Browse State-of-the-Art › Drug Discovery

Drug Discovery

566 papers with code · 28 benchmarks · 26 datasets archive 2025-07-28

Medical

Drug discovery is the task of applying machine learning to discover new candidate drugs.

( Image credit: A Turing Test for Molecular Generators )

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

28 leaderboard tables shown for this task, 28 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 28 until expanded.

Syntology 7 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): BindingDB (1 judged, 0 placed), KIBA (1 judged, 0 placed), DRD2 (1 judged, 0 placed), QED (4 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
QM9 (11 rows) PAMNet A Universal Framework for Accurate and Efficient Geometric Deep... code Syntology official (archive's flag): 2 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified Compare
Tox21 (11 rows) elEmBERT-V1 Structure to Property: Chemical Element Embeddings and a Deep... code — Compare
BACE (6 rows) TrimNet TrimNet: learning molecular representation from triplet messages... code — Compare
HIV dataset (5 rows) GraphConv + dummy super node + focal loss Learning Graph-Level Representation for Drug Discovery code — Compare
MUV (5 rows) TrimNet TrimNet: learning molecular representation from triplet messages... code — Compare
ToxCast (5 rows) TrimNet TrimNet: learning molecular representation from triplet messages... code — Compare
BBBP (4 rows) ProtoW-L2 Optimal Transport Graph Neural Networks code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified Compare
BindingDB (4 rows) AttentionSiteDTI AttentionSiteDTI: an interpretable graph-based model for... code — Compare
clintox (4 rows) BiLSTM Accelerating Drug Safety Assessment using Bidirectional-LSTM for... code — Compare
DAVIS-DTA (4 rows) SMT-DTA SSM-DTA: Breaking the Barriers of Data Scarcity in Drug-Target... code Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
KIBA (4 rows) SMT-DTA SSM-DTA: Breaking the Barriers of Data Scarcity in Drug-Target... code Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
LIT-PCBA(ALDH1) (4 rows) EGT+TGT-At-DP Triplet Interaction Improves Graph Transformers: Accurate... code Syntology official (archive's flag): 9 ran · 10 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified Compare
LIT-PCBA(KAT2A) (4 rows) EGT+TGT-At-DP Triplet Interaction Improves Graph Transformers: Accurate... code Syntology official (archive's flag): 9 ran · 10 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified Compare
LIT-PCBA(MAPK1) (4 rows) EGT+TGT-At-DP Triplet Interaction Improves Graph Transformers: Accurate... code Syntology official (archive's flag): 9 ran · 10 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified Compare
SIDER (4 rows) elEmBERT-V1 Structure to Property: Chemical Element Embeddings and a Deep... code — Compare
LIT-PCBA(ESR1_ant) (3 rows) GLAM An adaptive graph learning method for automated molecular... code — Compare
BindingDB IC50 (2 rows) DeepDTA DeepDTA: Deep Drug-Target Binding Affinity Prediction code — Compare
PCBA (2 rows) GraphConv + dummy super node Learning Graph-Level Representation for Drug Discovery code — Compare
BACE (β-secretase enzyme) (1 row) GLAM An adaptive graph learning method for automated molecular... code — Compare
BBBP (Blood-Brain Barrier Penetration) (1 row) GLAM An adaptive graph learning method for automated molecular... code — Compare
DRD2 (1 row) HierG2G Hierarchical Graph-to-Graph Translation for Molecules code — Compare
egfr-inh (1 row) Multi-input Neural network with Attention Attention-based Multi-Input Deep Learning Architecture for... code — Compare
ESOL (Estimated SOLubility) (1 row) GLAM An adaptive graph learning method for automated molecular... code — Compare
FreeSolv (Free Solvation) (1 row) GLAM An adaptive graph learning method for automated molecular... code — Compare
Lipophilicity (logd74) (1 row) GLAM An adaptive graph learning method for automated molecular... code — Compare
PDBbind (1 row) Ensemble locally constant networks Oblique Decision Trees from Derivatives of ReLU Networks code — Compare
QED (1 row) HierG2G Hierarchical Graph-to-Graph Translation for Molecules code — Compare
ToxCast (Toxicity Forecaster) (1 row) GLAM An adaptive graph learning method for automated molecular... code — Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

26 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

3 subtasks in the archive's task tree.

Papers archive 2025-07-28

archive papers tagged: 1,337 · with a code link: 566 · where Syntology ran a sample: 182 (140 with a run with no instrument failure, 42 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (182 of 1,337 tagged: 140 with a run with no instrument failure, 42 where every run was a failure of Syntology's instrument)

Page 1 of 14: papers 1 to 100 of 1,337, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 54 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections