Skip to content

GitLab

Last edited by Miquel Duran-Frigola
Page history

similarity and connectivity

Similarity and connectivity

The CC is based upon the similarity principle, i.e. similar molecules have similar properties. Similarity can be defined between pairs of molecules in any of the CC datasets.

When it comes to comparing molecules to other biological entities (antibodies, shRNAs, diseases, etc.), the similarity principle can be generalized to the notion of connectivity. A classical view of connectivity are molecules that mimic the transcriptional profile of a shRNA experiment, or molecules that revert the transcriptional profile of a disease state.

ConnectivityFigure-01

These are some ways similarity and connectivity can be applied in the CC:

Artboard_1

Easy calculation of similarity and connectivity

Calculating similarities and connectivities is the most important feature of the CC and, as such, it must be a flexible part of the repository. Similarities and connectivities are dataset-specific. The relevant scripts (i.e. the ones that lead to Signature Type 0) are within the pre-processing repository structure.

Every dataset has one (or more) pre-processing script(s), always consisting of two steps:

  1. Data gathering (and conversion to a standard input file).
    • In production phase (i.e. when building the dataset) data are gathered from downloads of from calculated molecular properties.
    • In the mapping phase (i.e. when including external molecules or biological entities) data parsed by the user or fetched from calculated molecular properties if these are available for the compounds of interest of the user.
  2. Standard input to Signature Type 0.
    • The outcome of step 1 is some sort of standard input for step 2.
    • The output of this step is a Signature type 0.
    • The complexity of this step can vary dramatically:
      • Very simple: Like in the case of 2D fingerprints where, simply, we take the corresponding molecular properties of the InChIKey provided. Likewise, the case of indications, where we read drug-disease pairs and map them.
      • Simple: The case of binding data where, in some occasions, we map target classes to the binding data.
      • Not so simple: The case of pathways, where we map targets to human orthologs, and then these to pathway annotations. In this case, the input may be of two types (i.e. targets or the pathways themselves).
      • Complex: The case of interactomes, where we map targets to human orthologs and these to several networks using HotNet. Here again, in this case the input may be of two types (i.e. targets or the neighbors themselves).
      • Very complex: The case of LINCS transcriptomics data (D1.001), we start from signatures of interest, we compare them to the Touchstone signatures using a GSEA-like metric, we aggregate them if necessary and we filter the outcome accordingly.

In practice:

  • At production phase, all procedures above (1 & 2) are wrapped in a fit() method of sign0.
  • For the mapping phase, step 2 is wrapped in a predict() method of sign0.
    • The method can have more than one entry point, i.e. multiple input types. Por example, in the biological processes dataset we may enter the targets or the biological process terms directly.
    • Inputs must be of an standard input format.

Standard input files

Type Format Description
InChIKeys TSV A one-column file containing InChIKeys. This will fetch the corresponding molecular properties from the CC database.
Key-feature pairs TSV A two-column file containing keys (first column) and features (second column). Features can be, for example, protein identifiers. Optionally, a third column can be included to specify the weight of the key-feature annotation.
Key profiles TSV A multiple-column file containing keys (first column) and features (second column onwards). These can be, for example, NCI-60 profiles, or chemical-genetic interaction profiles. If a header is not included, the order of the columns should match the one used in the CC internally.
Feature sets GMT A GMT-like file, typically used for gene sets. First column: Sample (signature) identifier. Second column: Agent (perturbagen, molecule, etc.) identifier. If empty, assume the same than first column. This is used in case it is necessary to aggregate downstream. Third column: Up features (genes). Can be NULL. Fourth column: Down features (genes). If empty, assume that there is no direction in the gene set, and only take the third column. Can be NULL.

We highly recommend that, when designing the datasets, features are as explicit as possible. A good way to start would be the metanodes defined in the Bioteque:

Metanode Abbreviation
Assay ASY
Cell CLL
Chemical entity CHE
Compartment CMP
Domain DOM
Compound CPD
Gene/Protein GEN
Disease DIS
Molecular function MFN
Pathway/process PWY
Protein class PCL
Perturbagen PGN
Symptom SYM
Tissue TIS
Pharmacologic class PHC

Obviously, it is mandatory that the vocabularies used in the production phase and the mapping phase match.

Distance metrics

From Signature Type 0 onwards, the CC only deals with two distance metrics: the cosine distance and the Euclidean distance. These are well-accepted metrics that capture two different properties: the direction and the absolute distance, respectively.

It may happen that some datasets require more advanced metrics, though. In this case, we recommend applying any required transformation of the data in the pre-processing, so as Signatures Type 0 are natively comparable using cosine/Euclidean distances. This can be achieved by metric learning algorithms. For example, one can incorporate a Siamese network in the pre-processing:

connectivity_examples-02

Entry points

The mapping (prediction) for new molecules/entities can be entered at one or multiple steps of the predict pipeline. The corresponding argument is entry_point.

Please note that, in this case, the key that is kept in the Signature Type 0 is exactly the one provided by the user.

Vocabularies are specified below. Terms in these vocabularies should look like:

Vocabulary Example
SMILES Cc1ccc(cc1Nc2nccc(n2)c3cccnc3)NC(=O)c4ccc(cc4)CN5CCN(CC5)C
InChI InChI=1S/C29H31N7O/c1-21-5-10-25(18-27(21)34-29-31-13-11-26(33-29)24-4-3-12-30-19-24)32-28(37)23-8-6-22(7-9-23)20-36-16-14-35(2)15-17-36/h3-13,18-19H,14-17,20H2,1-2H3,(H,32,37)(H,31,33,34)
InChIKey KTUFNOKKBVMGRW-UHFFFAOYSA-N
UniProtAC Q9H3N8
ChEMBL target class Class:1033
PDB ID 1f3v
ECOD domain ID e1m48A1
ECOD hierarchy ID E:e1m48A1 X:150 H:3 T:1 F:13
ChEBI CHEBI:52206
Reactome R-HSA-6804756
Gene Ontology GO:0023051
Interactome & Uniprot AC string_Q9H3N8 inbiomap_Q9H3N8...
Gene Names/Symbols HRH4
NCI60 cell lines MDA-MB-435
Yeast mutants YBL067C_sn1167
812 microscopy features Cells_AreaShape_Eccentricity
Cellosaurus CVCL_0382
ATC L L02 L02A L02AA L02AA03
MEDIC/MeSH DB00932
UMLS C0157733
DrugBank DB00930

A Chemistry

A1.001 2D fingerprints

  • Key-raw molecule: smiles / vocabulary: SMILES
  • Key-standard molecule: inchi / vocabulary: InChI
  • InChIKeys: inchikey [Default] / vocabulary: InChIKey

A2.001 3D fingerprints

  • Key-raw molecule: smiles / vocabulary: SMILES
  • Key-standard molecule: inchi / vocabulary: InChI
  • InChIKeys: inchikey [Default] / vocabulary: InChIKey

A3.001 Scaffolds

  • Key-raw molecule: smiles / vocabulary: SMILES
  • Key-standard molecule: inchi / vocabulary: InChI
  • InChIKeys: inchikey [Default] / vocabulary: InChIKey

A4.001 Structural keys

  • Key-raw molecule: smiles / vocabulary: SMILES
  • Key-standard molecule: inchi / vocabulary: InChI
  • InChIKeys: inchikey [Default] / vocabulary: InChIKey

A5.001 Physicochemistry

  • Key-raw molecule: smiles / vocabulary: SMILES
  • Key-standard molecule: inchi / vocabulary: InChI
  • InChIKeys: inchikey [Default] / vocabulary: InChIKey

B Targets

B1.001 Mechanism of action

  • Key-Protein pairs (-1/+1; default = -1): proteins [Default] / vocabulary: UniProtAC
  • Key-Class pairs (-1/+1; default = -1): classes / vocabulary: ChEMBL target class

B2.001 Metabolic genes

  • Key-Protein pairs: proteins [Default] / vocabulary: UniProtAC
  • Key-Class pairs: classes / vocabulary: ChEMBL target class

B3.001 Crystals

  • Key-structure pairs: structures / vocabulary: PDB ID
  • Key-domain pairs: domains [Default] / vocabulary: ECOD domain ID
  • Key-domain pairs: domain_hierarchies / vocabulary: ECOD hierarchy ID

B4.001 Binding

  • Key-Protein pairs (2/1; default = 1): proteins [Default] / vocabulary: UniProtAC
  • Key-Class pairs (2/1; default = 1): classes / vocabulary: ChEMBL target class

B5.001 HTS bioassays

  • Key-Protein pairs: proteins [Default] / vocabulary: UniProtAC
  • Key-Class pairs: classes / vocabulary: ChEMBL target class

C Networks

C1.001 Small molecule roles

  • Key-ChEBI pairs: terms [Default] / vocabulary: ChEBI

C2.001 Small molecule pathways

  • Key-metabolite pairs (neighbors) (10-1; default = 5): metabolites_neighbors [Default] / vocabulary: InChIKey

C3.001 Signaling pathways

  • Key-Protein pairs (2/1; default = 1): proteins [Default] / vocabulary: UniprotAC
  • Key-Pathway pairs (2/1; default = 1): pathways / vocabulary: Reactome

C4.001 Biological processes

  • Key-Protein pairs (2/1; default = 1): proteins [Default] / vocabulary: UniprotAC
  • Key-Process pairs (2/1; default = 1): processes / vocabulary: Gene Ontology (Biological processes)

C5.001 Interactome

  • Key-Protein pairs (exact nodes) (2/1; default = 1): proteins [Default] / vocabulary: UniprotAC
  • Key-Protein pairs (neighbors) (20-1; default = 10): protein_neighbors / vocabulary: UniprotAC
  • Key-Protein pairs (neighbors in specific network) (20-1; default = 10): protein_neighbors_network / vocabulary: Interactome & UniProtAC

D Cells

D1.001 Gene expression

  • Key-(perturbation)-Up&Down genes: up_down [Default] / vocabulary: Gene names/symbols

D2.001 Cancer cell lines

  • Key-Profile (score): profile [Default] / vocabulary: NCI-60 cell lines

D3.001 Chemical genetics

  • Key-Strain (2/1; default = 1): strain [Default] / vocabulary: Yeast mutants

D4.001 Morphology

  • Key-Measure (score): measure [Default] / vocabulary: 812 microscopy features

D5.001 Cell bioassays

  • Key-Cell: cell [Default] / vocabulary: Cellosaurus

E Clinics

E1.001 Therapeutic areas

  • Key-ATC: atc [Default] / vocabulary: ATC codes

E2.001 Indications

  • Key-Disease (4/1; default = 2): disease [Default] / vocabulary: MEDIC/MeSH

E3.001 Side effects

  • Key-Side effect: side_effect [Default] / vocabulary: UMLS

E4.001 Diseases and Toxicology

  • Key-Disease (M/T; mandatory): disease [Default] / vocabulary: MEDIC/MeSH

E5.001 Drug-drug interactions

  • Key-Drug: drug [Default] / vocabulary: DrugBank