Morten Nielsen CBS Bio Centrum DTU CENTER FOR

Morten Nielsen, CBS, Bio. Centrum, DTU CENTER FOR BIOLOGICAL SEQUENCE ANALYSIS TECHNICAL UNIVERSITY OF DENMARK DTU T cell Epitope predictions using bioinformatics (Neural Networks and hidden Markov models)

g n di n i b C H M http: //www. nki. nl/nkidep/h 4/neefjes. htm CENTER FOR BIOLOGICAL SEQUENCE ANALYSIS TECHNICAL UNIVERSITY OF DENMARK DTU Processing of intracellular proteins

Sars virus • Part of a pathogen protein • Successful processing – Proteasome cleavage – TAP binding • Binds to MHC molecule • Protein function – Early in replication • Sequence conservation in evolution CENTER FOR BIOLOGICAL SEQUENCE ANALYSIS TECHNICAL UNIVERSITY OF DENMARK DTU What makes a peptide a potential and effective epitope?

20% processed 0. 5% bind MHC 50% CTL response Lauemøller et al. , 2000 => 1/2000 peptide are immunogenic CENTER FOR BIOLOGICAL SEQUENCE ANALYSIS TECHNICAL UNIVERSITY OF DENMARK DTU From proteins to immunogens

GP 1200 protein Structure (1 GM 9) CENTER FOR BIOLOGICAL SEQUENCE ANALYSIS TECHNICAL UNIVERSITY OF DENMARK DTU Location of class I epitopes

CENTER FOR BIOLOGICAL SEQUENCE ANALYSIS TECHNICAL UNIVERSITY OF DENMARK DTU

Anchor positions http: //www. nki. nl/nkidep/h 4/neefjes. htm CENTER FOR BIOLOGICAL SEQUENCE ANALYSIS TECHNICAL UNIVERSITY OF DENMARK DTU MHC class I with peptide

• Simple Motifs – Allowed/non allowed amino acids • Extended motifs – Amino acid preferences (SYFPEITHI) – Anchor/Preferred/other amino acids • Hidden Markov models – Peptide statistics from sequence alignment • Neural networks – Can take sequence correlations into account CENTER FOR BIOLOGICAL SEQUENCE ANALYSIS TECHNICAL UNIVERSITY OF DENMARK DTU Prediction of HLA binding specificity

• • • SYFPEITHI database – 3500 peptides known to bind to HMC class I and II – Only published data MHCpep – 13000 peptides known to bind to HMC class I and II – Published data and direct submission – No update since 1998 Binding affinity assays – Quantitative data. How strong does a peptide bind to the MHC molecule? – Costly and people do not publish negative results. . CENTER FOR BIOLOGICAL SEQUENCE ANALYSIS TECHNICAL UNIVERSITY OF DENMARK DTU Where to get data?

• HLA Informatics Group, ANRI (HLA sequence database) • IMGT/HLA Database (HLA sequence database) • SYFPEITHI (Database of HLA Class I and II peptides) • MHCPEP (Database of HLA Class I and II peptides) • BIMAS (HLA Class I predictor) • SYFPEITHI (HLA Class I predictor) • Net. MHC (HLA Class I prediction) CENTER FOR BIOLOGICAL SEQUENCE ANALYSIS TECHNICAL UNIVERSITY OF DENMARK DTU Databases and web resources

SLLPAIVEL LLDVPTAAV HLIDYLVTS ILFGHENRV LERPGGNEI PLDGEYFTL ILGFVFTLT KLVALGINA KTWGQYWQV SLLAPGAKQ ILTVILGVL TGAPVTYST GAGIGVAVL KARDPHSGH AVFDRKSDA GLCTLVAML VLHDDLLEA ISNDVCAQV YTAFTIPSI NMFTPYIGV VVLGVVFGI GLYDGMEHL EAAGIGILT YLSTAFARV FLDEFMEGV AAGIGILTV YLLPAIVHI VLFRGGPRG ILAPPVVKL ILMEHIHKL ALSNLEVKL GVLVGVALI LLFGYPVYV DLMGYIPLV TITDQVPFS KIFGSLAFL KVLEYVIKV VIYQYMDDL IAGIGILAI KACDPHSGH LLDFVRFMG FIDSYICQV LMWITQCFL VKTDGNPPE RLMKQDFSV LMIIPLINV ILHNGAYSL KMVELVHFL TLDSQVMSL YLLEMLWRL ALQPGTALL FLPSDFFPS TLWVDPYEV MVDGTLLLL ALFPQLVIL ILDQKINEV ALNELLQHV RTLDKVLEV GLSPTVWLS RLVTLKDIV AFHHVAREL ELVSEFSRM FLWGPRALV VLPDVFIRC LIVIGILIL ACDPHSGHF VLVKSPNHV IISAVVGIL SLLMWITQC SVYDFFVWL RLPRIFCSC TLFIGSHVV MIMVKCWMI YLQLVFGIE STPPPGTRV SLDDYNHLV VLDGLDVLL SVRDRLARL AAGIGILTV GLVPFLVSV YMNGTMSQV GILGFVFTL SLAGGIIGV DLERKVESL HLSTAFARV WLSLLVPFV MLLAVLYCL YLNKIQNSL KLTPLCVTL GLSRYVARL VLPDVFIRC LAGIGLIAA SLYNTVATL GLAPPQHLI VMAGVGSPY QLSLLMWIT FLYGALLLA FLWGPRAYA SLVIVTTFV MLGTHTMEV MLMAQEALA KVAELVHFL RTLDKVLEV SLYSFPEPE SLREWLLRI FLPSDFFPS KLLEPVLLL MLLSVPLLL STNRQSGRQ LLIENVASL FLGENISNF RLDSYVRSL FLPSDFFPS AAGIGILTV MMRKLAILS VLYRYGSFS FLLTRILTI AVGIGIAVV VDGIGILTI RGPGRAFVT LLGRNSFEV LLWTLVVLL LLGATCMFV VLFSSDFRI RLLQETELV VLQWASLAV MLGTHTMEV LMAQEALAF IMIGVLVGV GLPVEYLQV ALYVDSLFF LLSAWILTA AAGIGILTV LLDVPTAAV SLLGLLVEV GLDVLTAKV FLLWATAEA ALSDHHIYL YMNGTMSQV CLGGLLTMV YLEPGPVTA AIMDKNIIL YIGEVLVSV HLGNVKYLV LVVLGLLAV GAGIGVLTA NLVPMVATV PLTFGWCYK SVRDRLARL RLTRFLSRV LMWAKIGPV SLFEGIDFY ILAKFLHWL SLADTNSLA VYDGREHTV ALCRWGLLL KLIANNTRV SLLQHLIGL AAGIGILTV FLWGPRALV LLDVPTAAV ALLPPINIL RILGAVAKV SLPDFGISY GLSEFTEYL GILGFVFTL FIAGNSAYE LLDGTATLR IMDKNIILK CINGVCWTV GIAGGLALL ALGLGLLPV AAGIGIIQI GLHCYEQLV VLEWRFDSR LLMDCSGSI YMDGTMSQV SLLLELEEV SLDQSVVEL STAPPHVNV LLWAARPRL YLSGANLNL LLFAGVQCQ FIYAGSLSA ELTLGEFLK AVPDEIPPL ETVSEQSNV LLDVPTAAV TLIKIQHTL QVCERIPTI KKREEAPSL STAPPAHGV ILKEPVHGV KLGEFYNQM ITDQVPFSV SMVGNWAKV VMNILLQYV GLQDCTMLV GIGIGVLAA QAGIGILLA PLKQHFQIV TLNAWVKVV CLTSTVQLV FLTPKKLQC SLSRFSWGA RLNMFTPYI LLLLTVLTV GVALQTMKQ RMFPNAPYL VLLCESTAV KLVANNTRL MINAYLDKL FAYDGKDYI ITLWQRPLV CENTER FOR BIOLOGICAL SEQUENCE ANALYSIS TECHNICAL UNIVERSITY OF DENMARK DTU Sequence information

MHC class I HLA-A 0201 • Height of a column equal to log 20 + S p log p • Relative height of a letter is p • Highly useful tool to visualize sequence motifs High information positions http: //www. cbs. dtu. dk/~gorodkin/appl/plogo. html CENTER FOR BIOLOGICAL SEQUENCE ANALYSIS TECHNICAL UNIVERSITY OF DENMARK DTU Sequence logo

10 peptides known to bind MHC ALAKAAAAM ALAKAAAAN ALAKAAAAR ALAKAAAAT ALAKAAAAV GMNERPILT GILGFVFTM TLNAWVKVV KLNEPVLLL AVVPFIVSV What can we learn? 1. A at P 1 favors 1. binding? 2. I is not allowed at P 9? 3. K at P 4 favors binding? CENTER FOR BIOLOGICAL SEQUENCE ANALYSIS TECHNICAL UNIVERSITY OF DENMARK DTU Characterizing a binding motif

• Description of binding motif • Example PA = 6/10 PG = 2/10 PT = PK = 1/10 PC = PD = …PV = 0 • Problems – Few data – Data redundancy/duplication ALAKAAAAM ALAKAAAAN ALAKAAAAR ALAKAAAAT ALAKAAAAV GMNERPILT GILGFVFTM TLNAWVKVV KLNEPVLLL AVVPFIVSV CENTER FOR BIOLOGICAL SEQUENCE ANALYSIS TECHNICAL UNIVERSITY OF DENMARK DTU Sequence information

Raw sequence counting CENTER FOR BIOLOGICAL SEQUENCE ANALYSIS TECHNICAL UNIVERSITY OF DENMARK DTU Sequence information ALAKAAAAM ALAKAAAAN ALAKAAAAR ALAKAAAAT ALAKAAAAV GMNERPILT GILGFVFTM TLNAWVKVV KLNEPVLLL AVVPFIVSV

• Poor or biased sampling of sequence space • I is not found at position P 9. Does this mean that I is forbidden? • No! Use Blosum substitution matrix to estimate pseudo frequency of I at P 9 ALAKAAAAM ALAKAAAAN ALAKAAAAR ALAKAAAAT ALAKAAAAV GMNERPILT GILGFVFTM TLNAWVKVV KLNEPVLLL AVVPFIVSV } Similar sequences Weight 1/5 CENTER FOR BIOLOGICAL SEQUENCE ANALYSIS TECHNICAL UNIVERSITY OF DENMARK DTU Pseudo-count and sequence weighting

CENTER FOR BIOLOGICAL SEQUENCE ANALYSIS TECHNICAL UNIVERSITY OF DENMARK DTU The Blosum matrix

CENTER FOR BIOLOGICAL SEQUENCE ANALYSIS TECHNICAL UNIVERSITY OF DENMARK DTU Sequence weighting ALAKAAAAM ALAKAAAAN ALAKAAAAR ALAKAAAAT ALAKAAAAV GMNERPILT GILGFVFTM TLNAWVKVV KLNEPVLLL AVVPFIVSV

• Sequence weighting and pseudo count – Prediction accuracy 0. 60 • Motif found on all data (485) – Prediction accuracy 0. 79 CENTER FOR BIOLOGICAL SEQUENCE ANALYSIS TECHNICAL UNIVERSITY OF DENMARK DTU Pseudo counts

• Estimate amino acid frequencies from alignment • Now a weight matrix is given as Wij = log(pij/qj) – Here i is a position in the motif, and j an amino acid. q j is the background frequency for amino acid j. • W is a L x 20 matrix, L is motif length • Score sequences to weight matrix by looking up and adding L values from matrix CENTER FOR BIOLOGICAL SEQUENCE ANALYSIS TECHNICAL UNIVERSITY OF DENMARK DTU Weight matrices

1 2 3 4 5 6 7 8 9 A 0. 6 -1. 6 0. 2 -0. 1 -1. 6 -0. 7 1. 1 -2. 2 -0. 2 R 0. 4 -6. 6 -1. 3 -0. 1 -1. 4 -3. 8 1. 0 -3. 5 N -3. 5 -6. 5 0. 1 -2. 0 0. 1 -1. 0 -0. 2 -0. 8 -6. 1 D -2. 4 -5. 4 1. 5 2. 0 -2. 2 -2. 3 -1. 3 -2. 9 -4. 5 C -0. 4 -2. 5 0. 0 -1. 6 -1. 2 1. 1 1. 3 -1. 4 0. 7 Q -1. 9 -4. 0 -1. 8 0. 5 0. 4 -1. 3 -0. 3 0. 4 -0. 8 ILYQVPFSV ALPYWNFAT MTAQWWLDA E -2. 7 -4. 7 -3. 3 0. 8 -0. 5 -1. 4 -1. 3 0. 1 -2. 5 G 0. 3 -3. 7 0. 4 2. 0 1. 9 -0. 2 -1. 4 -0. 4 -4. 0 H I L K M F -1. 1 1. 0 0. 3 0. 0 1. 4 1. 2 -6. 3 1. 0 5. 1 -3. 7 3. 1 -4. 2 0. 5 -1. 0 0. 3 -2. 5 1. 2 1. 0 -3. 3 0. 1 -1. 7 -1. 0 -2. 2 -1. 6 1. 2 -2. 2 -0. 5 -1. 3 -2. 2 1. 7 -1. 0 1. 8 0. 8 -1. 9 0. 2 1. 0 2. 1 0. 6 0. 7 -5. 0 1. 1 0. 9 0. 2 -0. 0 1. 1 -0. 5 0. 7 -2. 6 0. 9 2. 8 -3. 0 -1. 8 -1. 4 15. 0 -3. 4 0. 8 P -2. 7 -4. 3 -0. 1 1. 7 1. 2 -0. 4 1. 3 -0. 3 -6. 2 S 1. 4 -4. 2 -0. 3 -0. 6 -2. 5 -0. 6 -0. 5 0. 8 -1. 9 T -1. 2 -0. 5 -0. 2 -0. 1 0. 4 -0. 9 0. 8 -1. 6 W -2. 0 -5. 9 3. 4 1. 3 1. 7 -0. 5 2. 9 -0. 7 -4. 9 Y V 1. 1 0. 7 -3. 8 0. 4 1. 6 0. 0 -6. 8 -0. 7 1. 5 1. 0 -0. 0 2. 1 -0. 4 0. 5 1. 3 -1. 1 -1. 6 4. 5 Which peptide is most likely to bind? Which peptide second? CENTER FOR BIOLOGICAL SEQUENCE ANALYSIS TECHNICAL UNIVERSITY OF DENMARK DTU Scoring sequences to a weight matrix

• • The effect on the binding affinity of having a given amino acid at one position can be influenced by the amino acids at other positions in the peptide (sequence correlations). – Two adjacent amino acids may for example compete for the space in a pocket in the MHC molecule. Artificial neural networks (ANN) are ideally suited to take such correlations into account CENTER FOR BIOLOGICAL SEQUENCE ANALYSIS TECHNICAL UNIVERSITY OF DENMARK DTU How to predict

• Neural networks can learn higher order correlations! – What does this mean? A A => 0 A C => 1 C A => 1 C C => 0 No linear function can learn this pattern CENTER FOR BIOLOGICAL SEQUENCE ANALYSIS TECHNICAL UNIVERSITY OF DENMARK DTU Neural networks

w 11 w 12 w 21 v 2 v 1 w 22 CENTER FOR BIOLOGICAL SEQUENCE ANALYSIS TECHNICAL UNIVERSITY OF DENMARK DTU Neural networks

True positive proportion = TP/(AP) False positive proportion = FP/(AN) Pearson correlation Roc curves FP TP Aroc=0. 8 AN Aroc=0. 5 AP CENTER FOR BIOLOGICAL SEQUENCE ANALYSIS TECHNICAL UNIVERSITY OF DENMARK DTU Evaluation of prediction accuracy

Sequence motif and HMM’s Sequence motif cc: 0. 76 Aroc: 0. 92 HMM cc: 0. 80 Aroc: 0. 95 CENTER FOR BIOLOGICAL SEQUENCE ANALYSIS TECHNICAL UNIVERSITY OF DENMARK DTU Epitope predictions

Neural Networks cc: 0. 91 Aroc: 0. 98 CENTER FOR BIOLOGICAL SEQUENCE ANALYSIS TECHNICAL UNIVERSITY OF DENMARK DTU Epitope prediction.

CENTER FOR BIOLOGICAL SEQUENCE ANALYSIS TECHNICAL UNIVERSITY OF DENMARK DTU Evaluation of prediction accuracy

CENTER FOR BIOLOGICAL SEQUENCE ANALYSIS TECHNICAL UNIVERSITY OF DENMARK DTU Hepatitis C virus. Epitope predictions

• Netchop (http: //www. cbs. dtu. dk/services/Net. Chop-3. 0/) – Epitopes have strong C terminal cleavage – Epitopes can have strong internal cleavage sites • Selection strategy NMVPFFPPV. . S – High binding peptides – High cleavage probability at C terminal CENTER FOR BIOLOGICAL SEQUENCE ANALYSIS TECHNICAL UNIVERSITY OF DENMARK DTU Proteasomal cleavage

• 29 marts. Introduktion til hidden Markov models og weight matrices • 5 april. Introduktion til neural networks • 12 april. Introduktion til projekt • 10 maj. Aflever projekt CENTER FOR BIOLOGICAL SEQUENCE ANALYSIS TECHNICAL UNIVERSITY OF DENMARK DTU Hvad nu?