lazarus

Contents

• Overview — The wall · What Lazarus does
• Evidence — Four dead repos, resurrected · Reproduces the paper · Measured — the N=20 benchmark
• How it works — The five organs · Point it at a URL · Runs anywhere
• Use it — Registry & pull · Dashboard · decay-check · Compose pipelines · Give back
• Get started — Quickstart · Status · License

The wall

Computational science has a reproducibility problem. A huge fraction of published methods are open, cited, and unrunnable within a few years: the repo is stale, wired to a stack that no longer resolves, and the real capability is buried in scripts with no API. If you're on a small, budget-constrained ML-for-biology team, you hit this constantly — the exact method you need exists, but getting it to run costs days you don't have, so it gets abandoned.

What Lazarus does

Lazarus is an agent that revives dead research code, lets you compose the revivals into pipelines, and gives the fixes back to the community.

1. Revive — point it at a bare GitHub URL. Lazarus reads the repo and the paper the way a newcomer would and writes its own goal and sanity check, then runs a build → execute → read-traceback → repair loop in a sandbox. Pin dependencies to the commit era, resolve the binary chain, locate the real capability, and emit a fixed integration contract: an importable module, a CLI, a pinned container, and a smoke test that proves it runs on a fresh input and passes the sanity check it defined.
2. Compose — because every revival emits the same contract, a revived tool is a composable brick. Wire bricks from any domain/language/era into a pipeline with a small YAML; one command runs them, passing artifacts between steps (local / remote / GPU).
3. Give back — the fixes Lazarus finds (rotted URLs, broken paths, a 15-year-old undefined-behavior bug) become maintainer-ready pull requests with CI, so the method can't silently rot again.

Proof — four dead repos, resurrected autonomously

Each revived from its own dead environment using only general heuristics (no repo-specific notes), each emitting a callable package that passes its own smoke test standalone:

The dMaSIF run built a whole CUDA/KeOps GPU environment from a bare image and patched a source bug to unlock GPU execution the original forced to CPU. The fpocket run fought a SourceForge download interstitial, a modern-ld link-order break, and a 15-year-old overlapping-sprintf undefined-behavior bug that modern glibc exposed. Three genuinely different resurrection flavors — TF/CUDA/C.

Three-way head-to-head (the three site predictors, scored by one script on identical PD-L1 residue labels): ScanNet 0.915 · dMaSIF 0.854 · MaSIF 0.823. All localize the interface (a 13-residue consensus core); the two surface methods (MaSIF & dMaSIF) agree most (Spearman ρ 0.70). Details: analysis/RESULTS.md.

Point it at a URL — it writes its own plan

You don't hand Lazarus a goal; you hand it a link. A web-enabled Scout reads the repo and paper (and only those — never your notes) and drafts the whole plan: the capability to revive, a base image, and a falsifiable sanity check. Then it pauses for your OK before spending a turn.

lazarus resurrect https://github.com/jertubiana/ScanNet

Run cold against ScanNet with no hints, the Scout reconstructed — from the URL alone — a plan matching the one a human expert hand-wrote after days of work:

That's the democratization step: the expert judgment of what "revived" even means becomes something you get from pasting a link.

Then we pointed it at a repo we'd never touched, in a different field entirely. From just github.com/davek44/Basset — a 2016 Lua Torch7 genomics CNN (chromatin accessibility from DNA sequence) — the Scout planned it and the agent revived it end to end. Along the way it cleared a new class of decay (the README's 2016 Docker image ships a manifest modern Docker refuses to pull — converted with skopeo), and caught a silent scientific-correctness bug: the naive run scored mean AUROC 0.675, but the agent traced it to hg19's soft-masked lowercase bases falling through Basset's uppercase-only one-hot encoder, patched it, and reproduced the paper — mean AUROC 0.8944 vs 0.895 across all 164 cell types. A fifth brick, a new domain (genomics, not protein surfaces), a fourth dead framework — from a link. Details: docs/CHALLENGES.md §5.

And the one that shows the integrity of the sanity check: from github.com/gcorso/DiffDock — the ICLR-2023 diffusion molecular-docking model, ~2 years stale — the Scout revived it on GPU. Its shipped example is a hard case (top-1 ~5 Å, under DiffDock's own < 2 Å bar), so rather than fake a pass, Lazarus docked 8 complexes from DiffDock's own test set, reproduced its ~40 % top-1 success rate, and found a rock-solid hero case (6MOA: RMSD 0.35 Å — the predicted pose sitting on the crystal ligand). It refused to ship a green checkmark it hadn't earned. Details: docs/CHALLENGES.md §6.

Compose — an in-silico pipeline from revived bricks

examples/pipelines/binder_triage.yaml assembles methods that were each individually unrunnable a week ago into one binder-triage pipeline:

structure ─▶ ScanNet ─┐
          ─▶ dMaSIF ──┼─▶ consensus ─▶ interface residues that also line a druggable pocket
          ─▶ fpocket ─┘

lazarus run examples/pipelines/binder_triage.yaml \
  --input structure=4ZQK.pdb \
  --registry examples --registry components \
  --docker-host ssh://you@your-x86-gpu-box

Run live on PD-L1, it concluded: 27 interface residues (115, 123, 56, 121, 113…), but 0 druggable pockets → "the interface is clearly localized but not a druggable small- molecule pocket — a flat protein-protein interface, i.e. an antibody/biologic target." That's textbook immuno-oncology (PD-1/PD-L1 is an antibody target), reproduced from dead code. Sample output: examples/pipelines/sample_output_4ZQK/.

Give back

For the genuinely-abandoned repos, Lazarus prepares maintainer-ready PRs — the real fix plus a CI smoke test so it can't silently rot again:

• MaSIF — PR #93 — the rotted PDB download, fixed (direct RCSB fetch); verified to revive the built-in flow at ROC-AUC 0.9137. → giveback/masif/
• ScanNet — PR #16 — library_folder='' made to auto-detect the repo root; verified. → giveback/scannet/

(dMaSIF is skipped — CC BY-NC-ND, no-derivatives; fpocket's upstream is alive.)

Reproduces the paper

A smoke test proves a method runs; a benchmark proves it's *the method