ML models performed well in-distribution, but out-of-distribution hit discrimination depended on the specific target and ligand context, with no single method consistently dominating across cases.
- The authors conclude that benchmark performance alone cannot predict OOD generalization and release an open-source package, DEL-iver, for evaluating binding-prediction methods against DEL screening data.
This is the paper you send to anyone pushing to swap your docking rescore step for a single ML model. "No method dominates OOD" is the whole ballgame: your real triage work is always on a scaffold the model hasn't seen, and a benchmark AUC built on in-distribution DEL data tells you almost nothing about how a model will rank the novel matter you bring in next week. I don't read this as an argument against ML - Boltz-2 and friends are genuinely useful, fast filters - but as a case for running physics-based docking/cofolding in parallel, not as a fallback you only reach for when ML looks shaky. Target- and ligand-context dependence also means there's no one 'best' pipeline to standardize on company-wide; you validate per target, per chemotype, every time. DEL-iver going open-source is the practically useful bit - a shared OOD benchmark beats trusting a vendor's Tanimoto-flattered internal numbers.
New "Scope" Chemical Space Yields Ligand-Efficient Hits Across Three Targets
- "Scope" describes a mid-sized (10k-50k compound) chemical space positioned between minimal fragments and fully elaborated low-molecular-weight libraries, designed to maximize ligand efficiency and medicinal chemistry tractability.
- The authors introduce "Scope ring systems" (ring-X-ring) as a core organizing concept for building libraries and guiding functionalization toward sufficient potency.
- A 10k-compound Scope screening set — evaluated by SPR, native mass spectrometry, DSF, and biochemical assays — matches general diversity sets' primary hit rates even at higher screening concentrations, while showing superior ligand efficiency and higher hit rates after counter-screening.
- Case studies on trypanosomal CLK1 kinase, a 14-3-3/estrogen receptor-alpha molecular glue project, and SARS-CoV-2 main protease show the set yields diverse, tractable, ligand-efficient hits across varied binding sites.
The "sweet spot between fragments and full libraries" pitch isn't new — DEL, FBDD, and house libraries have all claimed it before. What's actually new in Scope is the ring-X-ring organizing logic: forcing vectors off two ring systems rather than one flat scaffold gives a built-in growth vector for SAR from hit one, the part fragment campaigns usually bolt on later. The number that matters to me isn't the hit rate, it's "higher hit rate after counter-screening" — that's fewer SPR artifacts and aggregators wasting my week. The real test is the 14-3-3/ERα glue case: PPI/glue targets chew up conventional libraries because there's no deep pocket to reward LE. If a rigid, moderately-sized scaffold set can seed a glue hit, that's the transferability claim worth watching, not the Mpro or CLK1 wins.
Benchmark Study Reveals Blind Spots in AI-Based Virtual Screening for Keap1-Nrf2
- A new benchmarking study examines a virtual-screening pipeline that chains structure-based co-folding models with learned-affinity scoring, an increasingly common setup for computational hit-finding.
- The cascade was applied to the Keap1-Nrf2 protein-protein interaction, a notoriously hard-to-drug target due to its flat, polar interface.
- Instead of trusting only the final ranked output, the authors assessed each stage separately against experimentally meaningful signal.
- They identify specific points where a stage's score diverges from that signal, a failure mode that can mislead downstream compound prioritization.
- The paper proposes per-stage control checks practitioners can run before relying on a cascade's final hit list, framing the work as a methodology and reliability study rather than a report of a new inhibitor.
Keap1-Nrf2 is exactly the flat, polar PPI where a co-folding model will happily spit out a confident-looking pose and the affinity scorer will rank it #1 for the wrong reasons — so a paper that pries the cascade apart stage-by-stage is more useful to me than another "we found a hit" claim. What I actually want out of this: a checklist to run on my own vendor or in-house pipeline before I let its top 20 dictate what goes on the synthesis queue. If the co-folding confidence and the affinity score are quietly diverging, that's exactly the failure mode that burns weeks on compounds that never had real signal behind them. No new chemical matter here, no binding mode to chase — just a reminder that for a target this treacherous, the ranked list is not the QC step. Filed under "read before ordering," not "read for the inhibitor."
New Fragment-Based Docking Method Targets Long, Flexible Peptide Ligands
- Researchers built STELLAR, a new docking workflow aimed at a persistent problem: current tools poorly handle long, highly flexible biopolymer ligands, including peptides exceeding roughly ten subunits, because of their vast conformational freedom.
- STELLAR splits such ligands into smaller fragments, docks each one separately, then reassembles them into a full-length, physically realistic pose, using established software including GNINA, RDKit, and GROMACS for refinement.
- Tested against known peptide-protein complexes from the Propedia database and the Protein Data Bank, the workflow reproduced experimentally observed binding poses with high accuracy.
- Compared with other state-of-the-art docking tools, it runs mainly on CPUs, scales linearly with ligand length, executes faster, and includes a ranking metric suited to high-throughput screening of long-chain polymer-protein interactions.
Ten residues is roughly where my patience with standard docking runs out — past that, chains have so much conformational freedom that I end up either restraining everything by hand or giving up on the exercise. Fragment-then-reassemble is a sensible workaround, and leaning on GNINA/RDKit/GROMACS instead of a black-box neural net means I can actually inspect intermediate poses. CPU-only, linear scaling is the detail that matters most day-to-day: no GPU queue, no cloud bill, just run it on the workstation overnight for a stapled-peptide library. Most ML docking tools give me a score with no real confidence handle for ranking; a purpose-built ranking metric for long-chain ligands is genuinely missing elsewhere. That said, Propedia/PDB benchmarks are known complexes — reproducing a crystal pose isn't the same as correctly ranking novel binders against a target with no solved structure. Worth a pilot run, not a blind swap-in.
STELLAR: A Fragment-Based Docking Workflow for Highly Flexible Long-Chain Biopolymers ↗
Dynamic Chemical Library Yields Sub-Picomolar Thrombin Inhibitor
- Researchers applied dynamic combinatorial chemistry (DCC), a hit-finding method in which reversible chemical building blocks assemble and reassemble under target guidance, letting the biological target itself select its best-binding partners.
- A new platform uses short peptide nucleic acid (PNA) tags to template three-fragment combinations, generating a library of 125,000 possible trivalent assemblies screened against thrombin.
- Candidate complexes are isolated by size-exclusion filtration and identified by MALDI mass spectrometry, compressing an entire selection-and-readout cycle to under an hour.
- Thrombin favored combinations engaging its active site and both flanking exosites at once, and this trivalent binding mode underlies the exceptionally tight affinity.
- The winning assembly is a fully reversible inhibitor with sub-picomolar affinity, achieving near-stoichiometric inhibition of thrombin activity.
DCC keeps getting overshadowed by DEL and FBDD, but this is the kind of result that should change that — a sub-hour select-and-read cycle via PNA templating plus MALDI readout tackles the real bottleneck that's always killed DCC in practice: slow kinetics and painful analytics. What actually earns the affinity isn't luck, though — it's rational exploitation of thrombin's well-mapped exosite architecture, deliberately building a trivalent ligand that bridges the active site and both exosites simultaneously. That's textbook multivalency applied with real target knowledge. My immediate skepticism: a PNA-templated trivalent assembly hitting sub-picomolar affinity is almost certainly a big, charged, un-drug-like molecule — I'd want MW, PK, and oral bioavailability numbers before getting excited about anything beyond a tool compound or long-acting parenteral candidate. Still, as a proof of concept for DCC against other exosite-rich or multi-pocket targets, this is a template worth stealing.
Discovery of a Reversible Sub‐Picomolar Thrombin Inhibitor Using DCC ↗
AI Screening Pipeline Flags Repositioned CASP4 Inhibitor Candidates for Alzheimer's
- CASP4, an inflammatory caspase linked to Alzheimer's disease, is the target of a new computational drug-repositioning pipeline built to screen DrugBank compounds for potential inhibitors.
- The workflow combined docking-based prioritization with ChemBERTa language-model embeddings and physicochemical descriptors to train machine-learning classifiers.
- A Random Forest classifier and regressor were used to identify likely active compounds and rank them by predicted potency.
- Downstream cheminformatics, PK-PD evaluation, and molecular docking narrowed the pool to five repositioning candidates.
- Molecular dynamics simulations and MM/PBSA free-energy analysis were then applied to assess binding stability, identifying two compounds (DB05316 and DB00519) with predicted binding compared favorably to the reference drug donepezil.
- The authors present the pipeline as a general strategy for prioritizing repurposed compounds against novel drug targets.
A five-stage funnel — docking, ChemBERTa embeddings, Random Forest, then MD/MM-PBSA — down to two compounds looks disciplined, but each stage has its own error rate, and stacking filters doesn't guarantee the errors cancel out. MM/PBSA rescoring of structurally unrelated ligands is notoriously unreliable for absolute ranking; chain enough filters and you can end up polishing false positives rather than eliminating them. Where this actually sits in the AI hit-finding wave: not novel chemistry, but faster triage of known-compound space, which is a real and growing niche. The genuine advantage is DrugBank sourcing — DB05316 and DB00519 already carry ADMET, safety, and formulation data, so there's no synthesis or fresh tox package standing between candidate and IND-enabling work. None of that substitutes for a binding assay. Until CASP4 activity is confirmed biochemically, this is a ranked hypothesis list, not a hit.
New Functional Screen Identifies Noninhibitory USP7 Ligand Enabling DUBTAC-Based CFTR Stabilization
- Ligands that bind deubiquitinating enzymes (DUBs) without blocking their catalytic activity are notoriously hard to find — a new on-bead, proximity-driven functional screening platform is designed to identify them.
- Such noninhibitory DUB ligands are essential for building DUBTACs (deubiquitinase-targeting chimeras), bifunctional molecules that stabilize target proteins by recruiting DUBs to strip ubiquitin marks, the inverse of degrader-based targeted protein degradation.
- That rarity has made noninhibitory DUB ligands the central bottleneck in DUBTAC development.
- Using the platform, the team discovered a previously unreported noninhibitory ligand for the deubiquitinase USP7.
- Conjugating this USP7 ligand to a CFTR-binding moiety produced a DUBTAC lead, WJ045, which stabilized cellular CFTR protein levels.
- The results demonstrate the platform's utility for discovering DUB-recruiting ligands and advancing targeted protein stabilization, with relevance to cystic fibrosis biology.
A noninhibitory DUB ligand is a harder ask than it sounds - you need a binder that occupies USP7 without touching the catalytic cleft, so a standard activity-inhibition screen is the wrong tool entirely. That's what makes the on-bead, proximity-driven functional assay the real story here: it's a hit-finding method, not just a molecule, and if it generalizes across other DUBs it addresses the actual bottleneck in this space. DUBTACs have quietly been the underdeveloped mirror image of degrader chemistry for years - everyone chasing PROTACs, almost nobody with tractable DUB recruiters in hand. WJ045 stabilizing CFTR is a nice proof point tying this to real biology, though it's a single cellular readout so far - want to see USP-family selectivity and whether the platform yields a second, unrelated ligand.
ER-Targeted NIR Probe Enables High-Throughput Discovery of hCES2A Inhibitors
- PA-HDCI, a near-infrared fluorogenic probe built on the HDCI fluorophore scaffold, localizes to the endoplasmic reticulum and reports on human carboxylesterase 2A (hCES2A) activity in living cells and animals.
- The probe combines a large Stokes shift, high metabolic stability, and reliable ER targeting, enabling in situ, real-time imaging of hCES2A function across multiple biological systems.
- Using PA-HDCI in a high-throughput screening assay, the team identified compound A4, a highly potent covalent inhibitor of hCES2A.
- hCES2A is the intestinal enzyme that converts the chemotherapy drug irinotecan into its toxic active metabolite, driving irinotecan-induced intestinal toxicity (IIT).
- In tumor-bearing mouse models, A4 showed a favorable safety profile and reduced irinotecan-associated intestinal toxicity while therapeutic efficacy was maintained.
- Together, the work delivers both a new imaging tool and a validated drug-discovery platform for hCES2A-targeted therapeutics.
Solid probe engineering, not just a screening reagent: coaxing ER-selective localization and a large Stokes shift out of the HDCI scaffold gives clean signal separation in situ — photophysics that holds up in cells, not just a cuvette. The real value-add is methodological. A mechanistic imaging tool doubling as an HTS readout turns hCES2A activity into a screenable phenotype in living systems, closing the usual gap between biochemical assays and cellular reality. Target-wise, nothing novel here — hCES2A is a known off-target liability that bioactivates irinotecan into its gut-toxic metabolite, so this is a 'fix the side effect' play, not a new mechanism. A4 is an HTS-derived covalent hit with encouraging mouse data, but still needs the standard covalent-hit workup: reactivity profiling, esterase-family selectivity, and SAR.
HTS Screen Identifies CGP7930, a Known GABA-B Modulator, as a Potent Activator of the Cardiac Mitochondrial Calcium Uniporter
- Researchers screened a library of 1,280 known bioactive compounds in search of pharmacological activators of the mitochondrial calcium uniporter complex (MCUc), a target for which potent, selective agonists have been scarce.
- The screen identified CGP7930 — a compound previously characterized as a GABA-B receptor allosteric modulator — as a potent activator of mitochondrial calcium uptake, highlighting a drug-repurposing angle for a difficult target.
- Mechanistic follow-up showed the activating effect depends on MICU1, a key regulatory subunit of the uniporter complex, pointing to a specific mode of action rather than a nonspecific membrane effect.
- Enhanced mitochondrial calcium entry translated into improved cardiac contractile bioenergetics, suggesting relevance to conditions involving impaired heart energy metabolism.
- The work provides a valuable pharmacological tool compound and a starting point for developing more selective next-generation MCU activators.
CGP7930 landing as an MCU activator is the kind of hit that's simultaneously a gift and a headache. MICU1-dependence is the real finding here — it means the compound isn't just permeabilizing membranes or brute-forcing the pore, it's engaging a regulatory interface, which is exactly what you want if you're hunting for a selectivity handle to build SAR around. But this molecule already has a day job as a GABA-B PAM, so before I'd touch it as a lead I'd want a counter-screen and a clean SAR series that walks GABA-B affinity down while holding MCU activation up — classic polypharmacology triage, not a bonus. As a repurposed known compound it buys you PK/tox data, not real IP or optimized potency; it's a starting point, not a lead. Given how thin the MCU tool-compound cupboard has been, though, any validated chemical matter here is worth chasing.
AI Co-Folding Model Boltz-2 Speeds Discovery of Novel AKR1B10 Inhibitors
- AKR1B10 is an aldo-keto reductase enzyme overexpressed in several cancer types, making it an attractive but challenging drug target.
- Researchers used Boltz-2, an AI-based protein-ligand co-folding model, to computationally screen a large, chemically diverse compound library and prioritize a small, diverse shortlist of candidates for lab testing.
- Experimental testing of that shortlist produced an unusually high hit rate, with most of the tested compounds showing real inhibitory activity against AKR1B10.
- Several confirmed hits reached submicromolar potency and carried chemical scaffolds not previously reported as AKR1B10 inhibitors.
- The results support co-folding AI models as a practical, resource-efficient way to convert computational predictions into experimentally validated drug leads, reducing reliance on brute-force screening.
• Most of a small, deliberately diverse shortlist came back with real inhibition. That hit rate isn't HTS-style luck; it's a model that has actually learned something about the pocket, not the kind of docking score I'd normally discount. • Novel scaffolds are the real prize, but I want SAR before I get excited: is potency riding on one privileged fragment, or is there a real vector to optimize? Submicromolar out of the gate on unprecedented chemotypes usually means headroom, not a dead-end analog of known reductase binders. • AKR1B10 sits close to AKR1B1 (aldose reductase) — selectivity is the whole game here; nobody needs another dirty aldo-keto reductase pan-inhibitor with off-target baggage. • This is one target, one campaign. I'd want to see it replicated on something without such a cooperative pocket before I trust co-folding over ensemble docking/FEP as a default triage step. Promising, not proven — but the direction hit-finding is heading.
Efficient Discovery of Potent AKR1B10 Inhibitors Using Co-folding Model Boltz-2 ↗
A SuFEx Click Reaction Streamlines DNA-Encoded Macrocyclic Peptide Libraries
- DNA-encoded libraries (DELs) let researchers screen ultralarge collections of macrocyclic peptides to find hit compounds for drug discovery, but efficient on-DNA cyclization chemistry has remained a bottleneck.
- A new on-DNA macrocyclization method uses sulfur(VI) fluoride exchange (SuFEx), a fast, click-type reaction, to close peptide rings directly on DNA tags.
- The design embeds a phenol and an aryl sulfonyl fluoride within a single DNA-tagged peptide, positioning the two groups to react with each other intramolecularly.
- Simply dissolving the construct in basic aqueous buffer triggers rapid, high-conversion cyclization without added catalysts or harsh conditions.
- The method enables efficient, high-yielding synthesis of ultralarge DNA-encoded macrocyclic peptide libraries, expanding the chemical space available for DEL-based hit discovery.
On-DNA chemistry is where good click reactions go to die — CuAAC needs copper that chews up your barcode, most coupling chemistry leaves truncation side-products you chase off HPLC for weeks. SuFEx actually respects the constraints: no metal, no coupling reagent, just a phenol and an ArSO2F sitting in basic water reacting with each other. That's "click" chemistry finally earning its name in DEL work instead of just borrowing the marketing. High conversion with zero catalyst also means boring QC, in the best sense — fewer truncated/uncyclized side-populations polluting the pool means the hits you pull downstream are more likely real signal, not artifacts of your worst-yielding step. For macrocycles — the space between small molecules and biologics everyone wants but few can screen efficiently — a clean cyclization step is what lets you scale diversity without sacrificing quality. This is the unglamorous methods advance that keeps unlocking new DEL generations.
SuFEx Cyclization Enables DNA-Encoded Macrocyclic Peptide Libraries for Drug Discovery ↗
Multimodal AI Framework Targets Drug-Resistant Bacteria While Screening for Toxicity
- Antimicrobial resistance is narrowing treatment options for pathogens like Staphylococcus aureus and Neisseria gonorrhoeae, motivating new computational discovery tools.
- MAPViS, a multimodal deep-learning framework, fuses molecular graph, fingerprint, and descriptor/3D geometric features via gated fusion, pretrained on ~10 million molecules using hierarchical pseudolabel classification and masked graph contrastive learning.
- After fine-tuning, it jointly predicts antibacterial activity against S. aureus and N. gonorrhoeae plus cytotoxicity risk in three human cell lines (HepG2, HSkMC, IMR-90).
- On benchmark and external validation data, MAPViS showed strong early-enrichment performance for S. aureus, with all ten top-ranked candidates confirmed experimentally active, while generalization to N. gonorrhoeae was more modest.
- The authors describe MAPViS as a scalable tool for joint activity-toxicity modeling to support antibiotic virtual screening.
Ligand-based, not structure-based — no target structure in the loop, so I'd worry about applicability domain once you push past its ~10M-molecule pretraining chemotypes into a new target class. The joint activity/cytotox head is the real differentiator: folding HepG2/HSkMC/IMR-90 flags into the same ranked list saves the counterscreen step I'd otherwise run manually — genuine time saved, not just convenience. But the S. aureus (10/10 confirmed) vs. N. gonorrhoeae ("modest") split is the tell: performance tracks training-data density per pathogen, not real antibacterial chemotype intuition. Before trusting a ranked hit list on an unfamiliar target, I'd want per-pathogen calibration and confirmed true negatives, not just top-10 hit rates. Good as a cheap pre-HTS triage filter; not a substitute for structure-based design or real counterscreening.
Reversible-Work Metadynamics Delivers Fast Hit Triage — and Exposes a Memorization Blind Spot in AI Co-Folding
- Virtual screening often yields false positives from fast, approximate scoring functions, while accurate free-energy calculations to filter them remain too costly for routine high-throughput use.
- The authors introduce CTMD (c(t)-based metadynamics), which ranks binding stability using the nonequilibrium reversible-work estimator c(t) from short, independent metadynamics runs, without requiring converged binding free energies.
- Across diverse targets and chemotypes, CTMD shows robust early enrichment while staying fast, transferable, and largely tuning-free.
- Benchmarking AI co-folding, the authors find Boltz-2's enrichment tracks similarity to its training data and persists even after active-site modifications, pointing to memorization rather than true binding physics.
- CTMD is offered as an open-source middle ground between quick docking/co-folding and costly free-energy methods, cutting wasted discovery-campaign resources.
A triage tier between docking and full FEP is exactly what's been missing from my workflow. Standard docking scores are too noisy to prioritize synthesis, and running FEP on every virtual-screening hit is a non-starter for budget and turnaround — CTMD's short, independent metadynamics runs with the c(t) estimator could slot right into that gap and actually change which compounds we send to synthesis, without a cluster's worth of compute. Open-source and largely tuning-free means it's adoptable without a specialist babysitting it. The Boltz-2 finding is the one I'd flag to my team before anyone leans on AI co-folding for real decisions: enrichment tracking training-set similarity even after active-site mutation means it may be pattern-matching known chemotypes, not scoring genuine binding physics. That's a trap for exactly the novel scaffolds we're chasing.
Early-Enrichment Hit Discovery via Reversible-Work c(t) Estimation in Metadynamics (CTMD) ↗
Bicyclic Peptide Libraries Deliver First Noncarbohydrate Inhibitors of the Hard-to-Drug Receptor Siglec-7
- Researchers used bicyclic genetically encoded peptide libraries (BiGEL) — phage-displayed peptides chemically stapled into two rings — to search for inhibitors of Siglec-7, a glycan-binding immune receptor considered notoriously hard to target with small molecules.
- Sequencing-based panning against Siglec-7 nominated hundreds of candidate peptides; a subset were confirmed as genuine binders by surface plasmon resonance and as functional disruptors of the Siglec-7:GD3 interaction by competitive ELISA, with machine learning models identifying further hits of similar potency.
- Structure-activity work showed the bicyclic ring architecture itself is essential for potency, and NMR studies located one optimized lead's binding site away from the canonical glycan-binding domain, pointing to a possible allosteric mechanism.
- Cell-based multivalent binding assays confirmed engagement with Siglec-7 but also revealed considerable nonspecific binding to receptor-negative cells, highlighting a selectivity challenge still to be resolved.
The allosteric site is the real hook here — a bicyclic peptide binding away from the canonical glycan pocket on a target everyone assumed only the carbohydrate-recognition domain was druggable gives you a completely different SAR vector than trying to out-compete sialic acid for its own pocket. That's genuinely exciting for Siglec-7. But I'd want the nonspecific binding in the cell assays resolved before getting attached to any single lead — multivalent avidity effects can paper over a mediocre core affinity, and that's exactly the kind of artifact that kills a program downstream. Bicyclics themselves are the right chemotype to bet on: synthesizable, chemically stable enough for iterative SAR, and unlike DEL small molecules they're not fighting the flat, shallow topology that's stalled every prior GBP inhibitor effort.
Many Virtual Screening 'Improvements' May Not Be Real, Pre-Registered Study Finds
- The preprint asks a foundational methods question: given the size of a typical structure-based virtual screening benchmark, how large a difference in AUROC or enrichment between two protocols can actually be distinguished from statistical noise.
- Rather than assuming benchmark comparisons are inherently reliable, the authors first directly measure these resolution limits.
- They then pre-registered six candidate interventions to docking/scoring protocols and tested each against the measured resolution limits, rather than reporting post-hoc 'wins.'
- The pre-registration design is meant to guard against selective reporting, a known issue where small, benchmark-specific gains get presented as general improvements.
- This is a methodology/rigor study, not a new-inhibitor or target-specific paper; it addresses how virtual screening improvements should be evaluated.
- Practical implication: many published claims of improved virtual screening performance may fall within the noise floor of typical benchmarks, so hit-finding teams should treat single-benchmark improvement claims cautiously.
Every VS vendor pitch should have to clear this paper's bar. If a 'protocol improvement' can't beat the measured noise floor of AUROC/enrichment on a benchmark our size, it's not an improvement — it's a coin flip dressed up in a webinar slide. Six pre-registered interventions is a high bar; realistically most of us won't pre-register anything before a campaign, but I can at least ask collaborators to report effect sizes against a resolution limit, not just a headline AUROC bump. Sharpest implication for me: the co-folding hype (Boltz-2 and friends) needs the same treatment — if those models are just pattern-matching PDB-adjacent chemotypes, their 'wins' over classic docking/FEP on public benchmarks could be memorization, not generalization. I'm not swapping FEP for a black box on this evidence alone.
Silencing PARP1 at the Gene Level: A G-Quadruplex-Binding Small Molecule Sidesteps PARP Inhibitor Toxicity
- Rather than inhibiting or trapping the PARP1 enzyme like approved PARP inhibitors (PARPis), researchers targeted the PARP1 gene promoter itself to shut down PARP1 production at the transcriptional level, aiming to avoid the hematologic toxicity and resistance mechanisms associated with PARPi-mediated PARP1 trapping.
- The promoter region forms a non-canonical (3+1) hybrid G-quadruplex structure distinguished by an adenine bulge, a distinctive DNA fold not previously exploited as a drug target.
- Combining computational modeling with biophysical characterization, the team identified a small molecule that selectively engages this unusual G-quadruplex architecture.
- In multiple myeloma cells, the compound reduced PARP1 expression, disrupted downstream DNA repair signaling, and triggered DNA damage-associated apoptosis.
- Healthy blood cells were largely spared, pointing to a possible therapeutic window distinct from conventional PARP inhibitor toxicity profiles.
The part that gets me: attacking PARP1 at the promoter instead of the active site. Every PARPi on the market — olaparib, niraparib, talazoparib — works by trapping or inhibiting the protein; the hematologic toxicity and trapping-driven resistance are baked into that mechanism. Silencing transcription via a G-quadruplex sidesteps the whole liability profile, at least on paper. That said, G4-targeting ligands are a rough class to work in — selectivity across the thousands of quadruplex-forming sequences in the genome is the perennial failure mode, not potency. And this (3+1) hybrid fold with an adenine bulge is a genuinely novel pocket, which cuts both ways: interesting SAR territory, but no playbook to lean on. Still early — a validated hit in MM cells, not a lead, let alone a candidate. Worth watching, not betting on yet.