Spaces:
Running
Running
Commit History
-
feat(design): bioluminescent green+violet palette and re-tuned landing hero
- Swap the whole instrument palette to life-green (#4ADE80 / #15803D) primary, violet (#A78BFA / #5B21B6) secondary, amber (#FBBF24) warnings across globals.css tokens, tailwind config, and every hardcoded chart/sequence color in src (alignment, phylo, domains, structure, interactions, ADMET). - Landing hero: split layout with a live binary-DNA viewer panel (0/1 glyphs flowing along green/violet strands, pointer parallax, reduced-motion static frame, ResizeObserver tracking), new workflow-first subcopy, spring entrances. - Sidebar: remove the floating collapse chevron; sidebar always expanded. - Remove CursorGlow component and all usages. - Sync design.md to the new palette and contrast values.deb8696
-
feat(export): add downloads to ADMET, MD, pairwise, AlphaFold, docking, pathway, plus 4 new learn topics
527a85d -
fix(frontend): stop polling after job completion and surface AI rate-limit retry countdown
224d629
-
Refine design system: semantic color tokens, tiered motion, denser result cards, VinaLog toolbar
5e98b5a
-
refactor(icons): migrate lucide-react to @phosphor-icons/react, remove dep
349f22c
-
feat(md): verified force field/solvent menu (ff14SB/ff15ipq/ff19SB/amberfb15/CHARMM36 x OBC1/OBC2/GBN2) with alanine-dipeptide createSystem startup probe; explicit errors for invalid combos; dynamic frontend menu
2583376
-
fix(frontend): clear stale results, prefill-only bridges, and results-ready banners
Stop bridge pages from auto-running searches on navigation, clear result cards when inputs change, and add completion banners with auto-scroll on polling job pages. Co-authored-by: Cursor <cursoragent@cursor.com>bc59cdc -
fix(md): don't abandon long jobs after 5 min + trim workload
The frontend poll loop gave up after 5 minutes, so any MD job taking longer on the throttled CPU-only Space showed 'Simulation timed out after 5 minutes' even though the backend finishes within its 60-minute window. Raise the poll cap to 65 min (md + function pages) so results always surface. Also trim default workload so typical jobs finish fast: minimize 500->300 steps, equilibrate 300->200, SASA 48->36 points / 5->4 frames.c6b3385 -
feat(md): clay simulation-parameter controls (force field, solvent, run length)
09fc54e
-
feat(md): temperature/KE, Rg and SASA traces; fix OpenMM in deployed image
- Add temperature (from kinetic energy), radius-of-gyration and Shrake-Ruger SASA time series to OpenMM production results; static single points in the BioPython fallback; avg summary keys. - Correct nm->A conversion in _positions_to_np (RMSD/Rg/SASA were 10x too small and mislabeled as angstrom). - Self-calibrating production length: probe real platform throughput so runs fit the budget on fast local OpenCL and slow CPU-only containers (HF Spaces). - Deployment: install openmm>=8.0 via pip (PyPI since 8.0) instead of the broken micromamba+site-packages symlink; add libgomp1 to worker image; fix libgl1-mesa-glx -> libgl1 for bookworm base. Verified in a built image: OpenMM 8.5.2 imports and a full 1CRN production run completes with sane temperature/Rg/SASA. - Random-data unit tests for Rg, SASA, temperature-from-KE and Langevin thermostat; production integration test asserts the new keys. - Frontend: charts for temperature, Rg and SASA; SASA avg in summary.8e3419e -
feat(md): real OpenMM production runs with accurate Ca RMSD
- OpenMM 8.x implicit-solvent fix (explicit obc2 forcefield, NoCutoff) - Strip non-standard residues before parameterization - Adaptive production length (target 250 ps, cap 1 ns) sized to atom count - Ca-atom Kabsch RMSD + per-residue Ca RMSF, minimization drift metric - Graceful fallback to BioPython analysis when OpenMM cannot build structure - Fix rdkit/OpenMM DLL conflict (preload openmm before rdkit in worker/conftest) - Frontend: adaptive production progress bar + extended result typescbef588
-
feat: cross-feature auto-fill bridges — data flows between all tools via sessionStorage
- Structure page: reads structure_query, auto-fetches, cross-links to Docking/MD/Function/Domains - UniProt page: reads uniprot_accession, auto-searches, cross-links to Domains/Structure/Interactions - Interactions page: reads interaction_gene, auto-submits - ADMET page: reads admet_smiles, auto-analyzes, cross-links to Docking - Function page: reads function_pdb_id, auto-predicts - MD page: reads md_pdb_id, auto-runs - Pathway page: reads pathway_query, auto-searches - Docking page: reads docking_pdb_id and docking_smiles - BLAST page: reads domains_accession (fixes broken Domains->BLAST bridge) - Job detail page: cross-links to Domains/Structure/Interactions/Docking/MD/Function - Domains page: adds Pathway bridge712d7a9
-
fix: ADMET import error + MD secondary structure accuracy
- admet.py: replaced GraphMolDescriptors.FractionCSP3 with Descriptors.FractionCSP3 (correct import path) - admet.py: removed unused rdm alias and rdFineMD import - md_sim.py: fixed phi/psi Ramachandran ranges for better sheet detection (beta sheet: psi 90-180 and -180 to -120, helix: -160 to -40 / -75 to 45) - md/page.tsx: Interpretation now checks sheets, not just helices (TIM barrel = sheet-rich, not coil) - md/page.tsx: Structural analysis mode hides meaningless zero values (temperature, timestep, integration steps, energy) - md/page.tsx: Shows 'Mode', 'Chains' instead for BioPython modeec85a6b -
feat: industrial-grade ADMET + detailed MD/function results
Backend (admet.py): - 50+ molecular descriptors (Fsp3, MR, volume, E-state, Wiener, Zagreb) - Full functional group analysis (12 groups) - 5 drug-likeness filters (Lipinski, Veber, Ghose, Egan, MDDR) - ADMET predictions: absorption (oral bio, Caco-2, Pgp, HIA), distribution (Vd, BBB, PPB, CNS), metabolism (CYP panel, half-life, LipE), toxicity (AMES, hERG, DILI, skin, LD50), clearance - Structural alerts: PAINS + Brenk - Composite drug-likeness score (0-100) and toxicity risk score (0-10) - Fixed imports (removed rdFineMD, Fragkins typo) Frontend (admet/page.tsx): - Tabbed layout: Overview, Properties, Drug-likeness, ADMET, Alerts - Risk badge components (color-coded pass/fail/risk levels) - Detailed ADMET category breakdowns - Structural alert summary with progress bar Frontend (md/page.tsx): - Simulation parameters card with engine/forcefield/solvent details - Integration steps progress bars - Energy analysis with convergence + production trace - RMSD/RMSF statistics (min/max/avg) …24c3fcb -
fix: stale job polling + 5min timeout + backend staleness guard
- Frontend: both MD and function prediction polls now timeout after 5 min - Backend status endpoints: auto-fail jobs stuck in queued/running for > 10 min - Prevents infinite polling of orphaned jobs (e.g. adfcd000)b5d0e97 -
fix: extract string from rate-limit error object to prevent React crash
7300a31 -
fix: OpenMM via micromamba + BioPython structural fallback, real error messages
bd95b9f -
feat: scientifically accurate MD simulation with OBC2 solvent, Kabsch RMSD, per-residue RMSF
3fba508
-
Phase 3a/4/5: ADMET descriptors (RDKit), MD simulation (OpenMM), function prediction (DeepFRI-inspired) — backend + frontend
99fb209